Title Multi-task learning for survival analysis using pathology images /
Translation of Title Daugialypis mokymasis išgyvenamumo analizėje naudojantis patologijos vaizdais.
Authors Kuzminas, Ovidijus
Full Text Download
Pages 58
Keywords [eng] multi­task learning, survival analysis, histopathology images, feature extraction, deep learning, daugelio tikslų mokymasis, išgyvenamumo analizė, histopatologijos vaizdai, informatyvių požymių ištraukimas, gilusis mokymasis
Abstract [eng] This thesis introduced a multi­task learning framework for survival analysis from a combination of histopathological images and clinical data. The integration of structured tabular data and unstruc­ tured whole­slide images (WSIs) improves the prediction of survival probability and time­to­event outcomes. The approach is based on usafe of pre­trained convolutional neural networks for feature extraction, watershed segmentation for preprocessing, parametric tile selection, and a multi­layer perceptron model for multi­task inference. The pipeline achieves a significant improvement in sur­ vivability estimation, reaching concordance index of 0.829 on the validation dataset and 0.823 on the test dataset, and outperforming baseline methods like Cox regression which was analyzed for the same dataset in the previous work. This research contributes to the field by presenting an effi­ cient methodology for integrating clinical and histopathological data, proposing framework for image preprocessing and tile selection, and employing customized loss functions for survival analysis tasks.
Dissertation Institution Vilniaus universitetas.
Type Master thesis
Language English
Publication date 2025