Oluwatosin Alabi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Oluwatosin Alabi has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
- Tom Vercauteren
School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
7 shared publications - Miaojing Shi
College of Electronic and Information Engineering, Tongji University, Shanghai, China
5 shared publications - Meng Wei
BMEIS School, King’s College London, London, UK
4 shared publications - Charlie Budd
BMEIS School, King’s College London, London, UK
3 shared publications Anna L. David
Elizabeth Garrett Anderson Institute for Women’s Health, University College London, London, UK
2 shared publicationsDanail Stoyanov
Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK
2 shared publications
Latest Publications
- 25 March 2026
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 21 (5) , 901-908
Grounding surgical action triplets with instrument instance segmentation: a dataset and target-aware fusion approach
Purpose Understanding surgical instrument–tissue interactions requires not only identifying which instrument performs which action on which anatomical target, but also grounding these interactions spatially within the surgical scene. Existing surgical action triplet recognition methods are limited to learning from frame-level classification, failing to reliably link actions to specific instrument instances. Previous attempts at spatial grounding have primarily relied on class activation maps, which lack the precision and robustness required for detailed instrument–tissue interaction analysis. To address this gap, we propose grounding surgical action triplets with instrument instance segmentation, or triplet segmentation for short, a new unified task which produces spatially grounded \(\langle \) instrument, verb, target \(\rangle \) outputs. Methods We start by presenting CholecTriplet-Seg, a large-scale dataset containing over 30,000 annotated frames, linking instrument instance masks with action verb and anatomical target annotations, and establishing the first benchmark for strongly supervised, instance-level triplet grounding and evaluation. To learn triplet segmentation, we propose TargetFusionNet, a novel architecture that extends Mask2Former with a target-aware fusion mechanism to address the challenge of accurate anatomical target prediction by fusing weak anatomy priors with instrument instance queries. Results Evaluated across recognition, detection, and triplet segmentation metrics, TargetFusionNet consistently improves performance over existing baselines, demonstrating that strong instance supervision combined with weak target priors significantly enhances the accuracy and robustness of surgical action understanding. Conclusion Triplet segmentation establishes a unified framework for spatially grounding surgical action triplets. The proposed CholecTriplet-Seg benchmark and TargetFusionNet architecture pave the way for more interpretable, fine-grained surgical scene understanding.- 25 March 2026
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 21 (5) , 901-908
Grounding surgical action triplets with instrument instance segmentation: a dataset and target-aware fusion approach
Purpose Understanding surgical instrument–tissue interactions requires not only identifying which instrument performs which action on which anatomical target, but also grounding these interactions spatially within the surgical scene. Existing surgical action triplet recognition methods are limited to learning from frame-level classification, failing to reliably link actions to specific instrument instances. Previous attempts at spatial grounding have primarily relied on class activation maps, which lack the precision and robustness required for detailed instrument–tissue interaction analysis. To address this gap, we propose grounding surgical action triplets with instrument instance segmentation, or triplet segmentation for short, a new unified task which produces spatially grounded \(\langle \) instrument, verb, target \(\rangle \) outputs. Methods We start by presenting CholecTriplet-Seg, a large-scale dataset containing over 30,000 annotated frames, linking instrument instance masks with action verb and anatomical target annotations, and establishing the first benchmark for strongly supervised, instance-level triplet grounding and evaluation. To learn triplet segmentation, we propose TargetFusionNet, a novel architecture that extends Mask2Former with a target-aware fusion mechanism to address the challenge of accurate anatomical target prediction by fusing weak anatomy priors with instrument instance queries. Results Evaluated across recognition, detection, and triplet segmentation metrics, TargetFusionNet consistently improves performance over existing baselines, demonstrating that strong instance supervision combined with weak target priors significantly enhances the accuracy and robustness of surgical action understanding. Conclusion Triplet segmentation establishes a unified framework for spatially grounding surgical action triplets. The proposed CholecTriplet-Seg benchmark and TargetFusionNet architecture pave the way for more interpretable, fine-grained surgical scene understanding.- Top Cited PapersOpen Access
- 14 January 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 109, 103945
Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge
- 14 January 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 109, 103945
Top Cited PapersOpen AccessComparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge
- 22 November 2025
- Published by Springer Nature
- p. 95-104
Semi-automated Retinal Microsurgery Video Annotation with SAM2: Comparative Analysis of Prompt Strategies
- 22 November 2025
- Published by Springer Nature
- p. 95-104
Semi-automated Retinal Microsurgery Video Annotation with SAM2: Comparative Analysis of Prompt Strategies
- Open Access
Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach
Understanding surgical instrument-tissue interactions requires not only identifying which instrument performs which action on which anatomical target, but also grounding these interactions spatially within the surgical scene. Existing surgical action triplet recognition methods are limited to learning from frame-level classification, failing to reliably link actions to specific instrument instances.Previous attempts at spatial grounding have primarily relied on class activation maps, which lack the precision and robustness required for detailed instrument-tissue interaction analysis.To address this gap, we propose grounding surgical action triplets with instrument instance segmentation, or triplet segmentation for short, a new unified task which produces spatially grounded outputs.We start by presenting CholecTriplet-Seg, a large-scale dataset containing over 30,000 annotated frames, linking instrument instance masks with action verb and anatomical target annotations, and establishing the first benchmark for strongly supervised, instance-level triplet grounding and evaluation.To learn triplet segmentation, we propose TargetFusionNet, a novel architecture that extends Mask2Former with a target-aware fusion mechanism to address the challenge of accurate anatomical target prediction by fusing weak anatomy priors with instrument instance queries.Evaluated across recognition, detection, and triplet segmentation metrics, TargetFusionNet consistently improves performance over existing baselines, demonstrating that strong instance supervision combined with weak target priors significantly enhances the accuracy and robustness of surgical action understanding.Triplet segmentation establishes a unified framework for spatially grounding surgical action triplets. The proposed benchmark and architecture pave the way for more interpretable, surgical scene understanding.
Open AccessGrounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach
Understanding surgical instrument-tissue interactions requires not only identifying which instrument performs which action on which anatomical target, but also grounding these interactions spatially within the surgical scene. Existing surgical action triplet recognition methods are limited to learning from frame-level classification, failing to reliably link actions to specific instrument instances.Previous attempts at spatial grounding have primarily relied on class activation maps, which lack the precision and robustness required for detailed instrument-tissue interaction analysis.To address this gap, we propose grounding surgical action triplets with instrument instance segmentation, or triplet segmentation for short, a new unified task which produces spatially grounded outputs.We start by presenting CholecTriplet-Seg, a large-scale dataset containing over 30,000 annotated frames, linking instrument instance masks with action verb and anatomical target annotations, and establishing the first benchmark for strongly supervised, instance-level triplet grounding and evaluation.To learn triplet segmentation, we propose TargetFusionNet, a novel architecture that extends Mask2Former with a target-aware fusion mechanism to address the challenge of accurate anatomical target prediction by fusing weak anatomy priors with instrument instance queries.Evaluated across recognition, detection, and triplet segmentation metrics, TargetFusionNet consistently improves performance over existing baselines, demonstrating that strong instance supervision combined with weak target priors significantly enhances the accuracy and robustness of surgical action understanding.Triplet segmentation establishes a unified framework for spatially grounding surgical action triplets. The proposed benchmark and architecture pave the way for more interpretable, surgical scene understanding.
- Open Access
SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation
Consistent surgical instrument segmentation is critical for automation in robot-assisted surgery. Yet, existing methods only treat instrument-level instance segmentation (IIS) or part-level semantic segmentation (PSS) separately, without interaction between these tasks. In this work, we formulate a surgical tool segmentation as a unified part-aware instance segmentation (PIS) problem and introduce SurgPIS, the first PIS model for surgical instruments. Our method adopts a transformer-based mask classification approach and introduces part-specific queries derived from instrument-level object queries, explicitly linking parts to their parent instrument instances. In order to address the lack of large-scale datasets with both instance- and part-level labels, we propose a weakly-supervised learning strategy for SurgPIS to learn from disjoint datasets labelled for either IIS or PSS purposes. During training, we aggregate our PIS predictions into IIS or PSS masks, thereby allowing us to compute a loss against partially labelled datasets. A student-teacher approach is developed to maintain prediction consistency for missing PIS information in the partially labelled data, e.g., parts of the IIS labelled data. Extensive experiments across multiple datasets validate the effectiveness of SurgPIS, achieving state-of-the-art performance in PIS as well as IIS, PSS, and instrument-level semantic segmentation.
Open AccessSurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation
Consistent surgical instrument segmentation is critical for automation in robot-assisted surgery. Yet, existing methods only treat instrument-level instance segmentation (IIS) or part-level semantic segmentation (PSS) separately, without interaction between these tasks. In this work, we formulate a surgical tool segmentation as a unified part-aware instance segmentation (PIS) problem and introduce SurgPIS, the first PIS model for surgical instruments. Our method adopts a transformer-based mask classification approach and introduces part-specific queries derived from instrument-level object queries, explicitly linking parts to their parent instrument instances. In order to address the lack of large-scale datasets with both instance- and part-level labels, we propose a weakly-supervised learning strategy for SurgPIS to learn from disjoint datasets labelled for either IIS or PSS purposes. During training, we aggregate our PIS predictions into IIS or PSS masks, thereby allowing us to compute a loss against partially labelled datasets. A student-teacher approach is developed to maintain prediction consistency for missing PIS information in the partially labelled data, e.g., parts of the IIS labelled data. Extensive experiments across multiple datasets validate the effectiveness of SurgPIS, achieving state-of-the-art performance in PIS as well as IIS, PSS, and instrument-level semantic segmentation.
- Top Cited PapersOpen Access
- 20 May 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 825
CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
In laparoscopic and robotic surgery, precise tool instance segmentation is an essential technology for advanced computer-assisted interventions. Although publicly available procedures of routine surgeries exist, they often lack comprehensive annotations for tool instance segmentation. Additionally, the majority of standard datasets for tool segmentation are derived from porcine(pig) surgeries. To address this gap, we introduce CholecInstanceSeg, the largest open-access tool instance segmentation dataset to date. Derived from the existing CholecT50 and Cholec80 datasets, CholecInstanceSeg provides novel annotations for laparoscopic cholecystectomy procedures in patients. Our dataset comprises 41.9k annotated frames extracted from 85 clinical procedures and 64.4k tool instances, each labelled with semantic masks and instance IDs. To ensure the reliability of our annotations, we perform extensive quality control, conduct label agreement statistics, and benchmark the segmentation results with various instance segmentation baselines. CholecInstanceSeg aims to advance the field by offering a comprehensive and high-quality open-access dataset for the development and evaluation of tool instance segmentation algorithms.
- 20 May 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 825
Top Cited PapersOpen AccessCholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
In laparoscopic and robotic surgery, precise tool instance segmentation is an essential technology for advanced computer-assisted interventions. Although publicly available procedures of routine surgeries exist, they often lack comprehensive annotations for tool instance segmentation. Additionally, the majority of standard datasets for tool segmentation are derived from porcine(pig) surgeries. To address this gap, we introduce CholecInstanceSeg, the largest open-access tool instance segmentation dataset to date. Derived from the existing CholecT50 and Cholec80 datasets, CholecInstanceSeg provides novel annotations for laparoscopic cholecystectomy procedures in patients. Our dataset comprises 41.9k annotated frames extracted from 85 clinical procedures and 64.4k tool instances, each labelled with semantic masks and instance IDs. To ensure the reliability of our annotations, we perform extensive quality control, conduct label agreement statistics, and benchmark the segmentation results with various instance segmentation baselines. CholecInstanceSeg aims to advance the field by offering a comprehensive and high-quality open-access dataset for the development and evaluation of tool instance segmentation algorithms.
- 5 February 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 101, 103480
Multitask learning in minimally invasive surgical vision: A review
- 5 February 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 101, 103480
Multitask learning in minimally invasive surgical vision: A review
- Open Access
- 3 October 2023
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 19 (1) , 181
Correction to: Robust fetoscopic mosaicking from deep learned flow fields
- 3 October 2023
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 19 (1) , 181
Open AccessCorrection to: Robust fetoscopic mosaicking from deep learned flow fields
- Open Access
- 3 May 2022
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 17 (6) , 1125-1134
Robust fetoscopic mosaicking from deep learned flow fields
Purpose: Fetoscopic laser photocoagulation is a minimally invasive procedure to treat twin-to-twin transfusion syndrome during pregnancy by stopping irregular blood flow in the placenta. Building an image mosaic of the placenta and its network of vessels could assist surgeons to navigate in the challenging fetoscopic environment during the procedure. Methodology: We propose a fetoscopic mosaicking approach by combining deep learning-based optical flow with robust estimation for filtering inconsistent motions that occurs due to floating particles and specularities. While the current state of the art for fetoscopic mosaicking relies on clearly visible vessels for registration, our approach overcomes this limitation by considering the motion of all consistent pixels within consecutive frames. We also overcome the challenges in applying off-the-shelf optical flow to fetoscopic mosaicking through the use of robust estimation and local refinement. Results: We compare our proposed method against the state-of-the-art vessel-based and optical flow-based image registration methods, and robust estimation alternatives. We also compare our proposed pipeline using different optical flow and robust estimation alternatives. Conclusions: Through analysis of our results, we show that our method outperforms both the vessel-based state of the art and LK, noticeably when vessels are either poorly visible or too thin to be reliably identified. Our approach is thus able to build consistent placental vessel mosaics in challenging cases where currently available alternatives fail.
- 3 May 2022
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 17 (6) , 1125-1134
Open AccessRobust fetoscopic mosaicking from deep learned flow fields
Purpose: Fetoscopic laser photocoagulation is a minimally invasive procedure to treat twin-to-twin transfusion syndrome during pregnancy by stopping irregular blood flow in the placenta. Building an image mosaic of the placenta and its network of vessels could assist surgeons to navigate in the challenging fetoscopic environment during the procedure. Methodology: We propose a fetoscopic mosaicking approach by combining deep learning-based optical flow with robust estimation for filtering inconsistent motions that occurs due to floating particles and specularities. While the current state of the art for fetoscopic mosaicking relies on clearly visible vessels for registration, our approach overcomes this limitation by considering the motion of all consistent pixels within consecutive frames. We also overcome the challenges in applying off-the-shelf optical flow to fetoscopic mosaicking through the use of robust estimation and local refinement. Results: We compare our proposed method against the state-of-the-art vessel-based and optical flow-based image registration methods, and robust estimation alternatives. We also compare our proposed pipeline using different optical flow and robust estimation alternatives. Conclusions: Through analysis of our results, we show that our method outperforms both the vessel-based state of the art and LK, noticeably when vessels are either poorly visible or too thin to be reliably identified. Our approach is thus able to build consistent placental vessel mosaics in challenging cases where currently available alternatives fail.