biostudies-literatureZhou XInnovative Research Team (in Science and Technology) in University of Henan ProvinceHenan Province Key Research and Development and Promotion ProjectsNational Natural Science Foundation of ChinaMajor Science and Technology Projects of Henan ProvinceNational Key Clinical Discipline, and the program of Guangdong Provincial Clinical Research Center for Digestive Diseases1523https://www.ebi.ac.uk/biostudies/studies/S-EPMC11658449biostudies-literatureUnknown24(1)<h4>Background</h4>Rectal cancer is a common cancer worldwide and lacks effective prognostic markers. The development of prognostic markers by computational pathology methods has attracted increasing attention. This paper aims to construct a prognostic signature from whole slide images for predicting progression-free survival (PFS) of rectal cancer through an unsupervised artificial intelligence algorithm.<h4>Methods</h4>A total of 238 patients with rectal cancer from two datasets were collected for the development and validation of the prognostic signature. A tumor detection model was built by transfer learning. Then, on the basis of the tumor patches recognized by the tumor detection model, a convolutional autoencoder model was built for decoding the tumor patches into deep latent featurBMC cancerWhole slide image based prognosis prediction in rectal cancer using unsupervised artificial intelligence.PMC116584498220170924IRTSTHN0422321023103152020B111117000423210231000982302298221100310500Liu YCao WLu YZhao QWang CGao ZZhou XDai JZhao ZZhao YYu YfalseWhole slide image based prognosis prediction in rectal cancer using unsupervised artificial intelligence.<h4>Background</h4>Rectal cancer is a common cancer worldwide and lacks effective prognostic markers. The development of prognostic markers by computational pathology methods has attracted increasing attention. This paper aims to construct a prognostic signature from whole slide images for predicting progression-free survival (PFS) of rectal cancer through an unsupervised artificial intelligence algorithm.<h4>Methods</h4>A total of 238 patients with rectal cancer from two datasets were collected for the development and validation of the prognostic signature. A tumor detection model was built by transfer learning. Then, on the basis of the tumor patches recognized by the tumor detection model, a convolutional autoencoder model was built for decoding the tumor patches into deep latent featur2024-01-01T00:00:00Z2024 Dec2025-04-04T21:46:16.127Z2025-04-04T21:46:16.127ZS-EPMC116584493969609010.1186/s12885-024-13292-5