Using ResNet to Utilize 4-class T2-FLAIR Slice Classification Based on the Cholinergic Pathways Hyperintensities Scale for Pathological Aging

TL;DR

This study addresses the manual burden of CHIPS slice selection in T2-FLAIR MRI by developing BSCA, a ResNet-based 4-class slice classifier. Trained on ADNI T2-FLAIR data (N=150) and tested on a local TPMIC cohort (N=30), BSCA automatically identifies the four CHIPS-relevant slices. The model achieves a high accuracy of 99.82% and a F1-score of 99.83%, indicating robust slice classification for screening purposes. This approach can streamline dementia risk assessment and may be integrated with WMH segmentation to quantify CHIPS scores in routine clinical workflows.

Abstract

The Cholinergic Pathways Hyperintensities Scale (CHIPS) is a visual rating scale used to assess the extent of cholinergic white matter hyperintensities in T2-FLAIR images, serving as an indicator of dementia severity. However, the manual selection of four specific slices for rating throughout the entire brain is a time-consuming process. Our goal was to develop a deep learning-based model capable of automatically identifying the four slices relevant to CHIPS. To achieve this, we trained a 4-class slice classification model (BSCA) using the ADNI T2-FLAIR dataset (N=150) with the assistance of ResNet. Subsequently, we tested the model's performance on a local dataset (N=30). The results demonstrated the efficacy of our model, with an accuracy of 99.82% and an F1-score of 99.83%. This achievement highlights the potential impact of BSCA as an automatic screening tool, streamlining the selection of four specific T2-FLAIR slices that encompass white matter landmarks along the cholinergic pathways. Clinicians can leverage this tool to assess the risk of clinical dementia development efficiently.

Figures (2)

• Figure 1: Residual network architecture
• Figure 2: The model performance metrics