Deep Learning in Medical Research: Strengths and Pitfalls

IntroductionDeep learning techniques are gaining momentum in medical research. Evidence shows that deep learning has advantages over humans in image identification and classification, such as facial image analysis in detecting people’s medical conditions. While positive findings are available, little is known about the state-of-the-art of deep learning-based facial image analysis in the medical context. For the consideration of patients’ welfare and the development of the practice, a timely understanding of the challenges and opportunities faced by research on deep-learning-based facial image analysis is needed. To address this gap, we aim to conduct a systematic review to identify the characteristics and effects of deep learning-based facial image analysis in medical research. Insights gained from this systematic review will provide a much-needed understanding of the characteristics, challenges, as well as opportunities in deep learning-based facial image analysis applied in the contexts of disease detection, diagnosis and prognosis.MethodsDatabases including PubMed, PsycINFO, CINAHL, IEEEXplore and Scopus will be searched for relevant studies published in English in September, 2021. Titles, abstracts and full-text articles will be screened to identify eligible articles. A manual search of the reference lists of the included articles will also be conducted. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was adopted to guide the systematic review process. Two reviewers will independently examine the citations and select studies for inclusion. Discrepancies will be resolved by group discussions till a consensus is reached. Data will be extracted based on the research objective and selection criteria adopted in this study.Ethics and disseminationAs the study is a protocol for a systematic review, ethical approval is not required. The study findings will be disseminated via peer-reviewed publications and conference presentations.PROSPERO registration numberCRD42020196473.

Download Full-text

An Accuracy vs. Complexity Comparison of Deep Learning Architectures for the Detection of COVID-19 Disease

Computation ◽

10.3390/computation9010003 ◽

2021 ◽

Vol 9 (1) ◽

pp. 3

Author(s):

Sima Sarv Ahrabi ◽

Michele Scarpiniti ◽

Enzo Baccarelli ◽

Alireza Momenzadeh

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Medical Research ◽

Binary Classification ◽

Lung Infection ◽

X Rays ◽

Training Process ◽

Learning Architectures

In parallel with the vast medical research on clinical treatment of COVID-19, an important action to have the disease completely under control is to carefully monitor the patients. What the detection of COVID-19 relies on most is the viral tests, however, the study of X-rays is helpful due to the ease of availability. There are various studies that employ Deep Learning (DL) paradigms, aiming at reinforcing the radiography-based recognition of lung infection by COVID-19. In this regard, we make a comparison of the noteworthy approaches devoted to the binary classification of infected images by using DL techniques, then we also propose a variant of a convolutional neural network (CNN) with optimized parameters, which performs very well on a recent dataset of COVID-19. The proposed model’s effectiveness is demonstrated to be of considerable importance due to its uncomplicated design, in contrast to other presented models. In our approach, we randomly put several images of the utilized dataset aside as a hold out set; the model detects most of the COVID-19 X-rays correctly, with an excellent overall accuracy of 99.8%. In addition, the significance of the results obtained by testing different datasets of diverse characteristics (which, more specifically, are not used in the training process) demonstrates the effectiveness of the proposed approach in terms of an accuracy up to 93%.

Download Full-text

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33011093 ◽

2019 ◽

Vol 33 ◽

pp. 1093-1101 ◽

Cited By ~ 4

Author(s):

Yuhao Niu ◽

Lin Gu ◽

Feng Lu ◽

Feifan Lv ◽

Zongji Wang ◽

...

Keyword(s):

Diabetic Retinopathy ◽

Deep Learning ◽

Medical Research ◽

Retinal Image ◽

Medical Diagnosis ◽

Vessel Segmentation ◽

Panel Survey ◽

Successful Performance ◽

Koch’S Postulates ◽

Image Diagnosis

Though deep learning has shown successful performance in classifying the label and severity stage of certain disease, most of them give few evidence on how to make prediction. Here, we propose to exploit the interpretability of deep learning application in medical diagnosis. Inspired by Koch’s Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector. To visualize the symptom and feature encoded in this descriptor, we propose a GAN based method to synthesize pathological retinal image given the descriptor and a binary vessel segmentation. Besides, with this descriptor, we can arbitrarily manipulate the position and quantity of lesions. As verified by a panel of 5 licensed ophthalmologists, our synthesized images carry the symptoms that are directly related to diabetic retinopathy diagnosis. The panel survey also shows that our generated images is both qualitatively and quantitatively superior to existing methods.

Download Full-text

Application of Scanning Electron Microscopy to Medical Research

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100061963 ◽

1969 ◽

Vol 27 ◽

pp. 12-13

Author(s):

J. D. Hutchison

Keyword(s):

Electron Microscopy ◽

Electron Microscope ◽

Medical Research ◽

Prosthetic Heart Valve ◽

School Of Medicine ◽

Transmission Electron ◽

Definition Of ◽

Mechanism Of Failure ◽

The Brain ◽

Scanning Electron

When the transmission electron microscope was commercially introduced a few years ago, it was heralded as one of the most significant aids to medical research of the century. It continues to occupy that niche; however, the scanning electron microscope is gaining rapidly in relative importance as it fills the gap between conventional optical microscopy and transmission electron microscopy.IBM Boulder is conducting three major programs in cooperation with the Colorado School of Medicine. These are the study of the mechanism of failure of the prosthetic heart valve, the study of the ultrastructure of lung tissue, and the definition of the function of the cilia of the ventricular ependyma of the brain.

Download Full-text

Clinical Science in the 1990s

Clinical Science ◽

10.1042/cs0780001 ◽

1990 ◽

Vol 78 (1) ◽

pp. 1-1

Author(s):

M. J. Brown

Keyword(s):

Medical Research ◽

Review Process ◽

Molecular Level ◽

Short Interval ◽

Clinical Science ◽

Molecular Medicine ◽

Mutual Benefit ◽

Real Progress ◽

General Journal

From this issue, Clinical Science will increase its page numbers from an average of 112 to 128 per monthly issue. This welcome change — equivalent to at least two manuscripts — has been ‘forced’ on us by the increasing pressure on space; this has led to an undesirable increase in the delay between acceptance and publication, and to a fall in the proportion of submitted manuscripts we have been able to accept. The change in page numbers will instead permit us now to return to our exceptionally short interval between acceptance and publication of 3–4 months; and at the same time we shall be able not only to accept (as now) those papers requiring little or no revision, but also to offer hope to some of those papers which have raised our interest but come to grief in review because of a major but remediable problem. Our view, doubtless unoriginal, has been that the review process, which is unusually thorough for Clinical Science, involving a specialist editor and two external referees, is most constructive when it helps the evolution of a good paper from an interesting piece of research. Traditionally, the papers in Clinical Science have represented some areas of research more than others. However, this has reflected entirely the pattern of papers submitted to us, rather than any selective interest of the Editorial Board, which numbers up to 35 scientists covering most areas of medical research. Arguably, after the explosion during the last decade of specialist journals, the general journal can look forward to a renaissance in the 1990s, as scientists in apparently different specialities discover that they are interested in the same substances, asking similar questions and developing techniques of mutual benefit to answer these questions. This situation arises from the trend, even among clinical scientists, to recognize the power of research based at the cellular and molecular level to achieve real progress, and at this level the concept of organ-based specialism breaks down. It is perhaps ironic that this journal, for a short while at the end of the 1970s, adopted — and then discarded — the name of Clinical Science and Molecular Medicine, since this title perfectly represents the direction in which clinical science, and therefore Clinical Science, is now progressing.

Download Full-text