Generalizable transfer learning of automated tumor segmentation from cervical cancers toward a universal model for uterine malignancies in diffusion-weighted MRI.

ABSTRACT:

Purpose

To investigate the generalizability of transfer learning (TL) of automated tumor segmentation from cervical cancers toward a universal model for cervical and uterine malignancies in diffusion-weighted magnetic resonance imaging (DWI).

Methods

In this retrospective multicenter study, we analyzed pelvic DWI data from 169 and 320 patients with cervical and uterine malignancies and divided them into the training (144 and 256) and testing (25 and 64) datasets, respectively. A pretrained model was established using DeepLab V3 + from the cervical cancer dataset, followed by TL experiments adjusting the training data sizes and fine-tuning layers. The model performance was evaluated using the dice similarity coefficient (DSC).

Results

In predicting tumor segmentation f

SUBMITTER: Lin YC 

PROVIDER: S-EPMC9871146 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature