assistant undergoing research training at Department of Information Technology, Division of Visual Information and Interaction
Keywords: image analysis visualization machine learning deep learning digital pathology ultrastructural pathology transmission electron microscopy opthalmology algorithm development radiology
Also available at
Amit is a doctoral student in Computerized Image Analysis with Quantitative Microscopy Group led by Prof. Carolina Wählby at Centre for Image Analysis, Uppsala University, Sweden. The current research focus is to develop a smart platform for ultrastructural imaging and automated analysis for Transmission Electron Microscopy under the supervision of Assoc. Prof. Ida-Maria Sintorn. This interdisciplinary research closely collaborates with the clinicians in Sweden (Uppsala Academic Hospital) and also have the industrial partner (Vironova AB, Stockholm). The research outcomes serve the industrial need for complete automated imaging and analysis of PCD diagnosis (a rear genetic disorder) to facilitate the clinicians (ultrastructural pathologists) in making a concrete diagnosis. The published research ideas also undergo real-time on the conventional TEM and recently developed low voltage electron microscope by Vironova AB, name MiniTEM.
Prior, he received Masters in Technology (M.Tech.) degree in Medical Imaging and Image Analysis from Indian Institute of Technology Kharagpur (IIT Kharagpur), India in 2010; B.E. degree in Biomedical Engineering from Rajiv Gandhi Technical University, Bhopal, India in 2008. He has been working towards developing image processing and machine learning algorithms to facilitate medical imaging and post analysis catering the academic and industrial needs for more than a decade. His industrial experience includes working with R&D groups of Carl Zeiss Meditec, Philips Innovation Centre, Philips Electronics India, and i2i TeleSolutions. His research interests include quantitative microscopy, electron and light microscopy, pattern analysis and machine intelligence, deep learning and their application in microscopy, radiology, and ophthalmology.
LinkedIn profile: https://www.linkedin.com/in/amit-suveer-08505417/
The current focus of research is on "Automated Imaging and Multiscale Analysis of Cellular Transmission Electron Microscopy Images". Transmission electron microscopy (TEM) is an essential diagnostic tool for screening human tissues at very high magnification (the ultrastructural level). The high resolution of TEM provides unique morphological information, significant for diagnosis and personalized care management (e.g., ciliopathy, various renal diseases, and early amyloid deposit detection). TEM can reveal all structures of a sample down to the nanometer scale without using specific stains or probes. Despite the advantages of TEM, it is minimally used because it is expensive, technically sophisticated and a special environment is required to house the bulky and sensitive machine. Interpretation of information is also subjective, time-consuming, and relies on a high level of expertise; and unfortunately, there is a lack of trained personnel.
In this project we are collaborating with microscope manufacturers, pathologists, and microscopists, to develop the next generation of image processing/analysis, and machine learning based tools that will significantly simplify and enhance the TEM imaging and analysis experience. The work includes automated steering of a TEM microscope for the regions of interest search, followed by automatic multiscale imaging of objects for time-efficient processing. Here, real-time processing guides the imaging, which involves techniques for automated detection and recognition of objects from multi-resolution TEM images, followed by non-rigid registration techniques to align the detected objects and the methods for super-resolution reconstruction to enhance the visualization of barely visible structures. Some of the relevant publications related to project are published in peer-reviewed conferences and journals.
Please contact the directory administrator for the organization (department or similar) to correct possible errors in the information.