Discrepancy-based Diffusion Models for Lesion Detection in Brain MRI

TL;DR

This paper introduces DDMD, a novel discrepancy-based diffusion model for brain lesion detection in MRI that leverages distribution discrepancies to improve detection without extensive annotations.

Contribution

The proposed DDMD framework uniquely incorporates discrepancy features, enabling effective lesion detection by modeling distribution differences among samples, surpassing existing annotation-dependent methods.

Findings

Outperforms state-of-the-art methods on BRATS2020 dataset

Effectively models distribution discrepancies for improved detection

Retains pixel-wise uncertainty for better segmentation

Abstract

Diffusion probabilistic models (DPMs) have exhibited significant effectiveness in computer vision tasks, particularly in image generation. However, their notable performance heavily relies on labelled datasets, which limits their application in medical images due to the associated high-cost annotations. Current DPM-related methods for lesion detection in medical imaging, which can be categorized into two distinct approaches, primarily rely on image-level annotations. The first approach, based on anomaly detection, involves learning reference healthy brain representations and identifying anomalies based on the difference in inference results. In contrast, the second approach, resembling a segmentation task, employs only the original brain multi-modalities as prior information for generating pixel-level annotations. In this paper, our proposed model - discrepancy distribution medical diffusion (DDMD) - for lesion detection in brain MRI introduces a novel framework by incorporating distinctive discrepancy features, deviating from the conventional direct reliance on image-level annotations or the original brain modalities. In our method, the inconsistency in image-level annotations is translated into distribution discrepancies among heterogeneous samples while preserving information within homogeneous samples. This property retains pixel-wise uncertainty and facilitates an implicit ensemble of segmentation, ultimately enhancing the overall detection performance. Thorough experiments conducted on the BRATS2020 benchmark dataset containing multimodal MRI scans for brain tumour detection demonstrate the great performance of our approach in comparison to state-of-the-art methods.