Breaking News
February 17, 2018 - ‘A Time Clock to a Tissue Clock’ for Acute Stroke Care
February 17, 2018 - Cancer Care Gets Personal | NIH News in Health
February 17, 2018 - Do more youth use or do youth use more?
February 17, 2018 - Eating faster linked to obesity
February 17, 2018 - Who’s Still Smoking? ACS Report Highlights Most Vulnerable Adults
February 17, 2018 - Study of smoking and genetics illuminates complexities of blood pressure
February 17, 2018 - Study reveals new link between bone cells and blood glucose level
February 17, 2018 - Children with reading challenges may have lower than expected binocular vision test results
February 17, 2018 - Mass Shootings Trigger Change for Emergency Medicine
February 17, 2018 - ECMO helps revive woman thought to be drowned
February 17, 2018 - Learning stress-reducing techniques may benefit people with epilepsy
February 17, 2018 - Shedding Pounds Before Weight-Loss Surgery a Smart Move
February 17, 2018 - FDA Approves New Cystic Fibrosis Drug Combo
February 17, 2018 - Augmented Reality helps surgeons to ‘see through’ tissue and reconnect blood vessels
February 17, 2018 - Emotional state affects operation of the entire brain instead of being restricted to specific regions
February 17, 2018 - Apalutamide Slows Metastasis in Prostate Cancer
February 17, 2018 - Kids’ well visits linked to lower appendicitis complications
February 17, 2018 - New NK cell-based immunotherapy effective against several types of leukemia
February 17, 2018 - Producing Super-Swelled Lyotropic Crystals for Drug Development
February 17, 2018 - Pfizer Receives Breakthrough Therapy Designation from FDA for PF-04965842, an oral JAK1 Inhibitor, for the Treatment of Patients with Moderate-to-Severe Atopic Dermatitis
February 17, 2018 - Molecular Imaging Flags Risk of AAA Rupture
February 17, 2018 - Researchers identify risk factors for sleep apnea during pregnancy
February 17, 2018 - More work required to find the right drug dosage for pediatric patients
February 17, 2018 - Factors ID’d That Predict RA Remission with Etanercept
February 17, 2018 - A handout or a hand up? How we judge others guides how we help others
February 17, 2018 - ACR receives grant to focus on projects that reduce health disparities
February 17, 2018 - Pimavanserin Might Be Safer Alternative to Ease Dementia Psychosis
February 17, 2018 - Risks of Lung Screening Seen Outweighing Benefits in Many with Smoking History
February 17, 2018 - The impact of Hurricane Harvey on pregnant moms
February 17, 2018 - Gene editing tool used to detect cancer
February 17, 2018 - Researchers detail molecular atlas of cells that form brain’s blood vessels
February 17, 2018 - TUM scientists observe formation of myelin sheaths around nerve fibers
February 17, 2018 - Worst Flu Season Yet? | Medpage Today
February 17, 2018 - Finding the root cause of bronchiolitis symptoms
February 17, 2018 - Climbing stairs reduces hypertension and strengthens muscles
February 17, 2018 - Nature paper unveils bacterial division
February 16, 2018 - Postoperative pain control following extensive pelvic exenteration
February 16, 2018 - Daré Bioscience, Inc. Enters into License and Collaboration Agreement for a Product with the Potential to Receive the First FDA Approval for Female Sexual Arousal Disorder
February 16, 2018 - Havana Embassy Staff: ‘Concussion Without Concussion’?
February 16, 2018 - Family impact of congenital Zika syndrome likely to last a lifetime
February 16, 2018 - STI Prevention Helped By Also Discussing Pot, Alcohol Use
February 16, 2018 - New method maps the dopamine system in Parkinson’s patients
February 16, 2018 - Monitoring the Environment of Aseptic Processes
February 16, 2018 - Study finds decline in number of clinical trials funded by NIH
February 16, 2018 - Scientists show connection between sugar chains and bone growth
February 16, 2018 - Researchers develop new method for producing personalized medicine
February 16, 2018 - Women exposed to cleaning products suffer decreased lung function, Study finds
February 16, 2018 - Stem cell vaccine helps protect mice against numerous cancers
February 16, 2018 - Does Your Valentine Have a Roving Eye? Watch Out
February 16, 2018 - All Your MIPS Questions Answered — Sort Of
February 16, 2018 - Mitochondria may protect brain against Parkinson’s
February 16, 2018 - Key proteins could help in controlling the risk of osteoarthritis during aging, Study finds
February 16, 2018 - New review examines effectiveness of cupping therapy in athletes
February 16, 2018 - Resolving Interfacial Protein Dynamics by STReM
February 16, 2018 - Study provides new insights on why healthy children die from flu
February 16, 2018 - Self-sampling followed by HPV testing can benefit women at risk of cervical cancer
February 16, 2018 - Biomedical engineers grow living windpipe structures from self-assembled modules
February 16, 2018 - New device could allow people with disabilities to live more independently, enhance their quality of life
February 16, 2018 - Research identifies gene variants that play key role in how ovarian cancer patients process chemotherapy
February 16, 2018 - iMedicalApps: OB Wheels App Review
February 16, 2018 - To improve self-control, call weight loss what it is: Difficult
February 16, 2018 - Cervical tumors may be vulnerable to therapies that attack cancer’s fuel supply, study shows
February 16, 2018 - Allergan Announces Positive Top Line Phase 3 Results for Ubrogepant – an Oral CGRP Receptor Antagonist for the Acute Treatment of Migraine
February 16, 2018 - Morning Break: Hello Not-So-Fresh; One Eye, 14 Worms; Foreign Accent Syndrome
February 16, 2018 - New medical advances marking the end of a long reign for ‘diet wizards’
February 16, 2018 - Researchers study how unexpected event makes people to stop an action
February 16, 2018 - Women using short-acting asthma relievers take longer to become pregnant, study shows
February 16, 2018 - Fathers maybe passing on ovarian cancer genes to their daughters
February 16, 2018 - Phonak expands its latest-generation Belong platform with Phonak Naída B, Phonak Sky B hearing aids
February 16, 2018 - FDA Approves Erleada (apalutamide) for Non-Metastatic Castration-Resistant Prostate Cancer
February 16, 2018 - Traces of caffeine and its byproducts in the blood can be indicative of Parkinson’s disease
February 16, 2018 - More Help Needed With Opioid Crisis, Senators Told
February 16, 2018 - Are women really under-represented in clinical trials?
February 16, 2018 - US-based clinical study highlights safety and effectiveness of MENTOR MemoryShape Gel Breast Implants
February 16, 2018 - Higher levels of lifestyle physical activity linked to more gray matter in older adults’ brains
February 16, 2018 - Pfizer to use BC Platforms’ technology solutions to analyze data in cardiovascular diseases
February 16, 2018 - Researchers find shortcomings in pregnancy and prenatal care for women with diabetes
February 16, 2018 - Study could lead to new therapies to improve movement control in stroke survivors
February 16, 2018 - Do Common Household Chemicals Affect Your Weight?
February 16, 2018 - Binocular Video Game Tx Disappoints in ‘Lazy Eye’ Trial
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