The Computed Tomography Findings and Follow-up Course of Pulmonary Nocardiosis.

OBJECTIVE: Our study aimed to elucidate the computed tomography (CT) features and follow-up course of pulmonary nocardiosis patients to improve the understanding and diagnostic accuracy of this disease. METHODS: The chest CT findings and clinical data of patients diagnosed with pulmonary nocardiosis by culture or histopathological examination in our hospital between 2010 and 2019 were retrospectively analyzed. RESULTS: A total of 34 cases of pulmonary nocardiosis were included in our study. Thirteen patients were on long-term immunosuppressant therapy, among whom 6 had disseminated nocardiosis. Among the immunocompetent patients, 16 had chronic lung diseases or a history of trauma. Multiple or solitary nodules represented the most common CT feature (n = 32, 94.12%), followed by ground-glass opacities (n = 26, 76.47%), patchy consolidations (n = 25, 73.53%), cavitations (n = 18, 52.94%), and masses (n = 11, 32.35%). There were 20 cases (61.76%) with mediastinal and hilar lymphadenopathy, 18 (52.94%) with pleural thickening, 15 (44.12%) with bronchiectasis, and 13 (38.24%) with pleural effusion. Significantly higher rates of cavitations were observed among immunosuppressed patients (85% vs 29%, P = 0.005). At follow-up, 28 patients (82.35%) clinically improved with treatment, while 5 (14.71%) had disease progression, and 1 (2.94%) died. CONCLUSIONS: Chronic structural lung diseases and long-term immunosuppressant use were found as risk factors for pulmonary nocardiosis. While the CT manifestations were highly heterogeneous, clinical suspicion should be raised upon findings of coexisting nodules, patchy consolidations, and cavitations, particularly in the presence of extrapulmonary infections such as those of the brain and subcutaneous tissues. A significant incidence of cavitations may be observed among immunosuppressed patients.

Radiomics Analysis of Multiphasic Computed Tomography Images for Distinguishing High-Risk Thymic Epithelial Tumors From Low-Risk Thymic Epithelial Tumors.

OBJECTIVES: The objective of this study is to preoperatively investigate the value of multiphasic contrast-enhanced computed tomography (CT)-based radiomics signatures for distinguishing high-risk thymic epithelial tumors (HTET) from low-risk thymic epithelial tumors (LTET) compared with conventional CT signatures. MATERIALS AND METHODS: Pathologically confirmed 305 thymic epithelial tumors (TETs), including 147 LTET (Type A/AB/B1) and 158 HTET (Type B2/B3/C), were retrospectively analyzed, and were randomly divided into training (n = 214) and validation cohorts (n = 91). All patients underwent nonenhanced, arterial contrast-enhanced, and venous contrast-enhanced CT analysis. The least absolute shrinkage and selection operator regression with 10-fold cross-validation was performed for radiomic models building, and multivariate logistic regression analysis was performed for radiological and combined models building. The performance of the model was evaluated by the area under the receiver operating characteristic curve (AUC of ROC), and the AUCs were compared using the Delong test. Decision curve analysis was used to evaluate the clinical value of each model. Nomogram and calibration curves were plotted for the combined model. RESULTS: The AUCs for radiological model in the training and validation cohorts were 0.756 and 0.733, respectively. For nonenhanced, arterial contrast-enhanced, venous contrast-enhanced CT and 3-phase images combined radiomics models, the AUCs were 0.940, 0.946, 0.960, and 0.986, respectively, in the training cohort, whereas 0.859, 0.876, 0.930, and 0.923, respectively, in the validation cohort. The combined model, including CT morphology and radiomics signature, showed AUCs of 0.990 and 0.943 in the training and validation cohorts, respectively. Delong test and decision curve analysis showed that the predictive performance and clinical value of the 4 radiomics models and combined model were greater than the radiological model ( P < 0.05). CONCLUSIONS: The combined model, including CT morphology and radiomics signature, greatly improved the predictive performance for distinguishing HTET from LTET. Radiomics texture analysis can be used as a noninvasive method for preoperative prediction of the pathological subtypes of TET.

Multi-scale segmentation squeeze-and-excitation UNet with conditional random field for segmenting lung tumor from CT images.

BACKGROUND AND OBJECTIVE: Lung cancer counts among diseases with the highest global morbidity and mortality rates. The automatic segmentation of lung tumors from CT images is of vast significance. However, the segmentation faces several challenges, including variable shapes and different sizes, as well as complicated surrounding tissues. METHODS: We propose a multi-scale segmentation squeeze-and-excitation UNet with a conditional random field (M-SegSEUNet-CRF) to automatically segment lung tumors from CT images. M-SegSEUNet-CRF employs a multi-scale strategy to solve the problem of variable tumor size. Through the spatially adaptive attention mechanism, the segmentation SE blocks embedded in 3D UNet are utilized to highlight tumor regions. The dense connected CRF framework is further added to delineate tumor boundaries at a detailed level. In total, 759 CT scans of patients with lung cancer were used to train and evaluate the M-SegSEUNet-CRF model (456 for training, 152 for validation, and 151 for test). Meanwhile, the public NSCLC-Radiomics and LIDC datasets have been utilized to validate the generalization of the proposed method. The role of different modules in the M-SegSEUNet-CRF model is analyzed by the ablation experiments, and the performance is compared with that of UNet, its variants and other state-of-the-art models. RESULTS: M-SegSEUNet-CRF can achieve a Dice coefficient of 0.851 ± 0.071, intersection over union (IoU) of 0.747 ± 0.102, sensitivity of 0.827 ± 0.108, and positive predictive value (PPV) of 0.900 ± 0.107. Without a multi-scale strategy, the Dice coefficient drops to 0.820 ± 0.115; without CRF, it drops to 0.842 ± 0.082, and without both, it drops to 0.806 ± 0.120. M-SegSEUNet-CRF presented a higher Dice coefficient than 3D UNet (0.782 ± 0.115) and its variants (ResUNet, 0.797 ± 0.132; DenseUNet, 0.792 ± 0.111, and UNETR, 0.794 ± 0.130). Although the performance slightly declines with the decrease in tumor volume, M-SegSEUNet-CRF exhibits more obvious advantages than the other comparative models. CONCLUSIONS: Our M-SegSEUNet-CRF model improves the segmentation ability of UNet through the multi-scale strategy and spatially adaptive attention mechanism. The CRF enables a more precise delineation of tumor boundaries. The M-SegSEUNet-CRF model integrates these characteristics and demonstrates outstanding performance in the task of lung tumor segmentation. It can furthermore be extended to deal with other segmentation problems in the medical imaging field.

Magnetic Resonance Imaging (MRI) Phenotypes May Provide Additional Information for Risk Stratification for Encapsulated Papillary Carcinoma of the Breast.

BACKGROUND: Encapsulated papillary carcinoma (EPC) of the breast is a rare entity. EPC can be underappreciated on percutaneous biopsy, which may require additional procedures if invasion is not recognized preoperatively. We aimed to investigate the magnetic resonance imaging (MRI) phenotypes correlated with preoperative pathological risk stratification for clinical guidance. MATERIALS AND METHODS: The preoperative MRI scans of 30 patients diagnosed with 36 EPCs in multiple centers between August 2015 and February 2020 were reviewed by two breast radiologists. According to the WHO classification published in 2019, EPCs were classified into two pathological subtypes: encapsulated papillary carcinoma and encapsulated papillary carcinoma with invasion. Clinicopathological analysis of the two subtypes and MR feature analysis were performed. RESULTS: Evaluation of the MRI phenotypes and pathological subtype information revealed that not circumscribed (P=0.04) was more common in EPCs with invasion than in EPCs. There was a significant difference in the age of patients (P=0.05), and the risk increased with age. The maximum diameter of the tumor increased with tumor risk, but there was no significant difference (P=0.36). Nearly half of the EPC with invasion patients showed hyperintensity on T1WI (P=0.19). A total of 63.6% of the EPC with invasion group showed non-mass enhancement surrounding (P=0.85). In addition, 29 patients (96.7%) had no axillary lymph node metastasis, and only one patient with EPC with invasion had axillary lymph node metastasis. Further pathological information analysis of EPCs showed that higher Ki-67 levels were more common in patients with EPCs with invasion (P=0.04). A total of 29 patients (96.7%) had the luminal phenotype, and one patient with EPC with invasion had the Her-2-positive phenotype. CONCLUSION: The margin, age and Ki-67 level were the key features for EPC risk stratification. In addition, these MRI signs, including a larger tumor, non-mass enhancement surrounding and axillary lymph node metastasis, may be suggestive of a high-risk stratification. Therefore, MRI phenotypes may provide additional information for the risk stratification of EPCs.

Deep CNN Model Using CT Radiomics Feature Mapping Recognizes EGFR Gene Mutation Status of Lung Adenocarcinoma.

To recognize the epidermal growth factor receptor (EGFR) gene mutation status in lung adenocarcinoma (LADC) has become a prerequisite of deciding whether EGFR-tyrosine kinase inhibitor (EGFR-TKI) medicine can be used. Polymerase chain reaction assay or gene sequencing is for measuring EGFR status, however, the tissue samples by surgery or biopsy are required. We propose to develop deep learning models to recognize EGFR status by using radiomics features extracted from non-invasive CT images. Preoperative CT images, EGFR mutation status and clinical data have been collected in a cohort of 709 patients (the primary cohort) and an independent cohort of 205 patients. After 1,037 CT-based radiomics features are extracted from each lesion region, 784 discriminative features are selected for analysis and construct a feature mapping. One Squeeze-and-Excitation (SE) Convolutional Neural Network (SE-CNN) has been designed and trained to recognize EGFR status from the radiomics feature mapping. SE-CNN model is trained and validated by using 638 patients from the primary cohort, tested by using the rest 71 patients (the internal test cohort), and further tested by using the independent 205 patients (the external test cohort). Furthermore, SE-CNN model is compared with machine learning (ML) models using radiomics features, clinical features, and both features. EGFR(-) patients show the smaller age, higher odds of female, larger lesion volumes, and lower odds of subtype of acinar predominant adenocarcinoma (APA), compared with EGFR(+). The most discriminative features are for texture (614, 78.3%) and the features of first order of intensity (158, 20.1%) and the shape features (12, 1.5%) follow. SE-CNN model can recognize EGFR mutation status with an AUC of 0.910 and 0.841 for the internal and external test cohorts, respectively. It outperforms the CNN model without SE, the fine-tuned VGG16 and VGG19, three ML models, and the state-of-art models. Utilizing radiomics feature mapping extracted from non-invasive CT images, SE-CNN can precisely recognize EGFR mutation status of LADC patients. The proposed method combining radiomics features and deep leaning is superior to ML methods and can be expanded to other medical applications. The proposed SE-CNN model may help make decision on usage of EGFR-TKI medicine.

Is a 5-mm diameter an appropriate cut-off value for the diagnosis of atypical adenomatous hyperplasia and adenocarcinoma in situ on chest computed tomography and pathological examination?

BACKGROUND: Preinvasive lesions, such as atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS), usually appear as pure ground-glass nodules (pGGNs) on thin-section computed tomography (TSCT). AAH is usually less than 5 mm wide on imaging and pathological examinations. We aimed to determine whether a 5-mm cut-off value was appropriate for the diagnosis of AAH and AIS. METHODS: We retrospectively analyzed the performance of TSCT in evaluating 80 pathologically confirmed preinvasive lesions (33 AAH lesions in 31 patients and 47 AIS lesions in 45 patients). We compared the following characteristics between the AAH and AIS groups: lesion diameter, density, rim, lobulation, spiculation, vacuole sign, aerated bronchus sign, pleural indentation sign, and pathological findings. RESULTS: All 80 lesions appeared as pGGNs. On TSCT, the average diameter of AAH lesions (6.0±1.64 mm) was significantly smaller than that of AIS lesions (8.7±3.16 mm; P<0.001). The area under the curve (AUC) for diameter was 0.792, and the best diagnostic cut-off value was 6.99 mm. On gross pathological examination, the average diameter of AAH lesions (4.6±1.99 mm) was significantly smaller that of AIS lesions (6.8±2.06 mm; P<0.001). The AUC was 0.794, and the best diagnostic cut-off value was 4.5 mm. The vacuole sign was common in AIS (P=0.021). AAH did not significantly differ from AIS (P>0.05) in terms of average CT value, uniformity of density, morphology, rim, lobulation, spiculation, pleural indentation sign, and aerated bronchus sign. CONCLUSIONS: Lesion size and the vacuole sign were beneficial in the diagnosis of AAH and AIS. The vacuole sign was common in AIS. The best diagnostic cut-off value of nodular diameter for differentiating between AAH and AIS was 6.99 mm on TSCT and 4.5 mm on gross pathology.

A new approach to predict lymph node metastasis in solid lung adenocarcinoma: a radiomics nomogram.

BACKGROUND: Lymph node metastasis (LNM) of lung cancer is an important factor related to survival and recurrence. The association between radiomics features of lung cancer and LNM remains unclear. We developed and validated a radiomics nomogram to predict LNM in solid lung adenocarcinoma. METHODS: A total of 159 eligible patients with solid lung adenocarcinoma were divided into training (n=106) and validation cohorts (n=53). Radiomics features were extracted from venous-phase CT images. We built a radiomics nomogram using a multivariate logistic regression model combined with CT-reported lymph node (LN) status. The performance of the radiomics nomogram was evaluated using the area under curve (AUC) of receiver operating characteristic curve. We performed decision curve analysis (DCA) within training and validation cohorts to assess the clinical usefulness of the nomogram. RESULTS: Fourteen radiomics features were chosen from 94 candidate features to build a radiomics signature that significantly correlated with LNM. The model showed good calibration and discrimination in the training cohort, with an AUC of 0.871 (95% CI: 0.804-0.937), sensitivity of 85.71% and specificity of 77.19%. In the validation cohort, AUC was 0.856 (95% CI: 0.745-0.966), sensitivity was 91.66%, and specificity was 82.14%. DCA demonstrated that the nomogram was clinically useful. The nomogram also showed good predictive ability in patients at high risk for LNM in the CT-reported LN negative (cN0) subgroup. CONCLUSIONS: The radiomics nomogram, based on preoperative CT images, can be used as a noninvasive method to predict LNM in patients with solid lung adenocarcinoma.

Computed Tomography Manifestations and Excision Cross-Complementation Group 1 Expression of Stage I Non-Small-Cell Lung Cancer and Their Correlation With Prognosis.

OBJECTIVE: The aim of this study was to evaluate the computed tomography (CT) manifestations and expression of the excision cross-complementation group 1 (ERCC1) and their correlation with prognosis in stage I non-small-cell lung cancer (NSCLC). MATERIALS AND METHODS: A total of 133 patients with stage I NSCLC with complete 3- and 5-year disease-free survival (DFS) and overall survival (OS) data, who underwent thoracic CT and pathological examination, were included. Expression of ERCC1 in tumor samples was evaluated using semiquantitative immunohistochemical analysis. RESULTS: The 3- and 5-year DFS rates for the 133 patients were 72.2% and 60.9%, respectively, and the 3- and 5-year OS rates were 89.5% and 82.0%, respectively. Significant differences in the 3- and 5-year DFS occurred (P = 0.003 and P = 0.001, respectively), whereas no significant differences in the 3- and 5-year OS were found (P = 0.099 and P = 0.062, respectively) between high and low ERCC1 protein expression. Patients with high expression of ERCC1 had a better prognosis. There was a significant correlation between tumors with an irregular edge and signs of spiculation on CT and low expression of ERCC1 evaluated using logistic regression analysis (P < 0.05). CONCLUSIONS: It was concluded that patients with stage I NSCLC with high ERCC1 expression had superior survival rates relative to those with low ERCC1 expression. Tumors with an irregular edge and signs of spiculation on CT were significantly correlated with low expression of ERCC1.