Quantifying the Association between Objectively Measured Physical Activity and Multiple Sclerosis in the UK Biobank.

INTRODUCTION: Objectively measured physical activity (PA) data were collected in the accelerometry substudy of the UK Biobank. UK Biobank also contains information about multiple sclerosis (MS) diagnosis at the time of and after PA collection. This study aimed to 1) quantify the difference in PA between prevalent MS cases and matched healthy controls, and 2) evaluate the predictive performance of objective PA measures for incident MS cases. METHODS: The first analysis compared eight accelerometer-derived PA summaries between MS patients ( N = 316) and matched controls (30 controls for each MS case). The second analysis focused on predicting time to MS diagnosis among participants who were not diagnosed with MS. A total of 19 predictors including eight measures of objective PA were compared using Cox proportional hazards models (number of events = 47; 585,900 person-years of follow-up). RESULTS: In the prevalent MS study, the difference between MS cases and matched controls was statistically significant for all PA summaries ( P < 0.001). In the incident MS study, the most predictive variable of progression to MS in univariate Cox regression models was lower age ( C = 0.604), and the most predictive PA variable was lower relative amplitude (RA, C = 0.594). A two-stage forward selection using Cox regression resulted in a model with concordance C = 0.693 and four predictors: age ( P = 0.015), stroke ( P = 0.009), Townsend deprivation index ( P = 0.874), and RA ( P = 0.004). A model including age, stroke, and RA had a concordance of C = 0.691. CONCLUSIONS: Objective PA summaries were significantly different and consistent with lower activity among study participants who had MS at the time of the accelerometry study. Among individuals who did not have MS, younger age, stroke history, and lower RA were significantly associated with a higher risk of a future MS diagnosis.

Weakly-Supervised Learning With Complementary Heatmap for Retinal Disease Detection.

There are many types of retinal disease, and accurately detecting these diseases is crucial for proper diagnosis. Convolutional neural networks (CNNs) typically perform well on detection tasks, and the attention module of CNNs can generate heatmaps as visual explanations of the model. However, the generated heatmap can only detect the most discriminative part, which is problematic because many object regions may exist in the region beside the heatmap in an area known as a complementary heatmap. In this study, we developed a method specifically designed multi-retinal diseases detection from fundus images with the complementary heatmap. The proposed CAM-based method is designed for 2D color images of the retina, rather than MRI images or other forms of data. Moreover, unlike other visual images for disease detection, fundus images of multiple retinal diseases have features such as distinguishable lesion region boundaries, overlapped lesion regions between diseases, and specific pathological structures (e.g. scattered blood spots) that lead to mis-classifications. Based on these considerations, we designed two new loss functions, attention-explore loss and attention-refine loss, to generate accurate heatmaps. We select both "bad" and "good" heatmaps based on the prediction score of ground truth and train them with the two loss functions. When the detection accuracy increases, the classification performance of the model is also improved. Experiments on a dataset consisting of five diseases showed that our approach improved both the detection accuracy and the classification accuracy, and the improved heatmaps were closer to the lesion regions than those of current state-of-the-art methods.

How to Extract More Information With Less Burden: Fundus Image Classification and Retinal Disease Localization With Ophthalmologist Intervention.

Image classification using convolutional neural networks (CNNs) outperforms other state-of-the-art methods. Moreover, attention can be visualized as a heatmap to improve the explainability of results of a CNN. We designed a framework that can generate heatmaps reflecting lesion regions precisely. We generated initial heatmaps by using a gradient-based classification activation map (Grad-CAM). We assume that these Grad-CAM heatmaps correctly reveal the lesion regions; then we apply the attention mining technique to these heatmaps to obtain integrated heatmaps. Moreover, we assume that these Grad-CAM heatmaps incorrectly reveal the lesion regions and design a dissimilarity loss to increase their discrepancy with the Grad-CAM heatmaps. In this study, we found that having professional ophthalmologists select 30% of the heatmaps covering the lesion regions led to better results, because this step integrates (prior) clinical knowledge into the system. Furthermore, we design a knowledge preservation loss that minimizes the discrepancy between heatmaps generated from the updated CNN model and the selected heatmaps. Experiments using fundus images revealed that our method improved classification accuracy and generated attention regions closer to the ground truth lesion regions in comparison with existing methods.

Endoscopic Image Clustering with Temporal Ordering Information Based on Dynamic Programming.

In this paper, we propose a clustering method with temporal ordering information for endoscopic image sequences. It is difficult to collect a sufficient amount of endoscopic image datasets to train machine learning techniques by manual labeling. The clustering of endoscopic images leads to group-based labeling, which is useful for reducing the cost of dataset construction. Therefore, in this paper, we propose a clustering method where the property of endoscopic image sequences is fully utilized. For the proposed method, a deep neural network was used to extract features from endoscopic images, and clustering with temporal ordering information was solved by dynamic programming. In the experiments, we clustered the esophagogastroduodenoscopy images. From the results, we confirmed that the performance was improved by using the sequential property.

Automatic segmentation of airway tree based on local intensity filter and machine learning technique in 3D chest CT volume.

PURPOSE: Airway segmentation plays an important role in analyzing chest computed tomography (CT) volumes for computerized lung cancer detection, emphysema diagnosis and pre- and intra-operative bronchoscope navigation. However, obtaining a complete 3D airway tree structure from a CT volume is quite a challenging task. Several researchers have proposed automated airway segmentation algorithms basically based on region growing and machine learning techniques. However, these methods fail to detect the peripheral bronchial branches, which results in a large amount of leakage. This paper presents a novel approach for more accurate extraction of the complex airway tree. METHODS: This proposed segmentation method is composed of three steps. First, Hessian analysis is utilized to enhance the tube-like structure in CT volumes; then, an adaptive multiscale cavity enhancement filter is employed to detect the cavity-like structure with different radii. In the second step, support vector machine learning will be utilized to remove the false positive (FP) regions from the result obtained in the previous step. Finally, the graph-cut algorithm is used to refine the candidate voxels to form an integrated airway tree. RESULTS: A test dataset including 50 standard-dose chest CT volumes was used for evaluating our proposed method. The average extraction rate was about 79.1 % with the significantly decreased FP rate. CONCLUSION: A new method of airway segmentation based on local intensity structure and machine learning technique was developed. The method was shown to be feasible for airway segmentation in a computer-aided diagnosis system for a lung and bronchoscope guidance system.