Saturday December 15, 2018

AI Outwits Doctors at Detecting Skin Cancer

It can be cured if detected early, but many cases are only diagnosed when the cancer is more advanced and harder to treat

0
//
Previous research has shown that obesity and high-fat diets both together and independently increase the risk of pancreatic cancer.
The actress was diagnosed with cancer earlier this year. Pixabay
Republish
Reprint

An Artificial Intelligence (AI) system has been found to detect skin cancer more accurately than a group of experienced dermatologists from 17 countries around the world, a study said on Tuesday.

In the experiment, the team of researchers from Germany, France and the US trained a form of AI or Machine Learning known as a deep learning convolutional neural network (CNN) to identify skin cancer by showing it more than 100,000 images of malignant melanomas — the most lethal form of skin cancer — as well as harmless moles.

When its performance was compared with that of 58 international dermatologists, the CNN missed fewer melanomas and misdiagnosed benign moles less often as malignant than the group of dermatologists, showed the findings published in the journal Annals of Oncology.

“The CNN works like the brain of a child. To train it, we showed the CNN more than 100,000 images of malignant and benign skin cancers and moles and indicated the diagnosis for each image,” said first author of the study Professor Holger Haenssle from the University of Heidelberg in Germany.

“Only dermoscopic images were used, that is lesions that were imaged at a 10-fold magnification. With each training image, the CNN improved its ability to differentiate between benign and malignant lesions,” Haenssle added.

Representational image (AI)
Representational image (AI). Pixabay

A CNN is an artificial neural network inspired by the biological processes at work when nerve cells (neurons) in the brain are connected to each other and respond to what the eye sees.

The CNN is capable of learning fast from images that it “sees” and teaching itself from what it has learned to improve its performance — a process known as Machine Learning.

“These findings show that deep learning convolutional neural networks are capable of out-performing dermatologists, including extensively trained experts, in the task of detecting melanomas,” Haenssle said.

The incidence of malignant melanoma is increasing, with an estimated 232,000 new cases worldwide and around 55,500 deaths from the disease each year.

Also Read: Satya Nadella: Robots Won’t Make People Jobless

It can be cured if detected early, but many cases are only diagnosed when the cancer is more advanced and harder to treat.

But despite the promising results from the experiment, the researchers do not envisage that the CNN would take over from dermatologists in diagnosing skin cancers, but that it could be used as an additional aid.

“This CNN may serve physicians involved in skin cancer screening as an aid in their decision whether to biopsy a lesion or not,” Haenssle said. (IANS)

Click here for reuse options!
Copyright 2018 NewsGram

Next Story

New AI Model by Google Can Help Detect Diabetic Retinopathy

For this purpose, it recently launched the "Google AI Impact Challenge"

0
Google
Google's new AI model to help detect diabetic retinopathy. Pixabay

Google has developed an Artificial Intelligence (AI) model that can detect diabetic retinopathy with a level of accuracy on par with human retinal specialists, the technology giant said.

Google is working on “rolling out this diabetic retinopathy initiative in clinics in India with Verily” — an Alphabet-owned company which works on life sciences research and development, Kent Walker, SVP of Global Affairs at Google, wrote in a blog post on Thursday.

More than 400 million people in the world have diabetes. A third of them have diabetic retinopathy — a complication that can cause permanent blindness.

“Using the new assistive technology, doctors and staff can screen more patients in less time, sparing people from blindness through a more timely diagnosis,” Walker said.

While the blindness can be prevented, diabetic retinopathy often goes undetected because people do not always get screenings.

“In major part, this is due to limited access to eye care specialists and staff capable of screening for the disease. This is a problem that AI can help us solve,” Walker said.

“Deploying this technology in underserved communities that don’t have enough eye specialists could be life-changing for many,” Walker added.

Diabetes
Representational image. Pixabay

Google began work on the model in collaboration with eye specialists in India and the US a few years back. They developed an AI system to help doctors analyse images of the back of the eye for signs of diabetic retinopathy.

“The results were promising,” Walker noted, while adding “we should work to make the benefits of AI available to everyone”.

Google has for several years applied AI research and engineering to projects in Asia Pacific with positive societal impact, including stopping illegal fishing in Indonesia, forecasting floods in India, and conserving native bird species in New Zealand, the blog post read.

Also Read- U.S.A: Myanmar’s Military Campaign Against Rohingya Muslims a ‘Mass Genocide’

Besides healthcare, the tech giant also wants to support more Asia Pacific organisations in using AI to help society by engaging with governments, non-profit organisations, universities and businesses.

For this purpose, it recently launched the “Google AI Impact Challenge”.

“Selected organisations who apply to the challenge will receive support from Google’s AI experts and Google.org grant funding from a $25 million pool,” Walker said. (IANS)