Connect with us

Hi, what are you looking for?

Life

Q&A: How AI can be a lifeline for overworked radiologists (Includes interview)

The number of medical images taken at hospitals has exploded, according to one study, from 1999 until 2010, the average CT exam increased from 82 images to 679, yet the number of radiologists has remained static. As a result, critical cases can often wait an hour or more until they are seen by a radiologist, and more than 97% of all medical images go without being analyzed.

To help address this and to aid the busy radiologist, artificial intelligence tools are filling the gap. In this rapidly emerging field, Israeli startup Aidoc is pioneering ways to improve medical image analysis.

To understand more, Digital Journal spoke with Aidoc CEO Elad Walach.

Digital Journal: What are the main demands facing radiologists?

Elad Walach: The biggest demand for radiologists is the massive increase in the amount of imaging performed on patients. Advanced imaging techniques like CT and MRI were once used only for the most serious of cases but they are now routine diagnostic tools. They also take more images per patient: In 1999, an average patient CT contained 82 images; by 2010, the number had increased to 679 per patient! Radiologists are faced with an ever-increasing workload as medical imaging becomes cheaper, more accessible and more advanced.

DJ: Do these demands result in errors?

Walach: Radiologists are tremendously talented physicians but obviously, if they have less time to spend on each patient and each image, there is an impact. That impact has been offset by the improvements in imaging tech itself. Patient outcomes are still improving because radiologists see both more images and higher-quality images. But the overload means that some images are never even looked at, and sometimes a doctor can spend only a couple of seconds per image.

DJ: How has radiology been affected by digital transformation?

Walach: Radiology was early to undergo digital transformation. Instead of old-fashioned X-Ray transparencies, most hospitals in advanced countries use picture archiving and communication systems (PACS) that digitize the whole process from image capture, storage and retrieval. PACS work for X-Rays, CTs and MRIs and use standards file formats. This actually makes it an excellent discipline for integrating Machine Learning because the data and infrastructure are already digital.

DJ: How is machine learning shaping radiology?

Walach: Machine Learning is helping radiologists in a few different ways. First, ML can help identify, flag and triage abnormalities in scans, adding an AI ‘second reader’ that helps radiologists confirm their work. In some cases, a computer-vision deep learning solution can detect abnormalities that may not be obvious to the human eye.

ML is also being used in radiology reports. Natural Language Processing is analyzing reports written by radiologists and understanding what they mean, enabling advanced data processing.

Avatar photo
Written By

Dr. Tim Sandle is Digital Journal's Editor-at-Large for science news. Tim specializes in science, technology, environmental, business, and health journalism. He is additionally a practising microbiologist; and an author. He is also interested in history, politics and current affairs.

You may also like:

Social Media

Wanna buy some ignorance? You’re in luck.

Tech & Science

Under new legislation that passed the House of Representatives last week, TikTok could be banned in the United States.

Life

Platforms like Instagram and Pinterest often suggest travel destinations based on your likes and viewing habits.

Social Media

From vampires and wendigos to killer asteroids, TikTok users are pumping out outlandish end-of-the-world conspiracy theories.