Computer Vision in Biomedical Engineering: Spring 2019

UPDATE: All students must complete your presentations by Week 16. The presentation should be based on recently published top-tier journal paper. Please contact TA (jiaoyining AT sjtu.edu.cn) to check whether your selection is qualified. You need finalize your talk information at least one week in advance of your schedule.

May 15

欧阳熹：Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

霍加宇：FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction

牛京阳：Radiomic features and multilayer perceptron network classifier: a robust MRI classification strategy for distinguishing glioblastoma from primary central nervous system lymphoma

陈黎云：Learning Correspondence from the Cycle-consistency of Time

JOEL DZIDZORVI KWAME DISU: 1. Machine and deep learning for workflow recognition during surgery; 2. A Machine Learning Approach to Predicting Case Duration for Robot-Assisted Surgery

CLINTON ELIAN GANDANA: Needle in a haystack: Interactive surgical instrument recognition through perception and manipulation

May 22

彭丹卉：MULTIMODAL IMAGE DENOISING BASED ON COUPLED DICTIONARY LEARNING

张健源：HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs

陈硕：DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction

周明：Feature Selective Anchor-Free Module for Single-Shot Object Detection

叶倩倩：Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

May 29

张梦吉：Kervolutional Neural Networks

郭有容：Deep Group-shuffling Random Walk for Person Re-identification

施政恺：Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss

许晓薇：Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network

王晗：Averaging Weights Leads to Wider Optima and Better Generalization

June 5

周美宣：Deep Depth Completion of a Single RGB-D Image

徐子薇：Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

ZAWAR KHAN KHATTAK：Spatio-spectral Representation Learning for Electroencephalographic Gait-Pattern Classification

VALENTIN DILEK：First Insights on a Passive Major Depressive Disorder Prediction System with Incorporated Conversational Chatbot

JAMIRAH BINT AHMED：Deep Evolutionary Networks with Expedited Genetic Algorithm for Medical Image Denoising

June 12

MEHMOONA AZMAT：Optimal deep learning model for classification of lung cancer on CT images

赵旺源：Deformable Image Registration Using Functions of Bounded Deformation

李雯丽：Towards artificial intelligence in mental health by improving schizophrenia prediction with multiple brain parcellation ensemble-learning

李钧：nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

刘一明：End-to-end Adversarial Retinal Image Synthesis

葛艺蒙：An Unsupervised Learning Model for Deformable Medical Image Registration

徐健玮：CornerNet: Detecting Objects as Paired Keypoints

Briefly speaking, the purpose of computer vision is to let computers act like human beings in terms of visual perception. In the other word, computers are expected to visualize and understand this world via images, videos, etc. Computer vision has moved forward significantly during past decades. Its accomplishments are now widely applied to numerous areas including biomedical engineering. This course shall introduce basic theories of computer vision, as well as its classical solutions. Also, applications related with biomedical engineering shall be the focus in this course, for the sake of revealing the miracles of computer vision.

Note: This 3-credit graduate-level course is taught every spring semester and in English. All course materials are hosted through Jbox. 

人工智能和医学（AI & Medicine）：2018春季学期

Note: All course materials are hosted through Jbox. This course will be moved to the spring semester since 2018.