Breaking News
August 14, 2018 - American Heart Association Urges Screen Time Limits for Youth
August 14, 2018 - Brief interventions during routine care reduce alcohol use among men with HIV
August 14, 2018 - New genome analysis could identify people at higher risk of common deadly diseases
August 14, 2018 - NIH grant for Mount Sinai to study use of inhaled corticosteroids for treatment of sickle cell disease
August 14, 2018 - Daicel supplies free nanodiamond samples to international researchers
August 14, 2018 - Switching anti-psychotic drugs in first-episode schizophrenia patients does not improve clinical outcomes
August 14, 2018 - Study to examine whether modulating gut bacteria can improve cardiac function in heart failure patients
August 14, 2018 - One out of two children not getting enough nutrients needed for their health
August 14, 2018 - Mono-antiplatelet therapy after aortic heart valve replacements may work as well as two drugs
August 14, 2018 - Aid-in-dying patient chooses his last day
August 14, 2018 - Exercise Really Can Chase Away the Blues, to a Point
August 14, 2018 - Surgical mesh implants may cause autoimmune disorders
August 14, 2018 - Researchers develop revolutionary zebrafish model to gain more insight into bone diseases
August 14, 2018 - Researchers discover secret communication hotline between breast cancers and normal cells
August 14, 2018 - Study examines how a person adapts to visual field loss after stroke
August 14, 2018 - Researchers show how specialized nucleic acid-based nanostructures could help target cancer cells
August 14, 2018 - Reducing opioid prescriptions for one operation can also spill over to other procedures
August 14, 2018 - E-cigarettes not so safe but still better than cigarettes
August 14, 2018 - Researchers find link between common ‘harmless’ virus and cardiovascular damage
August 14, 2018 - Initiation of PIMs associated with higher risk of fracture-specific hospitalizations and mortality
August 14, 2018 - Genetically modified mosquitoes and special bed nets help tackle deadly diseases
August 14, 2018 - Advances in treating hep C lead to new option for transplant patients
August 14, 2018 - Study finds quality of doctor-patient discussions about lung cancer screening to be ‘poor’
August 14, 2018 - MSU researchers uncover the effects of aging on regenerative ability of kidneys
August 14, 2018 - Better conditioning, throwing mechanics can help reduce elbow injuries in young baseball pitchers
August 14, 2018 - Brain game doesn’t offer brain gain
August 14, 2018 - Reproductive choices facing women with disabilities require careful consideration
August 14, 2018 - Scientists pinpoint the cause of a rare childhood seizure disorder
August 14, 2018 - Lumpectomy plus radiation associated with reduced risk of breast cancer death, study finds
August 14, 2018 - UAB study shows how ion channel differentiates newborn and mature neurons in the brain
August 14, 2018 - Experts highlight key knowledge gaps that need to be addressed in Ebola vaccine research
August 14, 2018 - Discovery could lead to new drugs against infection and inflammation
August 14, 2018 - Infection Prevention Differs Between Small, Large Hospitals
August 14, 2018 - Mom still matters—In study, young adults tended to prioritize parents over friends
August 14, 2018 - Deep brain stimulation might benefit those with severe alcoholism, preliminary studies show
August 14, 2018 - Study finds increased rate of repeat pregnancies in women with intellectual and developmental disabilities
August 14, 2018 - Lighter sedation fails to reduce risk of postoperative delirium in older patients
August 13, 2018 - Asking better questions about person’s memory could improve doctors’ understanding of patients
August 13, 2018 - U.S. Trauma Doctors Push for Stricter Gun Controls
August 13, 2018 - Asthma and flu: a double whammy
August 13, 2018 - 5 Questions: Donna Zulman on engaging high-need patients in intensive outpatient programs | News Center
August 13, 2018 - Behavioral Nudges Lead to Drop in Prescriptions of Potent Antipsychotic
August 13, 2018 - Potential New Class of Drugs May Reduce Cardiovascular Risk by Targeting Gut Microbes
August 13, 2018 - How to get your kids to eat better
August 13, 2018 - The importance of hearing your patients
August 13, 2018 - Transmission of F. tularensis unlikely to happen through the food chain
August 13, 2018 - Researchers discover epigenetic mechanism underlying ischemic cardiomyopathy
August 13, 2018 - Adolescent health programs receive only a tiny share of international aid, finds research
August 13, 2018 - Fracture risk increases by 30% after gastric bypass, study shows
August 13, 2018 - Quality-improvement project to standardize feeding practices helps micro preemies gain weight
August 13, 2018 - Long-term cannabinoid exposure impairs memory, study shows
August 13, 2018 - New intervention to reduce risk of HIV in young transgender women
August 13, 2018 - Japan human trial tests iPS cell treatment for Parkinson’s
August 13, 2018 - Altered nitrogen metabolism may contribute to emergence of new cancer mutations
August 13, 2018 - Cycling provides greatest health benefits, study finds
August 13, 2018 - Scientists discover biomarker for kidney cancer
August 13, 2018 - New test predicts the risk of serious disease before symptoms appear
August 13, 2018 - Cianna Medical receives FDA 510(k) clearance to extend indication of SCOUT reflector for use in soft tissue localization
August 13, 2018 - Ground-breaking discovery offers new hope for treatment of Alzheimer’s, other neurological diseases
August 13, 2018 - Medical nutrition therapy provided by RDNs benefits patients with chronic kidney disease
August 13, 2018 - Prenatal Tdap vaccination not linked with increased risk of autism in children, study shows
August 13, 2018 - One-Third of Canadian Patients Get Hip Fx Repair Within 24 Hours
August 13, 2018 - ANA (Antinuclear Antibody) Test: MedlinePlus Lab Test Information
August 13, 2018 - Traffic jams in the brain
August 13, 2018 - NIH awards $6.5 million to establish multi-institution biomedical technology resource center
August 13, 2018 - New marker in the blood could help predict person’s risk of developing kidney cancer
August 13, 2018 - New biomarker may provide clues to create diagnostic tool for hypoglycemia-associated autonomic failure
August 13, 2018 - Oxidative Stress Hampers Blood Vessel Dilation in Men
August 13, 2018 - Parents’ Religious Beliefs May Affect Kids’ Suicide Risk: Study
August 13, 2018 - Measure of belly fat in older adults is linked with cognitive impairment
August 13, 2018 - FDA permits marketing of first mobile medical app for contraceptive use to prevent pregnancy
August 13, 2018 - NUS scientists develop new technology to customize optimal drug ‘cocktail’ for myeloma patients
August 13, 2018 - Disordered eating behaviors up for overweight young adults
August 13, 2018 - Connection between Alzheimer’s disease and degenerative eye diseases
August 13, 2018 - Employer expectation of checking email during nonwork hours affects health of workers and families
August 13, 2018 - Rotavirus vaccination reduces infant diarrhea deaths by 34% in rural Malawi
August 13, 2018 - Approval of drug derived from cannabis not necessarily a win for weed
August 13, 2018 - Study shows COPD risk in women with asthma can be reduced
August 13, 2018 - FIND and genedrive announce study agreement to evaluate HCV ID Kit
August 13, 2018 - One in two people putting their eye health at risk during summer, says eye research charity
The Artificial Brain as Doctor

The Artificial Brain as Doctor

image_pdfDownload PDFimage_print

Computers are learning to distinguish whether skin lesion images are benign or malignant and require further treatment. It appears they are on par with, if not more accurate than, many dermatologists, a study shows.

Stanford University researchers compared a computer-driven deep neural network with dermatologists’ ability to visually classify possible melanoma and basal cell or squamous cell carcinoma lesions.

“We recruited 21 board-certified dermatologists and showed them 300 images, where they had to classify the lesions as benign or malignant, and whether they would biopsy or reassure the patient,” said the study’s lead author, Roberto A. Novoa, MD, of Stanford University in California. “From there, the algorithm performed about as well as the dermatologists, if not better. There were dermatologists who did perform better than the algorithm but, in general, this was a proof of concept study, so … we were demonstrating the efficacy of these algorithms for making the diagnosis.”

Computers That Think Like Humans

Deep neural networks are a type of computer algorithm within the field of artificial intelligence, which uses computers to mimic brain function, including reasoning.

While it might sound like a new concept, it’s not. Researchers reported on the potential for computers to diagnose facial tumors in 1986.

“The idea for neural networks has been around since the 1960s,” Novoa said. “But it was only in the last 5 years that the computing power and technological capabilities caught up to the math.”

Today’s neural networks take in vast amounts of information. They then learn the rules that lie behind the data to derive patterns and, eventually, correct answers, Novoa explained.

“Essentially, deep neural networks are mathematical equations that are stacked in layers. They start at the most basic level by learning the edges of all the objects in an image. Then, they move on to telling you this is a triangle or a square. The next layer might indicate whether an image is a cat or a dog. Finally, there’s a layer that says this is a Belgian Malinois or a German Shepherd … If it gets the answer wrong, it goes back through the equation and changes the values and weights of that equation until it gets the most answers correct for the most number of images. By doing so, it learns, over time, what’s important and what’s not.”

From Dogs to Skin Cancer

The genesis of the research, published in Nature last year, began 3 years ago, when Novoa said he saw the advances in the field of deep learning, where these computer programs could differentiate on their own between Belgian Shepherds and German Shepherds.

“I thought if we can do this for dogs, we can do this for skin cancer,” he said.

Novoa and his colleagues at Stanford gathered a dataset of nearly 130,000 images from the internet, including open source images and images from Stanford databases. The researchers went through the data and created a visual taxonomy for the more than 2,000 disease categories, whittling those down to 10 different general categories. The team then used the dataset in the deep neural network’s classifier.

The researchers measured the algorithm’s performance by creating a sensitivity-specificity curve. Sensitivity represented the algorithm’s ability to correctly identify malignant lesions, and specificity represented its ability to accurately identify benign lesions. Assessing the algorithm through the diagnostic tasks of keratinocyte carcinoma classification, melanoma classification, and melanoma classification when viewed using dermoscopy, the researchers found that the algorithm matched the dermatologists’ performance in all three tasks, with the area under the sensitivity-specificity curve amounting to at least 91% of the total area of the graph, according to a Stanford news release.

The deep neural network, in this case, had been trained to classify skin cancer, but the study was done on images of skin cancer that the network had not yet seen. “If you test it on images it has already seen, it already knows the answer,” Novoa said.

The images in the study already had biopsy-proven results. This allowed the researchers to know the true answers when testing the deep neural network and dermatologists.

The next step is to test the algorithm in the real world, Novoa said. “We’re currently putting together a clinical trial to see how well it will perform in the real world. We want to see how well it performs with real patients, with a smartphone camera and a variety of lighting.”

There have been other studies using artificial intelligence and deep neural networks to diagnose melanoma, but this one is different in a few ways, Novoa explained. “Most of the other studies were performed using dermoscopic images. Dermoscopy kind of limits the number of variables. It’s always taken from the same distance and with pretty similar lighting.

“This was looking at clinical images, but they were from a variety of different distances and angles. This also was looking at melanoma, squamous cell carcinoma, and basal cell carcinomas. So, there was a wider group of images. We used a pretty large dataset — it’s among the larger datasets we’ve seen to date.”

Implications

The basic idea of neural networks is that they do pattern recognition, just as a dermatologist would learn patterns and visual data, Novoa said.

Deep neural networks and artificial intelligence may have a growing role in dermatology to help dermatologists provide better care, but not to replace the need for human expertise. While the computer algorithms might be used to triage or screen patients, ultimately a healthcare professional will take responsibility (and liability) for the care.

Algorithms, though, still need improvement.

“If there are biases in the dataset, these can be introduced into the algorithm results,” he continued. “So, for a long time there is going to be a need for supervision of these results in order to have things work optimally. For example, if the algorithm has a ruler in the image, it’s more likely to call it cancer. Why? Because on average, images in our dataset that have rulers are more likely to be malignant. That’s just a small example of the kinds of biases that can be introduced into the data.”

The near future of the technology has far-reaching implications, including the potential development of such things as a smartphone-compatible algorithm, where consumers could capture a lesion in an image and the phone would screen it for skin cancer probability.

“Technology has been changing medicine and all of human endeavors for hundreds of years, but it hasn’t eliminated the need for doctors,” Novoa said. “I don’t think we’re going anywhere. I think dermatologists will be able to adapt and take advantage of these technologies to take care of patients.”

This article originally appeared on the website of our partner Dermatology Times, which is a part of UBM Medica. (Free registration is required.)

2018-01-15T13:00:00-0500

Tagged with:

About author

Related Articles