← Back to all news
arXiv AI By Sachin Dudda Nagaraju, Bendik Skarre Abrahamsen, Ashkan Moradi, Mattijs Elschot

A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3

Read the original on arXiv AI →

The study investigates how few expert-annotated cases are needed to fine‑tune MedSAM3 for abdominal organ segmentation using Low‑Rank Adaptation (LoRA). With only 10 annotated CT or MRI cases, the LoRA‑adapted models achieve performance comparable to specialist systems that require orders of magnitude more data, including reliable gallbladder segmentation and near‑state‑of‑the‑art results for liver, kidneys, and spleen. The approach also generalizes to cardiac segmentation on the Whole Heart dataset, and training takes only 3–5 hours per organ on a single GPU, roughly twice as fast as nnU-Net.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 4

MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation

arXiv:2608. 00195v1 Announce Type: cross Abstract: High-resolution 3D segmentation of hip and shoulder anatomy from CT and MRI is essential for surgical planning, yet frozen segmentation models often fail under domain shift.

By John Garcia Henao, Nicholas B\"unger, Benedikt Herzog, Cindy Guerrero Toro, Benjamin Vella, Matthias Biner, Rico Br\"utsch, Carmen Castroviejo Fernandez, Felix \"Ottl, Norman Juchler, Armando Hoch, Bettina Hochreiter, Sven Hirsch, Sebastiano Caprara
llmscomputer-visionbenchmarks
More like this →
arXiv AI
Sep 16

Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation

The paper presents the first systematic evaluation of out‑of‑distribution generalization for congenital heart disease (CHD) segmentation, using the ImageCHD cohort as a held‑out target. It compares several segmentation architectures under different training regimes, showing that in‑distribution performance is a poor predictor of cross‑cohort robustness: nnU‑Net drops from 0.77 to 0.51 Dice, while SwinUNETR maintains higher performance at 0.67 Dice. Limited target‑domain adaptation with only 11 labeled ImageCHD cases boosts all SwinUNETR variants above 0.76 Dice, highlighting the importance of explicit cross‑dataset testing.

By Aniketh Vijesh, Shrisharanyan Vasu, Abhijit Ramesh, Clare Pomeroy-Ward, Harikrishnan Anil Maya, Sarin Xavier, Mahesh Kappanayil, Gilad Gressel
computer-visionfine-tuning
More like this →