New AI Tool Could Boost the Early Detection of Lung Cancer

Lung cancer is the leading cause of cancer-linked fatalities among men and women, and survival beyond five years post-diagnosis is minimal. This is largely because most cases are detected when they are already advanced. Scientists are therefore searching for ways to boost early detection so that treatment outcomes can improve and survival can increase. 

A new study seems to have found a way to use AI to improve the early detection of this disease. This tool could be especially helpful in flagging lung cancer when tumors are still small and are harder to detect using the existing diagnostic tools. 

These existing tools, such as CT scans, have low rates of early detection of lung cancer because tumors tend to be so small at this stage, the cancerous tissue often resembles normal tissues, and human error can lead to many misses of problem cases. The new AI system was developed to address these shortcomings and increase the likelihood of catching lung cancer early. 

The researchers behind this system sought to improve the accuracy of tests done to detect the disease early and minimize errors due to human interpretation of scans. The model relies on CT scans in a way that takes a critical look at the finer details of a scan while also keeping the bigger structural picture in mind in order to get a more accurate assessment of a given case. This approach is similar to the way in which clinicians currently conduct their assessment by analyzing details while also taking into consideration the broader context. 

To train the model, the team used scans of both diseased lungs and images from healthy lungs. The model was then programmed to tell the difference between healthy lung tissue, tissue with benign growths, and tissue with cancerous growths. 

While testing the AI system, an accuracy rate of 96% was attained. This performance was superior to current diagnosis methods and remained consistent for all the different tests it was subjected to. However, the dataset used was limited and there is a need to further test the system on larger populations made up of diverse subjects. 

The researchers plan to conduct the needed refining of the system and subject it to additional tests in real-time as people are screened for lung cancer. 

If it proves to be successful in those rigorous tests, the model could be rolled out for use in clinical settings to help clinicians identify lung cancer much earlier than has previously been possible. When the disease is caught early, survival beyond five years could improve from the current 10% rate among those diagnosed late to approximately 90% or more in patients who get an early diagnosis. 

Given that advances in the development of cutting-edge therapies like the use of oncolytic virus therapy championed by entities like Calidi Biotherapeutics Inc. (NYSE American: CLDI) are being made, the outlook for lung cancer treatment looks a lot better than it has been in recent decades. 

About BioMedWire

BioMedWire (“BMW”) is a specialized communications platform with a focus on the latest developments in the Biotechnology (BioTech), Biomedical Sciences (BioMed) and Life Sciences sectors. It is one of 75+ brands within the Dynamic Brand Portfolio @ IBN that delivers: (1) access to a vast network of wire solutions via InvestorWire to efficiently and effectively reach a myriad of target markets, demographics and diverse industries; (2) article and editorial syndication to 5,000+ outlets; (3) enhanced press release enhancement to ensure maximum impact; (4) social media distribution via IBN to millions of social media followers; and (5) a full array of tailored corporate communications solutions. With broad reach and a seasoned team of contributing journalists and writers, BMW is uniquely positioned to best serve private and public companies that want to reach a wide audience of investors, influencers, consumers, journalists and the general public. By cutting through the overload of information in today’s market, BMW brings its clients unparalleled recognition and brand awareness.

BMW is where breaking news, insightful content and actionable information converge.

To receive SMS alerts from BioMedWire, “Biotech” to 888-902-4192 (U.S. Mobile Phones Only)

For more information, please visit https://www.BioMedWire.com

Please see full terms of use and disclaimers on the BioMedWire website applicable to all content provided by BMW, wherever published or re-published: https://www.BioMedWire.com/Disclaimer

BioMedWire
San Francisco, CA
www.BioMedWire.com
415.949.5050 Office
Editor@BioMedWire.com

BioMedWire is powered by IBN