BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Kolkata BEGIN:STANDARD DTSTART:19451014T230000 TZOFFSETFROM:+0630 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20231013T095908Z UID:0628A8B8-6412-499A-A542-541C58803989 DTSTART;TZID=Asia/Kolkata:20231011T190000 DTEND;TZID=Asia/Kolkata:20231011T200000 DESCRIPTION:This talk deals with two aspects of medical Imaging: image reco nstruction and segmentation. The first part covers the image reconstructio n for magnetic resonance imaging (MRI). Despite the capability of providin g high-resolution images\, the difficulties associated with lengthy acquis ition time necessitate reconstruction of the final image from a limited nu mber of k-space samples. The reconstruction problem falls under the broad class of ill-posed inverse problems\, and regularization is necessary for obtaining stable and meaningful solutions. However\, the accuracy of regul arized output depends on the regularization parameter choice. The adaptive estimation of the regularization parameter from the data for sparsity-pro moting methods will be discussed. The second part focuses on nerve segment ation in ultrasound images. The automated segmentation of the median nerve at the wrist and from wrist to elbow using different deep learning models along with the associated challenges will be discussed. Finally\, the tal k will conclude with a discussion on the implementation of the model in re al-time.\n\nSpeaker(s): Dr. Raji Susan Mathew\, \n\nVirtual: https://even ts.vtools.ieee.org/m/377686 LOCATION:Virtual: https://events.vtools.ieee.org/m/377686 ORGANIZER:ieee.sps.sb.iitkgp@gmail.com SEQUENCE:2 SUMMARY:IEEE SPS SBC Webinar: Data-driven Approaches for Improved Reconstru ction and Segmentation in Medical Imaging.(By Dr. Raji Susan Mathew) URL;VALUE=URI:https://events.vtools.ieee.org/m/377686 X-ALT-DESC:Description: <br /><p><span style="font-weight: 400\;">This talk deals with two aspects of medical Imaging: image reconstruction and segme ntation. The first part covers the image reconstruction for magnetic reson ance imaging (MRI). Despite the capability of providing high-resolution im ages\, the difficulties associated with lengthy acquisition time necessita te reconstruction of the final image from a limited number of k-space samp les. The reconstruction problem falls under the broad class of ill-posed i nverse problems\, and regularization is necessary for obtaining stable and meaningful solutions. However\, the accuracy of regularized output depend s on the regularization parameter choice. The adaptive estimation of the r egularization parameter from the data for sparsity-promoting methods will be discussed. The second part focuses on nerve segmentation in ultrasound images. The automated segmentation of the median nerve at the wrist and fr om wrist to elbow using different deep learning models along with the asso ciated challenges will be discussed. Finally\, the talk will conclude with a discussion on the implementation of the model in real-time.</span></p> END:VEVENT END:VCALENDAR