Machine Learning Powered Medical Image Analytics: Tools Waiting for - - PowerPoint PPT Presentation

Machine Learning Powered Medical Image Analytics: Tools Waiting for Applications

George Washko MD Division of Pulmonary and Critical Care Medicine Brigham and Women’s Hospital

Disclosures

• Consultancies: Astra Zeneca, GlaxoSmithKline,

Boehringer Ingelheim, BTG, Genentech, Janssen, Philips, PulmonX, Novartis, Regeneron, Vertex

• Quantitative Imaging Solutions: Founder of a

consulting group and software development LLC for data management

• Grants: NIH, Boehringer Ingelheim, BTG

(EKOS), Janssen, Lung Biotechnology

• Spouse: Works for Biogen

Medical Applications of ML

Matching Engines Patients with similar profile Treatments with similar Cost-Benefit ratio Discovery Clinical Trials Hypothesis generation Proof of concept Precision Medicine Genomics Tailored therapies Mobile Apps Well-being Chronic disease management Predictive Modeling Risk stratification Healthcare Analytics Workflows Patient flow optimization Detect process inefficiencies

Virtual Assistant Smart telemedicine Doctor assistants

Diagnosis and Treatment Clinical Decision Support Symptoms analyzer Automated Radiology Treatment efficacy

ML Healthcare

ACIL Activities

COPDGene

• 10,000 subjects with HRCT
• Genetic epidemiology of

COPD

Framingham Heart Study (PRC)

• Longitudinal analysis of lung disease
• Population-based (3000 subjects)

NETT

• 1,200 with severe COPD
• Extensive phenotypic data

CARDIA

• Coronary Artery Risk Development

in Young Adults

• Population based study

CT Analysis Applied Chest Imaging Laboratory Clinical Data

Why Thoracic Imaging?

• Airways
• Vasculature
• Parenchyma
• Heart
• Muscle
• Bone
• Adipose tissue
• Bone marrow
• Asthma
• BOS
• Bronchiectasis
• CVD
• COPD
• ILD
• Metabolic

syndrome

• Lung Cancer
• PVD/VTE

What’s Possible with ML Powered Image Analytics?

Image navigation/curation Disease and comorbid condition

• Detection
• Stratification
• Prognostication

– Natural history – Therapeutic response (“patients like me”)

• Monitoring therapeutic response

Organ Detection

Onieva, SPIE, 2018

Quantification without Segmentation

Bone Mineral Density González G, SPIE 2018

Organ Segmentation

RV (blue) and LV (red)

Normal Elevated PA pressures with RV dilation Systolic dysfunction and dilation of the LV Acad Radiol. 2017;24(5):594-602.

Predicting Clinical Outcomes

Acad Radiol. 2017;24(5):594-602.

1157 HRCT of fibrotic lung disease Training: 929, Validation: 89, Test: 139 Comparison of algorithm performance to majority vote of 91 specialists

Walsh et al. Lancet Resp Med 2018.

Direct Outcome Estimation

16 64

Input: 512x512x1 C1: 128x128x16 C2: 32x32x32 C3: 8x8x64 FC1: 1024 FC2: {2,#classes,1}

32

Conv + MaxPooling Conv + MaxPooling Conv +MaxPooling

González, Am J Respir Crit Care Med, 2017

• Respiratory Events
• Hospitalization

Path Forward?

Opportunities for ML powered image analytics:

– Clinical care

• Bringing expertise to resource limited areas (ILD, Lung Cancer, etc)

– QI – Billing/resource allocation

• Challenges:

– Model Corruption and Regulatory Review – Who will champion the effort?

COPDGene

• 10K smokers with a range of lung

dysfunction

• Volumetric CT scan
• 60% NHW, 40% AA

Magic?

• OR 38.9!
• Ethnicity – How did it work?

– Well documented differences in body composition/fat free mass – Skeletal structure

COPDGene Data Revisited

NHW AA

Bias and Discrimination

• Black and Latinx patients had 9% and

17% lower rates of admission to the cardiology service

Acknowledgements

• Raul San Jose Estepar
• David Bermejo-Pelaez
• Ruben San Jose Estepar
• Sarah Gerard
• Monica Iturrioz
• Rafael Moreta
• Pietro Nardelli
• James Ross
• Gonzalo Vegas Sanchez-Ferrero
• German Gonzalez Serrano
• NHLBI
• DoD
• Boehringer Ingelheim
• Johnson and Johnson
• Lung Biotechnology
• BTG Therapeutics
• George Washko
• Samuel Ash
• Angela Blake
• Carolyn Come
• Alejandro Diaz
• Wocizch (Remy) Dolliver
• Stefanie Mason
• Carrie Pistenmaa
• Nick Rahaghi
• Andrew Tsao