Parkinson's Disease Recognition Using SPECT Image and Interpretable AI: A Tutorial

TL;DR

This tutorial reviews and compares interpretation methods for deep learning models in Parkinson's disease recognition using SPECT images, highlighting suitable techniques for clinical interpretability and model selection.

Contribution

It introduces an evaluation framework for interpretation methods and demonstrates their application in selecting suitable models for PD recognition.

Findings

Guided backpropagation excels in showing fine-grained importance.

SHAP provides high-quality heatmaps at uptake depletion locations.

The evaluation framework helps in choosing appropriate interpretation methods.

Abstract

In the past few years, there are several researches on Parkinson's disease (PD) recognition using single-photon emission computed tomography (SPECT) images with deep learning (DL) approach. However, the DL model's complexity usually results in difficult model interpretation when used in clinical. Even though there are multiple interpretation methods available for the DL model, there is no evidence of which method is suitable for PD recognition application. This tutorial aims to demonstrate the procedure to choose a suitable interpretation method for the PD recognition model. We exhibit four DCNN architectures as an example and introduce six well-known interpretation methods. Finally, we propose an evaluation method to measure the interpretation performance and a method to use the interpreted feedback for assisting in model selection. The evaluation demonstrates that the guided backpropagation and SHAP interpretation methods are suitable for PD recognition methods in different aspects. Guided backpropagation has the best ability to show fine-grained importance, which is proven by the highest Dice coefficient and lowest mean square error. On the other hand, SHAP can generate a better quality heatmap at the uptake depletion location, which outperforms other methods in discriminating the difference between PD and NC subjects. Shortly, the introduced interpretation methods can contribute to not only the PD recognition application but also to sensor data processing in an AI Era (interpretable-AI) as feedback in constructing well-suited deep learning architectures for specific applications.