SlideShare une entreprise Scribd logo
1  sur  43
Télécharger pour lire hors ligne
Journal Review
Unsupervised Deep Learning Applied to Breast Density Segmentation
and Mammographic Risk Scoring
Jinseob Kim
December 27, 2017
Jinseob Kim Journal Review December 27, 2017 1 / 43
1 Introduction
2 Method
3 Result
4 Discussion
Jinseob Kim Journal Review December 27, 2017 2 / 43
Introduction
Introduction
Jinseob Kim Journal Review December 27, 2017 3 / 43
Introduction
The goal of this paper
Automatically learns features for images, which in our case are
mammograms
CSAE: convolutional sparse autoencoder
Sparse autoencoder within a convolutional architecture
Unlabelled data로 추상적인 feature학습 + label정보 이용해 분류: 2
optimization process
많은 unlabbeled data 이용 가능.
한번에 다 하는 것보다 Fast and stable
Jinseob Kim Journal Review December 27, 2017 4 / 43
Introduction
2 tasks
1 The automated segmentation of percentage mammographic
density (PMD)
2 Characterize mammographic textural (MT) patterns with the goal
of predicting whether a woman will develop breast cancer.
Structural information of breast tissue
Heterogeneity > density.
Manual vs automated
Harder than MD scoring,
The label of interest (healthy vs. diseased) is defined per image and not
per pixel (e.g., fatty vs. dense)
Jinseob Kim Journal Review December 27, 2017 5 / 43
Introduction
Model 요약
1 Multiscale denoising autoencoders
2 Convolutional architecture
3 Novel sparsity term to control the model capacity
Jinseob Kim Journal Review December 27, 2017 6 / 43
Introduction
Figure 1: Multiscale
Jinseob Kim Journal Review December 27, 2017 7 / 43
Method
Method
Jinseob Kim Journal Review December 27, 2017 8 / 43
Method
3 part
1 Generating input data
Multiscale
2 Model representation
CNN
3 Parameter learning
Sparse autoencoder: novel sparsity regularizer
Jinseob Kim Journal Review December 27, 2017 9 / 43
Method
Problem
1 Entire image를 input으로 쓰긴 어렵다..computational burden
2 Downsampling은 안된다. Fine scale로만 확인할 수 있는 feature..
Learn a compact representation for local neighbors (or patches) from
the image
Jinseob Kim Journal Review December 27, 2017 10 / 43
Method
Figure 2: Patch
Jinseob Kim Journal Review December 27, 2017 11 / 43
Method
Patch creation
1 Image resize: 50 pixel/mm
2 Sampling 48000 patches from whole data.
Restricted to 24pixel × 24pixel size
3 Density scoring
10% from the background and the pectoral muscle
45% from the fatty breast tissue
45% from the dense breast tissue.
4 Texture scoring
50% from the breast tissue of controls
50% from the breast tissue of cancer cases.
Jinseob Kim Journal Review December 27, 2017 12 / 43
Method
m = 24, M = 1, 4 layer: Conv + Maxpool + Conv + Conv
c = 1 (흑백): 칼라면 3
If t = 1, 인접한 m × m. t = 4, 더 큰 smoothed 그림에서 every 8th
pixel 선택.
K = {50, (50), 50, 100}, kernal size= {7, 2, 5, 5}
Jinseob Kim Journal Review December 27, 2017 13 / 43
Method
Multiscale input data
Capture long range interactions
Gaussian scale space
I(u; σt) = [I ∗ Gσt ](u)
Gσt =
1
2πσt
e
−(x2+y2)
σt
σt =
t−1
i=0
δ2i
δ : downsampling factor=2
Jinseob Kim Journal Review December 27, 2017 14 / 43
Method
Jinseob Kim Journal Review December 27, 2017 15 / 43
Method
Jinseob Kim Journal Review December 27, 2017 16 / 43
Method
Jinseob Kim Journal Review December 27, 2017 17 / 43
Method
Jinseob Kim Journal Review December 27, 2017 18 / 43
Method
Jinseob Kim Journal Review December 27, 2017 19 / 43
Method
3 step from z(l)
to z(l+1)
1 Extract sub-patches (called local receptive fields)
2 Feature learning: Learn transformation parameters (or features) by
autoencoding the local receptive fields
3 Feature encoding: Transform all local receptive fields using the learned
features from step 2.
Last: Softmax classifier(multinomial logistic regression)
Jinseob Kim Journal Review December 27, 2017 20 / 43
Method
Sparse autoencoder
전체 architecture에서 training할수도 있지만..
Use unsupervised learning: autoencoder
Sparse
Enables to learn a sparse overcomplete representation
Input보다 size가 큰 feature
Jinseob Kim Journal Review December 27, 2017 21 / 43
Method
Standard autoencoder
https://wikidocs.net/3413
Jinseob Kim Journal Review December 27, 2017 22 / 43
Method
Tied weight autoencoder
Input(r):Subpatch(d × d of c channel)
Encoder: K개 feature로 표현 (K < cd2)
a ≡ g(r) = φ(Wr + b)
φ(x) = max(0, x)
Decoder: K개 feature를 이용해서 다시 Input을 표현.
f (a) = ψ(W a + ˜b)
Tied weight
Jinseob Kim Journal Review December 27, 2017 23 / 43
Method
Learned features as input of next layer
1 subpatch 당 K차원 feature
1 patch 당 (m − d + 1) × (m − d + 1) × K 차원의 feature
Next layer의 input
Jinseob Kim Journal Review December 27, 2017 24 / 43
Method
Estimation
Jinseob Kim Journal Review December 27, 2017 25 / 43
Method
Sparse overcomplete representations
N(Basis Vectors) > dimensions of the input
K > cd2
This study, K = {50, (50), 50, 100}, kernal size= {7, 2, 5, 5}
http://mlsp.cs.cmu.edu/courses/fall2013/lectures/slides/class15.
sparseovercomplete.pdf
Jinseob Kim Journal Review December 27, 2017 26 / 43
Method
Type of Sparsity
1 Population sparsity: 적은 갯수의 feature로 input 설명
Compact encoding per example
2 Lifetime sparsity: 한 feature가 여러 input을 설명하는데 쓰이지 않음.
Example-specific features
Jinseob Kim Journal Review December 27, 2017 27 / 43
Method
Estimation: Novel sparsity term
Jinseob Kim Journal Review December 27, 2017 28 / 43
Method
Jinseob Kim Journal Review December 27, 2017 29 / 43
Method
Jinseob Kim Journal Review December 27, 2017 30 / 43
Method
Experiments and Datasets
2 different tasks (MD, MT)
First segmented mammograms into background, pectoral muscle,
and breast tissue region
3 different mammographic datasets
Density Dataset(493 mammograms of healthy women): radiologist
Texture Dataset(MMHS): trained observer
Dutch Breast Cancer Screening Dataset: Software(Volpara)
Jinseob Kim Journal Review December 27, 2017 31 / 43
Result
Result
Jinseob Kim Journal Review December 27, 2017 32 / 43
Result
MD: Density datasets
Initial output: 해당 pixel(patch)이 dense tissue class일 확률
빠른 training을 위해 dense tissue data를 많이 포함: overestimation
가능성
dense 판단 기준 threshold를 0.5에서 0.75로 올림
Jinseob Kim Journal Review December 27, 2017 33 / 43
Result
Image-wise average of the Dice coefficients
2 · |A ∩ B|
|A| + |B|
A: automated, B: radiologisat
Jinseob Kim Journal Review December 27, 2017 34 / 43
Result
Jinseob Kim Journal Review December 27, 2017 35 / 43
Result
MD: Dutch Breast Cancer Screening Dataset
Density dataset으로 얻은 모형을 이 dataset에 적용
Jinseob Kim Journal Review December 27, 2017 36 / 43
Result
MT: Texture Dataset
Initial output: 해당 pixel(patch)이 cancer class일 확률.
MT score per image: Breast area에서 patch 500개 랜덤으로 뽑아
Score 구한 후 평균.
랜덤으로 해도 AUC차이 0.01미만임을 확인.
Jinseob Kim Journal Review December 27, 2017 37 / 43
Result
MT: Dutch Breast Cancer Screening Dataset
Jinseob Kim Journal Review December 27, 2017 38 / 43
Discussion
Discussion
Jinseob Kim Journal Review December 27, 2017 39 / 43
Discussion
Summary
Present an unsupervised feature learning method for breast density
segmentation and automatic texture scoring.
Can learn useful features
After adapting a small set of hyperparameters (feature scales, output
size, and label classes), the CSAE model achieved state-of-the-art
results on each of the tasks
Jinseob Kim Journal Review December 27, 2017 40 / 43
Discussion
CSAE vs Classical CNN
The usage of unsupervised pre-training
성능증가
Jinseob Kim Journal Review December 27, 2017 41 / 43
Discussion
Limitation: MT scoring
하나의 mammogram은 어떤 위치든 다 같은 label: Case vs Control
Assumed that texture changes are systemic and occur at many
locations in the tissue
Jinseob Kim Journal Review December 27, 2017 42 / 43
Discussion
Conclusion: Future idea
Image의 여러 부분 정보(patch)를 합쳐서 하나의 label로 매핑.
더 많은 데이터, 컴퓨팅 성능 필요
Easily adjusted to support 3D data
Jinseob Kim Journal Review December 27, 2017 43 / 43

Contenu connexe

Tendances

[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...
[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...
[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...Susang Kim
 
Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolutionPrudhvi Raj
 
THE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSION
THE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSIONTHE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSION
THE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSIONcscpconf
 
AutoEncoder&GAN Introduction
AutoEncoder&GAN IntroductionAutoEncoder&GAN Introduction
AutoEncoder&GAN Introductionpko89403
 
Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)
Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)
Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)Alex Kozlov
 

Tendances (7)

[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...
[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...
[Paper] GIRAFFE: Representing Scenes as Compositional Generative Neural Featu...
 
Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
 
Pixel Recursive Super Resolution. Google Brain
 Pixel Recursive Super Resolution.  Google Brain Pixel Recursive Super Resolution.  Google Brain
Pixel Recursive Super Resolution. Google Brain
 
THE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSION
THE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSIONTHE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSION
THE EVIDENCE THEORY FOR COLOR SATELLITE IMAGE COMPRESSION
 
AutoEncoder&GAN Introduction
AutoEncoder&GAN IntroductionAutoEncoder&GAN Introduction
AutoEncoder&GAN Introduction
 
Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)
Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)
Exact Inference in Bayesian Networks using MapReduce (Hadoop Summit 2010)
 
Progressive Texture
Progressive TextureProgressive Texture
Progressive Texture
 

Similaire à Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring

Classification of Breast Masses Using Convolutional Neural Network as Feature...
Classification of Breast Masses Using Convolutional Neural Network as Feature...Classification of Breast Masses Using Convolutional Neural Network as Feature...
Classification of Breast Masses Using Convolutional Neural Network as Feature...Pinaki Ranjan Sarkar
 
A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...IRJET Journal
 
Study of relevancy, diversity, and novelty in recommender systems
Study of relevancy, diversity, and novelty in recommender systemsStudy of relevancy, diversity, and novelty in recommender systems
Study of relevancy, diversity, and novelty in recommender systemsChemseddine Berbague
 
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...IRJET Journal
 
A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...
A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...
A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...Editor IJCATR
 
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATIONMAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATIONVLSICS Design
 
V.KARTHIKEYAN PUBLISHED ARTICLE
V.KARTHIKEYAN PUBLISHED ARTICLEV.KARTHIKEYAN PUBLISHED ARTICLE
V.KARTHIKEYAN PUBLISHED ARTICLEKARTHIKEYAN V
 
Brain Tumor Classification using Support Vector Machine
Brain Tumor Classification using Support Vector MachineBrain Tumor Classification using Support Vector Machine
Brain Tumor Classification using Support Vector MachineIRJET Journal
 
Wheat leaf disease detection using image processing
Wheat leaf disease detection using image processingWheat leaf disease detection using image processing
Wheat leaf disease detection using image processingIJLT EMAS
 
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...IJCSEIT Journal
 
Automatic Attendance System using Deep Learning Framework
Automatic Attendance System using Deep Learning FrameworkAutomatic Attendance System using Deep Learning Framework
Automatic Attendance System using Deep Learning FrameworkPinaki Ranjan Sarkar
 
(Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning (Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning Omkar Rane
 
Application of deep leaning to computer vision
Application of deep leaning to computer visionApplication of deep leaning to computer vision
Application of deep leaning to computer visionDjamal Abide, MSc
 
Soft Computing Techniques Based Image Classification using Support Vector Mac...
Soft Computing Techniques Based Image Classification using Support Vector Mac...Soft Computing Techniques Based Image Classification using Support Vector Mac...
Soft Computing Techniques Based Image Classification using Support Vector Mac...ijtsrd
 

Similaire à Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring (20)

Classification of Breast Masses Using Convolutional Neural Network as Feature...
Classification of Breast Masses Using Convolutional Neural Network as Feature...Classification of Breast Masses Using Convolutional Neural Network as Feature...
Classification of Breast Masses Using Convolutional Neural Network as Feature...
 
Second subjective assignment
Second  subjective assignmentSecond  subjective assignment
Second subjective assignment
 
A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...A Review on Color Recognition using Deep Learning and Different Image Segment...
A Review on Color Recognition using Deep Learning and Different Image Segment...
 
Study of relevancy, diversity, and novelty in recommender systems
Study of relevancy, diversity, and novelty in recommender systemsStudy of relevancy, diversity, and novelty in recommender systems
Study of relevancy, diversity, and novelty in recommender systems
 
D05222528
D05222528D05222528
D05222528
 
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
IRJET - Factors Affecting Deployment of Deep Learning based Face Recognition ...
 
A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...
A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...
A Novel DBSCAN Approach to Identify Microcalcifications in Cancer Images with...
 
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATIONMAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
MAGNETIC RESONANCE BRAIN IMAGE SEGMENTATION
 
V.KARTHIKEYAN PUBLISHED ARTICLE
V.KARTHIKEYAN PUBLISHED ARTICLEV.KARTHIKEYAN PUBLISHED ARTICLE
V.KARTHIKEYAN PUBLISHED ARTICLE
 
Brain Tumor Classification using Support Vector Machine
Brain Tumor Classification using Support Vector MachineBrain Tumor Classification using Support Vector Machine
Brain Tumor Classification using Support Vector Machine
 
Wheat leaf disease detection using image processing
Wheat leaf disease detection using image processingWheat leaf disease detection using image processing
Wheat leaf disease detection using image processing
 
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
FACE RECOGNITION USING DIFFERENT LOCAL FEATURES WITH DIFFERENT DISTANCE TECHN...
 
J25043046
J25043046J25043046
J25043046
 
J25043046
J25043046J25043046
J25043046
 
Automatic Attendance System using Deep Learning Framework
Automatic Attendance System using Deep Learning FrameworkAutomatic Attendance System using Deep Learning Framework
Automatic Attendance System using Deep Learning Framework
 
(Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning (Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning
 
Ag044216224
Ag044216224Ag044216224
Ag044216224
 
Application of deep leaning to computer vision
Application of deep leaning to computer visionApplication of deep leaning to computer vision
Application of deep leaning to computer vision
 
Soft Computing Techniques Based Image Classification using Support Vector Mac...
Soft Computing Techniques Based Image Classification using Support Vector Mac...Soft Computing Techniques Based Image Classification using Support Vector Mac...
Soft Computing Techniques Based Image Classification using Support Vector Mac...
 
H0114857
H0114857H0114857
H0114857
 

Plus de Jinseob Kim

Fst, selection index
Fst, selection indexFst, selection index
Fst, selection indexJinseob Kim
 
Why Does Deep and Cheap Learning Work So Well
Why Does Deep and Cheap Learning Work So WellWhy Does Deep and Cheap Learning Work So Well
Why Does Deep and Cheap Learning Work So WellJinseob Kim
 
괴델(Godel)의 불완전성 정리 증명의 이해.
괴델(Godel)의 불완전성 정리 증명의 이해.괴델(Godel)의 불완전성 정리 증명의 이해.
괴델(Godel)의 불완전성 정리 증명의 이해.Jinseob Kim
 
New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...
New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...
New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...Jinseob Kim
 
가설검정의 심리학
가설검정의 심리학 가설검정의 심리학
가설검정의 심리학 Jinseob Kim
 
Win Above Replacement in Sabermetrics
Win Above Replacement in SabermetricsWin Above Replacement in Sabermetrics
Win Above Replacement in SabermetricsJinseob Kim
 
Regression Basic : MLE
Regression  Basic : MLERegression  Basic : MLE
Regression Basic : MLEJinseob Kim
 
iHS calculation in R
iHS calculation in RiHS calculation in R
iHS calculation in RJinseob Kim
 
Selection index population_genetics
Selection index population_geneticsSelection index population_genetics
Selection index population_geneticsJinseob Kim
 
질병부담계산: Dismod mr gbd2010
질병부담계산: Dismod mr gbd2010질병부담계산: Dismod mr gbd2010
질병부담계산: Dismod mr gbd2010Jinseob Kim
 
Case-crossover study
Case-crossover studyCase-crossover study
Case-crossover studyJinseob Kim
 
Generalized Additive Model
Generalized Additive Model Generalized Additive Model
Generalized Additive Model Jinseob Kim
 
Deep Learning by JSKIM (Korean)
Deep Learning by JSKIM (Korean)Deep Learning by JSKIM (Korean)
Deep Learning by JSKIM (Korean)Jinseob Kim
 
Machine Learning Introduction
Machine Learning IntroductionMachine Learning Introduction
Machine Learning IntroductionJinseob Kim
 
Deep learning by JSKIM
Deep learning by JSKIMDeep learning by JSKIM
Deep learning by JSKIMJinseob Kim
 
Multilevel study
Multilevel study Multilevel study
Multilevel study Jinseob Kim
 

Plus de Jinseob Kim (20)

Fst, selection index
Fst, selection indexFst, selection index
Fst, selection index
 
Why Does Deep and Cheap Learning Work So Well
Why Does Deep and Cheap Learning Work So WellWhy Does Deep and Cheap Learning Work So Well
Why Does Deep and Cheap Learning Work So Well
 
괴델(Godel)의 불완전성 정리 증명의 이해.
괴델(Godel)의 불완전성 정리 증명의 이해.괴델(Godel)의 불완전성 정리 증명의 이해.
괴델(Godel)의 불완전성 정리 증명의 이해.
 
New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...
New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...
New Epidemiologic Measures in Multilevel Study: Median Risk Ratio, Median Haz...
 
가설검정의 심리학
가설검정의 심리학 가설검정의 심리학
가설검정의 심리학
 
Win Above Replacement in Sabermetrics
Win Above Replacement in SabermetricsWin Above Replacement in Sabermetrics
Win Above Replacement in Sabermetrics
 
Regression Basic : MLE
Regression  Basic : MLERegression  Basic : MLE
Regression Basic : MLE
 
iHS calculation in R
iHS calculation in RiHS calculation in R
iHS calculation in R
 
Fst in R
Fst in R Fst in R
Fst in R
 
Selection index population_genetics
Selection index population_geneticsSelection index population_genetics
Selection index population_genetics
 
질병부담계산: Dismod mr gbd2010
질병부담계산: Dismod mr gbd2010질병부담계산: Dismod mr gbd2010
질병부담계산: Dismod mr gbd2010
 
DALY & QALY
DALY & QALYDALY & QALY
DALY & QALY
 
Case-crossover study
Case-crossover studyCase-crossover study
Case-crossover study
 
Generalized Additive Model
Generalized Additive Model Generalized Additive Model
Generalized Additive Model
 
Deep Learning by JSKIM (Korean)
Deep Learning by JSKIM (Korean)Deep Learning by JSKIM (Korean)
Deep Learning by JSKIM (Korean)
 
Machine Learning Introduction
Machine Learning IntroductionMachine Learning Introduction
Machine Learning Introduction
 
Tree advanced
Tree advancedTree advanced
Tree advanced
 
Deep learning by JSKIM
Deep learning by JSKIMDeep learning by JSKIM
Deep learning by JSKIM
 
Main result
Main result Main result
Main result
 
Multilevel study
Multilevel study Multilevel study
Multilevel study
 

Dernier

whole genome sequencing new and its types including shortgun and clone by clone
whole genome sequencing new  and its types including shortgun and clone by clonewhole genome sequencing new  and its types including shortgun and clone by clone
whole genome sequencing new and its types including shortgun and clone by clonechaudhary charan shingh university
 
LAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary Microbiology
LAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary MicrobiologyLAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary Microbiology
LAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary MicrobiologyChayanika Das
 
Environmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptxEnvironmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptxpriyankatabhane
 
Timeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological CorrelationsTimeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological CorrelationsDanielBaumann11
 
FBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxFBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxPayal Shrivastava
 
cybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitationcybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitationSanghamitraMohapatra5
 
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep LearningCombining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learningvschiavoni
 
Interpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWSTInterpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWSTAlexander F. Mayer
 
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPRPirithiRaju
 
Telephone Traffic Engineering Online Lec
Telephone Traffic Engineering Online LecTelephone Traffic Engineering Online Lec
Telephone Traffic Engineering Online Lecfllcampolet
 
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer ZahanaEGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer ZahanaDr.Mahmoud Abbas
 
ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...
ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...
ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...Chayanika Das
 
Q4-Mod-1c-Quiz-Projectile-333344444.pptx
Q4-Mod-1c-Quiz-Projectile-333344444.pptxQ4-Mod-1c-Quiz-Projectile-333344444.pptx
Q4-Mod-1c-Quiz-Projectile-333344444.pptxtuking87
 
The Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and FunctionThe Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and FunctionJadeNovelo1
 
Total Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of CannabinoidsTotal Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of CannabinoidsMarkus Roggen
 
Immunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.pptImmunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.pptAmirRaziq1
 
complex analysis best book for solving questions.pdf
complex analysis best book for solving questions.pdfcomplex analysis best book for solving questions.pdf
complex analysis best book for solving questions.pdfSubhamKumar3239
 

Dernier (20)

whole genome sequencing new and its types including shortgun and clone by clone
whole genome sequencing new  and its types including shortgun and clone by clonewhole genome sequencing new  and its types including shortgun and clone by clone
whole genome sequencing new and its types including shortgun and clone by clone
 
LAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary Microbiology
LAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary MicrobiologyLAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary Microbiology
LAMP PCR.pptx by Dr. Chayanika Das, Ph.D, Veterinary Microbiology
 
Environmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptxEnvironmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptx
 
Timeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological CorrelationsTimeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
Timeless Cosmology: Towards a Geometric Origin of Cosmological Correlations
 
FBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxFBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptx
 
cybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitationcybrids.pptx production_advanges_limitation
cybrids.pptx production_advanges_limitation
 
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep LearningCombining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
 
Interpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWSTInterpreting SDSS extragalactic data in the era of JWST
Interpreting SDSS extragalactic data in the era of JWST
 
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
 
Telephone Traffic Engineering Online Lec
Telephone Traffic Engineering Online LecTelephone Traffic Engineering Online Lec
Telephone Traffic Engineering Online Lec
 
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer ZahanaEGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
EGYPTIAN IMPRINT IN SPAIN Lecture by Dr Abeer Zahana
 
ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...
ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...
ESSENTIAL FEATURES REQUIRED FOR ESTABLISHING FOUR TYPES OF BIOSAFETY LABORATO...
 
Let’s Say Someone Did Drop the Bomb. Then What?
Let’s Say Someone Did Drop the Bomb. Then What?Let’s Say Someone Did Drop the Bomb. Then What?
Let’s Say Someone Did Drop the Bomb. Then What?
 
Q4-Mod-1c-Quiz-Projectile-333344444.pptx
Q4-Mod-1c-Quiz-Projectile-333344444.pptxQ4-Mod-1c-Quiz-Projectile-333344444.pptx
Q4-Mod-1c-Quiz-Projectile-333344444.pptx
 
Interferons.pptx.
Interferons.pptx.Interferons.pptx.
Interferons.pptx.
 
The Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and FunctionThe Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and Function
 
Ultrastructure and functions of Chloroplast.pptx
Ultrastructure and functions of Chloroplast.pptxUltrastructure and functions of Chloroplast.pptx
Ultrastructure and functions of Chloroplast.pptx
 
Total Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of CannabinoidsTotal Legal: A “Joint” Journey into the Chemistry of Cannabinoids
Total Legal: A “Joint” Journey into the Chemistry of Cannabinoids
 
Immunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.pptImmunoblott technique for protein detection.ppt
Immunoblott technique for protein detection.ppt
 
complex analysis best book for solving questions.pdf
complex analysis best book for solving questions.pdfcomplex analysis best book for solving questions.pdf
complex analysis best book for solving questions.pdf
 

Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring

  • 1. Journal Review Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring Jinseob Kim December 27, 2017 Jinseob Kim Journal Review December 27, 2017 1 / 43
  • 2. 1 Introduction 2 Method 3 Result 4 Discussion Jinseob Kim Journal Review December 27, 2017 2 / 43
  • 3. Introduction Introduction Jinseob Kim Journal Review December 27, 2017 3 / 43
  • 4. Introduction The goal of this paper Automatically learns features for images, which in our case are mammograms CSAE: convolutional sparse autoencoder Sparse autoencoder within a convolutional architecture Unlabelled data로 추상적인 feature학습 + label정보 이용해 분류: 2 optimization process 많은 unlabbeled data 이용 가능. 한번에 다 하는 것보다 Fast and stable Jinseob Kim Journal Review December 27, 2017 4 / 43
  • 5. Introduction 2 tasks 1 The automated segmentation of percentage mammographic density (PMD) 2 Characterize mammographic textural (MT) patterns with the goal of predicting whether a woman will develop breast cancer. Structural information of breast tissue Heterogeneity > density. Manual vs automated Harder than MD scoring, The label of interest (healthy vs. diseased) is defined per image and not per pixel (e.g., fatty vs. dense) Jinseob Kim Journal Review December 27, 2017 5 / 43
  • 6. Introduction Model 요약 1 Multiscale denoising autoencoders 2 Convolutional architecture 3 Novel sparsity term to control the model capacity Jinseob Kim Journal Review December 27, 2017 6 / 43
  • 7. Introduction Figure 1: Multiscale Jinseob Kim Journal Review December 27, 2017 7 / 43
  • 8. Method Method Jinseob Kim Journal Review December 27, 2017 8 / 43
  • 9. Method 3 part 1 Generating input data Multiscale 2 Model representation CNN 3 Parameter learning Sparse autoencoder: novel sparsity regularizer Jinseob Kim Journal Review December 27, 2017 9 / 43
  • 10. Method Problem 1 Entire image를 input으로 쓰긴 어렵다..computational burden 2 Downsampling은 안된다. Fine scale로만 확인할 수 있는 feature.. Learn a compact representation for local neighbors (or patches) from the image Jinseob Kim Journal Review December 27, 2017 10 / 43
  • 11. Method Figure 2: Patch Jinseob Kim Journal Review December 27, 2017 11 / 43
  • 12. Method Patch creation 1 Image resize: 50 pixel/mm 2 Sampling 48000 patches from whole data. Restricted to 24pixel × 24pixel size 3 Density scoring 10% from the background and the pectoral muscle 45% from the fatty breast tissue 45% from the dense breast tissue. 4 Texture scoring 50% from the breast tissue of controls 50% from the breast tissue of cancer cases. Jinseob Kim Journal Review December 27, 2017 12 / 43
  • 13. Method m = 24, M = 1, 4 layer: Conv + Maxpool + Conv + Conv c = 1 (흑백): 칼라면 3 If t = 1, 인접한 m × m. t = 4, 더 큰 smoothed 그림에서 every 8th pixel 선택. K = {50, (50), 50, 100}, kernal size= {7, 2, 5, 5} Jinseob Kim Journal Review December 27, 2017 13 / 43
  • 14. Method Multiscale input data Capture long range interactions Gaussian scale space I(u; σt) = [I ∗ Gσt ](u) Gσt = 1 2πσt e −(x2+y2) σt σt = t−1 i=0 δ2i δ : downsampling factor=2 Jinseob Kim Journal Review December 27, 2017 14 / 43
  • 15. Method Jinseob Kim Journal Review December 27, 2017 15 / 43
  • 16. Method Jinseob Kim Journal Review December 27, 2017 16 / 43
  • 17. Method Jinseob Kim Journal Review December 27, 2017 17 / 43
  • 18. Method Jinseob Kim Journal Review December 27, 2017 18 / 43
  • 19. Method Jinseob Kim Journal Review December 27, 2017 19 / 43
  • 20. Method 3 step from z(l) to z(l+1) 1 Extract sub-patches (called local receptive fields) 2 Feature learning: Learn transformation parameters (or features) by autoencoding the local receptive fields 3 Feature encoding: Transform all local receptive fields using the learned features from step 2. Last: Softmax classifier(multinomial logistic regression) Jinseob Kim Journal Review December 27, 2017 20 / 43
  • 21. Method Sparse autoencoder 전체 architecture에서 training할수도 있지만.. Use unsupervised learning: autoencoder Sparse Enables to learn a sparse overcomplete representation Input보다 size가 큰 feature Jinseob Kim Journal Review December 27, 2017 21 / 43
  • 22. Method Standard autoencoder https://wikidocs.net/3413 Jinseob Kim Journal Review December 27, 2017 22 / 43
  • 23. Method Tied weight autoencoder Input(r):Subpatch(d × d of c channel) Encoder: K개 feature로 표현 (K < cd2) a ≡ g(r) = φ(Wr + b) φ(x) = max(0, x) Decoder: K개 feature를 이용해서 다시 Input을 표현. f (a) = ψ(W a + ˜b) Tied weight Jinseob Kim Journal Review December 27, 2017 23 / 43
  • 24. Method Learned features as input of next layer 1 subpatch 당 K차원 feature 1 patch 당 (m − d + 1) × (m − d + 1) × K 차원의 feature Next layer의 input Jinseob Kim Journal Review December 27, 2017 24 / 43
  • 25. Method Estimation Jinseob Kim Journal Review December 27, 2017 25 / 43
  • 26. Method Sparse overcomplete representations N(Basis Vectors) > dimensions of the input K > cd2 This study, K = {50, (50), 50, 100}, kernal size= {7, 2, 5, 5} http://mlsp.cs.cmu.edu/courses/fall2013/lectures/slides/class15. sparseovercomplete.pdf Jinseob Kim Journal Review December 27, 2017 26 / 43
  • 27. Method Type of Sparsity 1 Population sparsity: 적은 갯수의 feature로 input 설명 Compact encoding per example 2 Lifetime sparsity: 한 feature가 여러 input을 설명하는데 쓰이지 않음. Example-specific features Jinseob Kim Journal Review December 27, 2017 27 / 43
  • 28. Method Estimation: Novel sparsity term Jinseob Kim Journal Review December 27, 2017 28 / 43
  • 29. Method Jinseob Kim Journal Review December 27, 2017 29 / 43
  • 30. Method Jinseob Kim Journal Review December 27, 2017 30 / 43
  • 31. Method Experiments and Datasets 2 different tasks (MD, MT) First segmented mammograms into background, pectoral muscle, and breast tissue region 3 different mammographic datasets Density Dataset(493 mammograms of healthy women): radiologist Texture Dataset(MMHS): trained observer Dutch Breast Cancer Screening Dataset: Software(Volpara) Jinseob Kim Journal Review December 27, 2017 31 / 43
  • 32. Result Result Jinseob Kim Journal Review December 27, 2017 32 / 43
  • 33. Result MD: Density datasets Initial output: 해당 pixel(patch)이 dense tissue class일 확률 빠른 training을 위해 dense tissue data를 많이 포함: overestimation 가능성 dense 판단 기준 threshold를 0.5에서 0.75로 올림 Jinseob Kim Journal Review December 27, 2017 33 / 43
  • 34. Result Image-wise average of the Dice coefficients 2 · |A ∩ B| |A| + |B| A: automated, B: radiologisat Jinseob Kim Journal Review December 27, 2017 34 / 43
  • 35. Result Jinseob Kim Journal Review December 27, 2017 35 / 43
  • 36. Result MD: Dutch Breast Cancer Screening Dataset Density dataset으로 얻은 모형을 이 dataset에 적용 Jinseob Kim Journal Review December 27, 2017 36 / 43
  • 37. Result MT: Texture Dataset Initial output: 해당 pixel(patch)이 cancer class일 확률. MT score per image: Breast area에서 patch 500개 랜덤으로 뽑아 Score 구한 후 평균. 랜덤으로 해도 AUC차이 0.01미만임을 확인. Jinseob Kim Journal Review December 27, 2017 37 / 43
  • 38. Result MT: Dutch Breast Cancer Screening Dataset Jinseob Kim Journal Review December 27, 2017 38 / 43
  • 39. Discussion Discussion Jinseob Kim Journal Review December 27, 2017 39 / 43
  • 40. Discussion Summary Present an unsupervised feature learning method for breast density segmentation and automatic texture scoring. Can learn useful features After adapting a small set of hyperparameters (feature scales, output size, and label classes), the CSAE model achieved state-of-the-art results on each of the tasks Jinseob Kim Journal Review December 27, 2017 40 / 43
  • 41. Discussion CSAE vs Classical CNN The usage of unsupervised pre-training 성능증가 Jinseob Kim Journal Review December 27, 2017 41 / 43
  • 42. Discussion Limitation: MT scoring 하나의 mammogram은 어떤 위치든 다 같은 label: Case vs Control Assumed that texture changes are systemic and occur at many locations in the tissue Jinseob Kim Journal Review December 27, 2017 42 / 43
  • 43. Discussion Conclusion: Future idea Image의 여러 부분 정보(patch)를 합쳐서 하나의 label로 매핑. 더 많은 데이터, 컴퓨팅 성능 필요 Easily adjusted to support 3D data Jinseob Kim Journal Review December 27, 2017 43 / 43