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 susceptibility ID: 913423
Download Presentation The PPT/PDF document "Dantong Yu Associate Professor" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Dantong Yu
Associate Professor
School
of Management
New Jersey Institute Of Technology
Slide2U
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.
Slide3A 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.
Slide4Malignant Samples
Benign Samples
Slide5We
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.
Slide6R.
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
Slide7In 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
Slide8Color
(RGB)
image
One 4x4x3 filter
(cube)
The result of a
single filter
Another filter
Slide9A
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
Slide10Put Everything Together
Slide11Training 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
Slide12We 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
Slide13Slide14The 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
Slide15Train 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.
Slide16E
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
Slide17Makes 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
Slide18Movidius 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
Slide19Training 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.
Slide20An Android application classifying skin lesion into Malignant or Benign