Uploaded image for project: 'SystemDS'
  1. SystemDS
  2. SYSTEMDS-1185

SystemML Breast Cancer Project

    XMLWordPrintableJSON

Details

    • Epic
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • SystemML 1.3
    • None
    • None
    • SystemML Breast Cancer Project

    Description

      Predicting Breast Cancer Proliferation Scores with Apache Spark and Apache SystemML

      Overview

      The Tumor Proliferation Assessment Challenge 2016 (TUPAC16) is a "Grand Challenge" that was created for the 2016 Medical Image Computing and Computer Assisted Intervention (MICCAI 2016) conference. In this challenge, the goal is to develop state-of-the-art algorithms for automatic prediction of tumor proliferation scores from whole-slide histopathology images of breast tumors.

      Background

      Breast cancer is the leading cause of cancerous death in women in less-developed countries, and is the second leading cause of cancerous deaths in developed countries, accounting for 29% of all cancers in women within the U.S. [1]. Survival rates increase as early detection increases, giving incentive for pathologists and the medical world at large to develop improved methods for even earlier detection [2]. There are many forms of breast cancer including Ductal Carcinoma in Situ (DCIS), Invasive Ductal Carcinoma (IDC), Tubular Carcinoma of the Breast, Medullary Carcinoma of the Breast, Invasive Lobular Carcinoma, Inflammatory Breast Cancer and several others [3]. Within all of these forms of breast cancer, the rate in which breast cancer cells grow (proliferation), is a strong indicator of a patient’s prognosis. Although there are many means of determining the presence of breast cancer, tumor proliferation speed has been proven to help pathologists determine the treatment for the patient. The most common technique for determining the proliferation speed is through mitotic count (mitotic index) estimates, in which a pathologist counts the dividing cell nuclei in hematoxylin and eosin (H&E) stained slide preparations to determine the number of mitotic bodies. Given this, the pathologist produces a proliferation score of either 1, 2, or 3, ranging from better to worse prognosis [4]. Unfortunately, this approach is known to have reproducibility problems due to the variability in counting, as well as the difficulty in distinguishing between different grades.

      References:
      [1] http://emedicine.medscape.com/article/1947145-overview#a3
      [2] http://emedicine.medscape.com/article/1947145-overview#a7
      [3] http://emedicine.medscape.com/article/1954658-overview
      [4] http://emedicine.medscape.com/article/1947145-workup#c12

      Goal & Approach

      In an effort to automate the process of classification, this project aims to develop a large-scale deep learning approach for predicting tumor scores directly from the pixels of whole-slide histopathology images. Our proposed approach is based on a recent research paper from Stanford [1]. Starting with 500 extremely high-resolution tumor slide images with accompanying score labels, we aim to make use of Apache Spark in a preprocessing step to cut and filter the images into smaller square samples, generating 4.7 million samples for a total of ~7TB of data [2]. We then utilize Apache SystemML on top of Spark to develop and train a custom, large-scale, deep convolutional neural network on these samples, making use of the familiar linear algebra syntax and automatically-distributed execution of SystemML [3]. Our model takes as input the pixel values of the individual samples, and is trained to predict the correct tumor score classification for each one. In addition to distributed linear algebra, we aim to exploit task-parallelism via parallel for-loops for hyperparameter optimization, as well as hardware acceleration for faster training via a GPU-backed runtime. Ultimately, we aim to develop a model that is sufficiently stronger than existing approaches for the task of breast cancer tumor proliferation score classification.

      References:
      [1] https://web.stanford.edu/group/rubinlab/pubs/2243353.pdf
      [2] See Preprocessing.ipynb .
      [3] See MachineLearning.ipynb , softmax_clf.dml , and convnet.dml .

      Systems Tasks

      From a systems perspective, we aim to support multi-node, multi-GPU distributed SGD training to support large-scale experiments for the specific breast cancer use case.

      To achieve this goal, the following steps as necessary:

      1. Single-node, CPU mini-batch SGD training (1 mini-batch at a time).
      2. Single-node, single-GPU mini-batch SGD training (1 mini-batch at a time).
      3. Single-node, multi-GPU data-parallel mini-batch SGD training (`n` parallel mini-batches for `n` GPUs at a time).
      4. Multi-node, CPU data-parallel mini-batch SGD training (`n` parallel mini-batches for `n` parallel tasks at a time).
      5. Multi-node, single-GPU data-parallel mini-batch SGD training (`n` parallel mini-batches for `n` total GPUs across the cluster at a time).
      6. Multi-node, multi-GPU data-parallel mini-batch SGD training (`n` parallel mini-batches for `n` total GPUs across the cluster at a time).

      —

      Here is a list of past and present JIRA epics and issues that have blocked, or are currently blocking progress on the breast cancer project.

      Overall Deep Learning Epic

      Past

      Present

      Attachments

        1. approach.svg
          1.49 MB
          Mike Dusenberry

        Issue Links

          depends upon

          Epic - Created by Jira Software - do not edit or delete. Issue type for a big user story that needs to be broken down. SYSTEMDS-540 Deep Learning

          • Major - Major loss of function.
          • In Progress

          Epic - Created by Jira Software - do not edit or delete. Issue type for a big user story that needs to be broken down. SYSTEMDS-618 Deep Learning DML Library

          • Major - Major loss of function.
          • In Progress

          Bug - A problem which impairs or prevents the functions of the product. SYSTEMDS-1078 Ultra Sparse Invalid number of serialized non-zeros

          • Blocker - Blocks development and/or testing work, production could not run
          • Closed

          Bug - A problem which impairs or prevents the functions of the product. SYSTEMDS-1140 Sparse/Caching performance bugs related to deep learning scripts

          • Blocker - Blocks development and/or testing work, production could not run
          • Closed

          New Feature - A new feature of the product, which has yet to be developed. SYSTEMDS-1160 Enable Prefetching of Mini-Batches

          • Major - Major loss of function.
          • Open

          Improvement - An improvement or enhancement to an existing feature or task. SYSTEMDS-1159 Enable Remote Hyperparameter Tuning

          • Major - Major loss of function.
          • Open

          Task - A task that needs to be done. SYSTEMDS-686 Implement Spark instructions for convolution and pooling functions

          • Major - Major loss of function.
          • Open
          Is contained by

          Umbrella - An overarching type made of sub-tasks SYSTEMDS-1783 Application of SystemML in Science and Engineering

          • Major - Major loss of function.
          • Open
          is related to

          Improvement - An improvement or enhancement to an existing feature or task. SYSTEMDS-1554 IPA Scalar Transient Read Replacement

          • Major - Major loss of function.
          • Closed

          Improvement - An improvement or enhancement to an existing feature or task. SYSTEMDS-1561 Improve constant folding during compilation

          • Major - Major loss of function.
          • Closed

          Activity

            People

              dusenberrymw Mike Dusenberry
              dusenberrymw Mike Dusenberry
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: