Breaking News
August 16, 2018 - Childhood exposure to secondhand smoke increases risk of COPD death in adulthood
August 16, 2018 - Scientists uncover key control mechanism of DNA replication
August 16, 2018 - NIH begins first-in-human trial of experimental live, attenuated Zika virus vaccine
August 16, 2018 - Two diabetes medications don’t slow progression of type 2 diabetes in youth
August 16, 2018 - 5 Questions: How Stanford research is making MRI scans safer for kids | News Center
August 16, 2018 - Columbia Celebrates 25th Anniversary of White Coat Ceremony
August 16, 2018 - Phonak’s new smallest and most discreet Virto B-Titanium hearing aid
August 16, 2018 - New project aims to study growth of water-based microorganisms
August 16, 2018 - New research confirms link between DDT exposure and autism
August 16, 2018 - Neurodevelopmental Anomalies, Birth Defects Linked to Zika ID’d
August 16, 2018 - Risk of heart failure up in ALVSD patients with diabetes
August 16, 2018 - Exercise reduces symptoms and fatigue in patients with chronic kidney disease
August 16, 2018 - Study reveals role of RUNX proteins in DNA repair
August 16, 2018 - New research finds no harm from average salt consumption
August 16, 2018 - Researchers develop new way of testing bacterial resistance to antibiotics
August 16, 2018 - Magnetic gene in aquarium fish could open doors to treatment for epilepsy, Parkinson’s
August 16, 2018 - Five tips for successful long-term breastfeeding
August 16, 2018 - Researchers identify brain networks involved in object naming
August 16, 2018 - Promoting HPV Vaccine Doesn’t Prompt Risky Sex by Teens: Study
August 16, 2018 - Treating Rheumatoid Arthritis: Search for a Cure
August 16, 2018 - Research shows in the long run, charcoal toothpaste likely won’t whiten teeth
August 16, 2018 - Seattle Children’s opens new clinic to provide convenient access to pediatric specialty care services
August 16, 2018 - Curious case of the lost contact lens
August 16, 2018 - GN Hearing unveils world’s first Premium-Plus hearing aid
August 16, 2018 - Parental life span linked with increased longevity and health in daughters
August 16, 2018 - Health leaders reveal ten most important medicines in NHS history
August 16, 2018 - Mobile health devices diagnose hidden heart condition in at-risk populations
August 16, 2018 - When it comes to shedding pounds, it pays to think big
August 16, 2018 - Liva Healthcare announces appointment of Thomas Cooke as clinical services manager in the UK
August 16, 2018 - New digital pharmacy aims to help people living with chronic care conditions
August 16, 2018 - Preventing ACL injuries in high school athletes
August 16, 2018 - Experts provide insight into novel concepts and approaches for stroke rehabilitation
August 16, 2018 - Scientists reverse congenital blindness in mouse model
August 16, 2018 - Study shows link between use of benzodiazepines and increased risk of Alzheimer’s disease
August 16, 2018 - Study provides new insight into how ‘trash bag of the cell’ traps and seals off waste
August 16, 2018 - Trial shows PARP inhibitor as novel treatment option for patients with advanced breast cancers
August 16, 2018 - Prenatal exposure to violence increases toddlers’ aggressive behavior to their mothers
August 16, 2018 - Can manipulating gut microbes improve cardiac function in patients with heart failure?
August 16, 2018 - Hearts of newborn piglets can completely heal after heart attacks
August 16, 2018 - Ablating the mutant p53 gene in mice with colorectal cancer inhibits tumor growth
August 16, 2018 - Higher BMI in people with prediabetes related to evening preference and lack of sufficient sleep
August 16, 2018 - Using peripheral nerve blocks to treat facial pain may produce long-term pain relief
August 16, 2018 - Neural stem cells are the key to tail regeneration
August 16, 2018 - Study compares genetic and neural contributions to ADHD in children with or without TBI
August 16, 2018 - Adding energy drinks to alcohol may exacerbate negative effects of binge drinking
August 16, 2018 - Eye Examination Can Help Detect Abuse in Children
August 16, 2018 - Know the Difference: Rheumatoid Arthritis or Osteoarthritis?
August 16, 2018 - From ‘sea of mutations,’ two possible cancer links rise to the surface
August 16, 2018 - Does medical school take too long?
August 16, 2018 - Brown University researchers reveal key physical properties of ‘giant’ cancer cells
August 16, 2018 - Regular resistance training improves exercise motivation
August 16, 2018 - Feds urge states to encourage cheaper plans off the exchanges
August 16, 2018 - Seven activities that prevent you from getting quality sleep during summer
August 16, 2018 - Five ways to tell if your baby is getting enough milk from breastfeeding
August 16, 2018 - From Pigs to Peacocks, What’s Up With Those ‘Emotional-Support Animals’?
August 16, 2018 - Breast cancers enlist the help of normal cells to help them spread and survive
August 16, 2018 - Engaging with “high-need” patients outside the clinic
August 16, 2018 - Research illuminates how online forum may offer suicide prevention support for males
August 16, 2018 - Researchers identify way to grow immune cells at large scale for preventing cancer reoccurrence
August 15, 2018 - Keck Medicine of USC’s hospitals ranked among nation’s best for the 10th consecutive year
August 15, 2018 - Researchers compare existing approaches for automating diagnostic procedures of skin lesions
August 15, 2018 - Autism risk determined by health of mom’s gut, research reveals
August 15, 2018 - WELL for Life challenges you to explore the great outdoors
August 15, 2018 - ‘Zombie’ gene protects elephants from cancer, study finds
August 15, 2018 - Ebola outbreak in Congo spreads to active combat zone
August 15, 2018 - Study highlights pollution exposure of babies in prams
August 15, 2018 - Study provides insight into link between sleep apnea and lipid metabolism
August 15, 2018 - New study focuses on promise of gene therapy for Amish nemaline myopathy
August 15, 2018 - Researchers discover new approach to alleviate chronic itch
August 15, 2018 - Uncovering the Mysteries of MS: Medical Imaging Helps NIH Researchers Understand the Tricky Disease
August 15, 2018 - Autistic people at greater risk of becoming homeless – new research
August 15, 2018 - New imaging technique can spot tuberculosis infection in an hour
August 15, 2018 - Scientists study effects of eating breakfast versus fasting overnight before exercise
August 15, 2018 - Talking with children about suicide could save lives
August 15, 2018 - Grip strength of children predicts future cardiometabolic health
August 15, 2018 - New polyclonal immunotherapy successfully neutralizes Ebola virus
August 15, 2018 - Innovative oncofertility program launched by RMA of New York and Mount Sinai Health System
August 15, 2018 - Study shows efficacy, safety of AAV5-based gene therapy to treat sheep model of achromatopsia
August 15, 2018 - Simple score helps predict which hospitalized heart attack patients are at high risk of readmissions
August 15, 2018 - New discoveries show how protein droplets do more than keep cells’ interiors tidy
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