An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-input digital drawing tasks

Abstract

Background Mild cognitive impairment (MCI) is an early stage of cognitive decline which could develop into dementia. An early detection of MCI is a crucial step for timely prevention and intervention. Recent studies have developed deep learning models to detect MCI and dementia using a bedside task like the classic clock drawing test (CDT). However, it remains a challenge to predict the early stage of the disease using the CDT data alone. Moreover, the state-of-the-art deep learning techniques still face black box challenges, making it questionable to implement them in a clinical setting. Methods We recruited 918 subjects from King Chulalongkorn Memorial Hospital (651 healthy subjects and 267 MCI patients). We propose a novel deep learning framework that incorporates data from the CDT, cube-copying, and trail-making tests. Soft label and self-attention were applied to improve the model performance and provide a visual explanation. The interpretability of the visualization of our model and the Grad-CAM approach were rated by experienced medical personnel and quantitatively evaluated using intersection over union (IoU) between the models’ heat maps and the regions of interest. Results Rather than using a single CDT image in the baseline VGG16 model, using multiple drawing tasks as inputs into our proposed model with soft label significantly improves the classification performance between the healthy aging controls and the MCI patients. In particular, the classification accuracy increases from 0.75 (baseline model) to 0.81. The F1-score increases from 0.36 to 0.65, and the area under the receiver operating characteristic curve (AUC) increases from 0.74 to 0.84. Compared to the multi-input model that also offers interpretable visualization, i.e., Grad-CAM, our model receives higher interpretability scores given by experienced medical experts and higher IoUs. Conclusions Our model achieves better classification performance at detecting MCI compared to the baseline model. In addition, the model provides visual explanations that are superior to those of the baseline model as quantitatively evaluated by experienced medical personnel. Thus, our work offers an interpretable machine learning model with high classification performance, both of which are crucial aspects of artificial intelligence in medical diagnosis.

Cardiac function in a large animal model of myocardial infarction at 7 T: deep learning based automatic segmentation increases reproducibility

“…Although there is only a minimal visual difference, the infarcted myocardium was labelled correctly in phase 11, as it was in most images with infarction. While further analysis was beyond the scope of this study, such information could be gained via attention mapping, where areas of images are mapped based on their impact on the model decision, essentially visualizing the attention of the model to different image regions 39 , 40 .…”

UNet++ Compression Techniques for Kidney and Cyst Segmentation in Autosomal Dominant Polycystic Kidney Disease

“…The trained model was tested on the unseen test set, and the quality of segmentation was assessed using two types of metrics -similarity metrics (the Dice similarity coefficient (DSC) [21], Precision and Intersection over Union (IoU)) and distance metrics (Mean Surface Distance (MSD) and Std. Surface Distance (sSD)) [22,23]. DSC measures the similarity between the predicted segmentation and ground truth masks.…”

Effect and mechanism of acupuncture on Alzheimer’s disease: A review

“…At present, for this intractable type of disease, there are no effective drugs and technical means for clinical treatment given at home and abroad (Martersteck et al, 2022;Ruengchaijatuporn et al, 2022). There are currently several claims in the clinic to the related pathogenesis of Alzheimer's disease, namely the cholinergic doctrine, the tau protein hypothesis, the neurovascular doctrine, the oxidative stress doctrine, the β-Amyloid theory, the brain-gut axis theory, etc., whether brain extracellular amyloid peptide exists β (Aβ) Deposition and intracellular tau protein (Tau) hyperphosphorylation while neurofibrillary tangles are the pathological diagnostic criteria of the disease, but the exact etiology of the AD is not well understood, and an effective cure for the AD is lacking to date.…”