MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909020542992384 |
|---|---|
| author | Bercean, Bogdan Alexandru Croitoru, Florinel Alin Hondru, Vlad Ceausescu, Ciprian Mihai Ionescu, Andreea Iuliana Ionescu, Radu Tudor |
| author_facet | Bercean, Bogdan Alexandru Croitoru, Florinel Alin Hondru, Vlad Ceausescu, Ciprian Mihai Ionescu, Andreea Iuliana Ionescu, Radu Tudor |
| contents | Anomaly detection in medical images is a challenging task, since anomalies are not typically available during training. Recent methods leverage a single pretext task coupled with a large-scale pre-trained model to reach state-of-the-art performance. Instead, we propose to learn multiple self-supervised and pseudo-labeling tasks from scratch, using a joint model based on Mixture-of-Experts (MoE). By carefully integrating multiple proxy tasks, the joint model effectively learns a robust representation of normal anatomical structures, so that anomaly scores can be derived based on how well the multi-task learner (MTL) solves each task during inference. We perform comprehensive experiments on BMAD, a recent benchmark that comprises a broad range of medical image modalities. The empirical results indicate that our multi-task learner is an effective anomaly detector, outperforming all state-of-the-art competitors on BMAD. Moreover, our model produces interpretable anomaly maps, potentially helping physicians in providing more accurate diagnoses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05891 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors Bercean, Bogdan Alexandru Croitoru, Florinel Alin Hondru, Vlad Ceausescu, Ciprian Mihai Ionescu, Andreea Iuliana Ionescu, Radu Tudor Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Anomaly detection in medical images is a challenging task, since anomalies are not typically available during training. Recent methods leverage a single pretext task coupled with a large-scale pre-trained model to reach state-of-the-art performance. Instead, we propose to learn multiple self-supervised and pseudo-labeling tasks from scratch, using a joint model based on Mixture-of-Experts (MoE). By carefully integrating multiple proxy tasks, the joint model effectively learns a robust representation of normal anatomical structures, so that anomaly scores can be derived based on how well the multi-task learner (MTL) solves each task during inference. We perform comprehensive experiments on BMAD, a recent benchmark that comprises a broad range of medical image modalities. The empirical results indicate that our multi-task learner is an effective anomaly detector, outperforming all state-of-the-art competitors on BMAD. Moreover, our model produces interpretable anomaly maps, potentially helping physicians in providing more accurate diagnoses. |
| title | MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.05891 |