CMIC/WEISS Joint Seminar Series– Wed 17 May at 1.00 pm

Title of presentation:  Computer vision assisted endoscopic pituitary surgery. 

Abstract of the presentation: Endoscopic pituitary surgery is a minimally invasive surgery where access to the pituitary tumour is gained by entering through a nostril. It is the most common way to remove a pituitary tumour but is a difficult technique to master. Surgical workflow analysis is the concept of breaking down a surgery into its workflow components and analysing the components in order to improve surgical outcomes. Developments in computer vision have allowed the of this analysis to be automated by applying the models to recorded videos of the surgery. The aim of this work is to leverage these state-of-the-art models and enhance them to specifically assist in endoscopic pituitary surgery.

Bio: Adrito is a PhD candidate at WEISS under Prof Stoyanov, Mr Marcus, and Dr Bano. Previous to this he read mathematics (MA) and astrophysics (MSci) at the University of Cambridge and worked in quantitative finance for 3-years.

2^nd Talk

Title: DSR: Direct Simultaneous Registration for Multiple 3D Images 

Abstract: In this talk, I will present a novel algorithm named Direct Simultaneous Registration (DSR) that registers a collection of 3D images in a simultaneous fashion without specifying any reference image, feature extraction and matching, or information loss or reuse. The algorithm optimizes the global poses of local image frames by maximizing the similarity between a predefined panoramic image and local images. Although we formulate the problem as a Direct Bundle Adjustment (DBA) that jointly optimizes the poses of local frames and the intensities of the panoramic image, by investigating the independence of pose estimation from the panoramic image in the solving process, DSR is proposed to solve the poses only and proved to be able to obtain the same optimal poses as DBA. The proposed method is particularly suitable for the scenarios where distinct features are not available, such as Transesophageal Echocardiography (TEE) images. Through the simulated and in-vivo experiments, we demonstrated that DSR outperforms the state-of-the-art registration methods in terms of accuracy and is very useful for overcoming the limited field of view of 3D TEE. 

Bio: Zhehua Mao is now a research fellow in the Surgical Robot Vision Group at WEISS, UCL. He recently completed his Ph.D. studies at the Robotics Institute of the University of Technology Sydney, where he received broad training in Simultaneous Localization and Mapping (SLAM) and medical image registration. In his Ph.D. studies, his research topic was 3D ultrasound fusion for transesophageal echocardiography, which aimed to reconstruct complete 3D images of regions of interest in both rigid and non-rigid scenarios by using multi-view images and SLAM techniques. Now, he is one of the research members of the project “Context Aware Augmented Reality for Endonasal Endoscopic Surgery”. His current research interests include medical image segmentation, multimodal image registration, tracking, and 3D reconstruction. 

Link to the Moodle page here: https://moodle.ucl.ac.uk/course/view.php?id=19613  
Please enrol with key: CMIC 
Alternatively, you can use the zoom link below to go direct to the seminar: https://ucl.zoom.us/j/99464005163?pwd=ZFdURkJ4TjJIeGVhbXpTclhuNE9WUT09
CMIC/WEISS Joint Seminar Series– Wed 17 May at 1.00 pm at Charles Bell House and online via ZOOM (link below) 
Link to the Moodle page here: https://moodle.ucl.ac.uk/course/view.php?id=19613  
Please enrol with key: CMIC 
Alternatively, you can use the zoom link below to go direct to the seminar: https://ucl.zoom.us/j/99464005163?pwd=ZFdURkJ4TjJIeGVhbXpTclhuNE9WUT09