3D Masked Modelling Advances Lesion Classification in Axial T2w Prostate MRI

TL;DR

This paper explores the use of Masked Image Modelling (MIM) with CNNs for prostate cancer lesion classification in axial T2w MRI, demonstrating improved AUC over traditional pre-training methods.

Contribution

It is the first to evaluate MIM in the context of 3D medical imaging for prostate cancer classification, showing its effectiveness over conventional pre-training.

Findings

MIM improves lesion classification performance in prostate MRI.

MIM with CNNs outperforms ImageNet pre-training in AUC.

Different masking strategies influence the effectiveness of MIM.

Abstract

Masked Image Modelling (MIM) has been shown to be an efficient self-supervised learning (SSL) pre-training paradigm when paired with transformer architectures and in the presence of a large amount of unlabelled natural images. The combination of the difficulties in accessing and obtaining large amounts of labeled data and the availability of unlabelled data in the medical imaging domain makes MIM an interesting approach to advance deep learning (DL) applications based on 3D medical imaging data. Nevertheless, SSL and, in particular, MIM applications with medical imaging data are rather scarce and there is still uncertainty. around the potential of such a learning paradigm in the medical domain. We study MIM in the context of Prostate Cancer (PCa) lesion classification with T2 weighted (T2w) axial magnetic resonance imaging (MRI) data. In particular, we explore the effect of using MIM when coupled with convolutional neural networks (CNNs) under different conditions such as different masking strategies, obtaining better results in terms of AUC than other pre-training strategies like ImageNet weight initialization.