Skin Lesion Classification and Segmentation for Imbalanced Classes using Deep Learning

Size: px
Start display at page:

Download "Skin Lesion Classification and Segmentation for Imbalanced Classes using Deep Learning"

Transcription

1 Skin Lesion Classification and Segmentation for Imbalanced Classes using Deep Learning Mohammed K. Amro, Baljit Singh, and Avez Rizvi Abstract - This paper summarizes our work for ISIC 2018 challenge in Skin Lesion Analysis Towards Melanoma Detection [1]for both Task 1: Lesion Boundary Segmentation and Task 3: Disease Classification of ISIC We used a modified version of U-Net called dilated U-Net for Task 1 utilizing 4-Fold training method and testing time augmentation during prediction phase with final accuracy 0.77 Jaccard score on ISIC 2018 validation set. For Task 3 we build two approaches. The first approach is a one-step classifier between seven lesions type, while the second approach works into two steps, the first step by binary classifying the lesion either Nevus lesion (the Major class in the dataset) or non- Nevis (the remaining classes), and the second step to classify between the remaining six lesions type. The average accuracy on approach one was 89.8% and 88.8% for approach two and reached 91.8 % when utilizing both approaches at the same time. INTRODUCTION Skin cancer, aka Melanoma, is one of the deadliest occurring problems in today's world. Even though it is the least common, the disease is responsible for around 91,000 deaths this year until now [2]. Early detection of skin lesions can help in its treatment and improve life. Dermoscopy refers to the examination of the skin [3] under a microscope to point out skin abnormalities and then classify them. Dermoscopic images are free from any skin surface reflections. These enhanced images help the dermatologist to diagnose melanoma accurately. Deep CNN has been known for producing state of the art results when it comes to medical diagnosis. We participated in the ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection challenge to train models that could act as a screening process for dermatologist by segmenting and classifying skin lesions. ISIC 2018 is based on HAM10000 ( Human Against Machine with training images ) dataset [3] with images in the training set, 193 images in the validation set, and 1000 images for testing set. The dataset contains lesions form seven classes (Melanoma, Melanocytic nevus, Basal cell carcinoma, Actinic keratosis, Benign keratosis, Dermatofibroma, and Vascular Lesions). TASK GOAL TASK 1: LESION BOUNDARY SEGMENTATION Submit automated predictions of lesion segmentation boundaries within dermoscopic images. EVALUATION METRIC The prediction scores are measured using threshold Jaccard index metric which compares pixel-wise agreement between a predicted segmentation and its corresponding ground truth with zero scores if the Jaccard index is less than 0.65 and Jaccard index value, otherwise. Then the mean of all per-image scores is taken as the final metric value for the entire set.

2 DATASET PROCESSING The original HAM10000 dataset from ISIC 2018 contains 2594 lesions with their 2594 corresponding masks. As a first step, we reviewed the dataset and discovered some issues in the ground truth masks as shown in figure 1. So in order to clean the dataset and train our network on accurate data, we train a sample network on the whole training set without validation allowing the network to overfitting then we checked only the images with a low score and compared the related mask. As an output of this step, we removed 106 images from the dataset and developed the model using 2488 images only. NETWORK ARCHITECTURE Figure 1 Sample of some issues in ground truth masks In task 1 for segmentation, we used a modified version of U-net architecture called dilated U-Net. In traditional U- Net design, the network consists of three parts: Encoder network, Bottleneck layers, and Decoder network, in our solution we used 6 CONV layers in the bottleneck part. TRAINING STRATEGY We train our model using 4-Fold cross-validation with 1866 images for training and 622 images for validation using RMSprop optimizer with learning rate. Using the K-fold cross-validation allow the model to train on the whole dataset which reduces the effect of any error in the provided masks by getting four different model each one validated on a different set of images. PREDICTION STRATEGY During prediction phase and for each model of our final 4-Fold models we used Test Time Augmentation (TTA) by conduct four predictions for each image (the original image, horizontal flipped image, vertical flipped images, and horizontal and vertical flipped image) as shown in figure 2. Then we calculated the average, the minimum, and the maximum for each fold ending with twelve different predictions for each lesion. In our final submission, we used the best three performing predictions on challenge validation set which was 0.77 threshold Jaccard index to be used for final testing prediction.

3 Figure 2 Prediction using Testing Time Augmentation TASK 1 RESULTS Table 1 shows the best score for each fold during model training which tested against 622 images without applying the challenge threshold of 0.65 value. Table 1 Task 1: Segmentation Performance

4 TASK 3: LESION DIAGNOSIS Figure 3 Different Type of Lesions TASK GOAL The primary objective of this task is to classify dermoscopic images from the following seven lesion types: Melanoma (MEL). Melanocytic nevus (NV). Basal cell carcinoma (BCC). Actinic keratosis (AKIEC). Benign keratosis (BKL). Dermatofibroma (DF). Vascular lesion (VASC). EVALUATION METRIC Final predicted results are scored using a multi-class accuracy metric (balanced across categories). DATASET PROCESSING According to the HAM1000 paper, the training dataset has images of skin similar skin lesions taken from different camera angles. The percentage data distribution for each class is shown in table 2

5 Table 2 HAM10000 Data Distribution The imbalance between classes is apparent especially for Dermatofibroma and Vascular Lesions. Most of the lesions are belonging to Melanocytic nevus class. Out of that, there were a total of 5515 unique images and 4500 images with variants. The table below shows the distribution for each class. NETWORK ARCHITECTURE During our classification work, we used two models, Xception [5] and DenseNet121 [6] trained on the ImageNet Dataset. We used the pre-trained weights in addition to three CONV layers with 2048, 512, and 512 neurons and two Dropout layers with drop factor 0.5. TRAINING STRATEGY We implemented two approaches. First approach to building one step classifier between all seven classes in the same time (7C model), and the second approach is to build two steps classifier with a binary classifier between Melanocytic nevus (the dominant class) and all other six classes together (2C Model), then pass the result to another classifier to classifier between the remaining six classes( 6C Model). We split the data into 70% training set and 30% testing set, and due to the presence of a different number of variants, the data was manually split. In this manual split, with careful consideration, all the unique skin lesion images were put in the testing split and the rest, which includes images with two or more variants, were put in the training split to prevent the models to overfitting during training processes, we used Adam with learning rate with different image sizes of 224, 256, 299, and 512. As it can be observed from the above table, the data is largely imbalanced. The majority class, the NV class, is 66% of the entire dataset while there were also classes that made up only 1-3% of the dataset. To deal with this issue, the

6 technique of upsampling the data was employed. This technique involved duplicating the number of images in each class until the number is equal to the number of images in the majority class (NV in 7C and 2C models and MEL for 6C model). Both the training and validation split were upsampled to obtain a balanced set of images which allow the model to train on balanced class trying to optimize the average accuracy. PREDICTION STRATEGY During prediction, we used ensemble prediction from all generated models with the two networks (Xception and Dense121) and with different image sizes (224, 256, 299, and 512). TASK 3 RESULTS We tested out models using the selected testing set with 3005 images. For 7C classifier, the average accuracy was 84.2 % as per figure 4, while the for 2C classifier we achieved 95.16% accuracy as per figure 5, and for 6C classifier, we scored 87.69% as per figure 6. During prediction, we used ensemble prediction from all generated models with the two networks (Xception and Dense121) and with different image sizes (224, 256, 299, and 512). Figure 4 7C Model Confusion Matrix for Local Test Dataset

7 Figure 5 2C Model Confusion Matrix for Local Test Dataset Figure 6 6C Model Confusion Matrix for Local Test Dataset

8 Figure 7 2C + 6C Confusion Matrix for Test Dataset Figure 8 2,6C + 7C Confusion Matrix for Test Dataset For final submission to the challenge we submit the result of the 7C model as approach one, and the output of 2C and 6C as approached two and the average of both prediction as approach three. For ISIC 2018 validation set which consists of 193 images we scored 88.8% using 7C model and 89.8% using 2C+6C models, and 91.8% with the average between 7C and 2,6C.

9 RESULTS AND CONCLUSION For Task 1: Segmentation, our model score 0.77 threshold Jaccard index on ISIC Validation, set while For Task 3: Classification, our ensembles models scored 88.9%, 89.8%, and 91.8% respectively. The primary challenge for segmentation task was the noise in the ground truth masks which solved by cleaning the dataset before training, while the challenge in classification task was the imbalance between classes which solved by upsampling. REFERENCES [1] "ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection," [Online]. Available: [2] "Melanoma Stats, Facts, and Figures," [Online]. Available: [3] "Dermoscopy & Mole Scans in Perth and Regional WA," [Online]. Available: [4] Philipp Tschandl and Cliff Rosendahl and Harald Kittler, "The {HAM10000} dataset, a large collection of multi-source dermatoscopic," Sci. Data, vol , p. 5, [5] F. Chollet, "Xception: Deep Learning with Depthwise Separable Convolutions," CoRR, vol. abs/ , [6] Gao Huang and Zhuang Liu and Kilian Q. Weinberger, "Densely Connected Convolutional Networks," CoRR, 2016.

arxiv: v2 [cs.cv] 30 Sep 2018

arxiv: v2 [cs.cv] 30 Sep 2018 A Detection and Segmentation Architecture for Skin Lesion Segmentation on Dermoscopy Images arxiv:1809.03917v2 [cs.cv] 30 Sep 2018 Chengyao Qian, Ting Liu, Hao Jiang, Zhe Wang, Pengfei Wang, Mingxin Guan

More information

Skin Lesion Attribute Detection for ISIC Using Mask-RCNN

Skin Lesion Attribute Detection for ISIC Using Mask-RCNN Skin Lesion Attribute Detection for ISIC 2018 Using Mask-RCNN Asmaa Aljuhani and Abhishek Kumar Department of Computer Science, Ohio State University, Columbus, USA E-mail: Aljuhani.2@osu.edu; Kumar.717@osu.edu

More information

arxiv: v3 [cs.cv] 2 Jun 2017

arxiv: v3 [cs.cv] 2 Jun 2017 Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for the Diagnosis of Skin Lesions arxiv:1703.01976v3 [cs.cv] 2 Jun 2017 Iván González-Díaz Department of Signal Theory and

More information

Detection of Melanoma Skin Cancer using Segmentation and Classification Algorithm

Detection of Melanoma Skin Cancer using Segmentation and Classification Algorithm Detection of Melanoma Skin Cancer using Segmentation and Classification Algorithm Mrs. P. Jegadeeshwari Assistant professor/ece CK College of Engineering &Technology Abstract - Melanoma is the most dangerous

More information

Deep Residual Architecture for Skin Lesion Segmentation

Deep Residual Architecture for Skin Lesion Segmentation Deep Residual Architecture for Skin Lesion Segmentation Venkatesh G M 1, Naresh Y G 1, Suzanne Little 2, and Noel O Connor 2 1 Insight Centre for Data Analystics-DCU, Dublin, Ireland 2 Dublin City University,

More information

Medical images, segmentation and analysis

Medical images, segmentation and analysis Medical images, segmentation and analysis ImageLab group http://imagelab.ing.unimo.it Università degli Studi di Modena e Reggio Emilia Medical Images Macroscopic Dermoscopic ELM enhance the features of

More information

Skin Lesion Classification Using GLCM Based Feature Extraction in Probabilistic Neural Network

Skin Lesion Classification Using GLCM Based Feature Extraction in Probabilistic Neural Network Skin Lesion Classification Using GLCM Based Feature Extraction in Probabilistic Neural Network [1] M. Kavitha, [2] M. Bagya Lakshmi Abstract:-- Melanoma is the deadliest form of skin cancer. Incidence

More information

Detection of skin cancer

Detection of skin cancer Detection of skin cancer Jan Larsen Section for Cognitive Systems DTU Informatics isp.imm.dtu.dk 1 Digital economy Systems neuroscience Multimedia Mobile services Machine learning Signal processing Cognitive

More information

CS 523: Multimedia Systems

CS 523: Multimedia Systems CS 523: Multimedia Systems Angus Forbes creativecoding.evl.uic.edu/courses/cs523 Today - Convolutional Neural Networks - Work on Project 1 http://playground.tensorflow.org/ Convolutional Neural Networks

More information

Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers

Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers Jeremy Kawahara, and Ghassan Hamarneh Medical Image Analysis Lab, Simon Fraser University, Burnaby, Canada {jkawahar,hamarneh}@sfu.ca

More information

Kaggle Data Science Bowl 2017 Technical Report

Kaggle Data Science Bowl 2017 Technical Report Kaggle Data Science Bowl 2017 Technical Report qfpxfd Team May 11, 2017 1 Team Members Table 1: Team members Name E-Mail University Jia Ding dingjia@pku.edu.cn Peking University, Beijing, China Aoxue Li

More information

Learning to Segment Object Candidates

Learning to Segment Object Candidates Learning to Segment Object Candidates Pedro Pinheiro, Ronan Collobert and Piotr Dollar Presented by - Sivaraman, Kalpathy Sitaraman, M.S. in Computer Science, University of Virginia Facebook Artificial

More information

MRI Tumor Segmentation with Densely Connected 3D CNN. Lele Chen, Yue Wu, Adora M. DSouze, Anas Z. Abidin, Axel Wismüller, and Chenliang Xu

MRI Tumor Segmentation with Densely Connected 3D CNN. Lele Chen, Yue Wu, Adora M. DSouze, Anas Z. Abidin, Axel Wismüller, and Chenliang Xu 1 MRI Tumor Segmentation with Densely Connected 3D CNN Lele Chen, Yue Wu, Adora M. DSouze, Anas Z. Abidin, Axel Wismüller, and MRI Brain Tumor Segmentation 2 Image source: https://github.com/naldeborgh7575/brain_segmentation

More information

Skin Lesion Segmentation Using TDLS Algorithm and Pattern Identification

Skin Lesion Segmentation Using TDLS Algorithm and Pattern Identification Skin Lesion Segmentation Using TDLS Algorithm and Pattern Identification Anu Thankaraj M tech Student, Electronics and Communication Department, MG University, India Abstract: The rapid growing rate of

More information

A new interface for manual segmentation of dermoscopic images

A new interface for manual segmentation of dermoscopic images A new interface for manual segmentation of dermoscopic images P.M. Ferreira, T. Mendonça, P. Rocha Faculdade de Engenharia, Faculdade de Ciências, Universidade do Porto, Portugal J. Rozeira Hospital Pedro

More information

SSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang

SSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang SSD: Single Shot MultiBox Detector Author: Wei Liu et al. Presenter: Siyu Jiang Outline 1. Motivations 2. Contributions 3. Methodology 4. Experiments 5. Conclusions 6. Extensions Motivation Motivation

More information

Dynamic Routing Between Capsules

Dynamic Routing Between Capsules Report Explainable Machine Learning Dynamic Routing Between Capsules Author: Michael Dorkenwald Supervisor: Dr. Ullrich Köthe 28. Juni 2018 Inhaltsverzeichnis 1 Introduction 2 2 Motivation 2 3 CapusleNet

More information

DEFECT INSPECTION FROM SCRATCH TO PRODUCTION. Andrew Liu, Ryan Shen Deep Learning Solution Architect

DEFECT INSPECTION FROM SCRATCH TO PRODUCTION. Andrew Liu, Ryan Shen Deep Learning Solution Architect DEFECT INSPECTION FROM SCRATCH TO PRODUCTION Andrew Liu, Ryan Shen Deep Learning Solution Architect Defect Inspection and its challenges AGENDA NGC Docker images Model set up - Unet Data preparation -

More information

Computer aided diagnosis of melanoma using Computer Vision and Machine Learning

Computer aided diagnosis of melanoma using Computer Vision and Machine Learning Computer aided diagnosis of melanoma using Computer Vision and Machine Learning Jabeer Ahmed Biomedical Engineering Oregon Health & Science University This paper presents a computer-aided analysis of pigmented

More information

Data Augmentation for Skin Lesion Analysis

Data Augmentation for Skin Lesion Analysis Data Augmentation for Skin Lesion Analysis Fábio Perez 1, Cristina Vasconcelos 2, Sandra Avila 3, and Eduardo Valle 1 1 RECOD Lab, DCA, FEEC, University of Campinas (Unicamp), Brazil 2 Computer Science

More information

An annotation tool for dermoscopic image segmentation

An annotation tool for dermoscopic image segmentation An annotation tool for dermoscopic image segmentation P. M. Ferreira Faculdade de Engenharia, Universidade do Porto Porto, Portugal meb09015@fe.up.pt T. Mendonça Faculdade de Ciências, Universidade do

More information

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:

More information

CS249: ADVANCED DATA MINING

CS249: ADVANCED DATA MINING CS249: ADVANCED DATA MINING Classification Evaluation and Practical Issues Instructor: Yizhou Sun yzsun@cs.ucla.edu April 24, 2017 Homework 2 out Announcements Due May 3 rd (11:59pm) Course project proposal

More information

Global Pattern Analysis and Classification of Dermoscopic Images Using Textons

Global Pattern Analysis and Classification of Dermoscopic Images Using Textons Global Pattern Analysis and Classification of Dermoscopic Images Using Textons Maryam Sadeghi a,b,c,tim. K.Lee a,b,c,davidmclean b,c,harveylui b,c,m.stellaatkins a a Simon Fraser University, 8888 University

More information

Channel Locality Block: A Variant of Squeeze-and-Excitation

Channel Locality Block: A Variant of Squeeze-and-Excitation Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan

More information

Weighted Convolutional Neural Network. Ensemble.

Weighted Convolutional Neural Network. Ensemble. Weighted Convolutional Neural Network Ensemble Xavier Frazão and Luís A. Alexandre Dept. of Informatics, Univ. Beira Interior and Instituto de Telecomunicações Covilhã, Portugal xavierfrazao@gmail.com

More information

Using Machine Learning for Classification of Cancer Cells

Using Machine Learning for Classification of Cancer Cells Using Machine Learning for Classification of Cancer Cells Camille Biscarrat University of California, Berkeley I Introduction Cell screening is a commonly used technique in the development of new drugs.

More information

IN order to distinguish melanoma from benign lesions, dermatologists. Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features

IN order to distinguish melanoma from benign lesions, dermatologists. Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features TO APPEAR IN: JBHI - SPECIAL ISSUE ON SKIN LESION IMAGE ANALYSIS FOR MELANOMA DETECTION c 208 IEEE Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features Jeremy Kawahara and Ghassan

More information

Lung nodule detection by using. Deep Learning

Lung nodule detection by using. Deep Learning VRIJE UNIVERSITEIT AMSTERDAM RESEARCH PAPER Lung nodule detection by using Deep Learning Author: Thomas HEENEMAN Supervisor: Dr. Mark HOOGENDOORN Msc. Business Analytics Department of Mathematics Faculty

More information

An Algorithm for the Automatic Detection of Abnormal Mitotic Figure towards the Automated Diagnosis of Melanoma

An Algorithm for the Automatic Detection of Abnormal Mitotic Figure towards the Automated Diagnosis of Melanoma 21st International Congress on Modelling and Simulation, Gold Coast, Australia, 29 v to 4 Dec 2015 www.mssanz.org.au/modsim2015 An Algorithm for the Automatic Detection of Abnormal towards the Automated

More information

Lecture 7: Semantic Segmentation

Lecture 7: Semantic Segmentation Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr

More information

Early detection of malignant melanoma using random forest algorithm

Early detection of malignant melanoma using random forest algorithm Early detection of malignant melanoma using random forest algorithm S.Amutha 1 1 National engineering college, ECE, amuthashenbagaraj@email.com Mrs.R.Manjula Devi 2 2 National engineering college, ECE,

More information

Classification of objects from Video Data (Group 30)

Classification of objects from Video Data (Group 30) Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time

More information

Classification of WBC for Blood Cancer Diagnosis using Deep Convolutional Neural Networks

Classification of WBC for Blood Cancer Diagnosis using Deep Convolutional Neural Networks Classification of WBC for Blood Cancer Diagnosis using Deep Convolutional Neural Networks Dhvani Kansara 1, Shaunak Sompura 2, Saifil Momin 3, Mitchell D silva 4 Student 1,2,3, Assistant Professor 4, Department

More information

3D Convolutional Neural Networks for Landing Zone Detection from LiDAR

3D Convolutional Neural Networks for Landing Zone Detection from LiDAR 3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping

More information

Convolutional Neural Network based Medical Imaging Segmentation: Recent Progress and Challenges. Jiaxing Tan

Convolutional Neural Network based Medical Imaging Segmentation: Recent Progress and Challenges. Jiaxing Tan Convolutional Neural Network based Medical Imaging Segmentation: Recent Progress and Challenges Jiaxing Tan Road Map Introduction CNN based Models Encoder-Decoder based Models GAN Based Models Some Challenges

More information

ImageNet Classification with Deep Convolutional Neural Networks

ImageNet Classification with Deep Convolutional Neural Networks ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky Ilya Sutskever Geoffrey Hinton University of Toronto Canada Paper with same name to appear in NIPS 2012 Main idea Architecture

More information

AUTOMATED DETECTION AND CLASSIFICATION OF CANCER METASTASES IN WHOLE-SLIDE HISTOPATHOLOGY IMAGES USING DEEP LEARNING

AUTOMATED DETECTION AND CLASSIFICATION OF CANCER METASTASES IN WHOLE-SLIDE HISTOPATHOLOGY IMAGES USING DEEP LEARNING AUTOMATED DETECTION AND CLASSIFICATION OF CANCER METASTASES IN WHOLE-SLIDE HISTOPATHOLOGY IMAGES USING DEEP LEARNING F. Ghazvinian Zanjani, S. Zinger, P. H. N. de With Electrical Engineering Department,

More information

Enhanced K-mean Using Evolutionary Algorithms for Melanoma Detection and Segmentation in Skin Images

Enhanced K-mean Using Evolutionary Algorithms for Melanoma Detection and Segmentation in Skin Images Enhanced K-mean Using Evolutionary Algorithms for Melanoma Detection and Segmentation in Skin Images Asmaa Aljawawdeh Department of Computer Science The University of Jordan Amman, Jordan Esraa Imraiziq

More information

CS145: INTRODUCTION TO DATA MINING

CS145: INTRODUCTION TO DATA MINING CS145: INTRODUCTION TO DATA MINING 08: Classification Evaluation and Practical Issues Instructor: Yizhou Sun yzsun@cs.ucla.edu October 24, 2017 Learnt Prediction and Classification Methods Vector Data

More information

3D-CNN and SVM for Multi-Drug Resistance Detection

3D-CNN and SVM for Multi-Drug Resistance Detection 3D-CNN and SVM for Multi-Drug Resistance Detection Imane Allaouzi, Badr Benamrou, Mohamed Benamrou and Mohamed Ben Ahmed Abdelmalek Essaâdi University Faculty of Sciences and Techniques, Tangier, Morocco

More information

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models

One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models [Supplemental Materials] 1. Network Architecture b ref b ref +1 We now describe the architecture of the networks

More information

Available Online through

Available Online through Available Online through www.ijptonline.com ISSN: 0975-766X CODEN: IJPTFI Research Article ANALYSIS OF CT LIVER IMAGES FOR TUMOUR DIAGNOSIS BASED ON CLUSTERING TECHNIQUE AND TEXTURE FEATURES M.Krithika

More information

Hide-and-Seek: Forcing a network to be Meticulous for Weakly-supervised Object and Action Localization

Hide-and-Seek: Forcing a network to be Meticulous for Weakly-supervised Object and Action Localization Hide-and-Seek: Forcing a network to be Meticulous for Weakly-supervised Object and Action Localization Krishna Kumar Singh and Yong Jae Lee University of California, Davis ---- Paper Presentation Yixian

More information

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs Zhipeng Yan, Moyuan Huang, Hao Jiang 5/1/2017 1 Outline Background semantic segmentation Objective,

More information

A Multi-task Framework for Skin Lesion Detection and Segmentation

A Multi-task Framework for Skin Lesion Detection and Segmentation A Multi-task Framework for Skin Lesion Detection and Segmentation Sulaiman Vesal 1 ( ), Shreyas Malakarjun Patil 1,2 ( ), Nishant Ravikumar 1, and Andreas K. Maier 1 1 Pattern Recognition Lab, Friedrich-Alexander-Universität

More information

Dermoscopic Image Segmentation via Multi-Stage Fully Convolutional Networks

Dermoscopic Image Segmentation via Multi-Stage Fully Convolutional Networks > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 1 Dermoscopic Image Segmentation via Multi-Stage Fully Convolutional Networks Lei Bi, Student Member, IEEE, Jinman

More information

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University.

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University. Visualizing and Understanding Convolutional Networks Christopher Pennsylvania State University February 23, 2015 Some Slide Information taken from Pierre Sermanet (Google) presentation on and Computer

More information

LSTM: An Image Classification Model Based on Fashion-MNIST Dataset

LSTM: An Image Classification Model Based on Fashion-MNIST Dataset LSTM: An Image Classification Model Based on Fashion-MNIST Dataset Kexin Zhang, Research School of Computer Science, Australian National University Kexin Zhang, U6342657@anu.edu.au Abstract. The application

More information

Evaluation Methodology between Globalization and Localization Features Approaches for Skin Cancer Lesions Classification

Evaluation Methodology between Globalization and Localization Features Approaches for Skin Cancer Lesions Classification Journal of Physics: Conference Series PAPER OPEN ACCESS Evaluation Methodology between Globalization and Localization Features Approaches for Skin Cancer Lesions Classification To cite this article: H

More information

Towards Grading Gleason Score using Generically Trained Deep convolutional Neural Networks

Towards Grading Gleason Score using Generically Trained Deep convolutional Neural Networks Towards Grading Gleason Score using Generically Trained Deep convolutional Neural Networks Källén, Hanna; Molin, Jesper; Heyden, Anders; Lundström, Claes; Åström, Karl Published in: 2016 IEEE 13th International

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information

3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing

3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing 3 Object Detection BVM 2018 Tutorial: Advanced Deep Learning Methods Paul F. Jaeger, of Medical Image Computing What is object detection? classification segmentation obj. detection (1 label per pixel)

More information

Pattern recognition (4)

Pattern recognition (4) Pattern recognition (4) 1 Things we have discussed until now Statistical pattern recognition Building simple classifiers Supervised classification Minimum distance classifier Bayesian classifier (1D and

More information

Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma

Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma IET Research Journals Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma Nazneen N Sultana 1, Bappaditya Mandal 2 and N. B. Puhan 1 1 School of Electrical Sciences, Indian

More information

Pigment Network Detection in Dermoscopy Images using Deep Learning

Pigment Network Detection in Dermoscopy Images using Deep Learning Pigment Network Detection in Dermoscopy Images using Deep Learning Pedro Filipe Coimbra de Sousa Thesis to obtain the Master of Science Degree in Electrical and Computer Engineering Supervisors: Dr. Ana

More information

Dense Fully Convolutional Network for Skin Lesion Segmentation

Dense Fully Convolutional Network for Skin Lesion Segmentation Dense Fully Convolutional Network for Skin Lesion Segmentation Ebrahim Nasr-Esfahani a, Shima Rafiei a, Mohammad H. Jafari b, Nader Karimi a, James S. Wrobel c, Kayvan Najarian c,d,e, Shadrokh Samavi a,f,

More information

arxiv: v4 [cs.cv] 13 Dec 2018

arxiv: v4 [cs.cv] 13 Dec 2018 Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000. Digital Object Identifier arxiv:1803.11078v4 [cs.cv] 13 Dec 2018 Asymmetric Loss Functions and Deep Densely Connected Networks

More information

Detecting Bone Lesions in Multiple Myeloma Patients using Transfer Learning

Detecting Bone Lesions in Multiple Myeloma Patients using Transfer Learning Detecting Bone Lesions in Multiple Myeloma Patients using Transfer Learning Matthias Perkonigg 1, Johannes Hofmanninger 1, Björn Menze 2, Marc-André Weber 3, and Georg Langs 1 1 Computational Imaging Research

More information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 551 Applied Machine Learning Lecture 16: Deep Learning COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all

More information

Convolutional Neural Networks

Convolutional Neural Networks Lecturer: Barnabas Poczos Introduction to Machine Learning (Lecture Notes) Convolutional Neural Networks Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications.

More information

Supplementary A. Overview. C. Time and Space Complexity. B. Shape Retrieval. D. Permutation Invariant SOM. B.1. Dataset

Supplementary A. Overview. C. Time and Space Complexity. B. Shape Retrieval. D. Permutation Invariant SOM. B.1. Dataset Supplementary A. Overview This supplementary document provides more technical details and experimental results to the main paper. Shape retrieval experiments are demonstrated with ShapeNet Core55 dataset

More information

A FPGA IMPLEMENTATION ON SKIN CANCER DETECTION USING TDLS ALGORITHM

A FPGA IMPLEMENTATION ON SKIN CANCER DETECTION USING TDLS ALGORITHM A FPGA IMPLEMENTATION ON SKIN CANCER DETECTION USING TDLS ALGORITHM 1 KHUSHBU JARUFLA, 2 K. KRISHNA SREE 1,2 PG (VLSI) Department of Electronics and Communication Engineering, VNR Vignana Jyothi Institute

More information

ECE 5470 Classification, Machine Learning, and Neural Network Review

ECE 5470 Classification, Machine Learning, and Neural Network Review ECE 5470 Classification, Machine Learning, and Neural Network Review Due December 1. Solution set Instructions: These questions are to be answered on this document which should be submitted to blackboard

More information

Atlas Of Confocal Microscopy In Dermatology

Atlas Of Confocal Microscopy In Dermatology Atlas Of Confocal Microscopy In Dermatology If searched for a book Atlas of Confocal Microscopy in Dermatology in pdf form, then you've come to the loyal site. We furnish utter release of this book in

More information

COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL

COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL 1 COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL ADITYA SRIRAM DECEMBER 1 st, 2016 Aditya Sriram CS846 Software Engineering for Big Data December 1, 2016 TOPICS 2 Paper Synopsis Content-Based

More information

Cost-Sensitive Learning of Deep Feature Representations from Imbalanced Data

Cost-Sensitive Learning of Deep Feature Representations from Imbalanced Data Cost-Sensitive Learning of Deep Feature Representations from Imbalanced Data S. H. Khan, M. Bennamoun, F. Sohel and R. Togneri arxiv:58.34v [cs.cv] 8 Dec 5 Abstract Class imbalance is a common problem

More information

Boundary Tracing Algorithm for Automatic Skin Lesion Detection in Macroscopic Images

Boundary Tracing Algorithm for Automatic Skin Lesion Detection in Macroscopic Images African Journal of Basic & Applied Sciences 9 (3): 137-145, 2017 ISSN 2079-2034 IDOSI Publications, 2017 DOI: 10.5829/idosi.ajbas.2017.137.145 Boundary Tracing Algorithm for Automatic Skin Lesion Detection

More information

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech Convolutional Neural Networks Computer Vision Jia-Bin Huang, Virginia Tech Today s class Overview Convolutional Neural Network (CNN) Training CNN Understanding and Visualizing CNN Image Categorization:

More information

Universität Freiburg Lehrstuhl für Maschinelles Lernen und natürlichsprachliche Systeme. Machine Learning (SS2012)

Universität Freiburg Lehrstuhl für Maschinelles Lernen und natürlichsprachliche Systeme. Machine Learning (SS2012) Universität Freiburg Lehrstuhl für Maschinelles Lernen und natürlichsprachliche Systeme Machine Learning (SS2012) Prof. Dr. M. Riedmiller, Manuel Blum Exercise Sheet 5 Exercise 5.1: Spam Detection Suppose

More information

Plankton Classification Using ConvNets

Plankton Classification Using ConvNets Plankton Classification Using ConvNets Abhinav Rastogi Stanford University Stanford, CA arastogi@stanford.edu Haichuan Yu Stanford University Stanford, CA haichuan@stanford.edu Abstract We present the

More information

Fusion of Structural and Textural Features for Melanoma Recognition

Fusion of Structural and Textural Features for Melanoma Recognition 818 Fusion of Structural and Textural Features for Melanoma Recognition K. Ramya Thamizharasi 1, J. Ganesh 2 1 M. Tech. Student, Dept. of Information Technology, Dr. Sivanthi Aditanar College of Engg.,

More information

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR)

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 63 CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 4.1 INTRODUCTION The Semantic Region Based Image Retrieval (SRBIR) system automatically segments the dominant foreground region and retrieves

More information

Tri-modal Human Body Segmentation

Tri-modal Human Body Segmentation Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4

More information

Detection-aided medical image segmentation using deep learning

Detection-aided medical image segmentation using deep learning Detection-aided medical image segmentation using deep learning A Master s Thesis Submitted to the Faculty of the Escola Tècnica d Enginyeria de Telecomunicació de Barcelona Universitat Politècnica de Catalunya

More information

Boundary Tracing Algorithm for Automatic Skin Lesion Detection in Macroscopic Images

Boundary Tracing Algorithm for Automatic Skin Lesion Detection in Macroscopic Images World Engineering & Applied Sciences Journal 8 (1): 25-33, 2017 ISSN 2079-2204 IDOSI Publications, 2017 DOI: 10.5829/idosi.weasj.2017.25.33 Boundary Tracing Algorithm for Automatic Skin Lesion Detection

More information

Micro-scale Stereo Photogrammetry of Skin Lesions for Depth and Colour Classification

Micro-scale Stereo Photogrammetry of Skin Lesions for Depth and Colour Classification Micro-scale Stereo Photogrammetry of Skin Lesions for Depth and Colour Classification Tim Lukins Institute of Perception, Action and Behaviour 1 Introduction The classification of melanoma has traditionally

More information

Fully Convolutional Networks for Semantic Segmentation

Fully Convolutional Networks for Semantic Segmentation Fully Convolutional Networks for Semantic Segmentation Jonathan Long* Evan Shelhamer* Trevor Darrell UC Berkeley Chaim Ginzburg for Deep Learning seminar 1 Semantic Segmentation Define a pixel-wise labeling

More information

Lowering the Bar: Deep Learning for Side Channel Analysis. Guilherme Perin, Baris Ege, Jasper van December 4, 2018

Lowering the Bar: Deep Learning for Side Channel Analysis. Guilherme Perin, Baris Ege, Jasper van December 4, 2018 Lowering the Bar: Deep Learning for Side Channel Analysis Guilherme Perin, Baris Ege, Jasper van Woudenberg @jzvw December 4, 2018 1 Before Signal processing Leakage modeling 2 After 3 Helping security

More information

k-nn Disgnosing Breast Cancer

k-nn Disgnosing Breast Cancer k-nn Disgnosing Breast Cancer Prof. Eric A. Suess February 4, 2019 Example Breast cancer screening allows the disease to be diagnosed and treated prior to it causing noticeable symptoms. The process of

More information

Pull the Plug? Predicting If Computers or Humans Should Segment Images Supplementary Material

Pull the Plug? Predicting If Computers or Humans Should Segment Images Supplementary Material In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016. Pull the Plug? Predicting If Computers or Humans Should Segment Images Supplementary Material

More information

Lecture 6 K- Nearest Neighbors(KNN) And Predictive Accuracy

Lecture 6 K- Nearest Neighbors(KNN) And Predictive Accuracy Lecture 6 K- Nearest Neighbors(KNN) And Predictive Accuracy Machine Learning Dr.Ammar Mohammed Nearest Neighbors Set of Stored Cases Atr1... AtrN Class A Store the training samples Use training samples

More information

Analysis of classifier to improve Medical diagnosis for Breast Cancer Detection using Data Mining Techniques A.subasini 1

Analysis of classifier to improve Medical diagnosis for Breast Cancer Detection using Data Mining Techniques A.subasini 1 2117 Analysis of classifier to improve Medical diagnosis for Breast Cancer Detection using Data Mining Techniques A.subasini 1 1 Research Scholar, R.D.Govt college, Sivagangai Nirase Fathima abubacker

More information

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Tutorial on Keras CAP 6412 - ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Deep learning packages TensorFlow Google PyTorch Facebook AI research Keras Francois Chollet (now at Google) Chainer Company

More information

Apply Lightweight Deep Learning on Internet of Things for Low-Cost and Easy-To-Access Skin Cancer Detection

Apply Lightweight Deep Learning on Internet of Things for Low-Cost and Easy-To-Access Skin Cancer Detection Apply Lightweight Deep Learning on Internet of Things for Low-Cost and Easy-To-Access Skin Cancer Detection Pranjal Sahu a, Dantong Yu b, and Hong Qin a a StonyBrook University, NY, USA b New Jersey Institute

More information

Automatic nevi segmentation using adaptive mean shift filters and feature analysis

Automatic nevi segmentation using adaptive mean shift filters and feature analysis Automatic nevi segmentation using adaptive mean shift filters and feature analysis Michael A. King a, Tim K. Lee ab*, M. Stella Atkins a, David I. McLean c a Computing Science, Simon Fraser University,

More information

Detection of a Single Hand Shape in the Foreground of Still Images

Detection of a Single Hand Shape in the Foreground of Still Images CS229 Project Final Report Detection of a Single Hand Shape in the Foreground of Still Images Toan Tran (dtoan@stanford.edu) 1. Introduction This paper is about an image detection system that can detect

More information

Classification of Dermoscopic Skin Cancer Images Using Color and Hybrid Texture Features

Classification of Dermoscopic Skin Cancer Images Using Color and Hybrid Texture Features IJCSNS International Journal of Computer Science and Network Security, VOL.16 No.4, April 2016 135 Classification of Dermoscopic Skin Cancer Images Using Color and Hybrid Texture Features Ebtihal Almansour

More information

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Du-Yih Tsai, Masaru Sekiya and Yongbum Lee Department of Radiological Technology, School of Health Sciences, Faculty of

More information

arxiv: v1 [cs.cv] 31 Mar 2016

arxiv: v1 [cs.cv] 31 Mar 2016 Object Boundary Guided Semantic Segmentation Qin Huang, Chunyang Xia, Wenchao Zheng, Yuhang Song, Hao Xu and C.-C. Jay Kuo arxiv:1603.09742v1 [cs.cv] 31 Mar 2016 University of Southern California Abstract.

More information

Facial Key Points Detection using Deep Convolutional Neural Network - NaimishNet

Facial Key Points Detection using Deep Convolutional Neural Network - NaimishNet 1 Facial Key Points Detection using Deep Convolutional Neural Network - NaimishNet Naimish Agarwal, IIIT-Allahabad (irm2013013@iiita.ac.in) Artus Krohn-Grimberghe, University of Paderborn (artus@aisbi.de)

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Convolutional Neural Networks for Handwritten Digit Recognition Andreas Georgopoulos CID: 01281486 Abstract Abstract At this project three different Convolutional Neural Netwroks

More information

Recurrent neural networks for polyphonic sound event detection in real life recordings

Recurrent neural networks for polyphonic sound event detection in real life recordings Recurrent neural networks for polyphonic sound event detection in real life recordings Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen Tampere University of Technology giambattista.parascandolo@tut.fi

More information

CrescendoNet: A New Deep Convolutional Neural Network with Ensemble Behavior

CrescendoNet: A New Deep Convolutional Neural Network with Ensemble Behavior CrescendoNet: A New Deep Convolutional Neural Network with Ensemble Behavior Xiang Zhang, Nishant Vishwamitra, Hongxin Hu, Feng Luo School of Computing Clemson University xzhang7@clemson.edu Abstract We

More information

DEEP BLIND IMAGE QUALITY ASSESSMENT

DEEP BLIND IMAGE QUALITY ASSESSMENT DEEP BLIND IMAGE QUALITY ASSESSMENT BY LEARNING SENSITIVITY MAP Jongyoo Kim, Woojae Kim and Sanghoon Lee ICASSP 2018 Deep Learning and Convolutional Neural Networks (CNNs) SOTA in computer vision & image

More information

Large-scale Video Classification with Convolutional Neural Networks

Large-scale Video Classification with Convolutional Neural Networks Large-scale Video Classification with Convolutional Neural Networks Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-Fei Note: Slide content mostly from : Bay Area

More information

EP-CapsNet: Extending Capsule Network with Inception Module for Electrophoresis Binary Classification

EP-CapsNet: Extending Capsule Network with Inception Module for Electrophoresis Binary Classification EP-CapsNet: Extending Capsule Network with Inception Module for Electrophoresis Binary Classification Elizabeth Tobing, Ashraf Murtaza, Keejun Han, Mun Y. Yi Graduate School of Knowledge Service Engineering

More information

Automated Diagnosis of Vertebral Fractures using 2D and 3D Convolutional Networks

Automated Diagnosis of Vertebral Fractures using 2D and 3D Convolutional Networks Automated Diagnosis of Vertebral Fractures using 2D and 3D Convolutional Networks CS189 Final Project Naofumi Tomita Overview Automated diagnosis of osteoporosis-related vertebral fractures is a useful

More information

arxiv: v1 [cs.cv] 29 Nov 2017

arxiv: v1 [cs.cv] 29 Nov 2017 Detection-aided liver lesion segmentation using deep learning arxiv:1711.11069v1 [cs.cv] 29 Nov 2017 Míriam Bellver, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Xavier Giró-i-Nieto, Jordi Torres,, Luc Van

More information