A novel collagen area fraction index to quantitatively assess bowel fibrosis in patients with Crohn's disease.

BACKGROUND: A validated histopathological tool to precisely evaluate bowel fibrosis in patients with Crohn's disease is lacking. We attempted to establish a new index to quantify the severity of bowel fibrosis in patients with Crohn's disease-associated fibrostenosis. METHODS: We analyzed the histopathological data of 31 patients with Crohn's disease strictures undergoing surgical resection. The most representative sections of resected strictured segments were stained with Masson trichrome to manifest bowel fibrosis. The collagen area fraction and histological fibrosis score were simultaneously calculated for the same section to evaluate the severity of bowel fibrosis. RESULTS: Collagen area fraction strongly correlated with histological fibrosis scores (r = 0.733, P < 0.001). It showed a stronger correlation (r = 0.561, P < 0.001) with the degree of bowel strictures than the histological fibrosis score did (r = 0.468, P < 0.001). It was also shown to be more accurate for diagnosing Crohn's disease strictures (area under the receiver operating characteristic curve = 0.815, P < 0.001) compared with the histological fibrosis score (area under the curve = 0.771, P < 0.001). High repeatability was observed for the collagen area fraction, with an intraclass correlation coefficient of 0.915 (P < 0.001). CONCLUSIONS: Collagen area fraction is a simple and reliable index to quantify the severity of bowel fibrosis in patients with Crohn's disease-associated fibrostenosis.

Deep learning for differentiation of osteolytic osteosarcoma and giant cell tumor around the knee joint on radiographs: a multicenter study.

OBJECTIVES: To develop a deep learning (DL) model for differentiating between osteolytic osteosarcoma (OS) and giant cell tumor (GCT) on radiographs. METHODS: Patients with osteolytic OS and GCT proven by postoperative pathology were retrospectively recruited from four centers (center A, training and internal testing; centers B, C, and D, external testing). Sixteen radiologists with different experiences in musculoskeletal imaging diagnosis were divided into three groups and participated with or without the DL model's assistance. DL model was generated using EfficientNet-B6 architecture, and the clinical model was trained using clinical variables. The performance of various models was compared using McNemar's test. RESULTS: Three hundred thirty-three patients were included (mean age, 27 years ± 12 [SD]; 186 men). Compared to the clinical model, the DL model achieved a higher area under the curve (AUC) in both the internal (0.97 vs. 0.77, p = 0.008) and external test set (0.97 vs. 0.64, p < 0.001). In the total test set (including the internal and external test sets), the DL model achieved higher accuracy than the junior expert committee (93.1% vs. 72.4%; p < 0.001) and was comparable to the intermediate and senior expert committee (93.1% vs. 88.8%, p = 0.25; 87.1%, p = 0.35). With DL model assistance, the accuracy of the junior expert committee was improved from 72.4% to 91.4% (p = 0.051). CONCLUSION: The DL model accurately distinguished osteolytic OS and GCT with better performance than the junior radiologists, whose own diagnostic performances were significantly improved with the aid of the model, indicating the potential for the differential diagnosis of the two bone tumors on radiographs. CRITICAL RELEVANCE STATEMENT: The deep learning model can accurately distinguish osteolytic osteosarcoma and giant cell tumor on radiographs, which may help radiologists improve the diagnostic accuracy of two types of tumors. KEY POINTS: • The DL model shows robust performance in distinguishing osteolytic osteosarcoma and giant cell tumor. • The diagnosis performance of the DL model is better than junior radiologists'. • The DL model shows potential for differentiating osteolytic osteosarcoma and giant cell tumor.