Dantong Yu Associate Professor - PowerPoint Presentation

Slide1

Dantong Yu

Associate Professor

School

of Management

New Jersey Institute Of Technology

U

ncontrolled growth of abnormal skin cells

Often caused by ultraviolet radiation from sunshine or tanning beds

Potential Genetic basis for susceptibilityA major public health problem, with over 5 million newly diagnosed cases in the United States each year.

A skin examination by a dermatologist is the way to get a definitive diagnosis of skin cancer.

In many cases, the appearance alone is sufficient to make the diagnosis.

Melanoma is the deadliest form of skin cancer, responsible for over 9,000 deaths each year.

Malignant Samples

Benign Samples

We

propose a

smartphone and IoT devices

based skin cancer detection system that utilizes deep learning and low-cost camera to take the snapshots of suspected skin lesions and distinguish between malignant and benign melanoma skin images.

R.

A.

Novoa

et. al., Dermatologist-level classification of skin cancer with deep neural networks. Nature 542 (Feb. 2017).Y. Li, A. Esteva*, R.

Novoa, J. Ko, S. Thrun

, Skin Cancer Detection and Tracking using Data Synthesis and Deep Learning,  

NIPS Machine Learning for Healthcare Workshop 2016 Apple

iTune

and Google play

SkinVision

– Prevent,

Detect

and Track Skin Cancer

In our method we use a variant of deep learning models called Convolutional Neural Networks (CNN)

A typical CNN comprises of Convolutional, Pooling and Fully Connected layers

Color

(RGB)

image

One 4x4x3 filter

(cube)

The result of a

single filter

Another filter

A

first layer of

filtersA second layer of filters

An MNIST

image

A third layer of

filters

(treat

this as

1176-D

vector)

A

“fully connected”

layer

(as before)Softmax probability of label

Put Everything Together

Training a Deep learning model from scratch is a time and resource consuming task. Not sufficient labeled data.

To ameliorate this problem we adopt a Transfer Learning Based approach

We adopt Inception Net, a deep Learning model trained on ImageNet dataset to classify natural images as our base model

Training a model such as Inception Net can take even weeks on a high end GPU

Therefore we fine-tuned Inception Net for the task of skin lesion classification into Malignant and Benign Melanoma

Inception Net Architecture

The Raspberry Pi 3 is single-board, low end computing device which has a quad-core Cortex-A53 processor with 1 GB RAM

Can support camera as well as display devices

C

osts around $35

Supports Linux OS

Train the model in a cluster of Raspberry PI in a distributed manner

Used Tensorflow

framework for training

Between-graph replication and synchronous training for parameter updates.

E

xperiment done on the dataset provided by the ISIC for the 2017 challenge on melanoma detection and classification.

After the Transfer Learning step we were able to achieve an accuracy of 76% on a dataset of 2750 images with 521 malignant and 2229 benign images

Makes the process cheap and readily available to masses

No network connectivity required therefore can be deployed to remote and diverse regions without any problems

Can be re-trained as per requirement on a low end device

Movidius stick an another low end device specifically designed to speed up inference using a deep learning model

In our experiments speed up of about 5 times was observed

Training complex networks to improve accuracy.

Integrate domain-knowledge, such as

combining the “ABCDE” characteristics (Asymmetry , Border irregularity, Color, Diameter, Evolving size

), SPIE 2018 Medical Image

Enrich Dataset with GAN and

InfoGan

by embedding cancer sample into body and creating more realistic looking images and evolution history for training advanced network models.

An Android application classifying skin lesion into Malignant or Benign