E38: The Virtual Biopsy Revolution with Dr. Tanishq Mathew Abraham (Part 2 of 2)

Published: June 22, 2023, 7 a.m.

Part 2 of Nathan's conversation with Tanishq Mathew Abraham focuses on Tanishq's work with virtual biopsy technology enabled by deep learning. This unique technology has the potential to address a number of important biomedical challenges; in particular, qOBM could help during live tumor and cancer removal surgeries.\nTanishq, a 19-year-old UC Davis grad and one of the youngest people in the world to receive a Ph.D, with a degree in biomedical engineering, is the founder of the Medical AI Research Center (MedARC). In case you haven\u2019t yet listened to part 1, check it out! That episode goes deep on Tanishq\u2019s first published paper: Reconstructions of the Mind\u2019s Eye, which encompasses breakthrough research on reconstructing visual perceptions from fMRI scans into images.\n\nWe're hiring across the board at Turpentine and for Erik's personal team on other projects he's incubating. He's hiring a Chief of Staff, EA, Head of Special Projects, Investment Associate, and more. For a list of JDs, check out: eriktorenberg.com.\n\nRECOMMENDED PODCAST:\nThe HR industry is at a crossroads. What will it take to construct the next generation of incredible businesses \u2013 and where can people leaders have the most business impact? Hosts Nolan Church and Kelli Dragovich have been through it all, the highs and the lows \u2013 IPOs, layoffs, executive turnover, board meetings, culture changes, and more. With a lineup of industry vets and experts, Nolan and Kelli break down the nitty-gritty details, trade offs, and dynamics of constructing high performing companies. Through unfiltered conversations that can only happen between seasoned practitioners, Kelli and Nolan dive deep into the kind of leadership-level strategy that often happens behind closed doors. Check out the first episode with the architect of Netflix\u2019s culture deck Patty McCord.\nhttps://link.chtbl.com/hrheretics\n\nThe Cognitive Revolution is a part of the Turpentine podcast network. To learn more: Turpentine.co\n\nTIMESTAMPS:\n(00:00) Episode Preview\n(03:26) Introducing Tanishq\u2019s second paper presenting an AI-enabled biopsy\xa0\n(06:39) Diagnostic applications of this unique slide-free and label-free technology (qOBM)\n(13:06) Leveraging deep learning, specifically generative adversarial networks (GANs)\n(14:55) Sponsor: Omneky\n(15:42) Framework for model\n(16:22) Challenges of medical data sets\n(20:11) Challenges of unpaired image to image translation, addressed with a CycleGAN architecture\xa0\n(22:19) What didn\u2019t work\n(25:44) Breaking down GAN frameworks\n(34:30) Simplifying data to better with the CycleGAN\n(36:02) Factors for errors and confusing the model\n(39:00) Compute and training requirements\n(41:35) How this technology can scale in the near term and improve patient care\n(45:53) Tanishq\u2019s relationships with EleutherAI and Stability AI\n(47:08) The future-looking focus of MedArc and unexplored opportunities\n(49:00) Developments in Medical AI field and interesting applications\n(55:11) Early education and AI\n(58:00) Would Tanishq get a neuralink?\n(1:00:00) Tanishq\u2019s hopes and fears for AI\n\nLINKS:\nPaper: Label- and slide-free tissue histology using 3D epi-mode quantitative phase imaging and virtual H&E staining https://arxiv.org/pdf/2306.00548.pdf \nAuthors: Tanishq Mathew Abraham, Paloma Casteleiro Costa, Caroline Filan, Zhe Guang, Zhaobin Zhang, Stewart Neill, Jeffrey J. Olson, Richard Levenson, Francisco E. Robles\n\nTWITTER:\n@iScienceLuvr (Tanishq)\n@MedARC_AI (MedARC)\n@CogRev_Podcast\n@labenz (Nathan)\n@eriktorenberg (Erik)\n\nSPONSOR:\nThank you Omneky (www.omneky.com) for sponsoring The Cognitive Revolution. Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work, customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off.\n\nMUSIC CREDIT:\nMusicLM