Friday March 22, 2019
Home Lead Story AI More Effic...

AI More Efficient in Detecting Skin Cancer Than Doctors, Finds Study

On average, flesh and blood dermatologists accurately detected 86.6 percent of skin cancers from the images, compared to 95 percent for the CNN.

0
//
A team from Germany, the United States and France taught an artificial intelligence system to distinguish dangerous skin lesions from benign ones, showing it more than 100,000 images.
There are about 232,000 new cases of melanoma, and 55,500 deaths, in the world each year, the research added.

A computer was better than human dermatologists at detecting skin cancer in a study that pitted human against machine in the quest for better, faster diagnostics, researchers said Tuesday.

A team from Germany, the United States and France taught an artificial intelligence system to distinguish dangerous skin lesions from benign ones, showing it more than 100,000 images.

The machine — a deep learning convolutional neural network or CNN — was then tested against 58 dermatologists from 17 countries, shown photos of malignant melanomas and benign moles.

Just over half the dermatologists were at “expert” level with more than five years of experience, 19 percent had between two and five years’ experience, and 29 percent were beginners with less than two years under their belt.

“Most dermatologists were outperformed by the CNN,” the research team wrote in a paper published in the journal Annals of Oncology.

On average, flesh and blood dermatologists accurately detected 86.6 percent of skin cancers from the images, compared to 95 percent for the CNN.

“The CNN missed fewer melanomas, meaning it had a higher sensitivity than the dermatologists,” the study’s first author Holger Haenssle of the University of Heidelberg said in a statement.

A team from Germany, the United States and France taught an artificial intelligence system to distinguish dangerous skin lesions from benign ones, showing it more than 100,000 images.
On average, flesh and blood dermatologists accurately detected 86.6 percent of skin cancers from the images, compared to 95 percent for the CNN. Pixabay

It also “misdiagnosed fewer benign moles as malignant melanoma… this would result in less unnecessary surgery.”

The dermatologists’ performance improved when they were given more information of the patients and their skin lesions.

The team said AI may be a useful tool for faster, easier diagnosis of skin cancer, allowing surgical removal before it spreads.

There are about 232,000 new cases of melanoma, and 55,500 deaths, in the world each year, they added.

Healthy Sleep and Depression: Healthy Sleep Key to Ward off Depression Later

But it is unlikely that a machine will take over from human doctors entirely, rather functioning as an aid.

Melanoma in some parts of the body, such as the fingers, toes and scalp, are difficult to image, and AI may have difficulty recognizing “atypical” lesions or ones that patients themselves are unaware of.

“Currently, there is no substitute for a thorough clinical examination,” experts Victoria Mar from Monash University in Melbourne and Peter Soyer of the University of Queensland wrote in an editorial published with the study. (VOA)

 

Next Story

Researchers Discover Balance of Two Enzymes That May Help Treat Pancreatic Cancer

While still in the earliest stages, Newton hoped this information might one day aid pancreatic diagnostics and treatment

0
Cancer
Cancer Ribbon. Pixabay

A new research has set the stage for clinicians to potentially use levels of a pancreatic cancer patient’s PHLPP1 and PKC enzymes as a prognostic and for researchers to develop new therapeutic drugs that change the balance of the two enzymes as a means to treat the disease.

The study, published on Wednesday in Molecular Cell, was led by Alexandra Newton, professor in the Department of Pharmacology at the University of California, San Diego, School of Medicine, and Timothy Baffi, a graduate student in her lab, Xinhua news agency reported.

The new study built on the team’s work in 2015 that found the enzyme PKC, which was believed in previous studies to promote tumour growth, actually suppressed it.

The latest study took the investigation a step further by uncovering how cells regulate PKC activity and discovered that any time an over-active PKC is inadvertently produced, the PHLPP1 “proofreader” tags it for destruction.

Cancer patient
Cancer patient.

“That means the amount of PHLPP1 in your cells determines your amount of PKC,” Newton said. “And it turns out those enzyme levels are especially important in pancreatic cancer.”

The team observed 105 pancreatic cancer tumours to analyze the enzyme levels in each one. About 50 per cent of patients with low PHLPP1/high PKC lived longer than five-and-a-half years.

Also Read- A Brain Circuit Can Help Reverse Craving for Liquor, Says Study

While still in the earliest stages, Newton hoped this information might one day aid pancreatic diagnostics and treatment.

Pancreatic cancer is caused by the abnormal and uncontrolled growth of cells in the pancreas, a large gland in the digestive system. It typically doesn’t show symptoms in the early stages. Sufferers tend to develop signs, such as back pain and jaundice, when it has spread to other organs. (IANS)