Breaking News
May 27, 2018 - Breast cancer survivors do not receive recommended level of screening after surgery
May 27, 2018 - Recommendations Developed for Managing Postpartum Pain
May 27, 2018 - Rheumatoid Arthritis (RA) | Arthritis Basics | Arthritis Types | Arthritis
May 27, 2018 - ‘Life support’ for transplant livers better than freezing: study
May 27, 2018 - Tree nut consumption linked to improved type 2 diabetes health
May 27, 2018 - Income and education gap causes racial differences in health behaviors, study shows
May 27, 2018 - Even at ‘Safe’ Levels, Air Pollution Puts Seniors at Risk
May 27, 2018 - Obstructive sleep apnea linked to thinning of calvaria, skull base
May 27, 2018 - Epigem’s Managing Director sets the bar for life sciences industry at VentureFest
May 27, 2018 - CPAP may reduce resting heart rate in prediabetic patients
May 27, 2018 - Study reveals striking disparities in health care access and quality across most nations
May 27, 2018 - The Yogi masters were right—meditation and breathing exercises can sharpen your mind
May 27, 2018 - SLU researcher aims to find solutions for diabetes patients at risk of hypoglycemia
May 27, 2018 - Scientists uncover the cause of insulin resistance in obesity
May 27, 2018 - $2.3 million NIH grant to support new project on oxytocin neurons and social behavior
May 27, 2018 - Less Driving Tied to Lower Cardiovascular Disease Risk
May 27, 2018 - Genetics Home Reference: LMNA-related congenital muscular dystrophy
May 27, 2018 - Long-term psychological study confirms time is the best medicine against homesickness
May 27, 2018 - Study explores if CPAP treatment can improve sexual QOL for sleep apnea patients
May 27, 2018 - Study investigates role played by brain in prosocial behavior
May 27, 2018 - New Guidelines Mean 1 in 3 Adults May Need Blood Pressure Meds
May 27, 2018 - Cerebrospinal Fluid (CSF) Analysis: MedlinePlus Lab Test Information
May 27, 2018 - Kids in tough neighborhoods head to ER more often
May 27, 2018 - Exercise alters brain’s dopamine system to help treat addiction, study finds
May 27, 2018 - Sepsis patients treated and released from ED for outpatient follow-up experience good outcomes
May 27, 2018 - Initiative cuts overuse of tests, treatments for bronchiolitis
May 27, 2018 - Study links ‘sleep spindles’ to memory reactivation
May 27, 2018 - Scientists develop new method to speed up genome evolution of baker’s yeast
May 27, 2018 - Sunscreen pills are fake says FDA
May 27, 2018 - Study finds increasing wealth gap between households of seniors and families with children
May 27, 2018 - Link between tuberculosis and Parkinson’s disease discovered
May 27, 2018 - Doctors call on health authorities for permission to provide stroke patients with life-saving treatment
May 26, 2018 - Couples who eat seafood-rich diet tend to get pregnant faster
May 26, 2018 - NIH summit presents recommendations to accelerate treatment development for Alzheimer’s disease
May 26, 2018 - Medication-related harm found to be common among older adults, but preventable
May 26, 2018 - Lunaphore and Vitro announce partnership to develop ISH protocols for RNA, DNA targets
May 26, 2018 - Cryoablation Efficacious for Cancer Pain, Review Finds
May 26, 2018 - Link between IBD and Parkinson’s might allow doctors to slow down condition
May 26, 2018 - Study finds fewer than 5% of low-income, urban mothers use prenatal vitamins before pregnancy
May 26, 2018 - California hospitals urge moms to favor breast milk over formula
May 26, 2018 - Most concussion patients do not receive follow-up care after hospital discharge, says study
May 26, 2018 - Lifetime risks of developing Alzheimer’s dementia vary by age, gender
May 26, 2018 - Researchers find novel ways to improve participation in clinical research
May 26, 2018 - Researchers develop methods for measuring free-base nicotine levels in e-cigarettes
May 26, 2018 - AHA: Preterm Birth Could Warn of Mom’s Future Heart Risks
May 26, 2018 - Some calories more harmful than others
May 26, 2018 - Study links cell size with commitment to division
May 26, 2018 - Researchers develop new, rapid blood test to detect liver damage
May 26, 2018 - Researchers discover cascade of immune processes linked to poor outcomes in aggressive breast cancer
May 26, 2018 - New research will use mathematics to solve mysteries in cell biology
May 26, 2018 - Proposed National Resilience Strategy to reverse catastrophic increases in ‘deaths of despair’
May 26, 2018 - Mice remain slim on burger diet
May 26, 2018 - BMC receives $13.5 million award to test methods for delivering childhood anxiety treatment
May 26, 2018 - ‘Right to Try Act’ will not benefit terminally-ill patients
May 26, 2018 - Study reveals novel statistical algorithm to identify potential disease genes
May 26, 2018 - Two genes play vital roles in malignant brain cancer
May 26, 2018 - Study explores link between groundwater lithium and diagnoses of bipolar disorder, dementia
May 26, 2018 - Researchers reveal stimulatory effects of myelin on young neural cells
May 26, 2018 - Small part of cellular protein that helps form long-term memories also drives neurodegeneration
May 26, 2018 - Four-legged friends can have heart issues, too
May 26, 2018 - Scientists create small, self-contained spaces inside mammalian cells
May 26, 2018 - Better Social Support Network Protects Black Men Against HIV
May 26, 2018 - National Heart, Lung, and Blood Institute (NHLBI)
May 26, 2018 - Burnout, depression can affect ophthalmology residents, study finds
May 26, 2018 - Latinos and African Americans more likely to experience serious depression than Whites
May 26, 2018 - Data from past epidemic could help improve response to future Ebola outbreaks
May 26, 2018 - Researchers provide insight into how the memory molecule limits brain plasticity
May 26, 2018 - OSU biologist describes ‘restoration ecology’ approach toward patient health
May 26, 2018 - New approach to study brown fat could aid in finding treatments for obesity
May 26, 2018 - UCI Center on Stress & Health receives NIH funding to develop digital health interventions
May 26, 2018 - Could More Fish in the Diet Boost Sex Lives and Fertility?
May 26, 2018 - NTU Singapore and SERI invent new scope to diagnose glaucoma
May 26, 2018 - Cancer cells co-opt pain-sensing ‘neural channel’ to increase tolerance against oxidative stress
May 26, 2018 - Study uncovers why pesticide exposure increases Parkinson’s disease risk in some people
May 26, 2018 - Study finds link between lead exposure and fertility rates
May 26, 2018 - Causes and treatment of acute heart failure vary by region, registry shows
May 26, 2018 - Delivery of standardized diabetes care could help achieve equitable health outcomes for all patients
May 26, 2018 - FDA authorizes marketing of OsteoDetect software for detecting wrist fractures
May 26, 2018 - HSE experts suggest new way of looking at infantilism
May 26, 2018 - Children and adolescents growing up in extreme societal conditions more likely to resort to violence
Researchers determine ‘sweet spot’ could enhance diagnosis of melanoma skin lesions

Researchers determine ‘sweet spot’ could enhance diagnosis of melanoma skin lesions

image_pdfDownload PDFimage_print

Too much, too little, just right. It might seem like a line from “Goldilocks and the Three Bears,” but actually describes an important finding from researchers in Florida Atlantic University’s College of Engineering and Computer Science. They have developed a technique using machine learning – a sub-field of artificial intelligence (AI) – that will enhance computer-aided diagnosis (CADx) of melanoma. Thanks to the algorithm they created – which can be used in mobile apps that are being developed to diagnose suspicious moles – they were able to determine the “sweet spot” in classifying images of skin lesions.

This new finding, published in the Journal of Digital Imaging, will ultimately help clinicians more reliably identify and diagnose melanoma skin lesions, distinguishing them from other types of skin lesions. The research was conducted in the NSF Industry/University Cooperative Research Center for Advanced Knowledge Enablement (CAKE) at FAU and was funded by the Center’s industry members.

Melanoma is a particularly deadly form of skin cancer when left undiagnosed. In the United States alone, there were an estimated 76,380 new cases of melanoma and an estimated 6,750 deaths due to melanoma in 2016. Malignant melanoma and benign skin lesions often appear very similar to the untrained eye. Over the years, dermatologists have developed different heuristic classification methods to diagnose melanoma, but to limited success (65 to 80 percent accuracy). As a result, computer scientists and doctors have teamed up to develop CADx tools capable of aiding physicians to classify skin lesions, which could potentially save numerous lives each year.

“Contemporary CADx systems are powered by deep learning architectures, which basically consist of a method used to train computers to perform an intelligent task. We feed them massive amounts of data so that they can learn to extract meaning from the data and, eventually, demonstrate performance comparable to human experts – dermatologists in this case,” said Oge Marques, Ph.D., lead author of the study and a professor in FAU’s Department of Computer and Electrical Engineering and Computer Science who specializes in machine cognition, medical imaging and health care technologies. “We are not trying to replace physicians or other medical professionals with artificial intelligence. We are trying to help them solve a problem faster and with greater accuracy, in other words enabling augmented intelligence.”

Images of skin lesions often contain more than just skin lesions – background noise, hair, scars, and other artifacts in the image can potentially confuse the CADx system. To prevent the classifier from incorrectly associating these irrelevant artifacts with melanoma, the images are segmented into two parts, separating the lesion from the surrounding skin, hoping that the segmented lesion can be more easily analyzed and classified.

“Previous studies have produced conflicting results: some research suggests that segmentation improves classification while other research suggests that segmentation is detrimental, due to a loss of contextual information around the lesion area,” said Marques. “How much we segment an image can either help or impede skin lesion classification.”

With that in mind, Marques and his collaborators Borko Furht, Ph.D., a professor in FAU’s Department of Electrical and Computer Engineering and Computer Science and director of the NSF-sponsored CAKE at FAU; Jack Burdick, a second-year master’s student at FAU; and Janet Weinthal, an undergraduate student at FAU, tested their hypothesis: “How much segmentation is too much?”

To test their hypothesis, the researchers first compared the effects of no segmentation, full segmentation, and partial segmentation on classification and demonstrated that partial segmentation led to the best results. They then proceeded to determine how much segmentation would be “just right.” To do that, they used three degrees of partial segmentation, investigating how a variable-sized non-lesion border around the segmented skin lesion affects classification results. They performed comparisons in a systematic and reproducible manner to demonstrate empirically that a certain amount of segmentation border around the lesion could improve classification performance.

Their findings suggest that extending the border beyond the lesion to include a limited amount of background pixels improves their classifier’s ability to distinguish melanoma from a benign skin lesion.

“Our experimental results suggest that there appears to be a ‘sweet spot’ in the degree to which the surrounding skin included is neither too great nor too small and provides a ‘just right’ amount of context,” said Marques.

Their method showed an improvement across all relevant measures of performance for a skin lesion classifier.

Source:

http://www.fau.edu/newsdesk/articles/melanoma-diagnosis.php

Tagged with:

About author

Related Articles