1
|
Budd C, Garcia-Peraza-Herrera LC, Huber M, Ourselin S, Vercauteren T. Rapid and robust endoscopic content area estimation: A lean GPU-based pipeline and curated benchmark dataset. COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING. IMAGING & VISUALIZATION 2023; 11:1215-1224. [PMID: 38600897 PMCID: PMC7615255 DOI: 10.1080/21681163.2022.2156393] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/22/2022] [Accepted: 11/19/2022] [Indexed: 01/07/2023]
Abstract
Endoscopic content area refers to the informative area enclosed by the dark, non-informative, border regions present in most endoscopic footage. The estimation of the content area is a common task in endoscopic image processing and computer vision pipelines. Despite the apparent simplicity of the problem, several factors make reliable real-time estimation surprisingly challenging. The lack of rigorous investigation into the topic combined with the lack of a common benchmark dataset for this task has been a long-lasting issue in the field. In this paper, we propose two variants of a lean GPU-based computational pipeline combining edge detection and circle fitting. The two variants differ by relying on handcrafted features, and learned features respectively to extract content area edge point candidates. We also present a first-of-its-kind dataset of manually annotated and pseudo-labelled content areas across a range of surgical indications. To encourage further developments, the curated dataset, and an implementation of both algorithms, has been made public (https://doi.org/10.7303/syn32148000, https://github.com/charliebudd/torch-content-area). We compare our proposed algorithm with a state-of-the-art U-Net-based approach and demonstrate significant improvement in terms of both accuracy (Hausdorff distance: 6.3 px versus 118.1 px) and computational time (Average runtime per frame: 0.13 ms versus 11.2 ms).
Collapse
|
2
|
Bahl A, Horgan CC, Janatka M, MacCormac OJ, Noonan P, Xie Y, Qiu J, Cavalcanti N, Fürnstahl P, Ebner M, Bergholt MS, Shapey J, Vercauteren T. Synthetic white balancing for intra-operative hyperspectral imaging. J Med Imaging (Bellingham) 2023; 10:046001. [PMID: 37492187 PMCID: PMC10363486 DOI: 10.1117/1.jmi.10.4.046001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2023] [Revised: 06/23/2023] [Accepted: 07/05/2023] [Indexed: 07/27/2023] Open
Abstract
Purpose Hyperspectral imaging shows promise for surgical applications to non-invasively provide spatially resolved, spectral information. For calibration purposes, a white reference image of a highly reflective Lambertian surface should be obtained under the same imaging conditions. Standard white references are not sterilizable and so are unsuitable for surgical environments. We demonstrate the necessity for in situ white references and address this by proposing a novel, sterile, synthetic reference construction algorithm. Approach The use of references obtained at different distances and lighting conditions to the subject were examined. Spectral and color reconstructions were compared with standard measurements qualitatively and quantitatively, using Δ E and normalized RMSE, respectively. The algorithm forms a composite image from a video of a standard sterile ruler, whose imperfect reflectivity is compensated for. The reference is modeled as the product of independent spatial and spectral components, and a scalar factor accounting for gain, exposure, and light intensity. Evaluation of synthetic references against ideal but non-sterile references is performed using the same metrics alongside pixel-by-pixel errors. Finally, intraoperative integration is assessed though cadaveric experiments. Results Improper white balancing leads to increases in all quantitative and qualitative errors. Synthetic references achieve median pixel-by-pixel errors lower than 6.5% and produce similar reconstructions and errors to an ideal reference. The algorithm integrated well into surgical workflow, achieving median pixel-by-pixel errors of 4.77% while maintaining good spectral and color reconstruction. Conclusions We demonstrate the importance of in situ white referencing and present a novel synthetic referencing algorithm. This algorithm is suitable for surgery while maintaining the quality of classical data reconstruction.
Collapse
Affiliation(s)
- Anisha Bahl
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
| | - Conor C. Horgan
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
- Hypervision Surgical Ltd., London, United Kingdom
| | | | - Oscar J. MacCormac
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
- King’s College Hospital, Denmark Hill, London, United Kingdom
| | | | - Yijing Xie
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
| | - Jianrong Qiu
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
- King’s College London, Centre for Craniofacial and Regenerative Biology, London, United Kingdom
| | | | | | | | - Mads S. Bergholt
- King’s College London, Centre for Craniofacial and Regenerative Biology, London, United Kingdom
| | - Jonathan Shapey
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
- Hypervision Surgical Ltd., London, United Kingdom
- King’s College Hospital, Denmark Hill, London, United Kingdom
| | - Tom Vercauteren
- King’s College London, School of Biomedical Engineering and Imaging Sciences, London, United Kingdom
- Hypervision Surgical Ltd., London, United Kingdom
| |
Collapse
|