Author Interviews, Dermatology, Technology / 03.04.2020
AI Improved Diagnosis of Skin Disorders, especially Distinguishing Benign from Malignant Tumors
MedicalResearch.com Interview with:
[caption id="attachment_53761" align="alignleft" width="168"] Dr. Jung Im Na[/caption]
Jung-Im Na, MD PhD
Associate Professor, Department of Dermatology
Seoul National University Bundang Hospital
Korea
MedicalResearch.com: What is the background for this study? Would you briefly explain what is meant by a convolutional neural network?
Response: When a very young child looks at a picture, she can easily identify cats and dogs, however, even the most advanced computers had struggled at this task until recently.
Computers began to “see” with the recent advancement of Deep Learning techniques. Deep Learning is a machine learning technique that teaches computers to learn from raw data. Most deep learning methods use artificial neural network architectures, imitating human brain, and convolutional neural networks (CNN) is a particular type of deep learning architecture, imitating the visual cortex. CNN is especially powerful for recognizing images. CNN exploit the information contained in image datasets to automatically learn features and patterns.
Dr. Jung Im Na[/caption]
Jung-Im Na, MD PhD
Associate Professor, Department of Dermatology
Seoul National University Bundang Hospital
Korea
MedicalResearch.com: What is the background for this study? Would you briefly explain what is meant by a convolutional neural network?
Response: When a very young child looks at a picture, she can easily identify cats and dogs, however, even the most advanced computers had struggled at this task until recently.
Computers began to “see” with the recent advancement of Deep Learning techniques. Deep Learning is a machine learning technique that teaches computers to learn from raw data. Most deep learning methods use artificial neural network architectures, imitating human brain, and convolutional neural networks (CNN) is a particular type of deep learning architecture, imitating the visual cortex. CNN is especially powerful for recognizing images. CNN exploit the information contained in image datasets to automatically learn features and patterns.
Dr. Bin Cao[/caption]
Bin Cao, Yeming Wang, Guohui Fan,
Lianghan Shang, Jiuyang Xu, DingyuZhang, Chen Wang
on behalf of LOTUS-China Study Group
China-Japan Friendship Hospital; Wuhan Jintinyan Hospital;
Institute of Respiratory Medicine, Chinese Academy of Medical Science
MedicalResearch.com: What is the background for this study?
Response: In the past two months, the outbreak of Coronavirus Disease 2019 (COVID-19) has been spreading rapidly across the world. Science and technology is the most powerful weapon for human to fight against diseases, especially in such a pandemic setting. Seeking for effective antiviral medication is the most critical and urgent among the many scientific tasks in the pandemic.
At the most critical moment in the fight against COVID-19, Chinese clinical scientists have stepped forward under extremely difficult research conditions to carry out clinical trials in antiviral treatment including lopinavir–ritonavir and remdesivir, in a swift, decisive and effective manner. These trials have attracted worldwide attention.
Recently, the Lopinavir–ritonavir Trial for suppression of SARS-CoV-2 in China (LOTUS-China) has been completed, which, with great clinical significance, can provide strong evidence for the treatment of COVID-19 both in China and around the world.
Dr. Jeffrey Smith[/caption]
Jeffrey R. Smith, MD PhD
Department of Medicine, Division of Genetic Medicine
Vanderbilt-Ingram Cancer Center, and Vanderbilt Genetics Institute
Vanderbilt University Medical Center
Medical Research Service
Tennessee Valley Healthcare System, Veterans Administration
Nashville, TN
MedicalResearch.com: What is the background for this study?
Response: Roughly 20% of men with prostate cancer have a family history of the disease, and 5% meet criteria for hereditary prostate cancer. Although prostate cancer has the greatest heritability of all common cancers (twice that of breast cancer), extensive heterogeneity of its inherited causes has presented a considerable obstacle for traditional pedigree-based genetic investigative approaches. Inherited causes across, as well as within families are diverse.
This study introduced a new familial case-control study design that uses extent of family history as a proxy for genetic burden. It compared a large number of men with prostate cancer, each from a separate family with a strong history of the disease, to screened men with no personal or family history. The study comprehensively deconstructs how the 8q24 chromosomal region impacts risk of hereditary prostate cancer, introducing several new analytical approaches. The locus had been known to alter risk of prostate, breast, colon, ovarian, and numerous additional cancers.
Dr. Kooraki[/caption]
Soheil Kooraki MSR MS, MD
on behalf of Dr. Ali Gholamrezanezhad MD and co-authors
Department of Radiological Sciences,
David Geffen School of Medicine, University of California at Los Angeles
Los Angeles, California
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: COVID19 is a novel strain of the coronavirus family causing pneumonia. Two similar strains were discovered in 2003 and 2012 to cause the so-called SARS and MERS outbreaks, respectively. Radiologists need to be prepared for the escalating incidence of COVID-19. We reviewed the literature to extract the epidemiologic and imaging features of SARS and MERS in comparison with known imaging features of COVID-19 pneumonia to have a better understanding of the imaging features of the COVID19 pneumonia in acute and post-recovery stages.
