Abhishek Kumar
Deep Learning Scientist(Engineer)

Predible Health

NEURAL NETWORK

NN as a Brain analogy

Image as an Array

Convolutional Neural Network

A brief idea of how a CNN works

Here are the components of a CNN model

  1. Convolution
  2. Non Linearity (in this example Relu)
  3. Pooling or Subsampling
  4. Classification

A CNN MODEL

Layer 1 and 2 (the initial ones)

CNN VISIUALIZATION

Layer 3 (the intermediate ones)

CNN VISIUALIZATION

Layer 4 and 5 (the last ones)

CNN VISIUALIZATION

Now comes transfer of knowledge/features

Introduction to Inception and my Hypothesis

Inception: The lifeline of Google (model A, the general features)

A model with specific features (model B, the intermediate)

Model C, very specific to our Dataset

A small intro to inception

  • A 152 layer network
  • Trained on imagenet (1000 classes)
  • Conventional CNN architecture with 1*1 window size

Results of A + B

  • B3B – the first 3 layers are copied from baseB and frozen. The remaining five higher layers are initialized randomly.

  • A3B – the first 3 layers are copied from baseA and frozen. The remaining five layers are initialized randomly

  • B3B+, like B3B but the first three layers are subsequently fine-tuned during training.

  • A3B+, like A3B but the first three layers are subsequently fine-tuned during training.

Architecture

Results of A + B

  • For a small network due to dependency of the layers, it performs very poorly
  • Consider VGG16, the model size is reduced by almost 300% with only 2-3% compromise in accuracy
  • Fine tunning is 2-10 times as faster as normal transfer Learning

Results of A + B + C

MEDICAL IMAGING

Liver Product

  • Full Owndership of Vessels and Liver
  • State-Of-The-Art Liver Segmentation (0.95 dice)
  • 2 Patent for Vessel Segmentation and Classification

Prostate

  • Prostate Gland Segmentation
  • Prostate Gland classification in PZ and CG
  • Nodule detection and Segmentation

Lung Cancer

  • Nodule detection (ongoing project........)

LIVER PRODUCT

My Proudest work, but why???

 

  • No prior work on Vessel Segmentation using Deep Learning (Only classicial Image Processing tech)
  • Almost no good papers talking about vessel classification into Hepatic and Portal veins (probably a very complex problem to solve)
  • PreProcessing and PostProcessing made the outputs very good

Let's have a look before getting into details

Forus Health

By Abhishek Kumar Tiwari

Forus Health

  • 819