PHIND Seminar Series: Assessing the Effects of Alternative Plant-Based Meats vs. Animal Meats on Biomarkers of Inflammation: A Secondary Analysis of the SWAP-MEAT Randomized Crossover Trial
11:00am – 12:00pm Seminar & Discussion
RSVP Here

Zoom Webinar Details
Webinar URL: . https://stanford.zoom.us/s/95966150853
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 959 6615 0853
Passcode: 253543

Anthony Crimarco, PhD
Research Program Manager
Menus of Change University Research Collaborative (MCRUC)
Stanford University

Abstract
Background: To conduct a secondary analysis of Stanford University’s Study With Appetizing Plantfood – Meat Eating Alternatives Trial (SWAP-MEAT) by assessing the effects of consuming plant-based meats versus animal meats on biomarkers of inflammation (clinical trials.gov registry: NCT03718988). We hypothesized that biomarkers of inflammation would be improved for the plant-based meats compared to the animal meats.

Methods: SWAP-MEAT was a randomized crossover trial that involved participants eating 2 or more servings of plant-based meats for 8 weeks (i.e. Plant-based phase) followed by 2 or more servings of animal meats for 8 weeks (i.e. Animal phase) or vice versa. Participants’ biomarkers of inflammation were assessed from blood samples collected every 2 weeks in the intervention. Using the Olink platform, changes in 92 biomarkers of inflammation were compared between baseline and the end of each dietary phase (week 8 and 16). Linear mixed effect models were conducted to assess if the changes were significantly different for the Plant phase compared to the Animal phase.

Results: A total of 36 participants completed the intervention and provided complete data. They were 67% women, 69% Caucasian, had an average age of 50±14 years and body mass index (BMI) of 28±5 kg/m². The results of the linear mixed effect models indicated only 4 out of the 92 biomarkers reached statistical significance.

Conclusions: The results were contrary to our hypothesis, since we expected relative improvements in biomarkers of inflammation during the Plant-based phase. It is possible that 8 weeks of reducing animal meat consumption are not enough to observe any significant improvements in systemic inflammation or that plant-based meat products themselves are not sufficient enough to improve inflammation compared to an overall, healthy plant-based dietary pattern.

About Anthony Crimarco
Anthony Crimarco is a Research Program Manager for Stanford University’s Menus of Change University Research Collaborative (MCRUC). His focus area of research includes diet and lifestyle interventions; the benefits of plant-based diets; and mHealth and eHealth. Dr. Crimarco received his Ph.D. in Health Promotion, Education, and Behavior at the University of South Carolina in 2019 and completed a T-32 Postdoctoral Fellowship at the Stanford Prevention Research Center in 2021.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology

PHIND Seminar Series: A theragnostic 3D ultrasound imaging system for high resolution image-guided therapy
11:00am – 12:00pm Seminar & Discussion
RSVP Here

Zoom Webinar Details
Webinar URL: https://stanford.zoom.us/s/93222928907
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 932 2292 8907
Passcode: 689567

Hanna Bendjador, PhD
Postdoctoral Scholar
Molecular Imaging Program at Stanford
Stanford University

Abstract
As a non-invasive, non-ionizing and accessible imaging modality, ultrasound imaging has seen its clinical impact growing exponentially in the past thirty years. Clinical indications and reimbursement for therapeutic ultrasound are rapidly expanding. Yet, theragnostic technologies facilitating ultrasound guidance of ultrasound-mediated therapy are limited.  In particular, 2D arrays that are capable of implementing and imaging ultrasound therapy are lacking. To propel the promise of the theragnostic treatment strategies forward, we have designed and tested a unique array and system for 3D ultrasound guidance of microbubble-based therapeutic protocols based on the frequency, temporal and spatial requirements.

About Hanna Bendjador
Hanna Bendjador received a BS and MS in Physics from ESPCI Paris in France, as well as an MS in Engineering and Management from Mines Paris School. She graduated with her PhD in 2020, under the supervision of Mickael Tanter in the Physics for Medicine Laboratory (ESPCI Paris, INSERM, France). Her work focused on SVD and matrix approaches for aberration correction and sound speed quantification in ultrafast ultrasound imaging. She joined the Ferrara Lab in 2021 where she is working on the issue of deep high-resolution imaging, in three dimensions, and in complex and aberrated media. She is also exploring novel array designs to provide a single tool for both ultrasound mediated therapy and imaging.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology

PHIND Seminar Series: Time Before Birth: A Look at Developing Human Brain
11:00am – 12:00pm Seminar & Discussion
RSVP Here

Location: Zoom
Zoom Details
Webinar URL: https://stanford.zoom.us/s/92656362694
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 926 5636 2694
Passcode: 530579

Liyue Shen, MS
PhD Student in Electrical Engineering
Stanford University

Abstract
Magnetic resonance imaging offers unrivaled visualization of the fetal brain, forming the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changing appearance of the fetal brain, variable image quality, and frequent motion artifacts. Here we present an end-to-end, attention-guided deep learning model that predicts gestational age with R2 score of 0.945, mean absolute error of 6.7 days, and concordance correlation coefficient of 0.970. The convolutional neural network was trained on a heterogeneous dataset of 741 developmentally normal fetal brain images ranging from 19 to 39 weeks in gestational age. We also demonstrate model performance and generalizability using independent datasets from four academic institutions across the U.S. and Turkey with R2 scores of 0.81 to 0.90 after minimal fine-tuning. The proposed regression algorithm provides an automated machine-enabled tool with the potential to better characterize in utero neurodevelopment and guide real-time gestational age estimation after the first trimester.

About Liyue Shen
Liyue Shen is a final-year Ph.D. candidate in Electrical Engineering at Stanford University, co-advised by John Pauly and Lei Xing. Her research focuses on the interdisciplinary field of Medical AI to develop efficient AI/ML-driven computational algorithms and techniques for biomedical imaging and processing to address real-world biomedical and healthcare problems. Her works have been published in both ML/CV conferences (ICLR, ICCV, CVPR) and medical journals (Nature BME, IEEE TMI, MedIA, Scientific Reports). She was the recipient of the Stanford Bio-X Bowes Graduate Student Fellowship, and was selected as Rising Star in EECS by MIT and Rising Star in Data Science by University of Chicago. She co-organized the Women in Machine Learning (WiML) Workshop at ICML 2021 and the Machine Learning for Healthcare (ML4H) Workshop at NeurIPS 2021. She received an M.Sc. from Stanford University. Before that, she conferred her bachelor’s degree in Electronic Engineering from Tsinghua University.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology

Third Annual Conference on Disability in Healthcare and Medicine

Join us for the third annual Stanford Conference on Disability in Healthcare and Medicine. The event will take place on Saturday, April 23, 2022, 8:00 am – 3:30 pm, via Livestream and Zoom Meeting breakout groups. This conference will be a deep learning opportunity for students, doctors, scientists, nurses, technologists, administrators, staff, and any and all other providers and allies. The event will feature leading experts in the field, including Alice Wong, MS, Andres Gallegos, Esq., Stephen Hinshaw, PhD, Clarissa Kripke, MD, FAAFP, and Amy Houtrow, MD, PhD, MPH. More information about the event is available here.

Location: Livestream and Zoom Meeting breakout groups
More Information & Registration

Hosted by: Stanford Medicine Alliance for Disability Inclusion and Equity (SMADIE)

PHIND Seminar Series: Developing a Deep Learning Model for Early Detection of Cardiovascular Disease and Toxicity
11:00am – 12:00pm Seminar & Discussion
RSVP Here

Location: Zoom
Webinar URL: https://stanford.zoom.us/s/99807278159
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 998 0727 8159
Passcode: 540496

Angela Zhang
MD/PhD student
Stanford University

Abstract
Induced pluripotent stem cell derived cardiomyocytes (iPSC-CMs) provide an opportunity to study cardiac development, cardiac disease, and cardiotoxicity. Here, we present a deep learning model that has been trained on a 100,000 image dataset of induced pluripotent stem cells (iPSCs) differentiating into cardiomyocytes. We demonstrate that the model is able to predict differentiation outcomes through classification and segmentation. We then investigate the molecular mechanism underlying the model’s predictions and finally demonstrate that the model can be used for high-throughput label-free screening of drugs and environmental toxins that can perturb cardiac development.

About Angela Zhang
Angela Zhang is currently a MD/PhD student in the Joseph C. Wu lab pursuing a PhD in Genetics and PhD minor in CS. Her research interests include applying deep learning methods to stem cell technology to advance drug screening and disease modeling. She graduated from Harvard College in 2016, majoring in Biomedical Engineering.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology

PHIND Seminar Series: A Test in the Palm of Your Hand: Investigating the Use of Smartphones for Clinical Testing of Sensory Function
11:00am – 12:00pm Seminar & Discussion
RSVP Here

Location: Li Ka Shing Center, LK120 & Zoom
Zoom Details
Webinar URL:  https://stanford.zoom.us/s/93062932704
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 930 6293 2704
Passcode: 038337

Allison Okamura, PhD, MS
Professor of Mechanical Engineering and, by courtesy, of Computer Science
Stanford University

Kyle Tadao Yoshida
PhD Student in Mechanical Engineering
Stanford University

Abstract
Traditionally, clinicians use tuning forks as a binary measure to assess vibrotactile sensory perception in patients with diminished sensation, such as after stroke or due to peripheral sensory neuropathy resulting from diabetes. The tuning fork method requires a clinician to strike the tuning fork against their palm, place the base on the patient’s skin, and then ask the patient to verbally indicate whether vibrations are perceived. This approach has low measurement resolution, and the vibrations are highly variable. Therefore, we propose using vibrations from a smartphone to deliver an accurate and precise sensory test. First, we demonstrate that a smartphone has more consistent vibrations compared to a tuning fork. We measured vibrations on surface of commercial smartphones with an accelerometer and compared the response to that of a tuning fork. The amplitudes of the smartphone vibrations were more consistent than those of the tuning fork, the tuning fork did not vibrate at its specified frequency, and the smartphone can be programmed to display a variety of specific vibration amplitudes and frequencies. Second, we developed an iOS app and conducted a human-subject study to show that the smartphone can measure a user’s absolute threshold of vibration perception. The app controls the smartphone vibration output and implements a staircase method threshold experiment in which the user responds whenever they feel a vibration. Absolute intensity threshold was calculated by averaging the vibration parameter readings when the user switches from feeling to not feeling a vibration, and vice versa. Our findings motivate future work to use smartphones to assess vibrotactile perception, allowing for increased patient monitoring and widespread accessibility.

About Allison Okamura
Allison Okamura received the BS degree from the University of California at Berkeley, and the MS and PhD degrees from Stanford University. She is Professor in the mechanical engineering department at Stanford University, with a courtesy appointment in computer science, and directs the CHARM Lab (http://charm.stanford.edu). She is an IEEE Fellow and is currently the co-general chair of the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems and a deputy director of the Wu Tsai Stanford Neurosciences Institute. Her awards include the IEEE Engineering in Medicine and Biology Society Technical Achievement Award, IEEE Robotics and Automation Society Distinguished Service Award, and Duca Family University Fellow in Undergraduate Education. Her academic interests include haptics, teleoperation, virtual reality, medical robotics, soft robotics, rehabilitation, and education. Outside academia, she enjoys spending time with her husband and two children, running, and playing ice hockey.

About Kyle Yoshida
Kyle Yoshida is a mechanical engineering PhD candidate in the CHARM Lab at Stanford University. He majored in bioengineering and minored in African studies at Harvard University. He received the NSF Graduate Research Fellowship, Stanford Graduate Research Fellowship, Stanford Enhancing Diversity in Graduate Education Fellowship, American Indian Science and Engineering Society Lighting the Pathway Fellowship, and Wu Tsai Mind, Brain, Computation, and Technology Student Training Grant. His research, spanning robotics and wearable/mobile haptics, has been recognized through awards at the IEEE International Conference on Soft Robotics, the IEEE International Conference on Robotics and Automation, and the Society for Integrative and Comparative Biology National Conference. In his free time, he manages Honua Scholars, a STEM-mentorship program recognized as one of the 2021 Top 10 Native STEM Enterprises to Watch by the American Indian Science and Engineering Society.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology

Second Annual Gambhir Symposium

The Second Annual Gambhir Symposium is taking place on Monday, July 18 to celebrate the legacy, impact, and scientific achievements of Sanjiv “Sam” Gambhir, MD, PhD. This year’s event will be fully virtual, but we will offer an in-person watch party of the virtual event for local participants at Stanford Hospital – Assembly Hall. The livestream link will be posted on the website closer to the event.

Dr. Sanjiv Sam Gambhir was a visionary who had a profound impact on the world of science and humanity. As a leader and pioneer in the fields of molecular imaging, early detection of cancer, and precision health, his enduring legacy can be seen in the research and innovations continuing in these fields today.

The Gambhir Symposium aims to celebrate Dr. Gambhir’s illustrious career and continue down the paths he forged by highlighting the work still ongoing in the fields he helped to cultivate. Join us to hear researchers and collaborators share current thoughts and future outlooks on Radiology.

Location:Virtual via Livestream or Watch Party at Stanford Hospital – Assembly Hall
More Information & Registration

Hosted by: Department of Radiology, Stanford University School of Medicine

PHIND Seminar Series: Developing a PET/MR imaging-guided immunotherapy in advanced prostate and bone cancer

11:00am – 12:00pm Seminar & Discussion
RSVP Here

Location: Zoom
Zoom Details
Webinar URL: https://stanford.zoom.us/s/94150758041
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 941 5075 8041
Passcode: 619536

Manoj Kumar, PhD
Postdoctoral Scholar
Stanford University

Abstract
Cancer immunotherapies aim to overcome the immune-suppressive barriers in the tumor microenvironment through activation or modulation of the innate or adaptive immune signals. Non-invasive imaging approaches such as positron emission tomography (PET) and magnetic resonance imaging (MRI) enable visualizing the tumor microenvironment’s immune compositions and dynamic changes in response to immunotherapy. Integrated PET/MRI enables simultaneous in vivo tracking of more than one immune target in the tumor, informing the development of more efficient immunotherapies.

B7-H4 is a recently discovered immune checkpoint protein that inhibits anti-tumoral T-cell function. We present a new imaging approach using a newly developed PET probe for imaging B7-H4 in mouse models of prostate cancer and osteosarcomas. Since B7-H4 inhibits the interaction between T-cells and tumor-associated macrophages (TAMs), we combined our imaging approach with ferumoxytol-enhanced MRI to track tumor-associated macrophages (TAMs) simultaneously. We demonstrate how B7-H4 expression on prostate cancers and osteosarcomas can be quantified with PET imaging. In addition, we show how integrated PET/MRI can demonstrate TAM activation after the B7-H4 blockade. We then investigate the ability of our integrated PET/MRI approach to predict tumor response to different combination immunotherapies by quantifying B7-H4 expression and TAM responses in the tumor microenvironment.

About Manoj Kumar
Manoj Kumar is currently a postdoctoral fellow at the Daldrup-Link laboratory in the Department of Radiology at Stanford University. He is working on designing PET and MRI imaging probes to enable real-time visualization of immune markers in the tumor microenvironment and develop more effective immunotherapy approaches for imaging-guided cancer treatment. Manoj received his Ph.D. in Clinical Investigation from the University of Wisconsin-Madison in 2020. His doctoral research focused on PET imaging of steroid hormone receptors to evaluate endocrine therapy response in advanced breast cancer. He has authored publications on molecular imaging, hormone receptor biology, cancer biology, and drug delivery.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology

PHIND Seminar Series: Opportunistic Disease Prediction using Already-Acquired Medical Imaging and Deep Learning

11:00am – 12:00pm Seminar & Discussion
RSVP Here

Location: LKSC, LK120 &Zoom
Zoom Details
Webinar URL: https://stanford.zoom.us/s/96233225915
Dial: US: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Webinar ID: 962 3322 5915
Passcode: 718123

Akshay Chaudhari, PhD
Assistant Professor of Radiology and, by courtesy, of Biomedical Data Science
Stanford University

Abstract
Over 88 million computed tomography (CT) scans are performed annually in the US, with abdominal CT accounting for ~20 million. While these scans answer specific clinical questions, a majority of the information in the rich 3D scans unrelated to the referral question is not evaluated. In this work, we will demonstrate how extracting additional biological insights beyond those required to answer the original clinical question can be used for predicting the onset of future disorders. We will demonstrate how we can analyze CT images using deep learning tools to opportunistically predict future cardiometabolic disorders with high accuracy. We will depict how we can combine medical imaging data with data from electronic medical records to improve the accuracy of such models. Overall, opportunistic imaging has the potential to be a paradigm-changing new tool to improve health outcomes through early detection and intervention without requiring additional diagnostic testing since it uses CT imaging that has already been acquired.

About Akshay Chaudhari
Dr. Chaudhari is an Assistant Professor in the Department of Radiology and (by courtesy) in the Department of Biomedical Data Science. He leads the Machine Intelligence in Medical Imaging research group at Stanford and has a primary research interest that lies at the intersection of artificial intelligence and medical imaging. Dr. Chaudhari is interested in the application of artificial intelligence techniques to all aspects of medical imaging, including automated schedule and reading prioritization, image reconstruction, quantitative analysis, and prediction of patient outcomes. His interests range from developing novel data-efficient machine learning algorithms to clinical deployment and validation of patient outcomes, both for medical imaging acquisition and subsequent analysis. He also conducts research in combining imaging with clinical, natural language, and time series data.

Hosted by: Garry Gold, MD
Sponsored by: PHIND Center & the Department of Radiology