Das, Adrito Prottush Abir;
(2025)
Computer vision assisted endoscopic pituitary surgery.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
thesis.pdf - Accepted Version Download (168MB) | Preview |
Abstract
The pituitary gland, a pea-sized organ found just off the base of the brain, performs essential functions required for sustaining human life. Adenomas that form on the pituitary gland are among the most common intracranial tumours, and if left untreated, symptomatic adenomas can cause blindness or even be life limiting. The transsphenoidal approach is a minimally invasive surgery where the adenoma is removed by entering through a nostril, considered the ‘gold standard’ treatment for most patients with symptomatic adenomas. However, the endoscopic transsphenoidal approach is a difficult skill to master, requiring dedicated fellowships. The field of computer vision assisted minimally invasive surgery has been shown to be useful for surgeons in a variety of ways. However, the field is dominated by models specific to laparoscopic cholecystectomy due to availability of public data. Therefore their generalisability is largely untested, especially for surgeries with much smaller working spaces, as is the case with endoscopic pituitary surgery. This thesis extends the existing field by being the first to:(I) create datasets consisting of annotated endoscopic pituitary surgery videos; (II) publicly releasing these datasets for use amongst the wider community; (III) testing the generalisability of the state-of-the-art models on these datasets; and (IV) creating new models to better suit the intricacies of endoscopic pituitary surgery videos. Additionally, this thesis demonstrates the many uses of computer vision assisted minimally invasive surgery, backed by clinical studies. This includes: (V) anatomy identification to highlight safe resection areas; (VI) surgical step classification to present analytics for use in surgical training and (VII) generating operation notes; and (VIII) surgical instrument tracking for assessing surgical skill.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Computer vision assisted endoscopic pituitary surgery |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2025. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Health Informatics |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10216615 |
Archive Staff Only
 |
View Item |
