Nearly half of the cases of the most common cancer worldwide, lung cancer, are treated with radiation therapy (RT). RT planning is a time-consuming, resource-intensive process that can take days to weeks to complete, and even highly trained doctors disagree on how much tissue to target with radiation. 

Furthermore, as cancer rates rise, a global shortage of radiation-oncology practitioners and clinics is expected to worsen. Researchers working under the Artificial Intelligence in Medicine Program of Mass General Brigham, Brigham and Women’s Hospital and collaborators developed and validated a deep learning algorithm capable of identifying and outlining (“segment”) a non-small cell lung cancer (NSCLC) tumor on computed tomography (CT) scan in seconds. The study, published in the Lancet Digital Health, also indicates that radiation oncologists using the algorithm in simulated clinics performed 65 percent faster than physicians not using the algorithm while working. 

According to Raymond Mak, corresponding author and MD of Brigham’s Department of Radiation Oncology, the most significant translation gap in AI applications to medicine is the failure to investigate how AI can be used to improve human clinicians and vice versa. 

The research team is working on how to create human-AI partnerships and collaborations that result in better patient outcomes. The benefit of this approach for patients includes greater consistency in tumor segmentation and shorter treatment times. Clinicians will benefit from less mundane but difficult computer work, which will reduce burnout and allow them to spend more time with patients.

The researchers trained their model to distinguish tumors from other tissues using CT images from 787 patients. The algorithm’s performance was evaluated using scans from over 1,300 patients from increasingly large datasets. The algorithm’s development and validation required close collaboration between data scientists and radiation oncologists. After discovering that the algorithm was incorrectly segmenting CT scans with lymph nodes, to improve its performance, the researchers retrained the model with more of these scans.

Finally, the researchers had eight radiation oncologists perform segmentation tasks as well as rate and edit segmentations created by another expert physician or the algorithm (they were not told which). The performance of human-AI collaborations and human-produced (de novo) segmentations did not differ significantly. 

Intriguingly, when editing an AI-produced segmentation versus a manually produced one, physicians worked 65 percent faster and with 32 percent less variation, even though they had no idea which one they were editing. In this blinded study, they also rated the quality of AI-drawn segmentations higher than the quality of human expert-drawn segmentations. 

In the future, the researchers intend to combine this work with previously developed AI models that can determine “organs at risk” of receiving unwanted radiation during cancer treatment (such as the heart) and thus exclude them from radiotherapy. They are continuing to research how physicians interact with AI to ensure that AI partnerships benefit clinical practice rather than harm it. The researchers are working on a second, independent segmentation algorithm that will validate both human and AI-drawn segmentations.

According to Hugo Aerts, Ph.D., co-author from the Department of Radiation Oncology, this study presents a novel AI model evaluation strategy that emphasizes the significance of human-AI collaboration. This is especially important because in silico (computer-simulated) evaluations can produce results that differ from clinical assessments. The approach presented in the study to identify non-small cell lung cancer tumors has the potential to pave the way for clinical deployment.

Story Source: Reference Paper | Reference Article

Learn More:

Top Bioinformatics Books

Learn more to get deeper insights into the field of bioinformatics.

Top Free Online Bioinformatics Courses ↗

Freely available courses to learn each and every aspect of bioinformatics.

Latest Bioinformatics Breakthroughs

Stay updated with the latest discoveries in the field of bioinformatics.

 | Website

Dr. Tamanna Anwar is a Scientist and Co-founder of the Centre of Bioinformatics Research and Technology (CBIRT). She is a passionate bioinformatics scientist and a visionary entrepreneur. Dr. Tamanna has worked as a Young Scientist at Jawaharlal Nehru University, New Delhi. She has also worked as a Postdoctoral Fellow at the University of Saskatchewan, Canada. She has several scientific research publications in high-impact research journals. Her latest endeavor is the development of a platform that acts as a one-stop solution for all bioinformatics related information as well as developing a bioinformatics news portal to report cutting-edge bioinformatics breakthroughs.


Please enter your comment!
Please enter your name here