Deep Learning For Automatic Gross Tumor Volumes Contouring in Esophageal Cancer Based on Contrast-Enhanced Computed Tomography Images: A Multi-Institutional Study.

PURPOSE: To develop and externally validate an automatic artificial intelligence (AI) tool for delineating gross tumor volume (GTV) in patients with esophageal squamous cell carcinoma (ESCC), which can assist in neo-adjuvant or radical radiation therapy treatment planning. METHODS AND MATERIALS: In this multi-institutional study, contrast-enhanced CT images from 580 eligible ESCC patients were retrospectively collected. The GTV contours delineated by 2 experts via consensus were used as ground truth. A 3-dimensional deep learning model was developed for GTV contouring in the training cohort and internally and externally validated in 3 validation cohorts. The AI tool was compared against 12 board-certified experts in 25 patients randomly selected from the external validation cohort to evaluate its assistance in improving contouring performance and reducing variation. Contouring performance was measured using dice similarity coefficient (DSC) and average surface distance. Additionally, our previously established radiomics model for predicting pathologic complete response was used to compare AI-generated and ground truth contours, to assess the potential of the AI contouring tool in radiomics analysis. RESULTS: The AI tool demonstrated good GTV contouring performance in multicenter validation cohorts, with median DSC values of 0.865, 0.876, and 0.866 and median average surface distance values of 0.939, 0.789, and 0.875 mm, respectively. Furthermore, the AI tool significantly improved contouring performance for half of 12 board-certified experts (DSC values, 0.794-0.835 vs 0.856-0.881, P = .003-0.048), reduced the intra- and interobserver variations by 37.4% and 55.2%, respectively, and saved contouring time by 77.6%. In the radiomics analysis, 88.7% of radiomic features from ground truth and AI-generated contours demonstrated stable reproducibility, and similar pathologic complete response prediction performance for these contours (P = .430) was observed. CONCLUSIONS: Our AI contouring tool can improve GTV contouring performance and facilitate radiomics analysis in ESCC patients, which indicates its potential for GTV contouring during radiation therapy treatment planning and radiomics studies.

Improving the accuracy of prognosis for clinical stage I solid lung adenocarcinoma by radiomics models covering tumor per se and peritumoral changes on CT.

OBJECTIVES: To assess methods to improve the accuracy of prognosis for clinical stage I solid lung adenocarcinoma using radiomics based on different volumes of interests (VOIs). METHODS: This retrospective study included patients with postoperative clinical stage I solid lung adenocarcinoma from two hospitals, center 1 and center 2. Three databases were generated: dataset A (training set from center 1), dataset B (internal test set from center 1), and dataset C (external validation test from center 2). Disease-free survival (DFS) data were collected. CT radiomics models were constructed based on four VOIs: gross tumor volume (GTV), 3 mm external to the tumor border (peritumoral volume [PTV]0~+3), 6 mm crossing tumor border (PTV-3~+3), and 6 mm external to the tumor border (PTV0~+6). The area under the receiver operating characteristic curve (AUC) was used to compare the model accuracies. RESULTS: A total of 334 patients were included (204 and 130 from centers 1 and 2). The model using PTV-3~+3 (AUC 0.81 [95% confidence interval {CI}: 0.75, 0.94], 0.81 [0.63, 0.90] for datasets B and C) outperformed the other three models, GTV (0.73 [0.58, 0.81], 0.73 [0.58, 0.83]), PTV0~+3 (0.76 [0.52, 0.87], 0.75 [0.60, 0.83]), and PTV0~+6 (0.72 [0.60, 0.81], 0.69 [0.59, 0.81]), in datasets B and C, all p < 0.05. CONCLUSIONS: A radiomics model based on a VOI of 6 mm crossing tumor border more accurately predicts prognosis of clinical stage I solid lung adenocarcinoma than that based on VOIs including overall tumor or external rims of 3 mm and 6 mm. KEY POINTS: • Radiomics is a useful approach to improve the accuracy of prognosis for stage I solid adenocarcinoma. • The radiomics model based on VOIs that includes 3 mm within and external to the tumor border (peritumoral volume [PTV]-3~+3) outperformed models that included either only the tumor itself or those that only included the peritumoral volume.

Construction of a Prognostic Model in Lung Adenocarcinoma Based on Ferroptosis-Related Genes.

Background: Lung adenocarcinoma is one of the most common malignant tumors of the respiratory system, ranking first in morbidity and mortality among all cancers. This study aims to establish a ferroptosis-related gene-based prognostic model to investigate the potential prognosis of lung adenocarcinoma. Methods: We obtained gene expression data with matching clinical data of lung adenocarcinoma from the The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. The ferroptosis-related genes (FRGs) were downloaded from three subgroups in the ferroptosis database. Using gene expression differential analysis, univariate Cox regression, and LASSO regression analysis, seven FRGs with prognostic significance were identified. The result of multivariate Cox analysis was utilized to calculate regression coefficients and establish a risk-score formula that divided patients with lung adenocarcinoma into high-risk and low-risk groups. The TCGA results were validated using GEO data sets. Then we observed that patients divided in the low-risk group lived longer than the overall survival (OS) of the other. Then we developed a novel nomogram including age, gender, clinical stage, TNM stage, and risk score. Results: The areas under the curves (AUCs) for 3- and 5-years OS predicted by the model were 0.823 and 0.852, respectively. Calibration plots and decision curve analysis also confirmed the excellent predictive performance of the model. Subsequently, gene function enrichment analysis revealed that the identified FRGs are important in DNA replication, cell cycle regulation, cell adhesion, chromosomal mutation, oxidative phosphorylation, P53 signaling pathway, and proteasome processes. Conclusions: Our results verified the prognostic significance of FRGs in patients with lung adenocarcinoma, which may regulate tumor progression in a variety of pathways.

Assessing the predictive accuracy of lung cancer, metastases, and benign lesions using an artificial intelligence-driven computer aided diagnosis system.

BACKGROUND: Artificial intelligence (AI) products have been widely used for the clinical detection of primary lung tumors. However, their performance and accuracy in risk prediction for metastases or benign lesions remain underexplored. This study evaluated the accuracy of an AI-driven commercial computer-aided detection (CAD) product (InferRead CT Lung Research, ICLR) in malignancy risk prediction using a real-world database. METHODS: This retrospective study assessed 486 consecutive resected lung lesions, including 320 adenocarcinomas, 40 other malignancies, 55 metastases, and 71 benign lesions, from September 2015 to November 2018. The malignancy risk probability of each lesion was obtained using the ICLR software based on a 3D convolutional neural network (CNN) with DenseNet architecture as a backbone (without clinical data). Two resident doctors independently graded each lesion using patient clinical history. One doctor (R1) has 3 years of chest radiology experience, and the other doctor (R2) has 3 years of general radiology experience. Cochran's Q test was used to assess the performances of the AI compared to the radiologists. RESULTS: The accuracy of malignancy-risk prediction using the ICLR for adenocarcinomas, other malignancies, metastases, and benign lesions was 93.4% (299/320), 95.0% (38/40), 50.9% (28/55), and 40.8% (29/71), respectively. The accuracy was significantly higher in adenocarcinomas and other malignancies compared to metastases and benign lesions (all P<0.05). The overall accuracy of risk prediction for R1 was 93.6% (455/486) and 87.4% for R2 (425/486), both of which were higher than the 81.1% accuracy obtained with the ICLR (394/486) (R1 vs. ICLR: P<0.001; R2 vs. ICLR: P=0.001), especially in assessing the risk of metastases (P<0.05). R1 performed better than R2 at risk prediction (P=0.001). CONCLUSIONS: The accuracy of the ICLR for risk prediction is very high for primary lung cancers but poor for metastases and benign lesions.

Early prediction of severity in coronavirus disease (COVID-19) using quantitative CT imaging.

PURPOSE: To evaluate whether the extent of COVID-19 pneumonia on CT scans using quantitative CT imaging obtained early in the illness can predict its future severity. METHODS: We conducted a retrospective single-center study on confirmed COVID-19 patients between January 18, 2020 and March 5, 2020. A quantitative AI algorithm was used to evaluate each patient's CT scan to determine the proportion of the lungs with pneumonia (VR) and the rate of change (RAR) in VR from scan to scan. Patients were classified as being in the severe or non-severe group based on their final symptoms. Penalized B-splines regression modeling was used to examine the relationship between mean VR and days from onset of symptoms in the two groups, with 95% and 99% confidence intervals. RESULTS: Median VR max was 18.6% (IQR 9.1-32.7%) in 21 patients in the severe group, significantly higher (P < 0.0001) than in the 53 patients in non-severe group (1.8% (IQR 0.4-5.7%)). RAR was increasing with a median RAR of 2.1% (IQR 0.4-5.5%) in severe and 0.4% (IQR 0.1-0.9%) in non-severe group, which was significantly different (P < 0.0001). Penalized B-spline analyses showed positive relationships between VR and days from onset of symptom. The 95% confidence limits of the predicted means for the two groups diverged 5 days after the onset of initial symptoms with a threshold of 11.9%. CONCLUSION: Five days after the initial onset of symptoms, CT could predict the patients who later developed severe symptoms with 95% confidence.

The prevalence and related factors of metabolic syndrome in outpatients with first-episode drug-naive major depression comorbid with anxiety.

Metabolic syndrome (MetS) is associated with depression, but its role in major depressive disorder comorbid with anxiety (AMD) is unclear. This study aimed to investigate the prevalence and clinical correlates of MetS in first-episode drug-naive (FEDN) patients with AMD in a Chinese Han population. In total, 1380 FEDN outpatients with AMD were recruited in this cross-sectional study. The sociodemographic features, clinical characteristics, history of suicide attempts, thyroid-stimulating hormone (TSH) levels, and MetS parameters of each subject were evaluated. All subjects were rated on the Hamilton Depression Rating Scale (HAM-D), Hamilton Anxiety Rating Scale (HAM-A), and the Positive and Negative Syndrome Scale positive symptom subscale. The prevalence of MetS among AMD patients was 8.04%. Compared to the non-MetS group, age, age of onset, TSH level, HAM-A and HAM-D scores, history of attempted suicide, and comorbid psychiatric symptoms were higher in the MetS group. Those in this group were also more likely to be married, and they had a lower educational level. Furthermore, age, psychiatric symptoms, suicide attempts, and higher TSH levels were independently associated with MetS in AMD patients. This study suggests a lower prevalence of MetS in FEDN patients with AMD in a Chinese Han population. Older age, comorbid psychiatric symptoms, history of attempted suicide, and higher TSH levels are related factors for MetS in AMD patients.

CT image visual quantitative evaluation and clinical classification of coronavirus disease (COVID-19).

OBJECTIVES: To explore the relationship between the imaging manifestations and clinical classification of COVID-19. METHODS: We conducted a retrospective single-center study on patients with COVID-19 from Jan. 18, 2020 to Feb. 7, 2020 in Zhuhai, China. Patients were divided into 3 types based on Chinese guideline: mild (patients with minimal symptoms and negative CT findings), common, and severe-critical (patients with positive CT findings and different extent of clinical manifestations). CT visual quantitative evaluation was based on summing up the acute lung inflammatory lesions involving each lobe, which was scored as 0 (0%), 1 (1-25%), 2 (26-50%), 3 (51-75%), or 4 (76-100%), respectively. The total severity score (TSS) was reached by summing the five lobe scores. The consistency of two observers was evaluated. The TSS was compared with the clinical classification. ROC was used to test the diagnosis ability of TSS for severe-critical type. RESULTS: This study included 78 patients, 38 males and 40 females. There were 24 mild (30.8%), 46 common (59.0%), and 8 severe-critical (10.2%) cases, respectively. The median TSS of severe-critical-type group was significantly higher than common type (p < 0.001). The ICC value of the two observers was 0.976 (95% CI 0.962-0.985). ROC analysis showed the area under the curve (AUC) of TSS for diagnosing severe-critical type was 0.918. The TSS cutoff of 7.5 had 82.6% sensitivity and 100% specificity. CONCLUSIONS: The proportion of clinical mild-type patients with COVID-19 was relatively high; CT was not suitable for independent screening tool. The CT visual quantitative analysis has high consistency and can reflect the clinical classification of COVID-19. KEY POINTS: • CT visual quantitative evaluation has high consistency (ICC value of 0.976) among the observers. The median TSS of severe-critical type group was significantly higher than common type (p < 0.001). • ROC analysis showed the area under the curve (AUC) of TSS for diagnosing severe-critical type was 0.918 (95% CI 0.843-0.994). The TSS cutoff of 7.5 had 82.6% sensitivity and 100% specificity. • The proportion of confirmed COVID-19 patients with normal chest CT was relatively high (30.8%); CT was not a suitable screening modality.