Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation
Abstract Semantic surgical scene segmentation is crucial for accurately identifying and delineating different tissue types during surgery, enhancing outcomes and reducing complications. Hyperspectral imaging provides detailed information beyond visible color filters, offering an enhanced view of tis...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Healthcare Technology Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/htl2.12102 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850099369942974464 |
|---|---|
| author | Alfie Roddan Tobias Czempiel Daniel S. Elson Stamatia Giannarou |
| author_facet | Alfie Roddan Tobias Czempiel Daniel S. Elson Stamatia Giannarou |
| author_sort | Alfie Roddan |
| collection | DOAJ |
| description | Abstract Semantic surgical scene segmentation is crucial for accurately identifying and delineating different tissue types during surgery, enhancing outcomes and reducing complications. Hyperspectral imaging provides detailed information beyond visible color filters, offering an enhanced view of tissue characteristics. Combined with machine learning, it supports critical tumor resection decisions. Traditional augmentations fail to effectively train machine learning models on illumination and sensor sensitivity variations. Learning to handle these variations is crucial to enable models to better generalize, ultimately enhancing their reliability in deployment. In this article, Calibration‐Jitter is introduced, a spectral augmentation technique that leverages hyperspectral calibration variations to improve predictive performance. Evaluated on scene segmentation on a neurosurgical dataset, Calibration‐Jitter achieved a F1‐score of 74.35% with SegFormer, surpassing the previous best of 70.2%. This advancement addresses limitations of traditional augmentations, improving hyperspectral imaging segmentation performance. |
| format | Article |
| id | doaj-art-34fb814071f040e7afa657589bfe26f7 |
| institution | DOAJ |
| issn | 2053-3713 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Healthcare Technology Letters |
| spelling | doaj-art-34fb814071f040e7afa657589bfe26f72025-08-20T02:40:30ZengWileyHealthcare Technology Letters2053-37132024-12-0111634535410.1049/htl2.12102Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentationAlfie Roddan0Tobias Czempiel1Daniel S. Elson2Stamatia Giannarou3The Hamlyn Centre for Robotic Surgery Department of Surgery and Cancer Imperial College London London UKThe Hamlyn Centre for Robotic Surgery Department of Surgery and Cancer Imperial College London London UKThe Hamlyn Centre for Robotic Surgery Department of Surgery and Cancer Imperial College London London UKThe Hamlyn Centre for Robotic Surgery Department of Surgery and Cancer Imperial College London London UKAbstract Semantic surgical scene segmentation is crucial for accurately identifying and delineating different tissue types during surgery, enhancing outcomes and reducing complications. Hyperspectral imaging provides detailed information beyond visible color filters, offering an enhanced view of tissue characteristics. Combined with machine learning, it supports critical tumor resection decisions. Traditional augmentations fail to effectively train machine learning models on illumination and sensor sensitivity variations. Learning to handle these variations is crucial to enable models to better generalize, ultimately enhancing their reliability in deployment. In this article, Calibration‐Jitter is introduced, a spectral augmentation technique that leverages hyperspectral calibration variations to improve predictive performance. Evaluated on scene segmentation on a neurosurgical dataset, Calibration‐Jitter achieved a F1‐score of 74.35% with SegFormer, surpassing the previous best of 70.2%. This advancement addresses limitations of traditional augmentations, improving hyperspectral imaging segmentation performance.https://doi.org/10.1049/htl2.12102biomedical imagingbrainimage segmentation |
| spellingShingle | Alfie Roddan Tobias Czempiel Daniel S. Elson Stamatia Giannarou Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation Healthcare Technology Letters biomedical imaging brain image segmentation |
| title | Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation |
| title_full | Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation |
| title_fullStr | Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation |
| title_full_unstemmed | Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation |
| title_short | Calibration‐Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation |
| title_sort | calibration jitter augmentation of hyperspectral data for improved surgical scene segmentation |
| topic | biomedical imaging brain image segmentation |
| url | https://doi.org/10.1049/htl2.12102 |
| work_keys_str_mv | AT alfieroddan calibrationjitteraugmentationofhyperspectraldataforimprovedsurgicalscenesegmentation AT tobiasczempiel calibrationjitteraugmentationofhyperspectraldataforimprovedsurgicalscenesegmentation AT danielselson calibrationjitteraugmentationofhyperspectraldataforimprovedsurgicalscenesegmentation AT stamatiagiannarou calibrationjitteraugmentationofhyperspectraldataforimprovedsurgicalscenesegmentation |