Breaking News
August 20, 2018 - Health Tip: Keep Diabetic Feet Healthier
August 20, 2018 - FDA approves brain stimulation device for OCD
August 20, 2018 - NYU Langone’s Perlmutter Cancer Center expands Blood and Marrow Transplant Program
August 20, 2018 - New drug shows potential to prevent painful side effect of therapy
August 20, 2018 - Illicit drug use is higher during celebratory events, may be worse than previously thought
August 20, 2018 - Exploring the relationship between fever and cancer incidence
August 20, 2018 - Study reveals how socioeconomic status affects racial, ethnic disparities in childhood cancer survival
August 20, 2018 - Brain tumors trap immune cells needed to fight cancer in the bone marrow, finds research
August 20, 2018 - Three factors that contribute to physician burnout
August 20, 2018 - Babies dependent on opioids need touch, not tech
August 20, 2018 - Understanding How Antibodies Shape the Gut Microbiome
August 20, 2018 - Cara Therapeutics Doses First Patient in Second Pivotal Phase 3 Efficacy Trial of Korsuva (CR845/difelikefalin) Injection in Hemodialysis Patients with Chronic Kidney Disease-Associated Pruritus
August 20, 2018 - Kidney transplant chains more effective in saving lives
August 20, 2018 - Study unravels cellular and molecular mechanisms behind dermal condensate formation
August 20, 2018 - New integrated gene logic-chips could have great value in medical care
August 20, 2018 - FDA Advisory Committee Recommends Approval of Paratek’s Omadacycline
August 20, 2018 - Total, open repairs decline for abdominal aortic aneurysms
August 20, 2018 - Novel system can pinpoint ingestible implants inside the body using wireless signals
August 20, 2018 - Infection rates of high risk oral HPV in England found to be lower than expected
August 20, 2018 - Making robots as valuable and trustworthy assistants for medical therapies
August 20, 2018 - Patients with low-risk blood clots can be better treated at home than at hospital
August 20, 2018 - Passive smoking exposure among kids greatly increases COPD risk late in life
August 20, 2018 - Primary Care Provider Burnout Rate Low in Small Practices
August 20, 2018 - Discovery presents treatment hope for Alzheimer’s and other neurodegenerative diseases
August 20, 2018 - Stroke patients appear to receive better care at teaching hospitals with less chance of readmission
August 20, 2018 - Distinct origin of ADHD identified In children with history of traumatic brain injury
August 20, 2018 - AHA: Wildfire Smoke Threatens Health of Those Near and Far
August 20, 2018 - Here’s a mental health workout that’s as simple as ABC
August 20, 2018 - Newly discovered cytoskeleton utilized by cancer cells for survival
August 19, 2018 - Bifidobacteria supplement colonizes gut of breastfed infants
August 19, 2018 - Why patients with Alzheimer’s markers never develop the condition
August 19, 2018 - ACA’s Medicaid expansion associated with increase in prescriptions for opioid use disorder treatment
August 19, 2018 - Important factor may be missing in models used to predict spread of epidemics from climate change
August 19, 2018 - Indian-Americans have fewer sudden infant deaths, study finds
August 19, 2018 - Experts advise against universal genomic screening of newborns
August 19, 2018 - New trial to investigate whether weight loss before conception can make mom and baby healthier
August 19, 2018 - Sun Pharma Announces FDA Approval of Cequa (cyclosporine) Ophthalmic Solution to Treat Dry Eye Disease
August 19, 2018 - Researchers examining Parkinson’s resilience
August 19, 2018 - HPI, INTEGRIS and USPI enter into agreement to offer patients more choice, flexibility of care
August 19, 2018 - Researchers find mechanism that prepares brain to replicate repeated actions
August 19, 2018 - Those who are emotionally stable when young may remain the most stable as they age
August 19, 2018 - URI professor develops simpler and quicker method for detecting impurity in heparin
August 19, 2018 - Mayo Medical Laboratories and NDSC collaborate to develop new patient blood-management solution
August 19, 2018 - Insight into endocrine cancers and treatment options
August 19, 2018 - HPV Legislation Doesn’t Impact Teen Sexual Behaviors
August 19, 2018 - Exenatide treatment alleviated symptoms of depression in patients
August 19, 2018 - Tufts researchers win grant to study integration of genomic sequencing into neonatal care
August 19, 2018 - Novel finger-prick test can help prevent toxoplasmosis
August 19, 2018 - Cosmetic Procedures Boost Well-Being, Poll Shows
August 19, 2018 - Responsive parenting intervention results in lower BMIs through age three
August 19, 2018 - Anticancer drugs can help plants to battle infection
August 19, 2018 - Sunscreen from bathers releases significant quantities of polluting titanium dioxide into the sea
August 19, 2018 - Case Western Reserve gets three-year grant to enhance food systems in Cleveland neighborhoods
August 19, 2018 - Teenagers can thank their parents’ positive attitude for avoiding obesity
August 19, 2018 - Body mass index positively linked with blood pressure
August 19, 2018 - New tool fills gap in Small Molecules market
August 19, 2018 - Study compares survival outcomes in rural and urban cancer patients enrolled in clinical trials
August 19, 2018 - Researchers develop molecular matrix that delivers healing stem cells to injured elderly muscles
August 19, 2018 - Teva and Regeneron Announce Positive Topline Phase 3 Fasinumab Results in Patients with Chronic Pain from Osteoarthritis of the Knee or Hip
August 19, 2018 - New study pinpoints ways to improve quality of food and nutrition research
August 19, 2018 - Ology Bioservices wins $8.4 million worth agreement to manufacture anti-Ebola monoclonal antibody
August 19, 2018 - New CRISPR technology may help eliminate mutated gene sequence
August 19, 2018 - “Zombie gene” protects elephants from cancer finds study
August 19, 2018 - Study explores how many American cities protect the rights of employed breastfeeding mothers
August 19, 2018 - FDA Approves Lenvima (lenvatinib) for First-line Treatment of Unresectable Hepatocellular Carcinoma (HCC)
August 19, 2018 - Pain: Considering Complementary Approaches (eBook)
August 19, 2018 - Autoimmune response drives vision loss in glaucoma
August 19, 2018 - Tandem Diabetes Care introduces t:slim X2 Insulin Pump with Basal-IQ Technology in the US
August 19, 2018 - Innovative platform developed to destroy cancer cells
August 19, 2018 - Lowering pH inside tumor cells can slow down spread of cancer
August 19, 2018 - Biomarker predicts kidney cancer risk years before diagnosis
August 19, 2018 - Consequences of healthcare-associated infections go beyond patients’ physical health
August 19, 2018 - New drug- free, nanotechnology-based method detects and treats oral plaque
August 19, 2018 - Integration of Opioid, Infectious Disease Treatment Needed
August 19, 2018 - How eye disorders may have influenced the work of famous painters
August 18, 2018 - Blood biomarker could help predict kidney cancer up to five years prior to diagnosis
August 18, 2018 - Dartmouth scientists create more sustainable feed for aquaculture
August 18, 2018 - Immigrants Not a Burden on U.S. Health Care: Study
August 18, 2018 - Women who eat fast food take longer to become pregnant
August 18, 2018 - Most YouTube videos on plastic surgery are misleading marketing campaigns
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