Friday December 6, 2019

Artificial Intelligence offers Quick Approach to Thyroid Cancer Screening: Study

The overall accuracy of the algorithm was 77.4 per cent

0
//
artificial intelligence, nobel prize
"Artificial intelligence is now one of the fastest-growing areas in all of science and one of the most talked-about topics in society." VOA

Using Artificial Intelligence (AI) with thyroid ultrasound offers a quick and non-invasive approach to thyroid cancer screening, says a new study.

The study, published in the journal PLOS Pathogens, suggests that automated machine learning shows promise as an additional diagnostic tool that could improve the efficiency of thyroid cancer diagnosis.

“Machine learning is a low-cost and efficient tool that could help physicians arrive at a quicker decision as to how to approach an indeterminate nodule,” said the study’s lead author John Eisenbrey from Thomas Jefferson University in the US.

According to the researchers, at present ultrasounds can tell if a nodule looks suspicious, and then the decision is made whether to do a needle biopsy, but fine-needle biopsies only act as a peephole, they don’t reveal the whole picture.

As a result, some biopsies return inconclusive results as to whether the nodule is malignant, or cancerous in other words.

In order to improve the predictive power of the first-line diagnostic, the ultrasound, researchers looked into machine learning or AI models developed by Google.

They applied a machine learning algorithm to ultrasound images of patients’ thyroid nodules to see if it could pick out distinguishing patterns.

The researchers trained the algorithm on images from 121 patients who underwent ultrasound-guided fine needle-biopsy with subsequent molecular testing.

Cancer
Cancer Ribbon. Pixabay

From 134 total lesions, 43 nodules were classified as high risk and 91 were classified as low risk, based on a panel of genes used in the molecular testing.

A preliminary set of images with known risk classifications was used to train the model or algorithm.

From this bank of labeled images, the algorithm utilised machine learning technology to pick out patterns associated with high and low risk nodules.

It used these patterns to form its own set of internal parameters that could be used to sort future sets of images; it essentially ‘trained’ itself on this new task.

Also Read: Smartphones, TV Sales Break Records in Diwali Season

Then the investigators tested the trained model on a different set of unlabeled images to see how closely it could classify high and low genetic risk nodules, compared to molecular tests results.

The researchers found that their algorithm performed with 97 per cent specificity and 90 per cent predictive positive value, meaning that 97 per cent of patients who truly have benign nodules will have their ultrasound read as ‘benign’ by the algorithm, and 90 per cent of malignant or ‘positive’ nodules are truly positive as classified by the algorithm.

The overall accuracy of the algorithm was 77.4 per cent. (IANS)

Next Story

US Chipmaker Intel Eyes AI on ‘Edge Computing’

It is designed to accelerate AI tasks, particularly ones like image processing, delivering performance up to six times the power efficiency of existing processors

0
Intel on Wednesday unveiled eight additional 10th Gen Intel Core processors for modern laptop computing.
Intel on Wednesday unveiled eight additional 10th Gen Intel Core processors for modern laptop computing. Pixabay

US chipmaker Intel Corp. has said that it will focus on “edge computing” that could hold the key to the success of artificial intelligence (AI) in the future.

Edge computing refers to the practice of storing data on computers located near cell towers and other network equipment to improve network response times. It is different from today’s Cloud-based system, where information is sent to a distant data centre, Yonhap news agency reported on Wednesday.

“Forty-three per cent of AI tasks will be handled by edge computing in 2023,” Kwon Myung-sook, CEO of Intel Korea, said in a statement during a forum in Seoul.

“AI devices empowered with edge function will jump 15-fold.”

The expansion of computing at the edge is an important growth opportunity for the chip giant — an estimated $65 billion market by 2023, Intel said.

Huawei, Atlas 900, World
The future of computing is a massive market worth more than two trillion US dollars. Pixabay

More AI is being incorporated into edge devices, from Internet of Things (IoT) devices to smartphones, as AI algorithms improve, according to the company.

“Innovation in edge computing has become necessary where data is most produced,” Kwon said. “It is why Intel is preparing a platform solution that can cover both hardware and software.”

Intel said AI will support and provide new services in eight key industries, including smart cities, robots and gaming.

Also Read: India Ranked 5th Worst Country For Use of Biometric Data: Comparitech Report

In order to do so, Intel said it will launch the next-generation Movidius Vision Processing Unit next year.

It is designed to accelerate AI tasks, particularly ones like image processing, delivering performance up to six times the power efficiency of existing processors. (IANS)