Bannone, Elisa; Collins, Toby; Esposito, Alessandro; Cinelli, Lorenzo; De Pastena, Matteo; Pessaux, Patrick; Felli, Emanuele; Andreotti, Elena; Okamoto, Nariaki; Barberio, Manuel; Felli, Eric; Montorsi, Roberto Maria; Ingaglio, Naomi; Rodríguez-Luna, María Rita; Nkusi, Richard; Marescaux, Jacque; Hostettler, Alexandre; Salvia, Roberto; Diana, Michele (2024). Surgical optomics: hyperspectral imaging and deep learning towards precision intraoperative automatic tissue recognition-results from the EX-MACHYNA trial. (In Press). Surgical endoscopy Springer-Verlag 10.1007/s00464-024-10880-1
![[img]](https://boris.unibe.ch/style/images/fileicons/text.png) |
Text
s00464-024-10880-1.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (3MB) | Request a copy |
BACKGROUND
Hyperspectral imaging (HSI), combined with machine learning, can help to identify characteristic tissue signatures enabling automatic tissue recognition during surgery. This study aims to develop the first HSI-based automatic abdominal tissue recognition with human data in a prospective bi-center setting.
METHODS
Data were collected from patients undergoing elective open abdominal surgery at two international tertiary referral hospitals from September 2020 to June 2021. HS images were captured at various time points throughout the surgical procedure. Resulting RGB images were annotated with 13 distinct organ labels. Convolutional Neural Networks (CNNs) were employed for the analysis, with both external and internal validation settings utilized.
RESULTS
A total of 169 patients were included, 73 (43.2%) from Strasbourg and 96 (56.8%) from Verona. The internal validation within centers combined patients from both centers into a single cohort, randomly allocated to the training (127 patients, 75.1%, 585 images) and test sets (42 patients, 24.9%, 181 images). This validation setting showed the best performance. The highest true positive rate was achieved for the skin (100%) and the liver (97%). Misclassifications included tissues with a similar embryological origin (omentum and mesentery: 32%) or with overlaying boundaries (liver and hepatic ligament: 22%). The median DICE score for ten tissue classes exceeded 80%.
CONCLUSION
To improve automatic surgical scene segmentation and to drive clinical translation, multicenter accurate HSI datasets are essential, but further work is needed to quantify the clinical value of HSI. HSI might be included in a new omics science, namely surgical optomics, which uses light to extract quantifiable tissue features during surgery.
Item Type: |
Journal Article (Original Article) |
|---|---|
Division/Institute: |
04 Faculty of Medicine > Department of Gastro-intestinal, Liver and Lung Disorders (DMLL) > Clinic of Visceral Surgery and Medicine > Hepatology 04 Faculty of Medicine > Department of Gastro-intestinal, Liver and Lung Disorders (DMLL) > Clinic of Visceral Surgery and Medicine |
UniBE Contributor: |
Felli, Eric |
Subjects: |
600 Technology > 610 Medicine & health |
ISSN: |
0930-2794 |
Publisher: |
Springer-Verlag |
Language: |
English |
Submitter: |
Pubmed Import |
Date Deposited: |
27 May 2024 09:08 |
Last Modified: |
27 May 2024 09:18 |
Publisher DOI: |
10.1007/s00464-024-10880-1 |
PubMed ID: |
38789623 |
Uncontrolled Keywords: |
Convolutional neural networks Deep learning Hyperspectral imaging Image-guided surgery Semantic scene segmentation Surgical data science |
BORIS DOI: |
10.48350/197079 |
URI: |
https://boris.unibe.ch/id/eprint/197079 |
Actions (login required)
 |
Edit item |