Applications of Deep Learning and Machine Learning in Computational Medicine

Computational medicine has emerged due to the advances in medical technology in parallel with big data and artificial intelligence. A new way of treating complex diseases is evolving called 'Precision Medicine' fueled by big data extracting meaningful information from individual variability. At the forefront is biomedical research aiming to promote the area of precision medicine. Though traditional machine learning methods have built successful models for cancer diagnosis to sars-cov2 pulmonary infection, the advent of modern deep learning methods has had phenomenal growth in genomics, electronic health records, and drug development. The challenges in Deep learning applications in medicine include lack of data, privacy, heterogeneity of data, and interpretability. Analysis and discussion on these problems provide a reference to improve the application of deep learning in medical health.

Transfer learning-based CNN diagnostic framework for diagnosis of COVID-19 from lung CT images

COVID-19 is an infectious disease that affects the respiratory system. To assist the physician in diagnosing lung disorders from chest CT images various systems have been developed and used. Detection of COVID-19 remains a challenging area of research. The objective of the work is to develop an inductive parameter-transfer learning-based approach for the prediction of COVID-19, pneumonia, from lung CT images. Our proposed approach is built on layer wise and convolution block-wise fine-tuning which designs the CNN architecture highly specific to lung CT image. We implemented the DenseNet201, InceptionV3, Xception, VGG19, and ResNet50 as baseline models. The network architectures are developed to learn feature representation of lung CT images. For the experimental analysis, five datasets are used. From the experimental results, it is inferred that the DenseNet201 model yields higher accuracy of 0.94 for Adam optimizer and 0.93 for the RMSprop optimizer compared to other models.

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Vascular and non-vascular UNet systems dominated with sUNet classes with attention. Most of the studies suffered from a low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings.

Deep Viewing for Covid-19 Detection from X-Ray Using CNN Based Architecture

The Covid-19 coronavirus has turned into a serious, life-threatening disease that is prevalent worldwide as it is most likely to infect. An automated protocol system is a compelling idea to stop the spread of covid19. This article aims at a deep learning model supported by a convolutional neural network (CNN) to facilitate automatic diagnosis from chest X-rays. A collection of 2875 covid19 images and 10293 X-ray pictures to recognize covid19 counts is being used as the data set for the drafting. From the experimental results, it can be seen that the proposed structure achieves 96% specificity, 97% AUC 96% accuracy, 96% sensitivity, and 96% F1-score. Therefore, the results of the proposed system will help clinicians and researchers discover COVID-19 patients and facilitate the treatment of COVID-19 patients.

Deploying Deep Transfer Learning Models To A Web-App For Sars-Cov-2 Detection Using Chest Radiography Images

According to the World Health Organization(WHO), the Coronavirus Disease 2019 (COVID-19) is a global hazard to the healthcare sector, with developing and highly populated countries like India influencing the country's rising economy. In this situation, early detection and diagnosis ofCOVID-19 are critical for mitigating the pandemic's impactCOVID-19 is critical for mitigating the damage induced by the pandemic disease;consequently, alternate methods for detecting COVID-19 other than manual lab-testing are necessary. This work aims to build and deploy deep Convolutional Neural Networks(CNN) image classification models to a python-flask based web app which is hosted onAWS-EC2 Linux based virtual server to predict if a person isCOVID-19 positive or negative just by uploading chest X-rayor computed tomography(CT)-scan image. Therefore, this method investigates the potential of Deep Transfer Learning algorithms such as Res Net 50,Inception V3, Xception, and VGG16 to act as an alternative for manual lab-based testing like reverse-transcription polymerase-chain-reaction(RT-PCR)tests, Rapid tests, and other various types of Antigen tests which, on average, takes 1-2 days to acquire the results, which is unbearable because the affected person can spread the disease to many more members of the population. The CNN models employed in this work are trained on chest X-rays and CT-scan image datasets obtained from verified radiologists' sources, then these datasets are pre-processed and normalized to achieve higher efficiency. Finally, these trained models are integrated with web-scripting files to create user-friendly web platform, allowing users to upload the sample of the chest X-ray or CT-scan image to refer and compare the predictions made by all four types of models on a single web plat form within a few minutes.

Emerging Technologies for Next Generation Remote Health Care and Assisted Living

Remote health care is currently one of the most promising solutions to ensure a high level of treatment outcome, cost-efficiency and sustainability of the healthcare systems worldwide. Even though research on remote health care can be traced back to the early days of the Internet, the recent COVID-19 has necessitated further improvement in existing health care systems with invigorated research on remote health care technologies. In this article we delve into the state-of-the-art research in latest technologies and technological paradigms that play a vital role in enabling the next generation remote health care and assisted living. First the need of using the latest technological developments in the domain of remote health care is briefly discussed. Then the most important technologies and technological paradigms that are crucial in enabling remote health care and assisted living are emphasised. Henceforth, a detailed survey of existing technologies, potential challenges in those technologies, and possible solutions is conducted. Finally, missing research gaps and important future research directions in each enabling technology are brought forth to motivate further research in remote health care.

Lightweight Skip Connections With Efficient Feature Stacking for Respiratory Sound Classification

As the number of deaths from respiratory diseases due to COVID-19 and infectious diseases increases, early diagnosis is necessary. In general, the diagnosis of diseases is based on imaging devices (e.g., computed tomography and magnetic resonance imaging) as well as the patient's underlying disease information. However, these examinations are time-consuming, incur considerable costs, and in a situation like the ongoing pandemic, face-to-face examinations are difficult to conduct. Therefore, we propose a lung disease classification model based on deep learning using non-contact auscultation. In this study, two respiratory specialists collected normal respiratory sounds and five types of abnormal sounds associated with lung disease, including those associated with four lung lesions in the left and right anterior chest and left and right posterior chest. For preprocessing and feature extraction, the noise was removed using three pass filters (low, band, and high), and respiratory sound features were extracted using the Log-Mel Spectrogram-Mel Frequency Cepstral Coefficient followed by feature stacking. Then, we propose a lung disease classification model of dense lightweight convolutional neural network-bidirectional gated recurrent unit skip connections using depthwise separable convolution based on the extracted respiratory sound information. The performance of the classification model was compared with both the baseline and the lightweight models. The results indicate that the proposed model achieves high performance and has an accuracy of 92.3%, sensitivity of 92.1%, specificity of 98.5%, and f1-score of 91.9%. Using the proposed model, we aim to contribute to the early detection of diseases during the COVID-19 pandemic.