A Shape Approximation for Medical Imaging Data

Deep Convolutional Neural Networks on Multiclass Classification of Three-Dimensional Brain Images for Parkinson's Disease Stage Prediction

Parkinson's disease (PD), a degenerative disorder of the central nervous system, is commonly diagnosed using functional medical imaging techniques such as single-photon emission computed tomography (SPECT). In this study, we utilized two SPECT data sets (n = 634 and n = 202) from different hospitals to develop a model capable of accurately predicting PD stages, a multiclass classification task. We used the entire three-dimensional (3D) brain images as input and experimented with various model architectures. Initially, we treated the 3D images as sequences of two-dimensional (2D) slices and fed them sequentially into 2D convolutional neural network (CNN) models pretrained on ImageNet, averaging the outputs to obtain the final predicted stage. We also applied 3D CNN models pretrained on Kinetics-400. Additionally, we incorporated an attention mechanism to account for the varying importance of different slices in the prediction process. To further enhance model efficacy and robustness, we simultaneously trained the two data sets using weight sharing, a technique known as cotraining. Our results demonstrated that 2D models pretrained on ImageNet outperformed 3D models pretrained on Kinetics-400, and models utilizing the attention mechanism outperformed both 2D and 3D models. The cotraining technique proved effective in improving model performance when the cotraining data sets were sufficiently large.

Classification of Plank Techniques Using Wearable Sensors

The plank is a common core-stability exercise. Developing a wearable inertial sensor system for distinguishing between acceptable and aberrant plank techniques and detecting specific deviations from acceptable plank techniques can enhance performance and prevent injury. The purpose of this study was to develop an inertial measurement unit (IMU)-based plank technique quantification system. Nineteen healthy volunteers (age: 20.5 ± 0.8 years, BMI: 22.9 ± 1.4 kg/m²) performed the standard plank technique and six deviations with five IMUs positioned on the occiput, cervical spine, thoracic spine, sacrum, and right radius to record movements. The random forest method was employed to perform the classification. The proposed binary tree classification model achieved an accuracy of more than 86%. The average sensitivities were higher than 90%, and the specificities were higher than 91%, except for one deviation (83%). These results suggest that the five IMU-based systems can classify the plank technique as acceptable or aberrant with good accuracy, high sensitivity, and acceptable specificity, which has significant implications in monitoring plank biomechanics and enabling coaching practice.

Self-normalized Classification of Parkinson's Disease DaTscan Images

Classifying SPECT images requires a preprocessing step which normalizes the images using a normalization region. The choice of the normalization region is not standard, and using different normalization regions introduces normalization region-dependent variability. This paper mathematically analyzes the effect of the normalization region to show that normalized-classification is exactly equivalent to a subspace separation of the half rays of the images under multiplicative equivalence. Using this geometry, a new self-normalized classification strategy is proposed. This strategy eliminates the normalizing region altogether. The theory is used to classify DaTscan images of 365 Parkinson's disease (PD) subjects and 208 healthy control (HC) subjects from the Parkinson's Progression Marker Initiative (PPMI). The theory is also used to understand PD progression from baseline to year 4.