Chuanbo Wang, Ye Guo, Zeyun Yu

Slides:



Advertisements
Similar presentations
A brief review of non-neural-network approaches to deep learning
Advertisements

NA-MIC National Alliance for Medical Image Computing Connected Threshold Image Filter Salma Bengali, Alan Morris, Josh Cates, Rob.
NA-MIC National Alliance for Medical Image Computing CARMA Inhomogeneity Correction Filter Alan Morris, Eugene Kholmovski, Josh Cates,
Flash Animation Using Linear Transformations By Kevin Hunter Kevin Hunter Marcus Yu Marcus Yu.
Intelligent Systems Lab. Recognizing Human actions from Still Images with Latent Poses Authors: Weilong Yang, Yang Wang, and Greg Mori Simon Fraser University,
A Framework for Photo-Quality Assessment and Enhancement based on Visual Aesthetics Subhabrata Bhattacharya Rahul Sukthankar Mubarak Shah.
Modeling 3D Deformable and Articulated Shapes Yu Chen, Tae-Kyun Kim, Roberto Cipolla Department of Engineering University of Cambridge.
Numbers
Lecture#6: segmentation Anat Levin Introduction to Computer Vision Class Fall 2009 Department of Computer Science and App math, Weizmann Institute of Science.
Li Wang, Yaozong Gao, Feng Shi, Gang Li, Dinggang Shen
Reihaneh Rostami, Zeyun Yu Computer Science Department University of Wisconsin – Milwaukee Objective -3D Point Matching is the process of finding a point.
Urban Building Damage Detection From Very High Resolution Imagery By One-Class SVM and Shadow Information Peijun Li, Benqin Song and Haiqing Xu Peking.
A Face processing system Based on Committee Machine: The Approach and Experimental Results Presented by: Harvest Jang 29 Jan 2003.
Tracking Turbulent 3D Features Lu Zhang Nov. 10, 2005.
A Multiresolution Symbolic Representation of Time Series Vasileios Megalooikonomou Qiang Wang Guo Li Christos Faloutsos Presented by Rui Li.
Unsupervised Visual Representation Learning by Context Prediction
CMA Coastline Matching Algorithm SSIP’99 - Project 10 Team H.
Cardiac Ablation Segmentation Preprocessing Workflow Workflow GUI Module.
Graphics Programming 2007 Hwang Yong-Hyeon Dongseo Univ. Automatic Detection of Region-Mura Defect in TFT-LCD Yong-Hyeon.
Lecture 4b Data augmentation for CNN training
Image from
10-1 人生与责任 淮安工业园区实验学校 连芳芳 “ 自我介绍 ” “ 自我介绍 ” 儿童时期的我.
INSTITUT DE RECERCA EN VISIÓ PER COMPUTADOR I ROBÒTICA – vicorob. udg
Combining CNN with RNN for scene labeling (segmentation)
Fast Preprocessing for Robust Face Sketch Synthesis
Cardiac Ablation Segmentation Preprocessing Workflow
Synthesis of X-ray Projections via Deep Learning
Final Year Project Presentation --- Magic Paint Face
Yahoo Mail Customer Support Number
Most Effective Techniques to Park your Manual Transmission Car
How do Power Car Windows Ensure Occupants Safety
CS 698 | Current Topics in Data Science
CS6890 Deep Learning Weizhen Cai
Using Transductive SVMs for Object Classification in Images
iPhone X and Deep Learning in Wound Assessment
Bird-species Recognition Using Convolutional Neural Network
ريكاوري (بازگشت به حالت اوليه)
RGB-D Image for Scene Recognition by Jiaqi Guo
: القسم 21 إجراء المقابلة التحفيزية.
الجزء 22:المقابلة التحفيزية
Chapter 10 Image Segmentation.
By: Behrouz Rostami, Zeyun Yu Electrical Engineering Department
THANK YOU!.
ECE 539 Intro-ANN Gaoang Wang
Inferring Edges by Using Belief Propagation
Object Detection Creation from Scratch Samsung R&D Institute Ukraine
Thank you.
Thank you.
Age and Gender Classification using Convolutional Neural Networks
Deep Neural Networks for Onboard Intelligence
TGS Salt Identification Challenge
Recurrent Encoder-Decoder Networks for Time-Varying Dense Predictions
Abnormally Detection
Image processing and computer vision pipeline for segmentation and cell detection. Image processing and computer vision pipeline for segmentation and cell.
Chongyang Zhang, Zeyun Hao, Yuese Ning, Guo-Liang Wang  Molecular Plant 
CIS 519 Recitation 11/15/18.
Department of Computer Science Ben-Gurion University of the Negev
Automating stroke lesion segmentation in brain images using a multi-model multi-path convolutional neural network Yunzhe.
Deep Object Co-Segmentation
Image Processing and Multi-domain Translation
SIDE: The Summarization IDE
Deep screen image crop and enhance
Deep screen image crop and enhance
Fully automated segmentation of cartilage from magnetic resonance images using improved 3D shape context and active shape model  T. Ye, X. Cui, H. Kim 
Introduction Few-Shot object Segmentation.
Nguyen Ngoc Hoang, Guee-Sang Lee, Soo-Hyung Kim, Hyung-Jeong Yang
Deep screen image crop and enhance
The experiment based on hier-attention
Shengcong Chen, Changxing Ding, Minfeng Liu 2018
Presentation transcript:

Chuanbo Wang, Ye Guo, Zeyun Yu Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net Chuanbo Wang, Ye Guo, Zeyun Yu

Introduction

Methods

Methods Cropped 3D Image Patches Segmentation Results Localization module Segmentation Cropping Input Predict Postprocessing Original Input Volume Cropped 3D Image Patches Segmentation Results Final Segmentation Preprocessing

Results

Results

Results Methods Mean Dice ± SD Mean AAD ± SD 3D U-Net 87.5 ± 0.9 1.1 ± 0.2 UNICHK 88.4 ± 3.7 1.3 ± 0.2 UNIJLU 91.5 ± 2.3 Our 3D method 89.0 ± 1.4 0.8 ± 0.3 Our 2D method 81.8 ± 1.3 2.4 ± 1.0

Results Training dataset Combination Mean Dice ± SD 1) opp, wat, fat and inn 87.9 ± 1.7 2) opp, wat and fat 89.0 ± 1.4 3) opp, wat and inn 88.0 ± 1.6 4) opp and wat 88.5 ± 1.6

Thank you