New Applications of AI in Cancer Research and Clinical Practice

On the first Friday of every month, the?AI Precision Health Institute at the?University of Hawai'i Cancer Center hosts a very popular seminar series on new applications of AI in cancer research and clinical practice. We host leading AI scientists and cancer researchers from around the world who have made important advances using AI in their work. In today's newsletter I'm sharing recaps of all presentations in the 2023 seminar series.

1. AI-Driven Surgical Robots To Diagnose and Treat Prostate Cancer
2. Advanced Machine Learning For Personalized Cancer Screening
3. Precision Oncology: Empowering Radiologists And Oncologists With AI
4. Presentations From AI Precision Health Institute Students
5. Deep Learning To Diagnose Breast Cancer With Very High Accuracy
6. AI For Ultrasound For Real-Time Breast Cancer Decision Support
7. Trustworthy AI and Clinical Validation In Breast Cancer Imaging
8. AI Based Lab Test Approved To Phenotype, Grade Breast Cancer
9. Disrupting the Indigenous DNA SupplyChain
10. Comparing AI Algorithms To Predict 5 Year Breast Cancer Risk
11. Machine Learning Techniques To Capture Insights Into Brain Tumor Biology
12. Robust Interpretability Methods For Large Language Models

AI Driven Surgical Robots To Diagnose and Treat Prostate Cancer

In this presentation, Bardia Kohn, PhD described recent progress in surgical tools, medical robotics, and AI that provide improved and effective diagnostic and treatment options for prostate cancer. Minimally invasive surgery introduces great potential for improving the accuracy and dexterity of a surgeon and minimizing trauma to the patient. Active “smart” needles, capable of bending inside tissue, can help surgeons reach deeper targets inside the human body more precisely than ever before through increasingly smaller incisions. Click here for a recap.

Advanced Machine Learning For Personalized Cancer Screening

In this presentation, Adam Yala, PhD described AI tools for risk assessment. Risk models impact millions of patients every year and guide screening and prevention efforts. Effective population cancer screening programs must balance the benefits of early detection against the harms of overscreening.? Dr. Yala demonstrated that AI based clinical models offer significant improvements over the current standard of care across globally diverse patient populations.?Click here for a recap.

Precision Oncology: Empower Radiologists & Oncologists With AI

In this presentation, Maya Khalifé, PhD, discussed the capabilities of Arterys' cloud-based intelligent diagnostic platform that combines clinical AI and workflow optimization to empower physicians to make more accurate and data-driven clinical decisions. Dr. Khalifé showcased Arterys’ AI-based oncology platform and demonstrated how it provides comprehensive cancer patient reporting and follow-up through an innovative and efficient workflow. Click here for a recap.

Presentations From AI Precision Health Institute students

• Deep learning furthers the understanding of local distributions of fat and muscle on body shape and health using 3D surface scans - Presented by Lambert Leong
• Can AI derived ultrasound breast density provide comparable breast cancer risk estimates to density derived from mammograms - Presented by Dustin Valdez
• Deep learning predicts all-cause mortality from longitudinal total-body DXA imaging - Presented by Yannik Glaser
• AI Detects, Classifies, and Describes Lesions in Clinical Breast Ultrasound Images - Presented by Arianna Bunnell

Deep Learning To Diagnose Breast Cancer With High Accuracy

In this presentation, Krzysztof Geras, PhD described his 7-year journey developing deep learning methods for breast cancer screening. Although deep learning is expected to transform medical imaging, it has proven to be much harder than expected. Dr. Geras descibed how he created a deep learning model that can perform a diagnosis with an accuracy comparable to experienced radiologists. To achieve this goal, Dr. Geras and his colleagues developed novel neural network architectures and training methods specific to medical imaging. He also discussed the limitations of his work and what can potentially be achieved in the next few years. Click here for a recap.

AI Trained For Breast Cancer Diagnosis Using Ultrasound

In this presentation, Jaeil Kim, PhD, founder of BeamWorks in South Korea, described his work using AI for breast cancer diagnosis using ultrasound. Dr. Kim developed AI-based decision support models for breast cancer using over 500,000 breast ultrasound images. In order to achieve real-time AI processing time, he utilized neural network compression and optimization methods which can reduce inference time and memory usage while maintaining diagnostic accuracy. He developed a light-weighted AI that is highly mobile and easy to access because it does not require a server or cloud computing. Click here for a recap.

Trustworthy AI and Clinical Validation In Breast Cancer Imaging

In this presentation, Oliver Diaz, PhD, described an international initiative for defining concrete guidelines that will facilitate the design, development, validation and deployment of trustworthy AI solutions in medicine and healthcare. In recent years, AI models have demonstrated remarkable effectiveness in the realms of cancer prevention, detection, and treatment planning. However, the integration of AI-based algorithms into clinical practices faces limitations, primarily stemming from the opaque nature of these models. Click here for a recap.

AI Based Lab Test Approved To Phenotype, Grade Breast Cancer

In this presentation Michael Donovan MD, PhD, and Gerardo Fernandez, MD, co-founders of PreciseDx, discussed the development and practical application of PreciseDx's digital laboratory-developed test to phenotype, grade, and prognosticate early-stage invasive breast cancer. The PreciseDx platform utilizes standardized, quantitative metrics in a comprehensive Morphology Feature Array?derived from millions of data points to standardize anatomic pathology with new levels of detail and patient specificity. This AI platform captures more information from every slide, stain, and tissue sample than humanly possible. Click here for a recap.

Disrupting the Indigenous DNA SupplyChain

In this presentation, Keolu Fox, PhD discussed the potential of big data ecosystems and?Indigenous?governance of AI. Dr. Fox is the first Kānaka Maoli (Native Hawaiian) to receive a doctorate in genome sciences. He has experience designing and engineering genome sequencing and editing technologies, and a decade of grassroots experience working with Indigenous partners to advance precision medicine and genome science. In this talk, Dr. Fox explored how Indigenous?data governance can?disrupt the current?supply?chain?and transform the field of data science. Click here for a recap.

Comparing AI Algorithms To Predict 5 Year Breast Cancer Risk

In this presentation, Vignesh Arasu, MD, PhD, from Kaiser Permanente Northern California Division of Research, discussed his study comparing mammography AI algorithms for 5-year breast cancer risk prediction. Clinical risk models depend on gathering information from different sources, which isn’t always available or collected. Recent advances in AI deep learning provide researchers with the ability to extract hundreds to thousands of additional mammographic features. Mammography-based AI risk models provide practical advantages over traditional clinical risk models because they use a single data source: the mammogram itself. Click here for a recap.

Machine Learning Techniques To Capture Insights Into Brain Tumor Biology

In this presentation, Pallavi Tiwari, PhD, Associate Professor in the Departments of Radiology, Biomedical Engineering, and Medical Physics at the University of Wisconsin, Madison, discussed her lab’s recent efforts in developing machine learning techniques to capture insights into the underlying tumor biology as observed across non-invasive imaging, histopathology, and omics data. Dr. Tiwari focuses on applications of this work for predicting disease outcome, recurrence, progression, and response to therapy specifically in the context of brain tumors. She also discussed current efforts in developing new image-based features for post-treatment evaluation and predicting response to chemo-radiation treatment. Click here for a recap.

Robust Interpretability Methods For Large Language Models

In this presentation, William Rudman a rising star in AI from Brown University and the Health NLP Lab at Brown & Tuebingen University discused his research on robust interpretability methods for large language models and their use in diagnostic decision making. His talk addressed the black-box nature of AI and described how to build interpretable models. His work focuses on finding more robust techniques for understanding deep learning models by investigating the vector space of model representations. For example his team found that a single basis dimension in fine-tuned large language models drives model decisions and preserves >99% of the original classification performance of the full model. Click here for a recap.

AI Precision Health Institute

The?AI Precision Health Institute Affinity Group?was formed to discuss current trends and applications of AI in cancer research and clinical practice. The group brings together AI researchers in a variety of fields including computer science, engineering, nutrition, epidemiology, and radiology with clinicians and advocates. The goal is to foster collaborative interactions to solve problems in cancer that were thought to be unsolvable a decade ago before the broad use of deep learning and AI in medicine.

Subscribe, Comment, Join Group

I'm interested in your feedback - please leave your comments.

To subscribe to the AI in Healthcare Milestones newsletter please click here.

To join the AI in Healthcare Milestones Group please click here.

Copyright ? 2023 Margaretta Colangelo. All Rights Reserved.

This article was written by?Margaretta Colangelo.?Margaretta is a leading AI analyst who tracks significant milestones in AI in healthcare. She consults with AI healthcare companies and writes about some of the companies she consults with. Margaretta serves on the advisory board of the AI Precision Health Institute at the University of Hawai?i?Cancer Center?@realmargaretta