A full-reference laparoscopic video quality assessment algorithm

Hrishikesh Hemanth Borate; Peter Andras Kara; Balasubramanyam Appina; Aniko Simon

doi:10.1117/12.2597348

1 August 2021 A full-reference laparoscopic video quality assessment algorithm

Hrishikesh Hemanth Borate, Peter Andras Kara, Balasubramanyam Appina, Aniko Simon

Proceedings Volume 11841, Optics and Photonics for Information Processing XV; 118410E (2021) https://doi.org/10.1117/12.2597348
Event: SPIE Optical Engineering + Applications, 2021, San Diego, California, United States

Abstract

In this paper, we introduce a full-reference quality assessment model for laparoscopic videos. The perceived quality of medical imaging in general is of upmost importance, as visual degradations may lead to severe negative impacts on diagnostic accuracy. Laparoscopy, also known as keyhole surgery, is a camera-assisted operation performed in the abdomen or the pelvis of the patient. Unlike the conventional utilization of telescopic rod lens systems, digital laparoscopy uses a miniature digital camera at the end of the laparoscope, and therefore, the surgeon fully relies on the quality of the medical video. In our scientific contribution, we utilize different image quality measures for each frame of the laparoscopic videos. We implement a regression neural network architecture on the frame-level features with the associated mean opinion score as labels. Finally, we calculate the average of the predicted frame-level scores to compute the overall quality score. The performance of the proposed model is evaluated on the well-known LVQ laparoscopic video dataset. The evaluation results confirm that our model is competitive with the state-of-the-art 2D full-reference and no-reference supervised algorithms. Furthermore, the model demonstrates robust performance across all distortion types of the dataset.

Conference Presentation

Citation Download Citation

Hrishikesh Hemanth Borate, Peter Andras Kara, Balasubramanyam Appina, and Aniko Simon "A full-reference laparoscopic video quality assessment algorithm", Proc. SPIE 11841, Optics and Photonics for Information Processing XV, 118410E (1 August 2021); https://doi.org/10.1117/12.2597348

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available