Multidetector CT features of pulmonary focal ground-glass opacity: differences between benign and malignant

Austin J.H., Müller N.L., Friedman P.J., Hansell D.M., Naidich D.P., Remy-Jardin M., Webb W.R., Zerhouni E.A.

Jang H.J., Lee K.S., Kwon O.J., Rhee C.H., Shim Y.M., Han J.

To assess an early thin-section computed tomographic (CT) finding of the localized formation of bronchioloalveolar carcinoma (BAC).From October 1994 to September 1995, four consecutive patients with biopsy-proved BAC were studied. Thin-section CT (n=4), radiographic (n=4), pathologic (n=4), and positron emission tomographic (n=2) findings were analyzed.Chest radiographs showed focal areas of poorly defined nodules (n=2) and poorly defined opacity (n=2). At thin-section CT, lesions appeared as isolated areas of ground-glass attenuation (n=2) and mixed areas of ground-glass attenuation and consolidation (n=2). The areas of ground-glass attenuation were 1.8-11 cm in longest diameter. A focal, isolated area of ground-glass attenuation changed into mixed areas with consolidation at serial CT in one patient. Mucinous and nonmucinous BACs were observed in two patients each. Positron emission tomography showed false-negative results for malignancy.Focal areas of ground-glass attenuation at CT could be an early sign of localized BAC.

Zerhouni E.A., Stitik F.P., Siegelman S.S., Naidich D.P., Sagel S.S., Proto A.V., Muhm J.R., Walsh J.W., Martinez C.R., Heelan R.T.

To evaluate the role of computed tomography (CT) in the investigation of pulmonary nodules, a special reference phantom that enabled CT densitometric measurements independent of variations between scanners and patients was used in ten institutions. A total of 384 nodules not considered calcified by conventional methods were examined; 118 (31%) proved to be benign, and in 65 of these (55%), unsuspected calcification was demonstrated. In 28 of the 65, definite calcification could be identified on thin-section CT scans by simple inspection of the scans at narrow windows. In the remaining 37, presence of calcification could not be clearly established without comparison with the reference CT number from the calibration phantom. CT was most effective in establishing the benignancy of nodules 3 cm or less in diameter and those with discrete or smooth margins. CT rarely yields a confident diagnosis of benign disease in larger nodules and in those with irregular or spiculated borders. After review of prior spot radiographs, low kilovolt peak spot radiographs, and conventional tomograms, the authors conclude that thin-section CT aided by a reference phantom in equivocal cases should be an integral part of the diagnostic approach to the pulmonary nodule.

Henschke C.I., Yankelevitz D.F., Mirtcheva R., McGuinness G., McCauley D., Miettinen O.S.

In the Early Lung Cancer Action Project (ELCAP), we found not only solid but also part-solid and nonsolid nodules in patients at both baseline and repeat CT screening for lung cancer. We report the frequency and significance of part-solid and nonsolid nodules in comparison with solid nodules.We reviewed all instances of a positive finding in patients at baseline (from one to six noncalcified nodules) and annual repeat screenings (from one to six newly detected noncalcified nodules with interim growth) to classify each of the nodules as solid, part-solid, or nonsolid. We defined a solid nodule as a nodule that completely obscures the entire lung parenchyma within it. Part-solid nodules are those having sections that are solid in this sense, and nonsolid nodules are those with no solid parts. Chi-square statistics were used to test for differences in the malignancy rates.Among the 233 instances of positive results at baseline screening, 44 (19%) involved a part-solid or nonsolid largest nodule (16 part-solid and 28 nonsolid). Among these 44 cases of positive findings, malignancy was diagnosed in 15 (34%) as opposed to a 7% malignancy rate for solid nodules (p = 0.000001). The malignancy rate for part-solid nodules was 63% (10/16), and the rate for nonsolid nodules was 18% (5/28). Even after standardizing for nodule size, the malignancy rate was significantly higher for part-solid nodules than for either solid ones (p = 0.004) or nonsolid ones (p = 0.03). The malignancy type in the part-solid or nonsolid nodules was predominantly bronchioloalveolar carcinoma or adenocarcinoma with bronchioloalveolar features, contrasting with other subtypes of adenocarcinoma found in the solid nodules (p = 0.0001). At annual repeat screenings, only 30 instances of positive test results have been obtained; seven of these involved part-solid or nonsolid nodules.In CT screening for lung cancer, the detected nodule commonly is either only part-solid or nonsolid, but such a nodule is more likely to be malignant than a solid one, even when nodule size is taken into account.

Aoki T., Nakata H., Watanabe H., Nakamura K., Kasai T., Hashimoto H., Yasumoto K., Kido M.

This study was performed to evaluate the evolution of peripheral lung adenocarcinomas using CT findings and histologic classification related to tumor doubling time.The subjects were 34 patients, each with an adenocarcinoma smaller than 3 cm. All patients underwent chest radiography and 10 of them had previously undergone CT more than 6 months before surgery. Tumor doubling time was estimated by examining sequential radiographs using the method originally described by Schwartz. Tumor growth was also observed by studying the changes on CT in the 10 patients who had previously undergone CT. The histologic classification (types A-F) was evaluated according to the criteria of Noguchi et al.Five (83%) of the six adenocarcinomas with tumor types A or B showed localized ground-glass opacity on high-resolution CT. All six tumors had a tumor doubling time of more than 1 year. Fifteen (71%) of the 21 tumors with type C showed partial ground-glass opacity mixed with localized solid attenuation on high-resolution CT. Ten (48%) of these 21 type C tumors had a tumor doubling time of more than 1 year. In types B and C, the solid component or the development of pleural indentation and vascular convergence increased during observation before surgery. All seven tumors with types D, E, and F showed mostly solid attenuation, and the tumor doubling time was less than 1 year in six (87%) of the seven tumors.Two main types of peripheral lung adenocarcinoma exist. The first type appears on CT as a localized ground-glass opacity with slow growth, and the other appears as a solid attenuation with rapid growth.

Yu H., Liu S., Li H., Xiao X., Dong W.

AbstractPurpose We aimed to retrospectively evaluate bronchial and nonbronchial systemic arteries using multi-detector row helical computed tomographic (MDCT) angiography in patients with pulmonary disorders. Materials and Methods Thirty-nine patients (24 men, 15 women; mean age, 63.4 years; range, 20–82 years) with congenital and acquired pulmonary disorders of the bronchial and nonbronchial systemic arteries underwent multi-detector row helical computed tomographic angiography of the thorax using a 16-detector row scanner. Each of these patients had experienced an episode of hemoptysis. Computed tomographic angiogram data, which included maximum intensity projections, multiplanar reconstruction, and three-dimensional volume-rendered images, were used to retrospectively analyse the characteristics of the bronchial and nonbronchial systemic arteries. Results We identified a total of 128 bronchial arteries (76 on the right side and 52 on the left) in 39 patients. We detected 42 nonbronchial systemic artery branches, including 19 internal mammary artery branches, 8 subclavian artery branches, 8 inferior phrenic artery branches, 5 intercostal artery branches, 1 thyrocervical trunk branch, and 1 celiac trunk branch. Thirty-five dilated and tortuous nonbronchial systemic arteries entered into the lung parenchyma and extended down to the lesions. Every case, except the one case of sequestration, was associated with pleural thickening where the vascular structures passed through the extrapleural fat. Conclusions The variations in both the bronchial artery anatomy and the location and type of the nonbronchial arteries were great. Nonbronchial arteries may be a significant source of hemoptysis. MDCT angiography can be used to detect detailed anatomical information about the origins and courses of bronchial and nonbronchial systemic arteries and their pathophysiologic features.

Kim T.J., Goo J.M., Lee K.W., Park C.M., Lee H.J.

To retrospectively compare the clinical, pathological, and thin-section CT features of persistent multiple ground-glass opacity (GGO) nodules with those of solitary GGO nodules.Histopathologic specimens were obtained from 193 GGO nodules in 136 patients (87 women, 49 men; mean age, 57; age range 33-81). The clinical data, pathologic findings, and thin-section CT features of multiple and solitary GGO nodules were compared by using t-test or Fisher's exact test.Multiple GGO nodules (n=105) included atypical adenomatous hyperplasia (AAH) (n=31), bronchioloalveolar carcinoma (BAC) (n=33), adenocarcinoma (n=34) and focal interstitial fibrosis (n=7). Solitary GGO nodules included AAH (n=8), BAC (n=15), adenocarcinoma (n=55) and focal interstitial fibrosis (n=10). AAH (P=.001) and BAC (P=.029) were more frequent in multiple GGO nodules, whereas adenocarcinoma (P

Cui Y., Ma D., Liu W.

In this report, we studied the value of the solitary pulmonary nodule (SPN)-bronchus relationship in determining the nature of SPN by multiplanar reconstruction (MPR) in multislice spiral computed tomography (MSCT). One hundred forty-eight SPN cases were enrolled. CT was performed in all cases using MSCT. Images were then transferred to a processing workstation for MPR. The results showed that MPR is a valuable tool for visualizing the SPN-bronchus relationship and that the SPN-bronchus relationship is useful in determining the nature and the degree of differentiation of SPN.

Kim H.Y., Shim Y.M., Lee K.S., Han J., Yi C.A., Kim Y.K.

Purpose: To retrospectively compare pure pulmonary ground-glass opacity (GGO) nodules observed on thin-section computed tomography (CT) images with histopathologic findings. Materials and Methods: The institutional review board approved this study and waived informed consent. Histopathologic specimens were obtained from 53 GGO nodules in 49 patients. CT scans were assessed in terms of nodule size, shape, contour, internal characteristics, and the presence of a pleural tag. The findings obtained were compared with histopathologic results. Differences in thin-section CT findings according to histopathologic diagnoses were analyzed by using the Kruskal-Wallis test or Fisher exact test. Results: Of 53 nodules in 49 patients (20 men, 29 women; mean age, 54 years; range, 29–78 years), 40 (75%) proved to be broncholoalveolar cell carcinoma (BAC) (n = 36) or adenocarcinoma with predominant BAC component (n = 4), three (6%) atypical adenomatous hyperplasia, and 10 (19%) nonspecific fibrosis or organizing pneumonia. No significant differences in morphologic findings on thin-section CT scans were found among the three diseases (all P > 0.05). A polygonal shape (25%, 10 of 40 nodules) and a lobulated or spiculated margin (45%, 18 of 40) in BAC or adenocarcinoma with predominant BAC component were caused by interstitial fibrosis or infiltrative tumor growth. A polygonal shape and a lobulated or spiculated margin were observed in two (20%) and three (30%) of 10 nodules, respectively, in organizing pneumonia/fibrosis were caused by granulation tissue aligned in a linear manner in perilobular regions with or without interlobular septal thickening. Conclusion: About 75% of persistent pulmonary GGO nodules are attributed to BAC or adenocarcinoma with predominant BAC component, and at thin-section CT, these nodules do not manifest morphologic features that distinguish them from other GGO nodules with different histopathologic diagnoses. © RSNA, 2007

Park C.M., Goo J.M., Lee H.J., Lee C.H., Chun E.J., Im J.

The popularization of computed tomography (CT) in clinical practice and the introduction of mass screening for early lung cancer with the use of CT have increased the frequency of findings of subtle nodules or nodular ground-glass opacity. Nodular ground-glass opacity may be observed in malignancies such as bronchioloalveolar carcinoma and adenocarcinoma, as well as in their putative precursors, such as atypical adenomatous hyperplasia. Nodular ground-glass opacity also may be seen in the presence of benign conditions, including focal interstitial fibrosis, inflammation, and hemorrhage. The persistence of nodular ground-glass opacity over time may be strongly suggestive of an early-stage malignancy, especially if the lesion increases in size or includes a solid component that increases in its extent. Persistent nodular ground-glass opacity also may remain stable in size but show increased attenuation. The more extensive the solid portions of the lesion, the higher the probability of malignancy and the poorer the prognosis. An awareness of the clinical setting, in addition to familiarity with the thin-section CT features of nodular ground-glass opacity at initial and follow-up imaging over several months, can help identify malignancy and achieve an accurate diagnosis. A meticulous evaluation of those CT features, and their correlation with specific histopathologic characteristics, also may enable a more accurate prognosis in cases of neoplastic disease.

Tsubamoto M., Kuriyama K., Kido S., Arisawa J., Kohno N., Johkoh T., Tomiyama N., Honda O., Kuroda C.

To evaluate the detection of small peripheral lung tumors on chest radiographs on the basis of the size of the tumor and its extent of ground-glass opacity (GGO) at thin-section computed tomography (CT).Chest radiographs of 75 patients with peripheral carcinomas 20 mm in diameter or smaller (26 localized bronchioloalveolar carcinomas [BACs], 49 other carcinomas) and 60 normal chest radiographs were retrospectively reviewed individually by 10 radiologists. The extent of GGO within the lesions at thin-section CT was reviewed retrospectively. The detection rates for localized BAC and other carcinomas on chest radiographs were calculated and were correlated with tumor size and extent of GGO.The mean sensitivity for detection of small peripheral carcinomas was 58.5% +/- 8.8 (standard error) for localized BAC and was 78.6% +/- 5.1 for other carcinomas (P =.024). Lesions that were smaller than 15 mm in diameter and had an extent of GGO of 70% or greater at thin-section CT were more difficult to detect than tumors that had larger diameters or less extensive GGO (chi(2) = 8.13, df = 1, P =.004).The detection of small peripheral carcinomas on chest radiographs is influenced by tumor size and extent of GGO as seen at thin-section CT.

Li F., Sone S., Abe H., MacMahon H., Doi K.

PURPOSE: To evaluate thin-section computed tomographic (CT) characteristics of malignant nodules on the basis of overall appearance (pure ground-glass opacity [GGO], mixed GGO, or solid opacity) in comparison with the appearance of benign nodules. MATERIALS AND METHODS: Institutional review board approval and patient consent were obtained. Follow-up diagnostic CT was performed in 747 suspicious pulmonary nodules detected at low-dose CT screening (17 892 examinations). Of 747 nodules, 222 were evaluated at thin-section CT (1-mm collimation), which included 59 cancers and 163 benign nodules (3–20 mm). Thin-section CT findings of malignant versus benign nodules with pure GGO (17 vs 12 lesions), mixed GGO (27 vs 29 lesions), or solid opacity (15 vs 122 lesions) were analyzed. Fisher exact test for independence was used to compare differences in shape, margin, and internal features between benign and malignant nodules. Positive predictive value (PPV) was analyzed when a category was significantly different from the others. RESULTS: Among nodules with pure GGO, a round shape was found more frequently in malignant lesions (11 of 17, 65%) than in benign lesions (two of 12, 17%; P = .02; PPV, 85%); mixed GGO, a subtype with GGO in the periphery and a high-attenuation zone in the center, was seen much more often in malignant lesions (11 of 27, 41%) than in benign lesions (two of 29, 7%; P = .004; PPV, 85%). Among solid nodules, a polygonal shape or a smooth or somewhat smooth margin was present less frequently in malignant than in benign lesions (polygonal shape: 7% vs 38%, P = .02; smooth or somewhat smooth margin: 0% vs 63%, P < .001), and 98% (46 of 47) of polygonal nodules and 100% (77 of 77) of nodules with a smooth or somewhat smooth margin were benign. CONCLUSION: Recognition of certain characteristics at thin-section CT can be helpful in differentiating small malignant nodules from benign nodules. © RSNA, 2004

Ujita M., Renzoni E.A., Veeraraghavan S., Wells A.U., Hansell D.M.

To describe the appearance and frequency of a perilobular pattern at thin-section computed tomography (CT) in patients with organizing pneumonia.Thin-section CT scans of 21 consecutive patients with cryptogenic organizing pneumonia were retrospectively reviewed. Two thoracic radiologists in consensus recorded the presence and distribution of the CT abnormalities (consolidation, ground-glass opacification, nodules, bandlike opacities, interlobular septal thickening, and findings of fibrosis), with a particular focus on the presence and predominant location of the perilobular pattern, that is, a poorly defined arcadelike or polygonal appearance.The perilobular pattern was present in 12 (57%) of 21 patients, 10 of whom had five or more perilobular opacities. Other CT features were consolidation (20 patients, 95%), which was predominantly a subpleural and/or peribronchial distribution in 17 patients, and ground-glass opacification (18 patients, 86%). Bandlike opacities and interlobular septal thickening were observed in four patients and one patient, respectively. The perilobular pattern abutted the pleural surface in 10 of 12 patients and was surrounded by aerated lung parenchyma in 11 of 12 patients. There was no obvious relationship between perilobular opacities and CT findings indicative of established fibrosis.A perilobular pattern was present in more than half of the patients, along with the expected thin-section CT features of organizing pneumonia.

Winer-Muram H.T.

The imaging evaluation of a solitary pulmonary nodule is complex. Management decisions are based on clinical history, size and appearance of the nodule, and feasibility of obtaining a tissue diagnosis. The most reliable imaging features are those that are indicative of benignancy, such as a benign pattern of calcification and periodic follow-up with computed tomography for 2 years showing no growth. Fine-needle aspiration biopsy and core biopsy are important procedures that may obviate surgery if there is a specific benign diagnosis from the procedure. In using the various imaging and diagnostic modalities described in this review, one should strive to not only identify small malignant tumors--where resection results in high survival rates--but also spare patients with benign disease from undergoing unnecessary surgery.

Park C.M., Goo J.M., Lee H.J., Lee C.H., Chung D.H., Chun E.J., Im J.

The purpose of this study was to describe the thin-section computed tomographic (CT) features of focal interstitial fibrosis manifesting as nodular ground-glass opacity (GGO) and its changes during follow-up. The thin-section CT findings of pathologically proven focal interstitial fibrosis manifesting as nodular GGO were retrospectively evaluated in nine patients (five women and four men; mean age, 59.3 years; age range, 34–81 years). The thin-section CT findings of each lesion were analyzed for multiplicity, location, shape, margin characteristics, pleural retraction or vascular convergence, size and internal attenuation, lesion internal features and lesion changes on follow-up CT scans (mean 90 days, range 5 to 215 days). All lesions manifested as a solitary nodular GGO (100%), and seven of the nine lesions (77.8%) were located in the upper lobe. Focal interstitial fibrosis was round or oval in shape in five cases (55.6%), complex in shape in three cases (33.3%) and polygonal in one case (11.1%). Lesion margins were smooth in five patients (55.6%), irregular in three (33.3%) and spiculated in one (11.1%). Pleural retraction or vascular convergence was present in two patients (22.2%). Lesions measured 4.8 mm to 25.5 mm (mean, 11.5 mm) and had attenuations ranging from −151 to −699 HU (mean, −514.7 HU). Eight (88.9%) manifested as pure nodular GGOs and one as mixed GGO with a spiculated margin. In all patients, no lesion changes were observed in follow-up CT scans. Focal interstitial fibrosis manifesting as nodular GGO usually presents as a solitary nodule with pure GGO on thin-section CT, which does not change significantly during follow-up.

Zhou T., Zhu P., Xia K., Zhao B.

Abstract Background Lung cancer is the most prevalent and lethal cancer globally, necessitating accurate differentiation between benign and malignant pulmonary nodules to guide treatment decisions. This study aims to develop a predictive model that integrates artificial intelligence (AI) analysis with biomarkers to enhance early detection and stratification of lung nodule malignancy. Methods The study retrospectively analyzed the patients with pathologically confirmed pulmonary nodules. AI technology was employed to assess CT features, such as nodule size, solidity, and malignancy probability. Additionally, lung cancer blood biomarkers were measured. Statistical analysis involved univariate analysis to identify significant differences among factors, followed by multivariate logistic regression to establish independent risk factors. The model performance was validated using receiver operating characteristic curves and decision curve analysis (DCA) for internal validation. Furthermore, an external dataset comprising 51 cases of lung nodules was utilized for independent validation to assess robustness and generalizability. Results A total of 176 patients were included, divided into benign/preinvasive (n = 76) and invasive cancer groups (n = 100). Multivariate analysis identified eight independent predictors of malignancy: lobulation sign, bronchial inflation sign, AI-predicted malignancy probability, nodule nature, diameter, solidity proportion, vascular endothelial growth factor, and lung cancer autoantibodies. The combined predictive model demonstrated high accuracy (area under the curve [AUC] = 0.946). DCA showed that the combined model significantly outperformed the traditional model, and also proved superior to models using AI-predicted malignancy probability or the seven lung cancer autoantibodies plus traditional model. External validation confirmed its robustness (AUC = 0.856), achieving a sensitivity of 0.80 and specificity of 0.86, effectively distinguishing between invasive and noninvasive nodules. Conclusion This combined approach of AI-based CT features analysis with lung cancer biomarkers provides a more accurate and clinically useful tool for guiding treatment decisions in pulmonary nodule patients. Further studies with larger cohorts are warranted to validate these findings across diverse patient populations.

Yu M., Cheng Y., Wen T., Zhang L., Wei X., Wang Y., Du J., Xie G., Bi L.

ABSTRACTBackgroundA screening tool was devised to aid the diagnosis and treatment of ground‐glass nodules (GGNs).MethodsThe current ambispective cohort study included retrospective collation of 20 variables synthesizing a patient's clinical characteristics, serum tumor markers, and CT results, which allowed division into noninvasive (benign, atypical adenomatous hyperplasia, and adenocarcinoma in situ) and invasive (minimally invasive and invasive adenocarcinomas) tumors to build a prediction nomogram and GGN screening scale. The model was verified internally. A prospective cohort of patients was randomly divided by envelope method into those assessed by the GGN screening scale and those assessed via CT values. The diagnostic efficiencies were compared to allow external verification of the model.ResultA total of 223 patients with 225 GGNs were recruited into the retrospective cohort between January 2021 and December 2022. Multivariable analysis showed sex, diameter, air bronchogram, and vessel convergence sign to be independent factors for prediction of noninvasive and invasive GGNs. Internal verification showed the model had a sensitivity of 70.7% and specificity of 75.0% with the Youden index at 0.457 and area under the curve (AUC) of 0.793 (95% CI: 0.734–0.852). Calibration curves indicated good internal stability (p = 0.357). Between January 2023 and March 2023, 147 patients with 148 GGNs were recruited into the prospective cohort. External verification showed the model had a sensitivity of 92.4% and specificity of 40.0% with the Youden index at 0.324 and AUC of 0.678 (95% CI: 0.509–0.847). Calibration curves indicated good external stability (p = 0.088). The scale was shown to have a sensitivity of 75.00%, specificity of 37.50%, positive predictive value of 91.53%, negative predictive value of 14.29%, and accuracy of 71.25%.ConclusionThe GGN screening scale has high sensitivity and accuracy, making it suitable for diagnosis of GGNs.

Jiang C., Zhao M., Zhang W.

Purpose To investigate the diagnostic value of 18F-fluorodeoxyglucose(FDG) PET/computed tomography (CT) for infiltrative subsolid nodules at different stages of lung adenocarcinoma and to explore predictive factors for invasive adenocarcinoma, providing compelling evidence for timely intervention. Methods A retrospective analysis was conducted on PET/CT imaging data of 170 subsolid nodules lesions confirmed postoperatively as lung adenocarcinoma or precursor glandular lesions. Lesions were categorized into preinvasive lesions including atypical adenomatous hyperplasia and adenocarcinoma in situ, microinvasive adenocarcinoma, and invasive adenocarcinoma. Compared the differences in imaging features and metabolic parameters among different groups and used a multifactor logistic regression model and receiver operating characteristic curve analysis to identify predictive factors for invasive adenocarcinoma. Results From preinvasive lesions through microinvasive adenocarcinoma to invasive adenocarcinoma, there was a gradual increase in nodule diameter, nodule area, and proportion of part-solid nodule. Statistical significance (P < 0.05) was observed in the rates of spiculation and pleural indentation between preinvasive lesions versus microinvasive adenocarcinoma and invasive adenocarcinoma groups. The maximum standardized uptake value and maximum standardized uptake ratio show statistically significant differences (P < 0.05) between the invasive adenocarcinoma group and the other groups. Logistic regression analysis indicated that nodule composition, nodule diameter, and maximum standardized uptake ratio were predictive factors for invasive adenocarcinoma (P < 0.05). For part-solid nodules, the longest diameter of the solid component has a high diagnostic value. Conclusion The imaging features of 18F-FDG PET/CT contribute to the diagnosis of infiltrative subsolid nodules at different stages of lung adenocarcinoma, providing robust evidence for timely intervention.

Deng H., Huang W., Zhou X., Zhou T., Fan L., Liu S.

ObjectivesThe purpose of this study was to develop and validate a new feature fusion algorithm to improve the classification performance of benign and malignant ground-glass nodules (GGNs) based on deep learning.MethodsWe retrospectively collected 385 cases of GGNs confirmed by surgical pathology from three hospitals. We utilized 239 GGNs from Hospital 1 as the training and internal validation set, and 115 and 31 GGNs from Hospital 2 and Hospital 3, respectively, as external test sets 1 and 2. Among these GGNs, 172 were benign and 203 were malignant. First, we evaluated clinical and morphological features of GGNs at baseline chest CT and simultaneously extracted whole-lung radiomics features. Then, deep convolutional neural networks (CNNs) and backpropagation neural networks (BPNNs) were applied to extract deep features from whole-lung CT images, clinical, morphological features, and whole-lung radiomics features separately. Finally, we integrated these four types of deep features using an attention mechanism. Multiple metrics were employed to evaluate the predictive performance of the model.ResultsThe deep learning model integrating clinical, morphological, radiomics and whole lung CT image features with attention mechanism (CMRI-AM) achieved the best performance, with area under the curve (AUC) values of 0.941 (95% CI: 0.898-0.972), 0.861 (95% CI: 0.823-0.882), and 0.906 (95% CI: 0.878-0.932) on the internal validation set, external test set 1, and external test set 2, respectively. The AUC differences between the CMRI-AM model and other feature combination models were statistically significant in all three groups (all p&lt;0.05).ConclusionOur experimental results demonstrated that (1) applying attention mechanism to fuse whole-lung CT images, radiomics features, clinical, and morphological features is feasible, (2) clinical, morphological, and radiomics features provide supplementary information for the classification of benign and malignant GGNs based on CT images, and (3) utilizing baseline whole-lung CT features to predict the benign and malignant of GGNs is an effective method. Therefore, optimizing the fusion of baseline whole-lung CT features can effectively improve the classification performance of GGNs.

Woo J.H., Kim J.H., Jeong D.Y., Park S.G., Jung M., Kim C.H., Lee J., Kim H.K., Han J., Kim T.J., Chung M.J., Cha Y.K.

Purpose: Focal interstitial fibrosis (FIF) manifesting as a persistent part-solid nodule (PSN) has been mistakenly treated surgically due to similar imaging features to invasive adenocarcinoma (ADC). The purpose of this study was to observe predictive imaging features correlated with FIF through CT morphologic analysis. Materials and Methods: From January 2009 to December 2020, 44 patients with surgically proven FIF in a single institution were enrolled and compared with 88 ADC patients through propensity score matching. Patient characteristics and CT morphologic analysis of persistent PSNs were used to identify predictive imaging features of FIF. Receiver operating characteristic (ROC) curve analysis was used to quantify the performance of imaging features. Results: A total of 132 patients with 132 PSNs (44 FIF, 88 ADC; mean age, 67.7±7.58; 75 females) were involved in our analysis. Multivariable analysis demonstrated that preserved peritumoral vascular margin (preserved vascular margin), preserved secondary pulmonary lobule margin (preserved lobular margin), and lower coronal to axial ratio (C/A ratio; cutoff: 1.005) were significant independent predictors of FIF (P<0.05). ROC curve analysis to evaluate the predictive value of the logistic model based on the imaging features of FIF, and the AUC value was 0.881. Conclusion: CT imaging features of preserved vascular margin, preserved lobular margin, and lower C/A ratio (cutoff, <1.005) might be helpful imaging features in discriminating FIF over ADC among persistent PSN in clinical practice.

Liu S., Yang S., Ye M., Fu B., Lv F., Chu Z.

Abstract Purpose To investigate the computed tomography (CT) characteristics of air-containing space and its specific patterns in neoplastic and non-neoplastic ground glass nodules (GGNs) for clarifying their significance in differential diagnosis. Materials and methods From January 2015 to October 2022, 1328 patients with 1,350 neoplastic GGNs and 462 patients with 465 non-neoplastic GGNs were retrospectively enrolled. Their clinical and CT data were analyzed and compared with emphasis on revealing the differences of air-containing space and its specific patterns (air bronchogram and bubble-like lucency [BLL]) between neoplastic and non-neoplastic GGNs and their significance in differentiating them. Results Compared with patients with non-neoplastic GGNs, female was more common (P < 0.001) and lesions were larger (P < 0.001) in those with neoplastic ones. Air bronchogram (30.1% vs. 17.2%), and BLL (13.0% vs. 2.6%) were all more frequent in neoplastic GGNs than in non-neoplastic ones (each P < 0.001), and the BLL had the highest specificity (93.6%) in differentiation. Among neoplastic GGNs, the BLL was more frequently detected in the larger (14.9 ± 6.0 mm vs. 11.4 ± 4.9 mm, P < 0.001) and part-solid (15.3% vs. 10.7%, P = 0.011) ones, and its incidence significantly increased along with the invasiveness (9.5–18.0%, P = 0.001), whereas no significant correlation was observed between the occurrence of BLL and lesion size, attenuation, or invasiveness. Conclusion The air containing space and its specific patterns are of great value in differentiating GGNs, while BLL is a more specific and independent sign of neoplasms.

Ye Y., Sun Y., Hu J., Ren Z., Chen X., Chen C.

AIM To develop a clinical–radiological model to predict the malignancy of solitary pulmonary nodules (SPNs) and to evaluate the accuracy of chest computed tomography imaging characteristics of SPN in diagnosing pathological type. MATERIALS AND METHODS The predictive model was developed using a retrospective cohort of 601 SPN patients (Group A) between July 2015 and July 2020. The established model was tested using a second retrospective cohort of 124 patients between August 2020 and August 2021 (Group B). The radiological characteristics of all adenocarcinomas in two groups were analysed to determine the correlation between radiological and pathological characteristics. RESULTS Malignant nodules were found in 78.87% of cases and benign in 21.13%. Two clinical characteristics (age and gender) and four radiological characteristics (calcification, vascular convergence, pleural retraction sign, and density) were identified as independent predictors of malignancy in patients with SPN using logistic regression analysis. The area under the receiver operating characteristic curve (0.748) of the present model was greater than the other two reported models. Diameter, spiculation, lobulation, vascular convergence, and pleural retraction signs differed significantly among pre-invasive lesions, minimally invasive adenocarcinoma, and invasive adenocarcinoma. Only diameter and density were significantly different among invasive adenocarcinoma subtypes. CONCLUSIONS Older age, male gender, no calcification, vascular convergence, pleural contraction sign, and lower density were independent malignancy predictors of SPNs. Furthermore, the pathological classification can be clarified based on the radiological characteristics of SPN, providing a new option for the prevention and treatment of early lung cancer.

Zhou Y., Cao X., Gu H., Gao S., Wu Y., Li H., Xiong B., Dong H., Lv Y., Yang R., Wu Y.

Abstract Background The widespread utilization of chest High-resolution Computed Tomography (HRCT) has prompted detection of pulmonary ground-glass nodules (GGNs) in otherwise asymptomatic individuals. We aimed to establish a simple clinical risk score model for assessing GGNs based on HRCT. Methods We retrospectively analyzed 574 GGNs in 574 patients undergoing HOOK-WIRE puncture and pulmonary nodule surgery from January 2014 to November 2018. Clinical characteristics and imaging features of the GGNs were assessed. We analyzed the differences between malignant and benign nodules using binary logistic regression analysis and constructed a simple risk score model, the VBV Score, for predicting the malignancy status of GGNs. Then, we validated this model via other 1200 GGNs in 1041 patients collected from three independent clinical centers in 2022. Results For the exploratory phase of this study, out of the 574 GGNs, 481 were malignant and 93 were benign. Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. Then, we derived a VBV Score = vacuole sign + air bronchogram + intra-nodular vessel sign, to predict the malignancy of GGNs, with a sensitivity, specificity, and accuracy of 95.6%, 80.6%, and 93.2%, respectively. We also validated it on other 1200 GGNs, with a sensitivity, specificity, and accuracy of 96.0%, 82.6%, and 95.0%, respectively. Conclusions Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. VBV Score showed good sensitivity, specificity, and accuracy for differentiating benign and malignant pulmonary GGNs.

Wang Y., Lyu D., Hu L., Wu J., Duan S., Zhou T., Tu W., Xiao Y., Fan L., Liu S.

AbstractThe study aims to investigate the value of intratumoral and peritumoral radiomics and clinical-radiological features for predicting spread through air spaces (STAS) in patients with clinical stage IA non-small cell lung cancer (NSCLC). A total of 336 NSCLC patients from our hospital were randomly divided into the training cohort (n = 236) and the internal validation cohort (n = 100) at a ratio of 7:3, and 69 patients from the other two external hospitals were collected as the external validation cohort. Univariate and multivariate analyses were used to select clinical-radiological features and construct a clinical model. The GTV, PTV5, PTV10, PTV15, PTV20, GPTV5, GPTV10, GPTV15, and GPTV20 models were constructed based on intratumoral and peritumoral (5 mm, 10 mm, 15 mm, 20 mm) radiomics features. Additionally, the radscore of the optimal radiomics model and clinical-radiological predictors were used to construct a combined model and plot a nomogram. Lastly, the ROC curve and AUC value were used to evaluate the diagnostic performance of the model. Tumor density type (OR = 6.738) and distal ribbon sign (OR = 5.141) were independent risk factors for the occurrence of STAS. The GPTV10 model outperformed the other radiomics models, and its AUC values were 0.887, 0.876, and 0.868 in the three cohorts. The AUC values of the combined model constructed based on GPTV10 radscore and clinical-radiological predictors were 0.901, 0.875, and 0.878. DeLong test results revealed that the combined model was superior to the clinical model in the three cohorts. The nomogram based on GPTV10 radscore and clinical-radiological features exhibited high predictive efficiency for STAS status in NSCLC.

Wu S., Fan X., Li X., Luo T., Li X., Li Q.

Abstract Objectives To evaluate the clinical and non-contrast computed tomography (CT) features of patients with benign pulmonary subsolid nodules (SSNs) with a solid component ≤ 5 mm and their development trends via follow-up CT. Methods We retrospectively collected 436 data from patients who had SSNs with a solid component ≤ 5 mm, including 69 with absorbable benign SSNs (AB-SSNs), 70 with nonabsorbable benign SSNs (NB-SSNs), and 297 with malignant SSNs (M-SSNs). Models 1, 2, and 3 for distinguishing the different types of SSNs were then developed and validated. Results Patients with AB-SSNs were younger and exhibited respiratory symptoms more frequently than those with M-SSNs. The frequency of nodules detected during follow-up CT was in the following order: AB-SSNs > NB-SSNs > M-SSNs. NB-SSNs were smaller than M-SSNs, and ill-defined margins were more frequent in AB-SSNs than in NB-SSNs and M-SSNs. Benign SSNs exhibited irregular shape, target sign, and lower CT values more frequently compared to M-SSNs, whereas the latter demonstrated bubble lucency more commonly compared to the former. Furthermore, AB-SSNs showed more thickened interlobular septa and satellite lesions than M-SSNs and M-SSNs had more pleural retraction than AB-SSNs (all p < 0.017). The three models had AUCs ranging 0.748–0.920 and 0.790–0.912 in the training and external validation cohorts, respectively. A follow-up CT showed nodule progression in four benign SSNs. Conclusions The three SSN types have different clinical and imaging characteristics, with some benign SSNs progressing to resemble malignancy. Critical relevance statement A good understanding of the imaging features and development trends of benign SSNs may help reduce unnecessary follow-up or interventions. This retrospective study explores the CT characteristics of benign SSNs with a solid component ≤ 5 mm by comparing AB-SSNs, NB-SSNs, and M-SSNs and delineates their development trends via follow-up CT. Key points 1. Different subsolid nodule types exhibit distinct clinical and imaging features. 2. A miniscule number of benign subsolid nodules can progress to resemble malignancy. 3. Knowing the clinical and imaging features and development trends of benign subsolid nodules can improve management. Graphical Abstract

Fu B., Zhang X., Lv F., Chu Z.

Zhou T., Tu W., Dong P., Duan S., Zhou X., Ma Y., Wang Y., Liu T., Zhang H., Feng Y., Huang W., Ge Y., Liu S., Li Z., Fan L.

To develop and validate a model for predicting chronic obstructive pulmonary disease (COPD) in patients with lung cancer based on computed tomography (CT) radiomic signatures and clinical and imaging features.We retrospectively enrolled 443 patients with lung cancer who underwent pulmonary function test as the primary cohort. They were randomly assigned to the training (n = 311) or validation (n = 132) set in a 7:3 ratio. Additionally, an independent external cohort of 54 patients was evaluated. The radiomic lung nodule signature was constructed using the least absolute shrinkage and selection operator algorithm, while key variables were selected using logistic regression to develop the clinical and combined models presented as a nomogram.COPD was significantly related to the radiomics signature in both cohorts. Moreover, the signature served as an independent predictor of COPD in the multivariate regression analysis. For the training, internal, and external cohorts, the area under the receiver operating characteristic curve (ROC, AUC) values of our radiomics signature for COPD prediction were 0.85, 0.85, and 0.76, respectively. Additionally, the AUC values of the radiomic nomogram for COPD prediction were 0.927, 0.879, and 0.762 for the three cohorts, respectively, which outperformed the other two models.The present study presents a nomogram that incorporates radiomics signatures and clinical and radiological features, which could be used to predict the risk of COPD in patients with lung cancer with one-stop chest CT scanning.

Gao R., Gao Y., Zhang J., Zhu C., Zhang Y., Yan C.

To construct a nomogram based on subjective CT signs and artificial intelligence (AI) histogram parameters to identify invasiveness of lung adenocarcinoma presenting as pure ground-glass nodules (pGGNs) and to evaluate its diagnostic performance. 187 patients with 228 pGGNs confirmed by postoperative pathology were collected retrospectively and divided into pre-invasive group [atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS)] and invasive group [minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC)]. All pGGNs were randomly assigned to training cohort (n = 160) and validation cohort (n = 68). Nomogram was developed using subjective CT signs and AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) curve. The nomogram was constructed with nodule shape, 3D mean diameter, maximum CT value, and skewness. It showed better discriminative power in differentiating invasive lesions from pre-invasive lesions with area under curve (AUC) of 0.849 (95% CI 0.790–0.909) in the training cohort and 0.831 (95% CI 0.729–0.934) in the validation cohort, which performed better than nodule shape (AUC 0.675, 95% CI 0.609–0.741), 3D mean diameter (AUC 0.762, 95% CI 0.688–0.835), maximum CT value (AUC 0.794, 95% CI 0.727–0.862), or skewness (AUC 0.594, 95% CI 0.506–0.682) alone in training cohort (for all, P < 0.05). For pulmonary pGGNs, the nomogram based on subjective CT signs and AI histogram parameters had a good predictive ability to discriminate invasive lung adenocarcinoma from pre-invasive lung adenocarcinoma, and it has the potential to improve diagnostic efficiency and to help the patient management.

Huang W., Deng H., Li Z., Xiong Z., Zhou T., Ge Y., Zhang J., Jing W., Geng Y., Wang X., Tu W., Dong P., Liu S., Fan L.

ObjectiveTo develop and validate the model for predicting benign and malignant ground-glass nodules (GGNs) based on the whole-lung baseline CT features deriving from deep learning and radiomics.MethodsThis retrospective study included 385 GGNs from 3 hospitals, confirmed by pathology. We used 239 GGNs from Hospital 1 as the training and internal validation set; 115 and 31 GGNs from Hospital 2 and Hospital 3 as the external test sets 1 and 2, respectively. An additional 32 stable GGNs from Hospital 3 with more than five years of follow-up were used as the external test set 3. We evaluated clinical and morphological features of GGNs at baseline chest CT and extracted the whole-lung radiomics features simultaneously. Besides, baseline whole-lung CT image features are further assisted and extracted using the convolutional neural network. We used the back-propagation neural network to construct five prediction models based on different collocations of the features used for training. The area under the receiver operator characteristic curve (AUC) was used to compare the prediction performance among the five models. The Delong test was used to compare the differences in AUC between models pairwise.ResultsThe model integrated clinical-morphological features, whole-lung radiomic features, and whole-lung image features (CMRI) performed best among the five models, and achieved the highest AUC in the internal validation set, external test set 1, and external test set 2, which were 0.886 (95% CI: 0.841-0.921), 0.830 (95%CI: 0.749-0.893) and 0.879 (95%CI: 0.712-0.968), respectively. In the above three sets, the differences in AUC between the CMRI model and other models were significant (all P &lt; 0.05). Moreover, the accuracy of the CMRI model in the external test set 3 was 96.88%.ConclusionThe baseline whole-lung CT features were feasible to predict the benign and malignant of GGNs, which is helpful for more refined management of GGNs.

Zhou Y., Cao X., Gu H., Gao S., Wu Y., Li H., Xiong B., Dong H., Lv Y., Yang R., Wu Y.

Abstract Background The widespread utilization of chest High-resolution Computed Tomography (HRCT) has prompted detection of pulmonary ground-glass nodules (GGNs) in otherwise asymptomatic individuals. We aimed to establish a simple clinical risk score model for assessing GGNs based on HRCT. Methods We retrospectively analyzed 574 GGNs in 574 patients undergoing HOOK-WIRE puncture and pulmonary nodule surgery from January 2014 to November 2018. Clinical characteristics and imaging features of the GGNs were assessed. We analyzed the differences between malignant and benign nodules using binary logistic regression analysis and constructed a simple risk score model, the VBV Score, for predicting the malignancy status of GGNs. Then, we validated this model via other 1200 GGNs in 1041 patients collected from three independent clinical centers in 2022. Results For the exploratory phase of this study, out of the 574 GGNs, 481 were malignant and 93 were benign. Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. Then, we derived a VBV Score = vacuole sign + air bronchogram + intra-nodular vessel sign, to predict the malignancy of GGNs, with a sensitivity, specificity, and accuracy of 95.6%, 80.6%, and 93.2%, respectively. We also validated it on other 1200 GGNs, with a sensitivity, specificity, and accuracy of 96.0%, 82.6%, and 95.0%, respectively. Conclusions Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. VBV Score showed good sensitivity, specificity, and accuracy for differentiating benign and malignant pulmonary GGNs.