Development and validation of survival prediction model for gastric adenocarcinoma patients using deep learning: A SEER-based study

Gastric cancer is the fifth most common cancer and the third most common cause of cancer death globally. Risk factors for the condition include Helicobacter pylori infection, age, high salt intake, and diets low in fruit and vegetables. Gastric cancer is diagnosed histologically after endoscopic biopsy and staged using CT, endoscopic ultrasound, PET, and laparoscopy. It is a molecularly and phenotypically highly heterogeneous disease. The main treatment for early gastric cancer is endoscopic resection. Non-early operable gastric cancer is treated with surgery, which should include D2 lymphadenectomy (including lymph node stations in the perigastric mesentery and along the celiac arterial branches). Perioperative or adjuvant chemotherapy improves survival in patients with stage 1B or higher cancers. Advanced gastric cancer is treated with sequential lines of chemotherapy, starting with a platinum and fluoropyrimidine doublet in the first line; median survival is less than 1 year. Targeted therapies licensed to treat gastric cancer include trastuzumab (HER2-positive patients first line), ramucirumab (anti-angiogenic second line), and nivolumab or pembrolizumab (anti-PD-1 third line).

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks. 12 pages, 3 figures, NeurIPS 2019

A regimen of epirubicin, cisplatin, and infused fluorouracil (ECF) improves survival among patients with incurable locally advanced or metastatic gastric adenocarcinoma. We assessed whether the addition of a perioperative regimen of ECF to surgery improves outcomes among patients with potentially curable gastric cancer. We randomly assigned patients with resectable adenocarcinoma of the stomach, esophagogastric junction, or lower esophagus to either perioperative chemotherapy and surgery (250 patients) or surgery alone (253 patients). Chemotherapy consisted of three preoperative and three postoperative cycles of intravenous epirubicin (50 mg per square meter of body-surface area) and cisplatin (60 mg per square meter) on day 1, and a continuous intravenous infusion of fluorouracil (200 mg per square meter per day) for 21 days. The primary end point was overall survival. ECF-related adverse effects were similar to those previously reported among patients with advanced gastric cancer. Rates of postoperative complications were similar in the perioperative-chemotherapy group and the surgery group (46 percent and 45 percent, respectively), as were the numbers of deaths within 30 days after surgery. The resected tumors were significantly smaller and less advanced in the perioperative-chemotherapy group. With a median follow-up of four years, 149 patients in the perioperative-chemotherapy group and 170 in the surgery group had died. As compared with the surgery group, the perioperative-chemotherapy group had a higher likelihood of overall survival (hazard ratio for death, 0.75; 95 percent confidence interval, 0.60 to 0.93; P=0.009; five-year survival rate, 36 percent vs. 23 percent) and of progression-free survival (hazard ratio for progression, 0.66; 95 percent confidence interval, 0.53 to 0.81; P<0.001). In patients with operable gastric or lower esophageal adenocarcinomas, a perioperative regimen of ECF decreased tumor size and stage and significantly improved progression-free and overall survival. (Current Controlled Trials number, ISRCTN93793971 [controlled-trials.com].). Copyright 2006 Massachusetts Medical Society.