Endoscopic full-thickness resection of T1 colorectal cancers: a retrospective analysis from a multicenter Dutch eFTR registry.

BACKGROUND: Complete endoscopic resection and accurate histological evaluation for T1 colorectal cancer (CRC) are critical in determining subsequent treatment. Endoscopic full-thickness resection (eFTR) is a new treatment option for T1 CRC < 2 cm. We aimed to report clinical outcomes and short-term results. METHODS: Consecutive eFTR procedures for T1 CRC, prospectively recorded in our national registry between November 2015 and April 2020, were retrospectively analyzed. Primary outcomes were technical success and R0 resection. Secondary outcomes were histological risk assessment, curative resection, adverse events, and short-term outcomes. RESULTS: We included 330 procedures: 132 primary resections and 198 secondary scar resections after incomplete T1 CRC resection. Overall technical success, R0 resection, and curative resection rates were 87.0 % (95 % confidence interval [CI] 82.7 %-90.3 %), 85.6 % (95 %CI 81.2 %-89.2 %), and 60.3 % (95 %CI 54.7 %-65.7 %). Curative resection rate was 23.7 % (95 %CI 15.9 %-33.6 %) for primary resection of T1 CRC and 60.8 % (95 %CI 50.4 %-70.4 %) after excluding deep submucosal invasion as a risk factor. Risk stratification was possible in 99.3 %. The severe adverse event rate was 2.2 %. Additional oncological surgery was performed in 49/320 (15.3 %), with residual cancer in 11/49 (22.4 %). Endoscopic follow-up was available in 200/242 (82.6 %), with a median of 4 months and residual cancer in 1 (0.5 %) following an incomplete resection. CONCLUSIONS: eFTR is relatively safe and effective for resection of small T1 CRC, both as primary and secondary treatment. eFTR can expand endoscopic treatment options for T1 CRC and could help to reduce surgical overtreatment. Future studies should focus on long-term outcomes.

Automatic image and text-based description for colorectal polyps using BASIC classification.

Colorectal polyps (CRP) are precursor lesions of colorectal cancer (CRC). Correct identification of CRPs during in-vivo colonoscopy is supported by the endoscopist's expertise and medical classification models. A recent developed classification model is the Blue light imaging Adenoma Serrated International Classification (BASIC) which describes the differences between non-neoplastic and neoplastic lesions acquired with blue light imaging (BLI). Computer-aided detection (CADe) and diagnosis (CADx) systems are efficient at visually assisting with medical decisions but fall short at translating decisions into relevant clinical information. The communication between machine and medical expert is of crucial importance to improve diagnosis of CRP during in-vivo procedures. In this work, the combination of a polyp image classification model and a language model is proposed to develop a CADx system that automatically generates text comparable to the human language employed by endoscopists. The developed system generates equivalent sentences as the human-reference and describes CRP images acquired with white light (WL), blue light imaging (BLI) and linked color imaging (LCI). An image feature encoder and a BERT module are employed to build the AI model and an external test set is used to evaluate the results and compute the linguistic metrics. The experimental results show the construction of complete sentences with an established metric scores of BLEU-1 = 0.67, ROUGE-L = 0.83 and METEOR = 0.50. The developed CADx system for automatic CRP image captioning facilitates future advances towards automatic reporting and may help reduce time-consuming histology assessment.

Optical diagnosis of colorectal polyp images using a newly developed computer-aided diagnosis system (CADx) compared with intuitive optical diagnosis.

BACKGROUND: Optical diagnosis of colorectal polyps remains challenging. Image-enhancement techniques such as narrow-band imaging and blue-light imaging (BLI) can improve optical diagnosis. We developed and prospectively validated a computer-aided diagnosis system (CADx) using high-definition white-light (HDWL) and BLI images, and compared the system with the optical diagnosis of expert and novice endoscopists. METHODS: CADx characterized colorectal polyps by exploiting artificial neural networks. Six experts and 13 novices optically diagnosed 60 colorectal polyps based on intuition. After 4 weeks, the same set of images was permuted and optically diagnosed using the BLI Adenoma Serrated International Classification (BASIC). RESULTS: CADx had a diagnostic accuracy of 88.3 % using HDWL images and 86.7 % using BLI images. The overall diagnostic accuracy combining HDWL and BLI (multimodal imaging) was 95.0 %, which was significantly higher than that of experts (81.7 %, P = 0.03) and novices (66.7 %, P < 0.001). Sensitivity was also higher for CADx (95.6 % vs. 61.1 % and 55.4 %), whereas specificity was higher for experts compared with CADx and novices (95.6 % vs. 93.3 % and 93.2 %). For endoscopists, diagnostic accuracy did not increase when using BASIC, either for experts (intuition 79.5 % vs. BASIC 81.7 %, P = 0.14) or for novices (intuition 66.7 % vs. BASIC 66.5 %, P = 0.95). CONCLUSION: CADx had a significantly higher diagnostic accuracy than experts and novices for the optical diagnosis of colorectal polyps. Multimodal imaging, incorporating both HDWL and BLI, improved the diagnostic accuracy of CADx. BASIC did not increase the diagnostic accuracy of endoscopists compared with intuitive optical diagnosis.