The Lung Cancer Channel is supported with funding from Johnson & Johnson (Gold) and Takeda (Gold).
VJOncology is an independent medical education platform. Supporters, including channel supporters, have no influence over the production of content. The levels of sponsorship listed are reflective of the amount of funding given to support the channel.
WCLC 2025 | Utilizing AI & deep learning to improve classifying and treating mesothelioma
Nicolas Alcala, PhD, International Agency for Research on Cancer, Lyon, France, discusses the importance of leveraging recent molecular advancements to improve classification and response to treatment in mesothelioma. Combining transcriptomic profiles with artificial intelligence (AI) and deep learning to infer molecular values from whole-slide images have potential, which can simplify the implementation of these techniques in research and clinical settings. This interview took place at 2025 World Conference on Lung Cancer (WCLC) in Barcelona, Spain.
These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.
Transcript
So, I think the main message we had for the community was to please use the new molecular resources and all the results that have been coming out in the recent years. So, in particular, in our study in 2023, we advocated for using additional markers that could be useful to stratify the patients to better understand why some patients respond to treatment, like why some don’t, like why some have a good prognosis, etc...
So, I think the main message we had for the community was to please use the new molecular resources and all the results that have been coming out in the recent years. So, in particular, in our study in 2023, we advocated for using additional markers that could be useful to stratify the patients to better understand why some patients respond to treatment, like why some don’t, like why some have a good prognosis, etc. So, we really think that they should embrace this. We showed a bit like all these results – we have the kid in particular to use estimates of the ploidy of the tumor, looking at the microenvironment on top of the morphology, and also look at the methylation level in the CpG islands. So, these four things we showed in the study that are very important to understand the differences between the patients. At the same time, we started to mention ways for researchers and clinicians to estimate these values. So, trying to advance a bit so it’s easier to implement in research settings and also in the clinic. Trying to look at different ways of doing this. So, we propose some ways for bioinformaticians to do it first. We’re trying to advance also for having some more simple biomarkers for our clinicians to use. And also, we are investigating the use of AI to just be able to, from a single whole slide image that is scanned, be able to infer all these values without needing to do any fancy molecular techniques, but just from the image infer directly the molecular classification.
This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.
Read more...
