The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field.

Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal features from time-series data from multiple sensors. We propose a deep neural network architecture that not only captures the spatio-temporal features of multiple sensor time-series data but also selects, learns important time points by utilizing a self-attention mechanism. We show the validity of the proposed approach across different data sampling strategies on six public datasets and demonstrate that the self-attention mechanism gave a significant improvement in performance over deep networks using a combination of recurrent and convolution networks. We also show that the proposed approach gave a statistically significant performance enhancement over previous state-of-the-art methods for the tested datasets. The proposed methods open avenues for better decoding of human activity from multiple body sensors over extended periods of time. The code implementation for the proposed model is available at https://github.com/isukrit/encodingHumanActivity.

Intracranial hemorrhage is a medical emergency that requires urgent diagnosis and immediate treatment to improve patient outcome. Machine learning algorithms can be used to perform medical image classification and assist clinicians in diagnosing radiological scans. In this paper, we apply 3-dimensional convolutional neural networks (3D CNN) to classify computed tomography (CT) brain scans into normal scans (N) and abnormal scans containing subarachnoid hemorrhage (SAH), intraparenchymal hemorrhage (IPH), acute subdural hemorrhage (ASDH) and brain polytrauma hemorrhage (BPH). The dataset used consists of 399 volumetric CT brain images representing approximately 12,000 images from the National Neuroscience Institute, Singapore. We used a 3D CNN to perform both 2-class (normal versus a specific abnormal class) and 4-class classification (between normal, SAH, IPH, ASDH). We apply image thresholding at the image pre-processing step, that improves 3D CNN classification accuracy and performance by accentuating the pixel intensities that contribute most to feature discrimination. For 2-class classification, the F1 scores for various pairs of medical diagnoses ranged from 0.706 to 0.902 without thresholding. With thresholding implemented, the F1 scores improved and ranged from 0.919 to 0.952. Our results are comparable to, and in some cases, exceed the results published in other work applying 3D CNN to CT or magnetic resonance imaging (MRI) brain scan classification. This work represents a direct application of a 3D CNN to a real hospital scenario involving a medically emergent CT brain diagnosis.

Successive layers in convolutional neural networks (CNN) extract different features from input images. Applications of CNNs to detect abnormalities in the 2D images or 3D volumes of body organs have recently become popular. However, computer-aided detection of diseases using deep CNN is challenging due to the absence of a large set of training medical images/scans and the relatively small and hard to detect abnormalities. In this paper, we propose a method for normalizing 3D volumetric scans using the intensity profile of the training samples. This aids the CNN by creating a higher contrast around the abnormal region of interest in the scan. We use the CQ500 head CT dataset to demonstrate the validity of our method for detecting different acute brain hemorrhages such as subarachnoid hemorrhage (SAH), intraparenchymal hemorrhage (IPH), subdural hematoma (SDH), and intraventricular hemorrhage (IVH). We compare the proposed method with a baseline, two variants of the 3D VGGNet architectures, Resnet, and show that the proposed method achieves significant improvement in classification performance. For binary classification, we achieved the best F1 score of 0.96 (normal vs SAH), 0.93 (normal vs IPH), 0.98 (normal vs SDH), and 0.99 (normal vs IVH), and for four-class classification, we obtained an average F1 score of 0.77. Finally, we show a limitation of the proposed method while detecting varied abnormalities. The proposed method has applications for abnormality detection for different organs.

With the wide applications of Wireless sensor networks (WSNs) in various fields such as environment monitoring, battlefield surveillance, healthcare, and intrusion detection, trust establishment among sensor nodes becomes vital requirement to improve security, reliability and successful cooperation. The existing trust management approaches for large scale WSN are failed due to their low dependability (i.e. cooperation), higher communication and memory overheads (i.e. resource inefficient). In this paper, we propose a novel and comprehensive trust estimation approach (LTS) for large scale WSN that employs clustering to improve cooperation, trustworthiness, and security by detecting malicious (faulty or selfish) sensor nodes with reduced resource (memory, power) consumption. The proposed scheme (LTS) operates on two levels namely, intra-cluster and inter-cluster along with distributed approach and centralized approach respectively to make accurate trust decision of sensor nodes with minimum overheads. LTS consists of unique features like robust trust estimation function, attack resistant and efficient trust aggregation at cluster head to obtain global feedback trust value. Data trust along with communication trust plays a significant role to cope with malicious nodes. In LTS, punishment and trust severity can be tuned according to the application requirement makes it an innovative trust estimation approach. Moreover, dishonest recommendations (outliers) are eliminated before aggregation at the base station by observing statistical dispersion. Theoretical and mathematical validation along with simulation results exhibit great performance of our proposed approach in terms of trust evaluation cost, prevention, and detection of malicious nodes as well as communication overhead.

In this work, a novel Ultra-wideband –Multi-Input-Multi-Output Antenna Sensor (UMAS) probe is designed for the detection of the malignant cells in the breast. The Sensor probe has four radiating elements and it is operated within the 2.8 GHz to 20 GHz ultra-wide band range. Isolation between the radiating element is more than 20 dB. Further, three kinds of the breast phantoms (i.e. normal phantom, phantom with single and multiple tumors) are fabricated using tissue mimicking material. The electrical characteristics of the malignant cells are different from non-malignant cells of the breast. The S-parameter and Specific Absorption Rate (SAR) analysis are best approaches to detect the malignant cells in the breast. The UMAS sensing probe is embedded on the phantoms and S-parameters of the probe are recorded from the Vector Network Analyzer (VNA). Measured S-parameters of the probe for normal and malignant phantoms are differ from each other. The statistical machine learning concept of Principal Component Analysis (PCA) is also applied on the measured S-Parameters. Which exhibits clear detection of normal and malignant breast phantoms. Further verification is done by using Simulation based specific absorption rate (SAR) study of the phantom models for tumor detection. The obtained maximum SAR results are well differentiating the normal phantom.