Neural Transformers for Intraductal Papillary Mucosal Neoplasms (IPMN) Classification in MRI images

TL;DR

This paper introduces a transformer-based AI model for classifying intraductal papillary mucosal neoplasms (IPMN) in MRI images, aiming to improve diagnostic accuracy and reduce variability compared to traditional methods.

Contribution

It presents a novel transformer-based classifier that leverages pre-training for better performance and interpretability in medical image diagnosis of IPMN.

Findings

Transformer model outperforms CNNs in IPMN classification.

Pre-training enhances the model's generalization and accuracy.

Supports the universal applicability of transformers in medical imaging.

Abstract

Early detection of precancerous cysts or neoplasms, i.e., Intraductal Papillary Mucosal Neoplasms (IPMN), in pancreas is a challenging and complex task, and it may lead to a more favourable outcome. Once detected, grading IPMNs accurately is also necessary, since low-risk IPMNs can be under surveillance program, while high-risk IPMNs have to be surgically resected before they turn into cancer. Current standards (Fukuoka and others) for IPMN classification show significant intra- and inter-operator variability, beside being error-prone, making a proper diagnosis unreliable. The established progress in artificial intelligence, through the deep learning paradigm, may provide a key tool for an effective support to medical decision for pancreatic cancer. In this work, we follow this trend, by proposing a novel AI-based IPMN classifier that leverages the recent success of transformer networks in generalizing across a wide variety of tasks, including vision ones. We specifically show that our transformer-based model exploits pre-training better than standard convolutional neural networks, thus supporting the sought architectural universalism of transformers in vision, including the medical image domain and it allows for a better interpretation of the obtained results.