Search

Abstract Accurate glioma subtype classification is critical for the treatment management of patients with brain tumors. Developing an automatically computer-aided algorithm for glioma subtype classification is challenging due to many factors. One of the difficulties is the label constraint. Specifically, each case is simply labeled the glioma subtype without precise annotations of lesion regions information. In this paper, we propose a novel hybrid fully convolutional neural network (CNN)-based method for glioma subtype classification using both whole slide imaging (WSI) and multiparametric magnetic resonance imagings (mpMRIs). It is comprised of two methods: a WSI-based method and a mpMRIs-based method. For the WSI-based method, we categorize the glioma subtype using a 2D CNN on WSIs. To overcome the label constraint issue, we extract the truly representative patches for the glioma subtype classification in a weakly supervised fashion. For the mpMRIs-based method, we develop a 3D CNN-based method by analyzing the mpMRIs. The mpMRIs-based method consists of brain tumor segmentation and classification. Finally, to enhance the robustness of the predictions, we fuse the WSI-based and mpMRIs-based results guided by a confidence index. The experimental results on the validation dataset in the competition of CPM-RadPath 2020 show the comprehensive judgments from both two modalities can achieve better performance than the ones by solely using WSI or mpMRIs. Furthermore, our result using the proposed method ranks the third place in the CPM-RadPath 2020 in the testing phase. The proposed method demonstrates a competitive performance, which is creditable to the success of weakly supervised approach and the strategy of label agreement from multi-modality data.

Falling is a major cause of personal injury and accidental death worldwide, in particular for the elderly. For aged care, a falling alarm system is highly demanded so that medical aid can be obtained immediately when the fall accidents happen. Previous studies on fall detection lacked practical considerations to deal with real-world situations, including the camera’s mounting angle, lighting differences between day and night, and the privacy protection for users. In our experiments, IR-depth images and thermal images were used as the input source for fall detection; as a result, detailed facial information is not captured by the system for privacy reasons, and it is invariant to the lighting conditions. Due to the different occurrence rates between fall accidents and other normal activities, supervised learning approaches may suffer from the problem of data imbalance in the training phase. Accordingly, in this study, anomaly detection is performed using unsupervised learning approaches so that the models were trained only with the normal cases while the fall accident was defined as an anomaly event. The proposed system takes sequential frames as the inputs to predict future frames based on a GAN structure, and it provides (1) multi-subject detection, (2) real-time fall detection triggered by motion, (3) a solution to the situation that subjects were occluded after falling, and (4) a denoising scheme for depth images. The experimental results show that the proposed system achieves the state-of-the-art performance and copes with the real-world cases successfully.

This paper reviews the former existing scheme on (n,n) -multiple secret sharing (MSS) for color images along with its slight limitation. This scheme generates a set of n shared images from a set of n secret images using the Chinese remainder theorem (CRT) and Boolean exclusive-OR (XOR) operation. This scheme works well if the number of secret images n is even number. However, the former scheme has a slight problem while the number of secret images n is an odd number. This paper proposes a new technique to overcome this problem by introducing symmetric and transferred masking coefficients to generate a set of shared images. To further improve the security level of the proposed method, a set of secret images is first transformed with hyperchaotic scrambling method before generating shared images. The security of the proposed (n,n)-MSS can also be increased by merging a shared color image into 2-D matrix representation. As documented in the experimental results, the proposed method offers a promising result on (n,n) -MSS scheme regardless of the number of secret images n is odd or even number. In addition, the proposed method outperforms the former existing (n,n)-MSS schemes in terms of quantitative measurements.

This paper proposes a new simple image encryption technique using the Beta chaotic map for performing the confusion and diffusion of input plain image. This image encryption is further applied to the multiple secret sharing (MSS). The former existing scheme in MSS employs the Chinese remainder theorem (CRT) and eXclusive-OR (XOR) operations to convert the secret image to become a set of shared images. The former scheme yields a good result while the number of secret images is even. However, it has slight limitation while the number of secret images is odd. This paper aims to overcome this problem by utilizing the proposed image encryption along with three new MSS approaches: 1) incorporating an additional random images; 2) performing k image encryption; and 3) using two different masking coefficients. As documented in the experimental section, the proposed method performs well in the MSS task. It solves the problem in former scheme on dealing with odd number of secret images. In addition, the proposed method is superior compared with the other competing schemes. The proposed image encryption also improves the security level in the MSS system.

This paper presents a simple technique for improving the quality of the halftoning-based block truncation coding (H-BTC) decoded image. The H-BTC is an image compression technique inspired from typical block truncation coding (BTC). The H-BTC yields a better decoded image compared to that of the classical BTC scheme under human visual observation. However, the impulsive noise commonly appears on the H-BTC decoded image. It induces an unpleasant feeling while one observes this decoded image. Thus, the proposed method presented in this paper aims to suppress the occurring impulsive noise by exploiting a deep learning approach. This process can be regarded as an ill-posed inverse imaging problem, in which the solution candidates of a given problem can be extremely huge and undetermined. The proposed method utilizes the convolutional neural networks (CNN) and residual learning frameworks to solve the aforementioned problem. These frameworks effectively reduce the impulsive noise occurrence, and at the same time, it improves the quality of H-BTC decoded images. The experimental results show the effectiveness of the proposed method in terms of subjective and objective measurements.

An efficient and geometric-distortion-free approach, namely the fast binary robust local feature (FBRLF), is proposed. The FBRLF searches the stable features from an image with the proposed multiscale adaptive and generic corner detection based on the accelerated segment test (MAGAST) to yield an optimum threshold value based on adaptive and generic corner detection based on the accelerated segment test (AGAST). To overcome the problem of image noise, the Gaussian template is applied, which is efficiently boosted by the adoption of an integral image. The feature matching is conducted by incorporating the voting mechanism and lookup table method to achieve a high accuracy with low computational complexity. The experimental results clearly demonstrate the superiority of the proposed method compared with the former schemes regarding local stable feature performance and processing efficiency.

Nonverbal communication plays a key role in conveying emotions during clinical interactions, but assessing it can be challenging. This study aims to develop a model for nonverbal communication using facial expression recognition and deep learning. A hybrid approach combining convolutional neural network (CNN)-based face detection and Extra Trees classifier was used to leverage CNN’s feature extraction and Extra Trees’ classification abilities. The study involved 88 nursing students participating in communication exercises with standardized patients, with their facial expressions scored by senior nurses and instructors, resulting in 3,318 labeled scores. The model, built using Extra Trees Regressor, found that students displayed adequate receptiveness, politeness, friendliness, and nonverbal empathy, with scores primarily between 60 and 70. By integrating clinical simulations with artificial intelligence, subjective bias was minimized, improving the stability of nonverbal behavior simulations. This model will be integrated into a nonverbal behavior learning platform to help nursing students develop communication skills and reduce anxiety during practice. The platform offers objective feedback, potentially enhancing healthcare education and telemedicine by providing advanced tools for evaluating nonverbal communication.