No abstract

The submucosal invasion depth predicts prognosis in early colorectal cancer. Although colorectal cancer with shallow submucosal invasion can be treated via endoscopic resection, colorectal cancer with deep submucosal invasion requires surgical colectomy. However, accurately diagnosing the depth of submucosal invasion via endoscopy is difficult. We developed a tool to diagnose the depth of submucosal invasion in early colorectal cancer using artificial intelligence. We reviewed data from 196 patients who had undergone a preoperative colonoscopy at the Osaka University Hospital and Osaka International Cancer Institute between 2011 and 2018 and were diagnosed pathologically as having shallow submucosal invasion or deep submucosal invasion colorectal cancer. A convolutional neural network for predicting invasion depth was constructed using 706 images from 91 patients between 2011 and 2015 as the training dataset. The diagnostic accuracy of the constructed convolutional neural network was evaluated using 394 images from 49 patients between 2016 and 2017 as the validation dataset. We also prospectively tested the tool from 56 patients in 2018 with suspected early-stage colorectal cancer. The sensitivity, specificity, accuracy, and area under the curve of the convolutional neural network for diagnosing deep submucosal invasion colorectal cancer were 87.2% (258/296), 35.7% (35/98), 74.4% (293/394), and 0.758, respectively. The positive predictive value was 84.4% (356/422) and the sensitivity was 75.7% (356/470) in the test set. The diagnostic accuracy of the constructed convolutional neural network seemed to be as high as that of a skilled endoscopist. Thus, endoscopic image recognition by deep learning may be able to predict the submucosal invasion depth in early-stage colorectal cancer in clinical practice.

Alternative treatment modalities are necessary because of the low response rates and unsuitability of molecular-targeted agents (MTA) and/or immune checkpoint inhibitors (iCIs) in HCC patients. Therefore, we analyzed whether drug-eluting beads (DEB)-transcatheter arterial chemoembolization (TACE) with low-dose-FP (Ultra-FP) therapy could improve the efficacy and safety of treatment in difficult-to-treat HCC patients, especially those with advanced stage HCC. From November 2017 to April 2021, 118 consecutive patients with non-resectable difficult-to-treat HCC were included in this study. All patients were treated with Ultra-FP therapy. After the weak DEB-TACE procedure, we administered low-dose FP for 2 weeks followed by resting for 4 weeks. The numbers of HCC patients CR/PR/SD/PD induced by Ultra-FP therapy were 36/52/17/13 (Modified RECIST) patients, respectively. The objective response rate of Ultra-FP therapy was 74.6% (88/118 patients). Tumor marker reduction was observed in 81.4% (96/118 patients). The objective response rate (ORR) in the HCC patients with portal vein tumor thrombosis (PVTT) was 75% (18/24 patients). Median overall survival (mOS) of all included HCC patients was 738 days. The mOS of HCC patients with PVTT (−)/PVTT (+) was 816 days/718 days. The proportion of patients based on ALBI grade system was not significantly different between pre- and after 3 course Ultra-FP therapy. Ultra-FP therapy might be an affordable treatment option for difficult-to-treat advanced HCC. ORR and overall survival after receiving Ultra-FP therapy were remarkable in comparison to various kinds of systemic therapy including MTA and iCIs.

No abstract