Adaptive PromptNet For Auxiliary Glioma Diagnosis without Contrast-Enhanced MRI

TL;DR

This paper introduces an adaptive PromptNet that accurately grades gliomas using only non-enhanced MRI data, reducing reliance on contrast-enhanced scans and improving diagnostic efficiency.

Contribution

The study presents a novel adaptive PromptNet that leverages prompt loss during training to enhance glioma grading performance without contrast-enhanced MRI data.

Findings

Achieved competitive glioma grading results on BraTS2020 dataset.

Effectively handles difficult samples through adaptive weighting.

Reduces need for contrast-enhanced MRI in clinical diagnosis.

Abstract

Multi-contrast magnetic resonance imaging (MRI)-based automatic auxiliary glioma diagnosis plays an important role in the clinic. Contrast-enhanced MRI sequences (e.g., contrast-enhanced T1-weighted imaging) were utilized in most of the existing relevant studies, in which remarkable diagnosis results have been reported. Nevertheless, acquiring contrast-enhanced MRI data is sometimes not feasible due to the patients physiological limitations. Furthermore, it is more time-consuming and costly to collect contrast-enhanced MRI data in the clinic. In this paper, we propose an adaptive PromptNet to address these issues. Specifically, a PromptNet for glioma grading utilizing only non-enhanced MRI data has been constructed. PromptNet receives constraints from features of contrast-enhanced MR data during training through a designed prompt loss. To further boost the performance, an adaptive strategy is designed to dynamically weight the prompt loss in a sample-based manner. As a result, PromptNet is capable of dealing with more difficult samples. The effectiveness of our method is evaluated on a widely-used BraTS2020 dataset, and competitive glioma grading performance on NE-MRI data is achieved.