Coreset Based Medical Image Anomaly Detection and Segmentation

Ciprian-Mihai Ceaușescu, Bogdan Alexe, Bogdan Alexe, Riccardo Volpi, Riccardo Volpi

2024

Abstract

We address the problem of binary classification of medical images employing an anomaly detection approach that uses only normal images for training. We build our method on top of a state-of-the-art anomaly detection method for visual inspection of industrial natural images, PatchCore, tailored to our tasks. We deal with the distribution shift between natural and medical images either by fine-tuning a pre-trained encoder on a general medical image dataset with ten classes or by training the encoder directly on a set of discriminative medical tasks. We employ our method for binary classification and evaluate it on two datasets: lung cancer from CT scan images and brain tumor from MRI images showing competitive results when compared to the baselines. Conveniently, this approach is able to produce segmentation masks used for localizing the anomalous regions. Additionally, we show how transformer encoders are up to the task allowing for improved F1 and AUC metrics on the anomaly task, also producing a better segmentation.

Paper Citation

in Harvard Style

Ceaușescu C., Alexe B. and Volpi R. (2024). Coreset Based Medical Image Anomaly Detection and Segmentation. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 549-558. DOI: 10.5220/0012395900003660

in Bibtex Style

@conference{visapp24,
author={Ciprian-Mihai Ceaușescu and Bogdan Alexe and Riccardo Volpi},
title={Coreset Based Medical Image Anomaly Detection and Segmentation},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP},
year={2024},
pages={549-558},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012395900003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
TI - Coreset Based Medical Image Anomaly Detection and Segmentation
SN - 978-989-758-679-8
AU - Ceaușescu C.
AU - Alexe B.
AU - Volpi R.
PY - 2024
SP - 549
EP - 558
DO - 10.5220/0012395900003660
PB - SciTePress