EE61008 | Spring 2024

Announcements	Medical Image Analysis	Quick Links
Video lectures for selected topics added. Coming up again in Spring 2024 in an OBE format!* *OBE is outcome-based education according to Washington Accord	EE61008, Spring 2024 Subject Type: Elective \| LTP: 3-1-0 \| Credits: 4 Location: NR213, Nalanda Complex Time: Slot H+S3(1) / Mon (2:00 - 2:55 PM) + Mon (5:00 - 5:55 PM) + Tue (4:00 - 5:55 PM) Instructor: Dr. Debdoot Sheet TA: Grading: Attendance 10%, Capstone Project 30%, Mid-Term 25%, End-Term 35%	Link to list of detailed reading texts. Grand Challenges in Biomedical Image Analysis Tools of the Trade: MeVisLab SDK \| Anaconda Python \| MedPy \| MikTex Latex compiler Archive of old questions

Why this subject?	Overview of this Subject
You get to learn about current technology in processing and analysis of medical images; a rapidly growing industry expected to reach $3.5 billion by 2020. If you are looking forward to a career in medical imaging instrument and softwares design, medical imaging, medical visualization, medical robotics and augmented reality, this is the key subject you should enroll for. The best parts just do not end here. A mix of hands-on tutorials coupled with lectures provide you with a balanced exposure to nuances of medical image analysis. Text books and reading materials are completely electronic, online and available as web-browser and smatphone apps. Prerequisite: Digital Image Processing Measure of Outcome: A student undertaking this subject would be graded based on perfromance in all of the following: (1) Regular participation in class activity. (2) Capstone Project on an active GrandChallenges in Bio-MedIA (in a group of 2-3). If you make up to the Top-3 teams on the GrandChallenge, you claim the Hall-of-Fame. (3) Make a mid-term proposal presentation for the Capstone Project. (4) Make an end-term presentation of the solution. Submit a 4-page term paper on the solution. (5) Appear for all the exams.

Why this subject?

Overview of this Subject

You get to learn about current technology in processing and analysis of medical images; a rapidly growing industry expected to reach $3.5 billion by 2020. If you are looking forward to a career in medical imaging instrument and softwares design, medical imaging, medical visualization, medical robotics and augmented reality, this is the key subject you should enroll for.

The best parts just do not end here. A mix of hands-on tutorials coupled with lectures provide you with a balanced exposure to nuances of medical image analysis. Text books and reading materials are completely electronic, online and available as web-browser and smatphone apps.

Prerequisite: Digital Image Processing

Measure of Outcome:
A student undertaking this subject would be graded based on perfromance in all of the following:
(1) Regular participation in class activity.
(2) Capstone Project on an active GrandChallenges in Bio-MedIA (in a group of 2-3).
If you make up to the Top-3 teams on the GrandChallenge, you claim the Hall-of-Fame.
(3) Make a mid-term proposal presentation for the Capstone Project.
(4) Make an end-term presentation of the solution. Submit a 4-page term paper on the solution.
(5) Appear for all the exams.

**Topics, Reading Text and Utilities**
Topic	Details
Introductory Concepts	Medical image analysis overview \| Video Lecture \| Article: IEEE Trans. Pat. Anal., Mach. Intell.. Human anatomy refresher and common concepts of pathology \| Book: Gray's anatomy Overview of medical imaging \| Chapter: Guide to Medical Image Analysis Medical image storage, transfer, viewing \| Chapter: Guide to Medical Image Analysis
Advanced Concepts of Digital Image Processing	Texture analysis \| Video Lecture \| Chapter: Biomedical Image Processing Classification and clustering \| Video Lecture \| Chapter: Guide to Medical Image Analysis Active contour models \| Video Lecture \| Chapter: Guide to Medical Image Analysis Random walks for image segmentation \| Video Lecture \| Chapter: IEEE Trans. Pat. Anal., Mach. Intell. Systematic evaluation and validation \| Video Lecture \| Chapter: Biomedical Image Processing Image registration \| Chapter: Guide to Medical Image Analysis
Machine Learning Concepts	Segmentation in feature space \| Chapter: Guide to Medical Image Analysis Decision trees and random forests \| Video Lecture 1 \| Video Lecture 2 \| Book: Decision Forests for Computer Vision and Medical Image Analysis Neural networks \| Video Lecture \| Chapter: DeepLearningBook.org Autoencoders using deep neural networks \| Video Lecture \| Chapter: DeepLearningBook.org Convolutional neural networks \| Video Lecture \| Chapter: DeepLearningBook.org
X-ray Imaging and Computed Tomography Video Lecture	X-ray imaging \| Chapter: Medical Imaging Technology Computed tomography imaging \| Chapter: Medical Imaging Technology CT Reconstruction \| Chapter: Principles of Computerized Tomographic Imaging Automatic (and semi-automatic) segmentation of vessels in the lungs from CT images \| Video Lecture VESSEL12 \| Article: Medical Image Analysis
Magnetic Resonance Imaging Video Lecture	Magnetic resonance imaging \| Chapter: Medical Imaging Technology Multi-class classification of patients with Alzheimer's disease (AD), mild cognitive impairment (MCI) and healthy controls (CN) using multi-center structural MRI data. \| CAD Dementia Challenge 2014 \| Article: NeuroImage
Ultrasonic Imaging Video Lecture	Physics and instrumentation of ultrasound imaging \| Whitepaper: Texas Instruments Segmentation of anatomical structures to measure obsteatric biometric parameters from 2D fetal ultrasound images. \| Challenge US 2012 \| Article: IEEE Trans. Med. Imaging Ultrasonic tissue characterization \| Video Lecture \| Article: Medical Image Analysis
Digital Pathology and Microscopy Video Lecture	Optical microscopy \| Zeiss Microscopy Tutorial \| Chapter: Encyclopedia of Imaging Science and Technology Histopathology image analysis \| Video Lecture \| Article: IEEE Rev. Biomed. Engg. (Semi-)automatic mitotic figure detection methods on regions extracted from whole-slide pathology images. \| AMIDA13 \| Article: Medical Image Analysis Manually tracking cells is an extremely laborious task, due to the large amount of image data acquired during live-cell studies. This challenge compares automatic approaches for cell tracking. \| Cell Tracking Challenge 2013 \| Article: Bioinformatics
Retinal Imaging Video Lecture	Retinal imaging and image analysis \| Article: IEEE Rev. Biomed. Engg. Retinal vessel extraction \| DRIVE Computer aided detection and diagnosis (CAD) of diabetic retinopathy. \| Retinopathy Online Challenge 2009 \| Article: IEEE Trans. Med. Imaging
Optical Coherence Tomography	Physics of OCT imaging \| Chapter: Optical Coherence Tomography OCT tissue characterization. \| Article: Journal of Biomedical Optics

Lecture Schedule and Resources

Learning Resources

Conferences	Int. Symp. Biomed. Imaging (ISBI), Med. Image Comput., Comp. Assist. Interv. (MICCAI), SPIE Med. Imaging, Int. Conf. Image Processing (ICIP), Computer Vision and Pattern Recognition (CVPR), Int. Conf. Comput. Vis. (ICCV), Eur. Conf. Comput. Vis. (ECCV), Asian Conf. Comput. Vis. (ACCV), ACM SIGGRAPH, ACM SIGGRAPH-Asia, Indian Conf. Vis., Graph., Image Process. (ICVGIP), Nat. Conf. Vis., Pat. Recog., Image Process., Graph. (NCVPRIPG)
Journals	Medical Image Analysis (MedIA), IEEE Trans. Med. Imaging (TMI), IEEE J. Biomed. Health Inf. (JBHI), IEEE Trans. Biomed. Engg. (TBME), SPIE J. Med. Imaging (JMI), Comput. Med. Imag., Graph. (CMIG), IEEE Trans. Image Process. (TIP), IEEE Trans. Pat. Anal., Mach. Intell. (T-PAMI), Int. J. Comput. Vis. (IJCV), IET Image Process. (IET-IP), ACM Trans. Graphics (TOG)
BioDigital Human	Web browser app that can be handy while understanding human anatomy for medical image analysis
Android Studio and SDK	Developer studio, IDE and SDK if you are interested to develop Android apps as part of your mini-project.
MicroDicom viewer	Handy software utility to quickly view DICOM files
Challenges @ ISBI	Collection of challenges in medical image analysis hosted at the International Symposium on Biomedical Imaging (ISBI).
Mammographic Image Analysis	Collection of mammography images provided by Mammographic Image Analysis Society (MIAS).
DRIVE: Digital Retinal Images for Vessel Extraction	A standard dataset of 40 color fundus images for comparative studies on segmentation of blood vessels in retinal images.
Drishti-GS Dataset	Dataset of color fundus retinal images for Glaucoma detection.
Farsiu's Dataset @ Duke Univ.	Collection of multiple datasets of ophthalmic OCT speckle images for tissue characterization, denoising, super-resolution and mosaicing.
MIT OCW Linear Algebra	Revise your Linear Algebra with video lectures and resources by Prof. Gilbert Strang.
Products / Labs / Companies	Predible, Aditya Imaging Information Technologies, Lattice Innovations, SigTuple, ImFusion, Definiens, SurgicEye, microDimensions, BrainLab, IBM Watson Health, Siemens Healthcare

Pedagogical Objectives

The aim is to teach students advanced technology in processing and analysis of medical images. It would be beneficial to students opting for specialization in medical imaging instrument design, medical imaging, medical visualization, medical robotics and augmented reality, who can use the gained skills in order to develop newer technological innovations and regularize their high-throughput clinical translation and usage.

On completion of the course, a student would be able to:
1. Explain and discuss the scientific principles of medial image formation, tissue energy interaction as basis for different imaging modalities, inter-relation between image appearance and tissue properties, quantitative medicine, multi-scale and multi-resolution relation in medical diagnostics, medical visualization and augmented reality.
2. Demonstrate the ability of analyzing medical images using their foundations of linear algebra, graph based and machine learning based approaches.
3. Design and develop new techniques for improving clinical workflow with incorporation of medical image analysis in regular clinical usage.