Early diagnosis of lung cancer is pivotal to effective treatment because this disease is very challenging to treat. Advances in AI are transforming the screening for this disease, improving both efficiency and accuracy. Existing screening methods such as low-dose CT have several challenges. These include high rates of false-positives and a high variability when reporting other incidental but critical information, such as findings on cardiovascular diseases.
Furthermore, the shortage of radiologists around the world means that less than 10% of people who need low-dose CT scans can actually undergo them.
New research published in the journal Nature Communications shows that a new multimodal foundation model can perform multiple tasks and enhance low-dose CT scan capabilities. This model boosts the accuracy of using low-dose CT scans to predict the risk of lung cancer by 20% and improves cardiovascular disease risk prediction accuracy by 10%.
An interdisciplinary combination of experts from various institutions collaborated in the research that led to the development of this system. The experts were from RPI (Rensselaer Polytechnic Institute), WFU (Wake Forest University) and MGH (Massachusetts General Hospital). This first-in-class model performs more than 12 related tasks at the same time. It leverages data obtained from various sources like CT scans, major clinical findings, radiology reports and the risk factors of patients.
This study has huge potential to impact clinical outcomes. Because it uses text information and CT scan images, it elevates the prediction and detection rates for lung cancer. Accurate prediction and detection of this disease plays a key role in improving the outcomes for patients. Another advantage of leveraging foundation models in the medical field is that these models can be further trained using CT scans used to screen for multiple conditions and this data can further enhance the ability of that model to be useful in related fields like oncology.
Prof. Ge Wang, one of the corresponding authors of this research, revealed that a key enabler of their study was the top-notch computing facility at RPI. He emphasized that their work illustrates the value of the synergy between medical research and AI. This synergy is likely to revolutionize the detection and treatment of diseases, he added.
These strides that are being made in how diseases like lung cancer are detected and the prediction of their likelihood to develop come at a time when many companies like Calidi Biotherapeutics Inc. (NYSE American: CLDI) are also making progress in developing new treatments targeting lung cancer. These developments on the detection front and treatment development front give hope that the treatment of diseases will improve significantly over the coming years.
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 70+ 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
