Agenda

Market Trends

Automated Cancer Diagnosis

Future Plans

Our Team

Computer-Aided Diagonosis in Medical Imaging

Market Trends

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Market Trends

Out of  600 million annual GP visits about  half could also be solved by eVisit   

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Market Trends

The University of Pittsburgh Medical Center decreased study management costs by 43% or $14 million 

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Market Trends

Digital mammography is already better than film mammography in detecting early stage cancer 

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Market Trends

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Since the launch of Pocket Pathologist in 2013 high resolution digital pathology images  are available with just a smartphone 

Market Trends

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Collaboration between patients and experts will be a leading trend in the future*

* Pathology Informatics Summit 2015: Shaping the Future of Clinical Informatics Michael Riben, MD

Market Trends

Whole slide image sharing and analysis is one of the crucial challenges of today

  • 100 million eVisits in 2014
  • Global health care cloud computing market expected to grow from  $1.82 billion in 2011 to $6.79 billion by 2018  
  • Computer - aided detection market expected to hit $1.47 billion by 2020
  • Advanced medical imaging within reach of everyone
  • Patient-to-patient social media collaboration 
  • Whole slide digital pathology imaging 

Automated Cancer Diagnosis

Miccai Digital Pathology Challenge 2015  

Classification Algorithm

Oligodendroglioma 87%

Astrocytoma 13%

Diagnosis

Automated Cancer Diagnosis

Classification Algorithm

Divide in Frames

Frame Segmentation 

Classify each frame

Classify the sample

Extract frames of interest

Classify nuclei in a frame

Whole slide image is divided in small frames 

Automated Cancer Diagnosis

Segmentation algorithm is used to extract nuclei 

Divide in Frames

Frame Segmentation 

Classify each frame

Classify the sample

Extract frames of interest

Classify nuclei in a frame

Classification Algorithm

Automated Cancer Diagnosis

Frames are ranked based on the number of nuclei and the most dense frames are found

Divide in Frames

Frame Segmentation 

Classify each frame

Classify the sample

Extract frames of interest

Classify nuclei in a frame

Classification Algorithm

Automated Cancer Diagnosis

Each nucleus is classified with certain probability

Oligodendrocyte 

Astrocyte 

Divide in Frames

Frame Segmentation 

Classify each frame

Classify the sample

Extract frames of interest

Classify nuclei in a frame

Classification Algorithm

Automated Cancer Diagnosis

Based on the percentage of nuclei of certain type each frame is classified 

Oligodendrocyte 

Astrocyte 

34%

66%

Astrocytoma

Divide in Frames

Frame Segmentation 

Classify each frame

Classify the sample

Extract frames of interest

Classify nuclei in a frame

Classification Algorithm

Automated Cancer Diagnosis

Divide in Frames

Frame Segmentation 

Classify each frame

Classify the sample

Extract frames of interest

Classify nuclei in a frame

Astrocytoma Frames > T

Astrocytoma

If the amount of frames classified as certain cancer  type is over specified threshold the whole sample is classified as that type

Classification Algorithm

  • Classification on MRI images is a viable alternative for some/many tumors
  • Preliminary results of our MRI classification algorithm are very promising: 88% though more data needed
  • Incorporation of MRI can improve results

Automated Cancer Diagnosis

MRI based Classification

Future goals

  • Develop algorithms that classifiy other common types   of cancer 
  • Incorporate MRI to improve results even further
  • Combine classification algorithms with our other products to create a platform 

Other types of cancer can be classified

using similar approach

Sarcoma

Medulloblastoma

Gangloglioma

Future goals

Social Media Collaboration

Med Image Viewer

Computer Aided Diagnosis

Medical Organizations

Expert Practitioners

Patients

Platform

Future goals

  • Tool that enables Expert collaboration
  • Storage unit and analytical service for Medical Facilities
  • Place where Patients can quickly get a second opinion

Medical Facilities can:

  1. Store vast amounts of images
  2. View images from many access points simultaneously
  3. Improve doctor to doctor cooperation within the organization as well as outside
  4. Make use of computer aided intervention tools and share the results easily

Platform

Future goals

  • Tool that enables Expert collaboration
  • Storage unit and analytical service for Medical Facilities
  • Place where Patients can quickly get a second opinion

Experts can :

  1. View
  2. Share
  3. Analyse
  4. Exchange knowledge
  5. Compare diagnosis 

Platform

Future goals

  • Tool that enables Expert collaboration
  • Storage unit and analytical service for Medical Facilities
  • Place where Patients can quickly get a second opinion

Patients can :

  1. Get expert opinon
  2. Compare with algorithmic solutions
  3. See other cases
  4. Share experience with other patients 

Platform

Our Team

Grzegorz Żurek

R&D Stermedia

 

Jakub Czakon

R&D Stermedia

Piotr Giedziun

CTO Stermedia

Witold Dyrka

R&D Stermedia

Piotr Krajewski

CEO Stermedia

Stermedia Cancer Diagnosis

By Stermedia Sp. z o.o.

Stermedia Cancer Diagnosis

presentation for Medicover

  • 1,338