Wednesday November 21, 2018

This AI Tool May Accelerate Diagnosis Of Eye Diseases, Pneumonia

Besides eye diseases, the tool was able to differentiate between viral and bacterial childhood pneumonia with greater than 90 percent accuracy

0
//
ai
The researchers also used occlusion testing, which allowed them to show areas of greatest importance when reviewing the scan images. Pixabay
Republish
Reprint

A novel image-based diagnostic tool, developed using artificial intelligence (AI) and machine learning techniques, may potentially speed up diagnoses and treatment of patients with retinal diseases and pneumonia among children, researchers say.

The findings showed that the new tool uses big data and AI to not only recognize two of the most common retinal diseases — macular degeneration and diabetic macular edema — but also to rate their severity.

“Macular degeneration and diabetic macular edema are the two most common causes of irreversible blindness but are both very treatable if they are caught early,” said Kang Zhang, Professor at the University of California-San Diego.

ALSO READ: Is Your Child Avoiding Eye Contact? He May Be Anxious, Says New Study

“Deciding how and when to treat patients has historically been handled by a small community of specialists who require years of training and are concentrated mostly in urban areas.”

ai
It can also distinguish between bacterial and viral pneumonia in children based on chest x-ray images. IANS

“In contrast, our AI tool can be used anywhere in the world, especially in the rural areas. This is important in places like India, China, and Africa, where there are relatively fewer medical resources,” Zhang said.

For the study, published in the journal Cell, the team studied over 200,000 optical coherence tomography (OCT) images using a technique called transfer learning, where knowledge gained in solving one problem is stored by a computer and applied to different but related problems.

“Machine learning is often like a black box where we don’t know exactly what is happening,” Zhang said.

The researchers then compared the diagnoses from the computer with those from ophthalmologists who reviewed the scans.

ALSO READ: Chronic Diseases Raise Cancer and Mortality Risk

The results showed that the tool “could generate a decision on whether or not the patient should be referred for treatment within 30 seconds and with more than 95 percent accuracy”, Zhang said.

Besides eye diseases, the tool was able to differentiate between viral and bacterial childhood pneumonia with greater than 90 percent accuracy.

It can also discern between cancerous and non-cancerous lesions detected on scans, Zhang said. (IANS)

Click here for reuse options!
Copyright 2018 NewsGram

Next Story

MediaTek Introduces SoC With Enhanced AI-Engine

Helio P70 comes with a 4G LTE modem and 300MBit/s (megabit per second) of download performance

0
Mediatek
MediaTek launches Helio P70 SoC with enhanced AI engine. (IANS)

Mobile phone chipset maker MediaTek on Wednesday launched the Helio P70 system-on-chip (SoC) with enhanced Artificial Intelligence (AI) engine designed to power full-featured smartphones at affordable price points.

The Helio P70 chipset comes with CPU (central processing unit) and GPU (graphics processing unit) upgrades for more powerful AI processing, and also brings upgraded imaging and camera support, a gaming performance boost and advanced connectivity features, MediaTek said in a statement.

“With an enhanced AI engine that works seamlessly across the CPU and GPU, Helio P70 delivers much faster performance for AI applications and is still highly power efficient,” said TL Lee, General Manager of MediaTek’s Wireless Communication business unit.

“The introduction of Helio P70 continues MediaTek’s commitment to deliver high-end smartphone features and advanced technology for the mass market,” Lee said.

The introduction of the Helio P70 follows the launch of the Helio P60 earlier this year, and builds on its hallmark features to power the full-featured smartphones.

Built with Taiwan Semiconductor Manufacturing Company’s (TSM) 12nm FinFET technology, the Helio P70 features a multi-core APU operating at up to 525 MHz (megahertz) for fast and efficient edge-AI processing.

The enterprise solutions major has integrated SAP CoPilot with the "SAP S/4HANA" Cloud.
AI will contribute to the biggest workload in data centres by 2020. Pixabay

The chipset packs four Arm Cortex-A73 2.1 GHz (gigahertz) processors and four Arm Cortex-A53 2.0 GHz processors in an octa-core big.LITTLE configuration.

For an additional power boost, the chipset has an improved Arm Mali-G72 MP3 GPU operating at up to 900 MHz, which provides a 13 per cent performance improvement compared to the Helio P60, MediaTek said.

Helio P70’s enhanced AI engine delivers a 10 to 30 per cent AI processing boost compared to the Helio P60, the company added.

Also Read- Samsung Partners With NEC To Explore New 5G Business Opportunities

The chipset is built on MediaTek’s NeuroPilot platform, the company’s hardware and software ecosystem to support edge-AI.

NeuroPilot supports common AI frameworks, including TensorFlow, TF Lite, Caffe, Caffe2 and custom third party offerings.

Helio P70 comes with a 4G LTE modem and 300MBit/s (megabit per second) of download performance. (IANS)