Happy to share the results of what has been a huge multi-institutional #CancerResearch team effort😀: #MachineLearning for #Immunotherapy outcome prediction from tumor #pathology whole-slide images across many different tumor types.

Patients with gastric intestinal metaplasia (GIM) undergo regular endoscopic surveillance, but <5% actually progress to gastric cancer. Excited to be part of a fantastic collaboration led by Robert Huang to identify a spatial transcriptomic signature for high-risk GIM.

Happy to share this blog post healthcommunity.nature.com/posts/using-ai… which nicely summarizes our recent collaborative work with Med Uni Graz and Google Health on #deeplearning for #colorectalcancer lymph node metastasis prediction. Full paper here:
nature.com/articles/s4385…

It was an honor presenting on #MachineLearning / #AI for #oncology with medical AI luminaries Jakob Nikolas Kather and Regina Barzilay at #AACR23 . Great to be working in such an exciting field at such an exciting time with such awesome people😊

It was great to present some of our digital pathology projects and multimodal frameworks at #PMWC23 and catching up with my co-presenters Dr. Mirabela Rusu, PhD and Jeanne Shen MD from Stanford AIMI

Excited to share our recent work in The Lancet Oncology on deep learning for MSI prediction in CRC! (How well does it compare to experienced GI pathologists? Find out here 😉: authors.elsevier.com/a/1cKZ05EIIgBX…) Rikiya Yamashita Jin Long Daniel Rubin QILab Stanford AIMI and Stanford Pathology

An easy-to-use platform for getting started with digital pathology collaboration. Appreciate that there's no paywall or time limit for trying it out!