Convolutional Neural Networks to Classify Alzheimer’s Disease Severity Based on SPECT Images: A Comparative Study

Abstract

Image recognition and neuroimaging are increasingly being used to understand the progression of Alzheimer’s disease (AD). However, image data from single-photon emission computed tomography (SPECT) are limited. Medical image analysis requires large, labeled training datasets. Therefore, studies have focused on overcoming this problem. In this study, the detection performance of five convolutional neural network (CNN) models (MobileNet V2 and NASNetMobile (lightweight models); VGG16, Inception V3, and ResNet (heavier weight models)) on medical images was compared to establish a classification model for epidemiological research. Brain scan image data were collected from 99 subjects, and 4711 images were used. Demographic data were compared using the chi-squared test and one-way analysis of variance with Bonferroni’s post hoc test. Accuracy and loss functions were used to evaluate the performance of CNN models. The cognitive abilities screening instrument and mini mental state exam scores of subjects with a clinical dementia rating (CDR) of 2 were considerably lower than those of subjects with a CDR of 1 or 0.5. This study analyzed the classification performance of various CNN models for medical images and proved the effectiveness of transfer learning in identifying the mild cognitive impairment, mild AD, and moderate AD scoring based on SPECT images.

Clinical Applications of Artificial Intelligence in Medical Imaging and Image Processing—A Review

“…This collection includes eight articles on detection, five on classification, four on segmentation, seven on prediction, five on quality improvement, and three on simulation. The following organs were of interest: the lungs (4), breasts (4), liver (3), brain (9), prostate (3), and others (8). Two studies were conducted on phantoms.…”

“…Two studies were conducted on phantoms. The most popular imaging modalities are MRI (11) and CT (8), but there are also works on radiography, ultrasound, and microscopic images. The achieved efficiencies cannot be clearly compared due to different research methodologies, but, as an example, in detection tasks, efficiency ranged from approx.…”