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.

Background: Sarcopenia, the age-related loss of muscle mass, is a negative prognostic factor in gastrointestinal cancer. Sarcopenia combined with visceral obesity (sarcopenic obesity) is associated with poor outcomes. We explored the influence of obesity and other factors on the prognosis of patients with colorectal cancer diagnosed with sarcopenia. Methods: We enrolled 211 patients with colorectal cancer diagnosed with preoperative sarcopenic obesity who underwent radical resection at Osaka University Hospital between January 2009 and January 2012. Muscle mass was assessed using the psoas muscle mass index. Obesity was evaluated by measuring the visceral fat area in the umbilical region. Patients were categorized into two groups: sarcopenia with obesity (SO) and sarcopenia without obesity (non-SO). Overall survival, cancer-specific survival, and cancer-related relapse-free survival (CRRFS) were compared between the two groups. Patient characteristics, including age, sex, body mass index, serum albumin, C-reactive protein, tumor markers, prognostic nutritional index (PNI), modified Glasgow prognostic score (mGPS), and geriatric nutritional risk index (GNRI), were also analyzed. Results: CRRFS was significantly shorter in the SO group than in the non-SO group (p = 0.028). PNI, mGPS, and GNRI were not identified as significant prognostic factors for CRRFS. Multivariate analysis highlighted sarcopenic obesity, elevated carcinoembryonic antigen levels, and unfavorable histological types as significant predictors of poor CRRFS outcomes. Conclusions: Sarcopenic obesity is an independent predictor of poor prognosis in patients with CRC. Thus, interventions aimed at increasing muscle mass and reducing visceral fat could potentially improve the prognosis of these patients.

First-line chemotherapy with maintenance therapy is expected to be well-tolerated and improve survival in patients with metastatic colorectal cancer (mCRC). This study evaluated the efficacy and safety of trifluridine/tipiracil (TAS-102) plus bevacizumab (Bev) as maintenance therapy for mCRC, omitting both oxaliplatin and fluoropyrimidines. Patients with untreated mCRC initially received induction chemotherapy with fluoropyrimidine, oxaliplatin plus bevacizumab for 3–4 months. After achieving stable disease or better on imaging, 52 patients transitioned to maintenance therapy with TAS+Bev: TAS-102 (35 mg/m², twice daily on days 1–5 and 8–12) plus Bev (5.0 mg/kg on Days 1 and 15, intravenously). Progression-free survival 1 (PFS1), defined as the time the start of maintenance therapy to disease progression or death, was evaluated as the primary endpoint. The median cumulative dose of oxaliplatin during induction was 529 mg/m². Median PFS1 during TAS+Bev maintenance was 8.7 months (95%CI: 5.5-12.3). The response rate and disease control rate during maintenance were 59.6% and 94.2%, respectively. Oxaliplatin reintroduction was feasible in 53.8% (28/52) of patient with a median total first-line chemotherapy duration was 16.2 months (95%CI: 14.5–20.6). Safety outcomes, including dose intensity and adverse events, were acceptable. This strategy of switching to first-line maintenance therapy with TAS+Bev demonstrated promising efficacy and safety. This strategy effectively avoided cumulative neurotoxicity, preserved quality of life and enabled reintroduction of oxaliplatin, suggesting it may represent a promising alternative strategy for patients ineligible for prolonged oxaliplatin-based treatment. Overall survival analysis is currently ongoing. [UMIN Trial ID: UMIN000031317]