Paper Detail

Continual pretraining Prostate MRI ViT Encoder for task alignment

Bilal A. Sidiqi, Yipei Wang, Shaheer U. Saeed, Shiqi Huang, Daniel C. Alexander, Yipeng Hu

arxiv Score 3.8

Published 2026-10-14 · First seen 2026-10-15

General AI

Abstract

Building foundation models for MRI has emerged as a promising direction for advancing medical image analysis and improving accessibility of task specific models. Existing approaches primarily focus on effective pretraining strategies and evaluating their performance across diverse downstream tasks. While these methods show performance gains, limited attention has been given to understanding task alignment between pretraining and downstream objectives. Unlike language models, where the two stages are naturally aligned, such alignment is less evident in vision based applications. Motivated by this gap, we explore continual pretraining. Specifically, continually pretraining a pretrained ViT encoder using Low-Rank Adaptation (LoRA) on a prostate segmentation task to enhance task alignment and downstream performance. We further perform layer-wise representational analysis using Centered Kernel Alignment (CKA) to assess representational shifts and their correlation with task outcomes. Our experiments show improved performance in 3 of 6 downstream tasks and comparable results in the others. Our Feature analysis reveals that, for segmentation tasks, continually pretrained encoder features exhibit greater similarity to those of the finetuned encoder than the original pretrained encoder, correlating with observed performance gains.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{sidiqi2026continual,
  title = {Continual pretraining Prostate MRI ViT Encoder for task alignment},
  author = {Bilal A. Sidiqi and Yipei Wang and Shaheer U. Saeed and Shiqi Huang and Daniel C. Alexander and Yipeng Hu},
  year = {2026},
  abstract = {Building foundation models for MRI has emerged as a promising direction for advancing medical image analysis and improving accessibility of task specific models. Existing approaches primarily focus on effective pretraining strategies and evaluating their performance across diverse downstream tasks. While these methods show performance gains, limited attention has been given to understanding task alignment between pretraining and downstream objectives. Unlike language models, where the two stages},
  url = {https://arxiv.org/abs/2610.20217},
  keywords = {cs.CV, cs.LG},
  eprint = {2610.20217},
  archiveprefix = {arXiv},
}

Metadata

{}