Deep Learning for Distinguishing Morphological Features of Acute

  • Slides: 10
Download presentation
Deep Learning for Distinguishing Morphological Features of Acute Promyelocytic Leukemia John-William Sidhom, MD/Ph. D

Deep Learning for Distinguishing Morphological Features of Acute Promyelocytic Leukemia John-William Sidhom, MD/Ph. D Candidate ’ 21 Department of Biomedical Engineering Johns Hopkins University School of Medicine Ingharan J Siddarthan, Bo-Shiun Lai, Adam Luo, Bryan Hambley, Jennifer Bynum, Amy S. Duffield, Michael B. Streiff, Alison R. Moliterno, Philip H. Imus, Christian B. Gocke, Lukasz P. Gondek, Amy E. De. Zern, Alexander S Baras, Thomas S. Kickler, Mark Levis, Eugene Shenderov December 6, 2020 Sidney Kimmel Comprehensive Cancer Center Johns Hopkins University

Disclosure I have no financial disclosure or conflicts of interest with the presented material

Disclosure I have no financial disclosure or conflicts of interest with the presented material in this presentation. 2

APL • Acute Promyelocytic Leukemia (APL) is subtype of Acute Myeloid Leukemia (AML). •

APL • Acute Promyelocytic Leukemia (APL) is subtype of Acute Myeloid Leukemia (AML). • Defined by translocation - t(15; 17) • Distinguished clinically by rapidly progressive and fatal course, often from disseminated intravascular coagulation (DIC). 3

Problem • Acute nature requires prompt recognition and initiation of life-saving All-transretinoic Acid (ATRA).

Problem • Acute nature requires prompt recognition and initiation of life-saving All-transretinoic Acid (ATRA). • However, gold standard genetic tests (PCR, FISH) can often take days to confirm the diagnosis. • Therapy is often initiated on clinical suspicion. – Aided by visualization of peripheral smear looking 4 for pathognomonic Auer rods.

Hypothesis Deep learning model could more accurately and quickly diagnose APL from peripheral smear,

Hypothesis Deep learning model could more accurately and quickly diagnose APL from peripheral smear, providing clinicians the diagnostic information needed to quickly identify and treat patients with APL. 5

Patient Population • Identified via retrospective chart review from a list of confirmed FISH

Patient Population • Identified via retrospective chart review from a list of confirmed FISH t(15; 17)-positive (n = 34) and -negative (n = 72) patients presenting at The Johns Hopkins Hospital (JHH). • Inclusion criteria included new disease diagnosis, no prior treatment, and availability of peripheral blood smear image uploaded to Cella. Vision. • Patients were separated into a discovery cohort presenting prior to 1/2019 (APL, n = 22; AML, n=60) and a validation cohort presenting on or after 1/2019 (APL, n = 12; AML, n = 12). 6

Deep Learning Model 7

Deep Learning Model 7

Performance • 10 academic oncologists were provided peripheral smears from the validation cohort and

Performance • 10 academic oncologists were provided peripheral smears from the validation cohort and asked to identify APL patients. • Benchmarked against deep learning model as well as proportion of promyelocytes as determined by Cellavision algorithm. + Oncologists 8

Explainable AI 9

Explainable AI 9

Conclusion • Deep learning model capable of rapid and accurate diagnosis of APL from

Conclusion • Deep learning model capable of rapid and accurate diagnosis of APL from universally available peripheral smears. • Explainable artificial intelligence is provided for biological insights to facilitate clinical management and reveal morphological concepts previously unappreciated in APL. • The deep learning framework we have delineated is applicable to any diagnostic pipeline that can leverage a peripheral blood smear, potentially allowing for efficient diagnosis and early treatment of disease. 10

Morphological Stylistics Morphological stylistics deals with morphological expressiveMorphological Stylistics Morphological stylistics deals with morphological expressive
Morphological Filtering Spatial Filtering Morphological Filtering Morphological operatorsMorphological Filtering Spatial Filtering Morphological Filtering Morphological operators
Morphological Change Morphological Change By morphological change weMorphological Change Morphological Change By morphological change we
Deep Levels Deep Levels Deep Centers Deep TrapsDeep Levels Deep Levels Deep Centers Deep Traps
Deep Deep deep Deep down in my soulDeep Deep deep Deep down in my soul
Analogizing and Distinguishing Fact Patterns Distinguishing Hazelwood fromAnalogizing and Distinguishing Fact Patterns Distinguishing Hazelwood from
DISTINGUISHING FEATURES OF GLOBALISATION Describe the key featuresDISTINGUISHING FEATURES OF GLOBALISATION Describe the key features
Deep Thoughts on Deep Learning Mark Stamp DeepDeep Thoughts on Deep Learning Mark Stamp Deep
Morphology Morphological Processes and Morphological Processing John BarndenMorphology Morphological Processes and Morphological Processing John Barnden