ELEC 444/6661 Medical Image Processing
|Instructor:||Dr. Hassan Rivaz|
|Guest lecturers:||Dr. Rupert Brooks (two weeks) and Dr. Habib Benali (one week)|
|Course description:||This course covers the principles and algorithms used in the processing and analysis of medical images. Topics include denoising, machine learning, image registration and similarity metrics. Image analysis methods on the most common medical imaging modalities (X-ray, MRI, CT, ultrasound) will be covered. Projects and assignments will provide students experience working with actual medical imaging data.|
|Prerequisites:||Undergraduate students: ELEC 364 or ELEC 342 Signals and Systems and a strong knowledge of linear algebra.|
|Credits:||Undergraduate course ELEC 444: 3 credits. Graduate course ELEC 6661: 4 credits. The graduate course requires carrying out a significantly more demanding project, which accounts for the exra credit.|
|Location & time:||FG B080, Thursday 12noon to 2:30PM|
|Text Book:||Medical Image Processing, 2014, By Wolfgang Birkfellner, CRC Press, ISBN: 978-1466555570.|
|Reference Book:||Medical Image Processing, 2009, By Geoff Dougherty, Cambridge University Press, ISBN: 9780521860857.|
|Assignments:||Three assignments + one final project (in MATAB or another language based on student preference). Marker: Mr. Morteza Mirzaei, email: morteza.mirzaei1369 AT gmail.com|
|General POD:||Mr. Md Ashik. Email: rasel.ashik ATsign gmail.com. Please do not contact ashik for deep learning or Google Cloud related questions. For those questions, please contact Kibria (info below).|
|Lab time/location:||Tuesdays 15:15 to 19:15. Locations: H907. Ask questions from POD Mr. Md Ashik. It is not mandatory to attend lab sessions. No material is presented here, only questions are answered. Note that for deep learning questions, you should not go to the lab. Instead, you should contact the deep learning POD Mr. Kibria (info below).|
|Deep learning POD:||Mr. Golam Kibria. Email: mgk0706161 ATsign gmail.com. Please contact Kibria only for deep learing questions and arrange a time to meet him at EV10.113.|
|Project:||All students (grad and ugrad) must present in the last class on Nov 29. The project due date is on Friday Dec 7 at 11:59AM and should be emailed to morteza.mirzaei1369 AT gmail.com.|
|Project for undergrads:||Undergrads registered in ELEC 444 have an option of implementing a paper or doing a project based on the RANSAC algorithms. The students who choose the RANSAC project don't need to write a report and should email their code by Friday Dec 7 at 11:59AM to morteza.mirzaei1369 AT gmail.com.|
|Undergraduate (3 credits)||Graduate (4 credits)|
|Assignments||Post date||Due date||Points|
|1. Matrix and image manupulation||Wednesday Sept 12, 9AM||Tuesday Sept 25, 11:59PM||1 point|
|2. Detecting edges of brain MRI||Thursday Oct 11, 9AM||Tuesday Oct 23, 11:59PM||4.5 points|
|3. k-means segmentation of brain MRI||Thursday Oct 25, 9AM||Tuesday Nov 6, 11:59PM||4.5 points|
|1, Sep 6||Logistics, introduction to X-ray, CT and nuclear imaging|
|2, Sep 10 from 8:30AM to 10:45AM||Introduction to ultrasound and Magnetic Resonance (MR) imaging, images in Matlab|
|3, Sep 20||Neuroimaging|
|4, Sep 27||Convolution, aliasing in medical images|
|5, Oct 4||Denoising techniques in medical imaging, edge detection in medical images|
|6, Oct 11||Machine learning in medical imaging|
|Oct 18||Midterm in class stating at 12noon (mark your calendar)|
|8, Oct 25||Introduction to medical image segmentation, RANSAC and k-means in medical imaging|
|9, Nov 1||From linear filters to deep learning|
|10, Nov 8||Convolutional neural networks (aka CNN or ConvNet)|
|11, Nov 15||Registration of medical images, similarity metrics (sum of squared differences, normalized cross correlation, correlation ratio, joint entropy, mutual information)|
|12, Nov 22||Computer vision and motion estimation in ultrasound elastography|
|13, Nov 29||Student presentations|
|Database of images possibly useful for projects:|
1) BrainWeb MRI link ,
2) Ultrasound RF data link ,
3) Ultrasound raw data link ,
4) Fetal ultrasound head circumfrence: paper and data ,
5) Ultrasound data for segmentation provided by the paper below:
Yap, Moi Hoon, Gerard Pons, Joan Marti, Sergi Ganau, Melcior Sentis, Reyer Zwiggelaar, Adrian K. Davison, and Robert Marti. "Automated breast ultrasound lesions detection using convolutional neural networks." IEEE journal of biomedical and health informatics 22, no. 4 (2018): 1218-1226.
6) Ultrasound data for deep learning segmentation: Cunningham et al ,
7) 3D MRI and ultrasound: the BITE Database,
And the RESECT Database paper, the RESECT Database download
8) 3D MRI of Brain: BRATS.
9) 3D MRI of Brain: WMH Segmentation.
10) 3D MRI of Brain: OASIS.
10) Chest CT from dir-lab .
11) Chest CT from National Lung Screening Trial .
12) Pancreas CT from TCIA Pancreas CT-82 .
13) CT and MRI of several different organs Medical Decathlon .
14) CT, chest x-ray, digital pathology etc. Cancer Data Access System .
15) Liver CT LiTS - Liver Tumor Segmentation Challenge .
16) Abdominal CT IEEE TMI's DenseVNet Multi-organ Segmentation on Abdominal CT .
17) Inbreast Digital mamography link .
18) Curated Breast Imaging Subset of DDSM link .
|Acknowledgments:||Dr. Rivaz would like to thank the Google Cloud Program for providing students registered in this course credits for using Google Cloud.|