Session Abstract – PMWC 2023 Silicon Valley

Track 4 - January 27 9.00 A.M.-3.00 P.M.


Track Chair: Sean Khozin, CancerLinQ

  • PMWC Award Ceremony:
    Pioneer Honoree: Daniela Ushizima, LBNL, UCSF, UCB & Lea Grinberg, UCSF
  • Pattern Recognition and Content Quantification in Early-stage Disease Diagnosis (PANEL)
    Chair: Daniela Ushizima, LBNL, UCSF, UCB
    - Lea Grinberg, UCSF
    - Suzanne Baker, LBL
  • Second Phase of AI Imaging is Clinical Validation
    - Sean Khozin, CancerLinQ
  • Large-Scale Spatial Omics Imaging Analysis To Decipher The Tumor Microenvironment
    - Joseph Lehar, Owkin
  • Latest Achievement in AI Imaging Technology in the area of Radiology and Pathology
    Chair: Wim Van Hecke, Icometrix
    - Joachim H. Schmid, NanoString Technologies
    - Fedaa Najdawi, PathAI
    - Nurit Paz Yaacov, Imagene
    - Neil Weisenfeld, 10x
  • AI in Radiology & Pathology Applications (Clinical Research)
    Chair: Mirabela Rusu, Stanford
    - Saeed Hassanpour, Dartmouth
    - Jeanne Shen, Stanford
    - Pratik Mukherjee, UCSF
  • PMWC NCI Showcase
    - Omid Moghadam, Rapid
  • PMWC Showcase
    - Amanda Hanson, Spartanburg Regional Healthcare System

 Session Chair Profile

PMWC PIONEER AWARD
Developed a new and reliable technique for diagnosing Alzheimer’s disease and measuring the efficacy of experimental treatments

Ph.D., Staff Scientist, Affiliate Faculty, Data Scientist, LBNL, UCSF, UCB

Biography
Dani Ushizima is a Computer Scientist focused on Computer Vision and Machine Learning algorithms to characterize materials toward self-driving labs. Her research has impacted projects that depend on experimental data coming from instruments reliant on x-ray, electron, confocal, and other light-matter interactions. In 2015, Ushizima received the U.S. DOE Early Career Research award to work on pattern recognition for scientific images. In 2021, she was honored by 3M as one of the top "25 Latina in Science" for biomedical research. Also in 2021, Ushizima and colleagues received the Berkeley Lab Halback award for creating machine-learning-based techniques to solve a problem that has plagued third-generation light sources: fluctuations in beam size. Currently, Ushizima leads research projects in the Center for Advanced Mathematics for Energy Related Applications (CAMERA). Jointly with UCSF Grinbergs lab, she has developed a new technique for diagnosing Alzheimer’s disease and supporting measurement of the efficacy of experimental treatments.

Talk
Alzheimer's immunohistochemistry and deep learning
We will discuss our end-to-end deep learning-based workflow to process human brain, combining imaging antibodies with CT, MRI, and PET. We will show how Tau marked with multiple antibodies holds the promise to help validation of the relationship between molecular signals detected by PET imaging AND the corresponding neural microstructures they originate from.


 Speaker Profile

PMWC PIONEER AWARD
Developed a new and reliable technique for diagnosing Alzheimer’s disease and measuring the efficacy of experimental treatments

M.D., Ph.D., John Douglas French Alzheimer Foundation Endowed Professorrofessor , UCSF

Biography
Dr. Lea Tenenholz Grinberg is a neuropathologist specializing in brain aging, most notably, Alzheimer’s diseases. She is a Full Professor and a John Douglas French Alzheimer’s Foundation Endowed Professor at the UCSF Memory and Aging Center, where she co-led the Neuropathology Core. She is also a Professor of Pathology at the University of Sao Paulo. Dr. Grinberg is the recipient of several awards and have co-authored over 260 scientific papers. The Grinberg Lab investigates factors influencing clinical expression of Alzheimer’s pathology and other tauopathies to lead to better diagnostic tools and therapeutic targets that minimize clinical decline in AD by following up on Dr. Grinberg’s initial discoveries of brainstem vulnerability in Alzheimer’s disease. Her discoveries had changed the understanding on the basis of sleep disturbances in these diseases. The Lab combines classical quantitative neuropathological techniques with advanced computer vision tools and multiplex molecular probing in postmortem human tissue

Talk
Unveiling the Basis of Neuroimaging Signal with Histology
neuroimaging findings is often based on assumptions because of its lower resolution compared to microscopy. We developed a computational and histological pipeline to process and stain whole human brain volumes, 3D reconstruct the histological volume at microscopical level and perfectly align histology-based cytoarchitectonic and protein deposition 3D maps to their neuroimaging counterparts.


 Speaker Profile

Ph.D., SVP R&D Strategy, Owkin

Biography
Over 20 years experience as an innovator and executive, focused on using data and digital technologies to transform health care. Before my current activities at Owkin, venture and board member/advisor to multiple organizations, I led cross-functional teams and drove scientific projects at J&J/Janssen (as VP of Data Science), Google/Verily, Novartis, and CombinatoRx.


 Speaker Profile

Ph.D., Staff Scientist, Affiliate Faculty, Data Scientist, LBNL, UCSF, UCSF

Biography
Dani Ushizima is a Computer Scientist focused on Computer Vision and Machine Learning algorithms to characterize materials toward self-driving labs. Her research has impacted projects that depend on experimental data coming from instruments reliant on x-ray, electron, confocal, and other light-matter interactions. In 2015, Ushizima received the U.S. DOE Early Career Research award to work on pattern recognition for scientific images. In 2021, she was honored by 3M as one of the top "25 Latina in Science" for biomedical research. Also in 2021, Ushizima and colleagues received the Berkeley Lab Halback award for creating machine-learning-based techniques to solve a problem that has plagued third-generation light sources: fluctuations in beam size. Currently, Ushizima leads research projects in the Center for Advanced Mathematics for Energy Related Applications (CAMERA). Jointly with UCSF Grinbergs lab, she has developed a new technique for diagnosing Alzheimer’s disease and supporting measurement of the efficacy of experimental treatments.


 Speaker Profile

M.D., Ph.D., John Douglas French Alzheimer Foundation Endowed Professorrofessor , UCSF

Biography
Dr. Lea Tenenholz Grinberg is a neuropathologist specializing in brain aging, most notably, Alzheimer’s diseases. She is a Full Professor and a John Douglas French Alzheimer’s Foundation Endowed Professor at the UCSF Memory and Aging Center, where she co-led the Neuropathology Core. She is also a Professor of Pathology at the University of Sao Paulo. Dr. Grinberg is the recipient of several awards and have co-authored over 260 scientific papers. The Grinberg Lab investigates factors influencing clinical expression of Alzheimer’s pathology and other tauopathies to lead to better diagnostic tools and therapeutic targets that minimize clinical decline in AD by following up on Dr. Grinberg’s initial discoveries of brainstem vulnerability in Alzheimer’s disease. Her discoveries had changed the understanding on the basis of sleep disturbances in these diseases. The Lab combines classical quantitative neuropathological techniques with advanced computer vision tools and multiplex molecular probing in postmortem human tissue

Talk
unveiling the basis of neuroimaging signal with histology
neuroimaging findings is often based on assumptions because of its lower resolution compared to microscopy. We developed a computational and histological pipeline to process and stain whole human brain volumes, 3D reconstruct the histological volume at microscopical level and perfectly align histology-based cytoarchitectonic and protein deposition 3D maps to their neuroimaging counterparts.


 Speaker Profile

Ph.D., Computational Staff Scientist, LawrenceBerkeleyLab

Biography
Suzanne Baker got her bachelor degree in Biomedical engineering from Tulane University and her PhD in Vision Science from University of California, Berkeley. Her research focuses on methods development in brain positron emission tomography (PET) in aging and dementia. Her primary interests are tracer evaluation, pharmacokinetic modeling, harmonizing multi-site data, reference region analysis, between tracer comparison and partial volume correction. She serves as the PET core for many multi-center studies. She has performed preliminary evaluation of Flortaucipir and JNJ067 tau PET tracers. She consults for Genentech on their tau PET tracer. She recently was awarded a $40 million NIH grant to compare Flortaucipir and MK6240 tau PET tracers in a head-to-head cohort, which will include comparisons to measurements of tau in plasma.

Talk
Considerations in methods for tau PET quantification
A useful PET tracer has high affinity for the protein of interest and has none-to-low binding to anything else. In aging and dementia, the correlation of tau accumulation with cognitive decline makes it an interesting target for therapies. Here Ill explore methods of amplifying the signal and decreasing the noise.


 Speaker Profile

M.D., M.P.H., Affiliate , MIT

Biography
Sean Khozin is an oncologist and data scientist. He is a globally recognized leader in building solutions at the intersection of biology, technology, and AI/machine learning to advance biomedical research and therapeutic development.

Talk
Artificial Intelligence as a Tool to Reclassify Diseases
Despite the recent advances in the development of new medicines, many patients do not derive any benefit from available therapies and diseases like metastatic cancers remain largely incurable. Catalyzing the next wave of biomedical breakthroughs and precision therapies requires a paradigm shift in classification of diseases using AIML solutions.


 Speaker Profile

Ph.D., Founder & CEO, icometrix

Biography
Wim Van Hecke is an academic engineer by training with two Master degrees in applied biomedical engineering and neuroimaging, and a PhD in advanced MRI artificial intelligence analysis. He is the author of more than 250 scientific publications, has an H-index of 44, and is the editor of a clinical neuroimaging handbook. Together with the icometrix team, he developed 8 FDA cleared and CE marked solutions in the field of neurology. He’s also a visiting professor at the free university of Brussels.

Talk
Time is brain - precision medicine in neurology
The societal and economic burden of chronic neurological conditions, such as Alzheimers disease and Multiple Sclerosis, is immense. However, current care pathways are variable and disease monitoring is qualitative and subjective. Hence, there is a huge need for digital health solutions and AI to enter the era of precision medicine in neurology.


 Speaker Profile

Ph.D., Ph.D., Vice President, R&D Spatial Informatics & AI, NanoString

Biography
Joachim Schmid recently joined NanoString as Vice President of Spatial Informatics & AI and oversees the development of innovative software solutions and data analysis methods for spatial biology. Previously he worked in various R&D leadership positions at Tripath Imaging, Dako, and Roche Tissue Diagnostics.


 Speaker Profile

M.D., Director of Pathology, PathAI

Biography
Dr. Najdawi is a board certified anatomical pathologist specialized in gastrointestinal and endocrine pathology. She works at the intersection of Artificial Intelligence and Anatomical Pathology at PathAI, where she is using her pathology expertise to guide a multidisciplinary team with a mission to improve patient outcomes with AI-powered pathology. Dr. Najdawis pathology journey started in Australia and she completed her AP training and two fellowships in gastrointestinal and endocrine pathology at Brigham and Women’s Hospital, Harvard Medical School. She has over 12 years of experience in the medical field, and is certified to practice medicine in the USA, Australia, and Jordan. She has multiple peer-reviewed publications and presented her work at national and international meetings. Her current research is focused on leveraging AI and digital pathology tools to empower precision pathology.


 Speaker Profile

Ph.D., Assistant Professor, Stanford

Biography
Dr. Mirabela Rusu received a Master of Engineering from the National Institute of Applied Sciences, France and her MS and PhD in Computational Biomedicine from University of Texas Houston. During her postdoctoral training at Case Western Reserve University, Dr. Rusu developed computational tools for the integration and interpretation of multi-modal medical imaging data. Dr. Rusu joined GE Global Research in 2015 as an Image Analysis Scientist and developed analytic methods for biomedical data interpretation. Since 2018, Dr. Rusu leads the Personalized Integrative Medicine Laboratory (http://pimed.stanford.edu) which focuses on developing analytic methods to spatially align radiology and pathology images in patients that undergo surgery for cancer treatment. Moreover, her team uses the registered data to label the radiology images and extract pathomic MRI biomarkers that allow the training of deep learning models to automatically detect and distinguish indolent from aggressive prostate cancer on MRI.

Talk
Bridging the gap between radiology and pathology images


 Speaker Profile

Ph.D., Principal Scientist, 10x Genomics

Biography
Neil leads analysis software pipeline development for the Visium line of spatial transcriptomics products at 10x. He has over 25 years experience in image analysis algorithm development for diverse applications including functional brain imaging, image-guided neurosurgery, neonatal brain MRI, and pathology image analysis. Prior to joining 10x, he was a senior computational biologist at the Broad Institute working on algorithms for de novo genome assembly.

Talk
High-resolution mapping of the breast cancer tumor micro environment
We describe new methods that bring together single-cell gene expression (Chromium Fixed RNA Profiling), spatial transcriptomics (Visium CytAssist), and automated, microscopy-based in situ technology (Xenium In Situ) to better characterize the breast cancer tumor microenvironment leading to new biological insights about the trajectory of disease.


 Speaker Profile

Ph.D., Associate Professor, Dartmouth

Biography
Dr. Hassanpour’s research is focused on building novel machine learning and multimodal data analysis methods to inform precision health. His lab has been a pioneer in advancing digital pathology through deep learning methodologies. He has led multiple NIH-funded research projects on developing new machine learning models for medical image analysis and clinical text mining to improve diagnosis, prognosis, and personalized therapies. His research has resulted in numerous publications, software, and datasets that are widely recognized and received multiple awards, including the 2019 Agilent Early Career Professor Award for breakthroughs in digital pathology. Before joining Dartmouth, he worked as a Research Engineer at Microsoft. Dr. Hassanpour received his Ph.D. in Electrical Engineering with a minor in Biomedical Informatics from Stanford University and completed his postdoctoral training at Stanford Center for Artificial Intelligence in Medicine & Imaging.

Talk
AI for Digital Pathology
With the recent expansions of whole-slide digital scanning, archiving, and high-throughput tissue banks, digital pathology is primed to benefit dramatically from AI. This talk will cover several clinical applications of AI for characterizing histopathological patterns on high-resolution microscopy images for the classification, prognosis, and treatment of cancerous and precancerous lesions.


 Speaker Profile

Ph.D., Ph.D., Chief Scientific Officer, Imagene

Biography
Dr. Nurit Paz-Yaacov is the Chief Scientific Officer at Imagene AI - a BioMed startup company with groundbreaking technology in the field of precision oncology using Artificial Intelligence.Dr. Paz-Yaacov brings more than 20 years of multidisciplinary scientific research in human genetics and genomic sequencing and interpretation, with an emphasis on cancer research.Prior to her role at Imagene AI, Dr. Paz-Yaacov was the Head of Scientific Research at Genoox, a cloud platform that provides actionable interpretation for real-time/real-life genomic data.Dr. Paz-Yaacov holds B.Sc, M.Sc, and Ph.D. degrees from Tel-Aviv University and completed her Postdoctoral studies at Bar-Ilan University. Her studies, and research in the fields of cancer, applied genomics, and epi-genomics, received recognition through numerous publications and prizes.


 Speaker Profile

M.D., Assistant Professor of Pathology, Stanford

Biography
Dr. Shen is a board-certified pathologist and Associate Director of Pathology for the Stanford Center for Artificial Intelligence in Medicine and Imaging. She has served as a principal investigator and collaborator on multiple academic and industry-sponsored studies in digital and computational pathology and oncology, and as a a medicolegal, startup, and venture capital consultant focused on applications in digital pathology and AI.


 Speaker Profile

Chairman of the Board, Rapid

Biography
Omid Moghadam is the founder and CEO of Namida Lab, a revenue-stage diagnostics company specializing in developing and commercializing liquid biopsy tests for early cancer detection. Namidas first product, Auria, is a direct-to-consumer proteomic test allowing women to take charge of their breast health. Hes an inventor, entrepreneur, venture investor, and educator. He specializes in launching new ventures with social impact in health and technology. Moghadam has inventions in medical imaging, cryptography, microprocessor design, medical devices, diagnostics, digital photography, data-science and communications. Hes the past founder or co-founder of nine companies in Healthcare IT, genomics, diagnostics, and medical imaging, and has held executive positions at Intel, Eastman Kodak, and CTG-AMS Corporations. He formerly served on the advisory boards of Robert Wood Johnson Foundation, Childrens Hospital Boston, Abbott Corporation, and California Healthcare Foundation and has held academic positions at Harvard Medical School department of biomedical informatics, as well as an Executive-In-Residence position at UCLA.


 Speaker Profile

M.D., Ph.D., M.D., Ph.D., John Douglas French Alzheimer Foundation Endowed Professorrofessor , UCSF

Biography
Dr. Lea Tenenholz Grinberg is a neuropathologist specializing in brain aging, most notably, Alzheimers diseases. She is a Full Professor and a John Douglas French Alzheimers Foundation Endowed Professor at the UCSF Memory and Aging Center, where she coled the Neuropathology Core. She is also a Professor of Pathology at the University of Sao Paulo. Dr. Grinberg is the recipient of several awards and have coauthored over 260 scientific papers. The Grinberg Lab investigates factors influencing clinical expression of Alzheimers pathology and other tauopathies to lead to better diagnostic tools and therapeutic targets that minimize clinical decline in AD by following up on Dr. Grinbergs initial discoveries of brainstem vulnerability in Alzheimers disease. Her discoveries had changed the understanding on the basis of sleep disturbances in these diseases. The Lab combines classical quantitative neuropathological techniques with advanced computer vision tools and multiplex molecular probing in postmortem human tissue