Can General-Purpose Omnimodels Compete with Specialists? A Case Study in Medical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yizhe, Chen, Qiang, Zhou, Tao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911181049954304
author Zhang, Yizhe
Chen, Qiang
Zhou, Tao
author_facet Zhang, Yizhe
Chen, Qiang
Zhou, Tao
contents The emergence of powerful, general-purpose omnimodels capable of processing diverse data modalities has raised a critical question: can these ``jack-of-all-trades'' systems perform on par with highly specialized models in knowledge-intensive domains? This work investigates this question within the high-stakes field of medical image segmentation. We conduct a comparative study analyzing the zero-shot performance of a state-of-the-art omnimodel (Gemini, the ``Nano Banana'' model) against domain-specific deep learning models on three distinct tasks: polyp (endoscopy), retinal vessel (fundus), and breast tumor segmentation (ultrasound). Our study focuses on performance at the extremes by curating subsets of the ``easiest'' and ``hardest'' cases based on the specialist models' accuracy. Our findings reveal a nuanced and task-dependent landscape. For polyp and breast tumor segmentation, specialist models excel on easy samples, but the omnimodel demonstrates greater robustness on hard samples where specialists fail catastrophically. Conversely, for the fine-grained task of retinal vessel segmentation, the specialist model maintains superior performance across both easy and hard cases. Intriguingly, qualitative analysis suggests omnimodels may possess higher sensitivity, identifying subtle anatomical features missed by human annotators. Our results indicate that while current omnimodels are not yet a universal replacement for specialists, their unique strengths suggest a potential complementary role with specialist models, particularly in enhancing robustness on challenging edge cases.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00866
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can General-Purpose Omnimodels Compete with Specialists? A Case Study in Medical Image Segmentation
Zhang, Yizhe
Chen, Qiang
Zhou, Tao
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
The emergence of powerful, general-purpose omnimodels capable of processing diverse data modalities has raised a critical question: can these ``jack-of-all-trades'' systems perform on par with highly specialized models in knowledge-intensive domains? This work investigates this question within the high-stakes field of medical image segmentation. We conduct a comparative study analyzing the zero-shot performance of a state-of-the-art omnimodel (Gemini, the ``Nano Banana'' model) against domain-specific deep learning models on three distinct tasks: polyp (endoscopy), retinal vessel (fundus), and breast tumor segmentation (ultrasound). Our study focuses on performance at the extremes by curating subsets of the ``easiest'' and ``hardest'' cases based on the specialist models' accuracy. Our findings reveal a nuanced and task-dependent landscape. For polyp and breast tumor segmentation, specialist models excel on easy samples, but the omnimodel demonstrates greater robustness on hard samples where specialists fail catastrophically. Conversely, for the fine-grained task of retinal vessel segmentation, the specialist model maintains superior performance across both easy and hard cases. Intriguingly, qualitative analysis suggests omnimodels may possess higher sensitivity, identifying subtle anatomical features missed by human annotators. Our results indicate that while current omnimodels are not yet a universal replacement for specialists, their unique strengths suggest a potential complementary role with specialist models, particularly in enhancing robustness on challenging edge cases.
title Can General-Purpose Omnimodels Compete with Specialists? A Case Study in Medical Image Segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2509.00866