Imaging/Microscopy

AI@��: Machine Learning for Microscopy Image Analysis

sandstormer — Mon, 22 Nov 2021 21:40:37 +0000

AI@��: Machine Learning for Microscopy Image Analysis sandstormer Mon, 11/22/2021 - 16:40

Directors: Jan Funke, HHMI Janelia Research Campus; Anna Kreshuk, E�� Heidelberg; and Shalin Mehta, Chan Zuckerberg Biohub, San Francisco

Course Description

The goal of this course is to familiarize researchers in the life sciences with state-of-the-art deep learning techniques for microscopy image analysis and to introduce them to tools and frameworks that facilitate independent application of the learned material after the course.

The following topics will be covered extensively during lectures, exercises, and project work:

image denoising and restoration (fully supervised and self-supervised),
image translation (i.e., generating fluorescent-like images from label-free acquisitions),
image segmentation (various flavors will be presented and explored),
image classification,
object detection and tracking in 2D and 3D time-lapse movies, and
discrete optimization techniques (i.e. for tracking or for the reconstruction of biological structures of interest).

The course will be organized into two one week phases. Week 1 is a lecture- and exercise-based phase that starts by introducing basic and later also more advanced concepts of deep learning and allows participants to learn in detail how existing state-of-the-art methods and tools operate under the hood. The second week is project-based, where students will work together with numerous experts to apply the newly acquired knowledge and skills to their own datasets and analysis problems. Faculty and TAs will assist the students in data preparation, problem formalization, network architecture design, tool selection, model training, prediction, and evaluation.

Students will leave the course with an appreciation for the power and limitations of deep learning as well as broad knowledge of key tools that apply deep-learning based methods to microscopy image data.

The course assumes familiarity with the Python programming language, but does not assume any prior experience with machine learning or deep learning techniques. To ensure that students can “hit the ground running”, we will provide pre-course materials and exercises that will enable students to assess their programming skills and introduce basic data handling and Python coding basics. Students are highly encouraged to bring their own microscopy datasets to work on during the second week, ideally with some amount of existing label data that can be used to train adequate deep learning models. This course is limited to a maximum of 24 students.

Optical Microscopy & Imaging in the Biomedical Sciences

sandstormer — Mon, 22 Nov 2021 21:38:19 +0000

Optical Microscopy & Imaging in the Biomedical Sciences sandstormer Mon, 11/22/2021 - 16:38

Directors: Joerg Bewersdorf, Yale University; and Alison North, The Rockefeller University

Course Description

This course is designed primarily for research scientists, postdoctoral trainees, core facility directors/staff and graduate students working in the biological sciences. Non-biologists seeking a comprehensive introduction to microscopy and digital imaging in the biomedical sciences will also benefit greatly from this course. The 9-day course is limited to 24 participants to ensure a truly interactive, hands-on experience. It consists of interrelated lectures, laboratory exercises, demonstrations, and discussions that will enable the participants to obtain and interpret high quality microscope data, to understand and assess potential artifacts, to perform quantitative optical measurements, and to generate digital images for documentation and analysis that accurately present the data. The course also places a strong emphasis on appropriate sample preparation, including choice of fluorescent probes and fluorescent proteins, and tissue clearing and refractive index matching. Particular emphasis will be placed on ‘picking the right tool for the job’.

Topics to be covered include:

Fundamental principles of microscope design, image formation, resolution and contrast;
Transmitted light and fluorescence microscopy techniques;
Cameras, signal to noise ratio, digital image recording, processing and analysis, multispectral imaging;
Advanced fluorescence – fluorescent probes, fluorescent biosensors, TIRF, FRET, FLIM, FRAP, polarization of fluorescence, fluorescence correlation spectroscopy;
Digital image restoration/deconvolution, and 3-D imaging principles;
Confocal and multiphoton laser scanning microscopy and light-sheet microscopy;
Super-resolution techniques including localization microscopy, stimulated emission depletion microscopy (STED), structured illumination microscopy and expansion microscopy.

Course participants will have direct hands-on experience with state-of-the-art microscopes, a variety of digital cameras, and image processing software provided by major optical, electronics, and software companies. Instruction will be provided by experienced staff from universities and industry. Participants are encouraged to bring their own, fixed biological specimens, and to discuss individual research problems with the faculty.

Analytical and Quantitative Light Microscopy

sandstormer — Mon, 22 Nov 2021 21:34:54 +0000

Analytical and Quantitative Light Microscopy sandstormer Mon, 11/22/2021 - 16:34

Directors: Peter Kner, University of Georgia; and Alexa Mattheyses, University of Alabama, Birmingham

Course Laboratory Director: Gary Laevsky, Princeton University

Course Description

A comprehensive and intensive course in light microscopy for researchers in biology, medicine, and material sciences. This course provides a systematic and in-depth examination of the theory of image formation and application of video and digital methods for exploring subtle interactions between light and the specimen. This course emphasizes the quantitative issues that are critical to the proper interpretation of images obtained with modern wide-field and confocal microscopes. This course is limited to 32 students.

Laboratory exercises, demonstrations, and discussions include: (1) geometrical and physical optics of microscope image formation including Abbe’s theory of the microscope and Fourier optics; (2) interaction of light and matter; (3) phase contrast polarization and interference microscopy for the nondestructive analysis of molecular and fine-structural organization in living cells; (4) fluorescence microscopy, quantification of fluorescence, and GFP; (5) principles and application of digital video imaging, recording, analysis, and display; (6) digital image processing and quantitative digital image deconvolution; (7) ratiometric measurement of intracellular ion concentrations; (8) confocal microscopy; and (9) new advances in light microscopy such as FRET, FLIM, TIRF, and patterned illumination.

The program is designed primarily for: (1) university faculty, professional researchers, postdoctoral fellows, and advanced graduate students in the life sciences who wish to expand their experience in microscopy and to understand the quantitative issues associated with analysis of data obtained with optical microscopes; (2) individuals well-grounded in the physical sciences, who wish to exploit microscopy techniques for analyzing dynamic fine-structural and chemical changes; and (3) industrial scientists and engineers interested in advancing the design of equipment and techniques involving video and digital microscopy.

Lectures are followed by small group laboratory sessions and demonstrations. As a result, students will have opportunities for extensive hands-on experience with state-of-the-art optical, electronic, and digital imaging equipment guided by an experienced staff from universities and industry.

Imaging/Microscopy

AI@��������: Machine Learning for Microscopy Image Analysis

Course Description

Optical Microscopy & Imaging in the Biomedical Sciences

Course Description

Analytical and Quantitative Light Microscopy

Course Description

AI@��: Machine Learning for Microscopy Image Analysis