BACKGROUND: Lung cancer is one of the most common malignant tumors worldwide and a major cause of cancer-related deaths. Early-stage lung cancer is often manifested as pulmonary nodules, and accurate assessment of the malignancy risk is crucial for prolonging survival and avoiding overtreatment. This study aims to construct a model based on image feature parameters automatically extracted by artificial intelligence (AI) to evaluate its effectiveness in predicting the malignancy of part-solid nodule (PSN). METHODS: This retrospective study analyzed 229 PSN from 222 patients who underwent pulmonary nodule resection at Lanzhou University Second Hospital between October 2020 and February 2025. According to pathological results, 45 cases of benign lesions and precursor glandular lesion were categorized into the non-malignant group, and 184 cases of pulmonary malignancies were categorized into the malignant group. All patients underwent preoperative chest computed tomography (CT), and AI software was used to extract imaging feature parameters. Univariate analysis was used to screen significant variables; variance inflation factor (VIF) was calculated to exclude highly collinear variables, and LASSO regression was further applied to identify key features. Multivariate Logistic regression was used to determine independent risk factors. Based on the selected variables, five models were constructed: Logistic regression, random forest, XGBoost, LightGBM, and support vector machine (SVM). Receiver operating characteristic (ROC) curves were used to assess the performance of the models. RESULTS: The independent risk factors for the malignancy of PSN include roughness (ngtdm), dependence variance (gldm), and short run low gray-level emphasis (glrlm). Logistic regression achieved area under the curves ( AUCs) of 0.86 and 0.89 in the training and testing sets, respectively, showing good performance. XGBoost had AUCs of 0.78 and 0.77, respectively, demonstrating relatively balanced performance, but with lower accuracy. SVM showed an AUC of 0.93 in the training set, which decreased to 0.80 in the testing set, indicating overfitting. LightGBM performed excellently in the training set with an AUC of 0.94, but its performance declined in the testing set, with an AUC of 0.88. In contrast, random forest demonstrated stable performance in both the training and testing sets, with AUCs of 0.89 and 0.91, respectively, exhibiting high stability and excellent generalizability. CONCLUSIONS The random forest model constructed based on independent risk factors demonstrated the best performance in predicting the malignancy of PSN and could provide effective auxiliary predictions for clinicians, supporting individualized treatment decisions.
.
Humans ; Male ; Female ; Lung Neoplasms/pathology* ; Middle Aged ; Retrospective Studies ; Artificial Intelligence ; Aged ; Tomography, X-Ray Computed ; Adult ; Solitary Pulmonary Nodule/diagnostic imaging* ; ROC Curve

The incidence and mortality of lung cancer rank first among all malignant tumors in China. With the popularization of high resolution computed tomography (CT) in clinic, chest CT has become an important means of clinical screening for early lung cancer and reducing the mortality of lung cancer. Imaging findings of early lung adenocarcinoma often show partial solid nodules with ground glass components. With the development of imaging, the relationship between the imaging features of some solid nodules and their prognosis has attracted more and more attention. At the same time, with the development of 3D-reconstruction technology, clinicians can improve the accuracy of diagnosis and treatment of such nodules.This article focuses on the traditional imaging analysis of partial solid nodules and the imaging analysis based on 3D reconstruction, and systematically expounds the advantages and disadvantages of both.
.
Adenocarcinoma of Lung/pathology* ; Humans ; Image Processing, Computer-Assisted ; Lung Neoplasms/pathology* ; Solitary Pulmonary Nodule/pathology* ; Tomography, X-Ray Computed

Due to emphasis on early screening for lung cancer, the detection rate of multiple ground glass opacities (GGOs) on computed tomography (CT) image increases in recent years, and research on multifocal adenocarcinomas presented by GGOs has been thriving. It is more common in women and non-smokers and has excellent prognosis both in patients with natural history and after surgery. These clinical features suggest that it is likely to be a distinct disease entity. From the perspective of molecular genetics, lesions in the same individual are likely to have distinct clonal features. Therefore, genetic heterogeneity is the most prominent feature of multifocal pulmonary adenocarcinomas with GGOs. The genetic heterogeneity is expected to assist the diagnosis of multifocal pulmonary adenocarcinoma and intrapulmonary metastasis, and also suggests that genetic testing of the GGO lesions is of great therapeutic significance. Some GGO lesions may harvest the similar clonal feature, which provide new evidence for the theory of spread through air spaces (STAS).
.
Adenocarcinoma ; diagnostic imaging ; genetics ; pathology ; Adenocarcinoma of Lung ; Humans ; Lung Neoplasms ; diagnostic imaging ; genetics ; pathology ; Retrospective Studies ; Solitary Pulmonary Nodule ; diagnostic imaging ; genetics ; pathology ; Tomography, X-Ray Computed

We report a case of inadvertent hoarseness after surgery for primary pulmonary amyloidosis. A 55-year-old male was transferred to our facility due to a lung mass. Chest computed tomography revealed a solitary pulmonary nodule. Positron emission tomography-computed tomography showed fluorodeoxyglucose uptake in the main mass and in the mediastinal lymph nodes. To confirm the pathology of the mass, wedge resection and thorough lymph node dissection were performed via video-assisted thoracic surgery (VATS). No complications except for hoarseness were observed; hoarseness developed soon after surgery and lasted for 3 months. The main mass was diagnosed as amyloidosis, but this was not found in the lymph nodes. In conclusion, VATS wedge resection for peripheral amyloidosis is a feasible and safe procedure. However, mediastinal lymph node dissection is not recommended unless there is evidence of a clear benefit.
Amyloidosis* ; Electrons ; Hoarseness ; Humans ; Lung ; Lymph Node Excision ; Lymph Nodes ; Lymphatic Diseases* ; Male ; Middle Aged ; Pathology ; Solitary Pulmonary Nodule ; Thoracic Surgery, Video-Assisted ; Thorax

OBJECTIVETo assess the value of (18)F-FDG PET/CT in the diagnosis of solitary nodular-type bronchoalveolar carcinoma (BAC).

METHODSThe clinical and radiographic data were analyzed retrospectively in 30 patients with pathologically confirmed solitary nodular-type BAC who underwent (18)F-FDG PET/CT examinations between August, 2005 and December, 2006. The morphological and radioactive findings of the lesions were reviewed, and the maximum standard uptake values (SUVmax) were measured. The diagnostic accuracy of PET, PET/CT, and HRCT were analyzed.

RESULTSThe (18)F-FDG SUV was markedly lower in BAC than in other well differentiated adenocarcinoma. In 19 of the BAC cases, PET showed a SUVmax of no less than 2.5, demonstrating positive changes. Of the total of 30 cases, 5 had ground glass opacity (GGO) changes, 3 exhibited mixed nodules with GGO changes around the lesions, and 22 cases presented with solid nodules. HRCT showed that BAC located often in the superior lobes of the bilateral lungs, mostly below the pleura in the surrounding lung field; the lesions were patchy or nodular with irregular shapes, showing lobulation in 22 cases, spiculation in 15 cases, pleural indentation in 21 cases, and vacuolar changes in 4 cases. The diagnostic accuracy of PET, PET/CT and HRCT for solitary nodular-type BAC was 36.67%, 93.33%, and 93.33%, respectively.

CONCLUSIONThe SUVmax of BAC provides only limited value for defining the nature of the lesions, but can serve as a general reference for assessing the disease activity. PET/CT, which allows both functional and imaging assessment, can be a valuable modality to reduce the misdiagnosis rate of BAC.

Carcinoma ; diagnosis ; Fluorodeoxyglucose F18 ; Humans ; Lung ; pathology ; Lung Neoplasms ; diagnosis ; Positron-Emission Tomography ; Retrospective Studies ; Solitary Pulmonary Nodule ; diagnosis ; Tomography, X-Ray Computed

OBJECTIVETo explore the CT features of ground-glass nodules (GGN) including preinvasive lesions [atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS)], minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC).

METHODSNinety-seven GGN lesions confirmed by operation pathology were included in this study. The lesions were divided into three groups: preinvasive lesion group (24 cases), MIA group (39 cases), IAC group (34 cases). The lesion size, 3-dimensional ratio, 2-dimensional ratio in axial images, lesion density, shape, speculation, lobulation, air-containing space and pleural indentation on the preoperative CT images in the three groups were analyzed and compared with pathological results. The data were statistically analyzed using SPSS 17.0.

RESULTSAll preinvasive lesions presented as pure GGN on CT image, most showed round-like shape, clear and smooth border. MIA presented as pure GGN or mixed GGN on CT image, most showed round-like shape, with a clear and smooth border. IAC most presented as mixed GGN on CT image, often showed irregular shape. Speculation, lobulation, air-containing space and pleural indentation displayed gradually increasing from preinvasive lesions to MIA and IAC. There were statistically significant differences in lesion size, CT density, shape, air-containing space, speculation, pleural indentation and long diameter of solid component between the MIA and IAC groups (P < 0.05 for all). There were statistically significant differences in CT density values and long diameters of solid component of the lesions between the preinvasive lesion group and MIA group (P < 0.05). The AUC of solid component of the preinvasive lesion group and MIA group was 0.705, and that of the MIA and IAC groups was 0.814.

CONCLUSIONComprehensive analysis of the CT image features of GGNs, especially the solid component in the lesions, may help to the preoperative and differential diagnosis of preinvasive lesions, MIA and IAC.

Adenocarcinoma ; diagnostic imaging ; pathology ; Adult ; Aged ; Diagnosis, Differential ; Female ; Humans ; Hyperplasia ; Lung ; diagnostic imaging ; pathology ; Lung Neoplasms ; diagnostic imaging ; pathology ; Male ; Middle Aged ; Neoplasm Invasiveness ; Precancerous Conditions ; diagnostic imaging ; pathology ; Solitary Pulmonary Nodule ; diagnostic imaging ; pathology ; Tomography, X-Ray Computed

Humans ; Printing ; methods ; ROC Curve ; Solitary Pulmonary Nodule ; pathology

As the detection and characterization of lung nodules are of paramount importance in thoracic radiology, various tools for making a computer-aided diagnosis (CAD) have been developed to improve the diagnostic performance of radiologists in clinical practice. Numerous studies over the years have shown that the CAD system can effectively help readers identify more nodules. Moreover, nodule malignancy and the response of malignant lung tumors to treatment can also be assessed using nodule volumetry. CAD also has the potential to objectively analyze the morphology of nodules and enhance the workflow during the assessment of follow-up studies. Therefore, understanding the current status and limitations of CAD for evaluating lung nodules is essential to effectively apply CAD in clinical practice.
Clinical Trials as Topic ; *Diagnosis, Computer-Assisted ; Diagnosis, Differential ; Humans ; Lung Neoplasms/pathology/*radiography ; Predictive Value of Tests ; Radiographic Image Interpretation, Computer-Assisted ; Radiography, Thoracic ; Sensitivity and Specificity ; Solitary Pulmonary Nodule/pathology/*radiography ; *Tomography, X-Ray Computed

OBJECTIVE: We wanted to evaluate the usefulness of the computer-aided detection (CAD) system for detecting pulmonary nodules in real clinical practice by using the CT images. MATERIALS AND METHODS: Our Institutional Review Board approved our retrospective study with a waiver of informed consent. This study included 166 CT examinations that were performed for the evaluation of pulmonary metastasis in 166 patients with colorectal cancer. All the CT examinations were interpreted by radiologists and they were also evaluated by the CAD system. All the nodules detected by the CAD system were evaluated with regard to whether or not they were true nodules, and they were classified into micronodules (MN, diameter < 4 mm) and significant nodules (SN, 4 < or = diameter < or = 10 mm). The radiologic reports and CAD results were compared. RESULTS: The CAD system helped detect 426 nodules; 115 (27%) of the 426 nodules were classified as true nodules and 35 (30%) of the 115 nodules were SNs, and 83 (72%) of the 115 were not mentioned in the radiologists' reports and three (4%) of the 83 nodules were non-calcified SNs. One of three non-calcified SNs was confirmed as a metastatic nodule. According to the radiologists' reports, 60 true nodules were detected, and 28 of the 60 were not detected by the CAD system. CONCLUSION: Although the CAD system missed many SNs that are detected by radiologists, it helps detect additional nodules that are missed by the radiologists in real clinical practice. Therefore, the CAD system can be useful to support a radiologist's detection performance.
Colorectal Neoplasms/*pathology ; *Diagnosis, Computer-Assisted ; Female ; Humans ; Lung Neoplasms/*radiography/secondary ; Male ; Middle Aged ; Retrospective Studies ; Solitary Pulmonary Nodule/*radiography/secondary ; *Tomography, X-Ray Computed

OBJECTIVETo evaluate the value of dynamic enhanced-CT in differential diagnosis of solitary pulmonary nodules.

METHODSSixty-three solitary pulmonary nodules were evaluated by dynamic enhanced multi-slice CT. Images were obtained before and at 20 s, 30 s, 45 s, 60 s, 75 s, 90 s, 120 s, 180 s, 300 s, 540 s, 720 s, 900 s and 1200 s after the injection of contrast media. All lesion enhanced parameters and morphological features were recorded. The differences between benign and malignant nodules were analyzed. The diagnostic sensitivity and specificity of solitary pulmonary nodules were evaluated by receiver operator characteristic analysis.

RESULTSCT enhancement value at 120 s [(29.5 ± 30.2) HU vs. (32.5 ± 14.7) HU, P = 0.023], washout at 20 min [(36.5 ± 24.6) HU vs. (15.6 ± 16.6) HU, P = 0.044], washout ratio at 20 min [(36.5 ± 24.6)% vs. (17.8 ± 14.5)%, P = 0.006], slope of washout at 20 min [(0.006 ± 0.005)%/s vs. (0.002 ± 0.0016)%/s, P = 0.001], type II (24/42 vs. 4/21, P = 0.004) and III (5/42 vs. 9/21, P = 0.005) curves were significantly different between benign and malignant nodules. Using the above mentioned parameters, the results of receiver operator characteristic analysis had a sensitivity of 64.3% and specificity of 84.2% for identification of malignant tumors. The morphological features including round-like, triangle-like, multi-angle, spiculation, light lobulation, the degree of edge (sharp, clear, blur), vessel convergence sign, vacuole sign, airing of bronchi, cut-off of the bronchi and depression of pleura were significantly different between benign and malignant nodules. The results of ROC analysis showed that the above mentioned morphological features had a sensitivity of 92.9% and specificity of 100% for differentiating malignant tumors from benign nodules. The results of ROC analysis showed that combination of morphological features and dynamic enhancement parameters had a sensitivity of 95.2% and specificity of 100% for identification of malignant tumors.

CONCLUSIONSDynamic enhanced CT images can evaluate morphological and enhancement features of solitary pulmonary nodules. Combination of morphological features and enhancement characteristics can improve the accuracy of diagnosis.

Adenocarcinoma ; diagnostic imaging ; Adult ; Aged ; Carcinoma, Squamous Cell ; diagnostic imaging ; Colonic Neoplasms ; pathology ; Contrast Media ; Diagnosis, Differential ; Female ; Hamartoma ; diagnostic imaging ; Humans ; Lung Diseases ; diagnostic imaging ; Lung Neoplasms ; diagnostic imaging ; secondary ; Male ; Middle Aged ; ROC Curve ; Radiographic Image Enhancement ; Sensitivity and Specificity ; Solitary Pulmonary Nodule ; diagnostic imaging ; Tomography, Spiral Computed ; methods ; Tuberculoma ; diagnostic imaging ; Tuberculosis, Pulmonary ; diagnostic imaging