LAUSR

BACKGROUND Metastatic lateral lymph node dissection can improve survival in patients with rectal adenocarcinoma, with or without chemoradiotherapy. However, the optimal imaging diagnostic criteria for lateral lymph node metastases remain undetermined. OBJECTIVE We aimed to develop a lateral lymph node metastasis diagnostic artificial intelligence tool using deep learning, for patients with rectal adenocarcinoma who underwent radical surgery and lateral lymph node dissection. DESIGN Retrospective study. SETTINGS Multicenter study. PATIENTS Total 209 patients with rectal adenocarcinoma, who underwent radical surgery and lateral lymph node dissection at 15 participating hospitals, were enrolled in the study and allocated to training (n = 139), test (n = 17), or validation (n = 53) cohorts. MAIN OUTCOME MEASURES In the neoadjuvant treatment group, images taken before pre-treatment images were classified as baseline images and those after pre-treatment, as pre-surgery images. In the upfront surgery group, pre-surgery images were classified as both baseline and pre-surgery images. We constructed two types of artificial intelligence, using baseline and pre-surgery images, by inputting the patches from these images into ResNet-18. We assessed the diagnostic accuracy of the two types of artificial intelligence. RESULTS Overall, 124 patients underwent surgery alone, 52 received neoadjuvant chemotherapy, and 33 received chemoradiotherapy. The number of resected lateral lymph nodes in the training, test, and validation cohorts was 2,418, 279, and 850, respectively. The metastatic rates were 2.8%, 0.7%, and 3.7%, respectively. In the validation cohort, the precision-recall area under the curve was 0.870 and 0.963 for the baseline and pre-surgery images, respectively. Although both baseline and pre-surgery images provided good accuracy for diagnosing lateral lymph node metastases, the accuracy of pre-surgery images was better than that of baseline images. LIMITATIONS The number of cases is small. CONCLUSION The artificial intelligence tool is a promising tool to diagnose lateral lymph node metastasis with high accuracy.