Search

Background and Aim: High‐grade dysplasia (HGD) and T1 lesions are accidentally resected by cold snare polypectomy (CSP) and the characteristics, and follow‐up of them has not been reported. In this study, we analyzed the histopathological findings and recurrence of them. Methods: This was a multicenter retrospective‐cohort study. We collected HGD and T1 lesions of ≤ 10 mm resected by CSP among 15 520 patients receiving CSP from 2014 to 2019 at nine related institutions, and we extracted only cases receiving definite follow‐up colonoscopy after CSP of HGD and T1 lesions. We analyzed these tumor's characteristics and therapeutic results such as R0 resection and local recurrence and risk factors of recurrence. Results: We collected 103 patients (0.63%) and extracted 80 lesions in 74 patients receiving follow‐up colonoscopy for CSP scar. Mean age was 68.4 ± 12.0, and male rate was 68.9% (51/80). The mean tumor size (mm) was 6.6 ± 2.5, and the rate of polypoid morphology and rectum location was 77.5% and 25.0%. The rate of magnified observation was 53.8%. The rates of en bloc resection and R0 resection were 92.5% and 37.5%. The local recurrence rate was 6.3% (5/80, median follow‐up period: 24.0 months). The recurrence developed within 3 months after CSP for four out of five recurrent cases. Comparing five recurrent lesions to 75 non‐recurrent lesions, a positive horizontal margin was a significant risk factor (60.0% vs 10.7%, P < 0.001). Conclusions: High‐grade dysplasia and T1 resected by CSP were analyzed, and the local recurrence rate of them was substantially high. [ABSTRACT FROM AUTHOR]

Background and Aim Methods Results Conclusion There are no previous studies in which computer‐aided diagnosis (CAD) diagnosed colorectal cancer (CRC) subtypes correctly. In this study, we developed an original CAD for the diagnosis of CRC subtypes.Pretraining for the CAD based on ResNet was performed using ImageNet and five open histopathological pretraining image datasets (HiPreD) containing 3 million images. In addition, sparse attention was introduced to improve the CAD compared to other attention networks. One thousand and seventy‐two histopathological images from 29 early CRC cases at Kyoto Prefectural University of Medicine from 2019 to 2022 were collected (857 images for training and validation, 215 images for test). All images were annotated by a qualified histopathologist for segmentation of normal mucosa, adenoma, pure well‐differentiated adenocarcinoma (PWDA), and moderately/poorly differentiated adenocarcinoma (MPDA). Diagnostic ability including dice sufficient coefficient (DSC) and diagnostic accuracy were evaluated.Our original CAD, named Colon‐seg, with the pretraining of both HiPreD and ImageNET showed a better DSC (88.4%) compared to CAD without both pretraining (76.8%). Regarding the attentional mechanism, Colon‐seg with sparse attention showed a better DSC (88.4%) compared to other attentional mechanisms (dual: 79.7%, ECA: 80.7%, shuffle: 84.7%, SK: 86.9%). In addition, the DSC of Colon‐seg (88.4%) was better than other types of CADs (TransUNet: 84.7%, MultiResUnet: 86.1%, Unet++: 86.7%). The diagnostic accuracy of Colon‐seg for each histopathological type was 94.3% for adenoma, 91.8% for PWDA, and 92.8% for MPDA.A deep learning‐based CAD for CRC subtype differentiation was developed with pretraining and fine‐tuning of abundant histopathological images. [ABSTRACT FROM AUTHOR]