Imanol Luengo
Research Subjects
Imanol Luengo has a total of 116 co-authors. Here are the top co-authors by number of shared publications:
- Danail Stoyanov
University College London
8 shared publications - Ricardo Sanchez-Matilla
Centre for Intelligent Sensing Queen Mary University of London London UK
5 shared publications - Nicolas Toussaint
AI Centre of Excellence, Medtronic Ltd., Watford, UK
4 shared publications - Abdolrahim Kadkhodamohammadi
ICube University of Strasbourg CNRS IHU Strasbourg France
3 shared publications - Emanuele Colleoni
Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London (UCL), London, U.K.
3 shared publications - Muhammad Asad
Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom
3 shared publications
Latest Publications
- 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
- 2 January 2026
- Published by Springer Nature
- p. 74-84
Temporally Stable Monocular Depth Estimation in Surgical Vision
- 2 January 2026
- Published by Springer Nature
- p. 74-84
Temporally Stable Monocular Depth Estimation in Surgical Vision
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP, 1
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated “Corruptions”– An EndoVis’24 Challenge
Surgical data science has seen rapid ad vancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes, DNNs have been proven susceptible to minor "corrup tions," substantially impairing the model's performance, introducing a major concern for the translation of cutting-edge technology, especially in high-stakes scenarios. We introduce the SegSTRONG-C challenge dedicated to better understanding model deterioration under unforeseen but plausible non-adversarial "corruption" and the capabilities of contemporary methods that seek to improve it. Built on a dataset generated through counterfactual robotic replay, SegSTRONG-C provides paired clean and "corrupted" samples, enabling reproducible evaluation of model robustness. Participants are challenged to train tool segmentation algorithms on "uncorrupted" data and evaluate them on "corrupted" test domains for the binary robot tool segmentation task. Through comprehensive baseline experiments and participating submissions from widespread community engagement, SegSTRONG-C reveals key themes for model failure and identifies promising directions for improving robustness. The performance of challenge winners, achieving an average 0.9394 DSC and 0.9301 NSD across the unreleased test sets with "corruption" types: bleeding, smoke, and low brightness. This highlights how prior knowledge, customized training strategies, and architectural choice can be leveraged to improve robustness. In conclusion, the SegSTRONG-C challenge has identified practical approaches for enhancing model robustness. However, most approaches rely on conventional techniques that have known limitations. Looking ahead, we advocate for expanding intellectual diversity and creativity in non-adversarial robustness beyond data augmentation, calling for new paradigms that enhance universal robustness to unforeseen "corruptions" to facilitate richer applications in surgical data science.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP, 1
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated “Corruptions”– An EndoVis’24 Challenge
Surgical data science has seen rapid ad vancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes, DNNs have been proven susceptible to minor "corrup tions," substantially impairing the model's performance, introducing a major concern for the translation of cutting-edge technology, especially in high-stakes scenarios. We introduce the SegSTRONG-C challenge dedicated to better understanding model deterioration under unforeseen but plausible non-adversarial "corruption" and the capabilities of contemporary methods that seek to improve it. Built on a dataset generated through counterfactual robotic replay, SegSTRONG-C provides paired clean and "corrupted" samples, enabling reproducible evaluation of model robustness. Participants are challenged to train tool segmentation algorithms on "uncorrupted" data and evaluate them on "corrupted" test domains for the binary robot tool segmentation task. Through comprehensive baseline experiments and participating submissions from widespread community engagement, SegSTRONG-C reveals key themes for model failure and identifies promising directions for improving robustness. The performance of challenge winners, achieving an average 0.9394 DSC and 0.9301 NSD across the unreleased test sets with "corruption" types: bleeding, smoke, and low brightness. This highlights how prior knowledge, customized training strategies, and architectural choice can be leveraged to improve robustness. In conclusion, the SegSTRONG-C challenge has identified practical approaches for enhancing model robustness. However, most approaches rely on conventional techniques that have known limitations. Looking ahead, we advocate for expanding intellectual diversity and creativity in non-adversarial robustness beyond data augmentation, calling for new paradigms that enhance universal robustness to unforeseen "corruptions" to facilitate richer applications in surgical data science.
- Open Access
Learning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy
Purpose: Accurate assessment of surgical complexity is essential in Laparoscopic Cholecystectomy (LC), where severe inflammation is associated with longer operative times and increased risk of postoperative complications. The Parkland Grading Scale (PGS) provides a clinically validated framework for stratifying inflammation severity; however, its automation in surgical videos remains largely unexplored, particularly in realistic scenarios where complete videos must be analyzed without prior manual curation. Methods: In this work, we introduce STC-Net, a novel framework for SingleTimestamp-based Complexity estimation in LC via the PGS, designed to operate under weak temporal supervision. Unlike prior methods limited to static images or manually trimmed clips, STC-Net operates directly on full videos. It jointly performs temporal localization and grading through a localization, window proposal, and grading module. We introduce a novel loss formulation combining hard and soft localization objectives and background-aware grading supervision. Results: Evaluated on a private dataset of 1,859 LC videos, STC-Net achieves an accuracy of 62.11% and an F1-score of 61.42%, outperforming non-localized baselines by over 10% in both metrics and highlighting the effectiveness of weak supervision for surgical complexity assessment. Conclusion: STC-Net demonstrates a scalable and effective approach for automated PGS-based surgical complexity estimation from full LC videos, making it promising for post-operative analysis and surgical training.
Open AccessLearning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy
Purpose: Accurate assessment of surgical complexity is essential in Laparoscopic Cholecystectomy (LC), where severe inflammation is associated with longer operative times and increased risk of postoperative complications. The Parkland Grading Scale (PGS) provides a clinically validated framework for stratifying inflammation severity; however, its automation in surgical videos remains largely unexplored, particularly in realistic scenarios where complete videos must be analyzed without prior manual curation. Methods: In this work, we introduce STC-Net, a novel framework for SingleTimestamp-based Complexity estimation in LC via the PGS, designed to operate under weak temporal supervision. Unlike prior methods limited to static images or manually trimmed clips, STC-Net operates directly on full videos. It jointly performs temporal localization and grading through a localization, window proposal, and grading module. We introduce a novel loss formulation combining hard and soft localization objectives and background-aware grading supervision. Results: Evaluated on a private dataset of 1,859 LC videos, STC-Net achieves an accuracy of 62.11% and an F1-score of 61.42%, outperforming non-localized baselines by over 10% in both metrics and highlighting the effectiveness of weak supervision for surgical complexity assessment. Conclusion: STC-Net demonstrates a scalable and effective approach for automated PGS-based surgical complexity estimation from full LC videos, making it promising for post-operative analysis and surgical training.
- 12 October 2025
- Published by Springer Nature
- p. 115-124
Zero-Shot Monocular Metric Depth for Endoscopic Images
- 12 October 2025
- Published by Springer Nature
- p. 115-124
Zero-Shot Monocular Metric Depth for Endoscopic Images
- Open Access
Zero-shot Monocular Metric Depth for Endoscopic Images
Monocular relative and metric depth estimation has seen a tremendous boost in the last few years due to the sharp advancements in foundation models and in particular transformer based networks. As we start to see applications to the domain of endoscopic images, there is still a lack of robust benchmarks and high-quality datasets in that area. This paper addresses these limitations by presenting a comprehensive benchmark of state-of-the-art (metric and relative) depth estimation models evaluated on real, unseen endoscopic images, providing critical insights into their generalisation and performance in clinical scenarios. Additionally, we introduce and publish a novel synthetic dataset (EndoSynth) of endoscopic surgical instruments paired with ground truth metric depth and segmentation masks, designed to bridge the gap between synthetic and real-world data. We demonstrate that fine-tuning depth foundation models using our synthetic dataset boosts accuracy on most unseen real data by a significant margin. By providing both a benchmark and a synthetic dataset, this work advances the field of depth estimation for endoscopic images and serves as an important resource for future research. Project page, EndoSynth dataset and trained weights are available at https://github.com/TouchSurgery/EndoSynth.
Open AccessZero-shot Monocular Metric Depth for Endoscopic Images
Monocular relative and metric depth estimation has seen a tremendous boost in the last few years due to the sharp advancements in foundation models and in particular transformer based networks. As we start to see applications to the domain of endoscopic images, there is still a lack of robust benchmarks and high-quality datasets in that area. This paper addresses these limitations by presenting a comprehensive benchmark of state-of-the-art (metric and relative) depth estimation models evaluated on real, unseen endoscopic images, providing critical insights into their generalisation and performance in clinical scenarios. Additionally, we introduce and publish a novel synthetic dataset (EndoSynth) of endoscopic surgical instruments paired with ground truth metric depth and segmentation masks, designed to bridge the gap between synthetic and real-world data. We demonstrate that fine-tuning depth foundation models using our synthetic dataset boosts accuracy on most unseen real data by a significant margin. By providing both a benchmark and a synthetic dataset, this work advances the field of depth estimation for endoscopic images and serves as an important resource for future research. Project page, EndoSynth dataset and trained weights are available at https://github.com/TouchSurgery/EndoSynth.
- 28 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5540-5550
DIPO: Differentiable Parallel Operation Blocks for Surgical Neural Architecture Search
Deep learning has been used across a large number of computer vision tasks, however designing the network architectures for each task is time consuming. Neural Architecture Search (NAS) promises to automatically build neural networks, optimised for the given task and dataset. However, most NAS methods are constrained to a specific macro-architecture design which makes it hard to apply to different tasks (classification, detection, segmentation). Following the work in Differentiable NAS (DNAS), we present a simple and efficient NAS method, Differentiable Parallel Operation (DIPO), that constructs a local search space in the form of a DIPO block, and can easily be applied to any convolutional network by injecting it in-place of the convolutions. The DIPO block's internal architecture and parameters are automatically optimised end-to-end for each task. We demonstrate the flexibility of our approach by applying DIPO to 4 model architectures (U-Net, HRNET, KAPAO and YOLOX) across different surgical tasks (surgical scene segmentation, surgical instrument detection, and surgical instrument pose estimation) and evaluated across 5 datasets. Results show significant improvements in surgical scene segmentation (+10.5% in CholecSeg8K, +13.2% in CaDIS), instrument detection (+1.5% in ROBUST-MIS, +5.3% in RoboKP), and instrument pose estimation (+9.8% in RoboKP).
- 28 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5540-5550
DIPO: Differentiable Parallel Operation Blocks for Surgical Neural Architecture Search
Deep learning has been used across a large number of computer vision tasks, however designing the network architectures for each task is time consuming. Neural Architecture Search (NAS) promises to automatically build neural networks, optimised for the given task and dataset. However, most NAS methods are constrained to a specific macro-architecture design which makes it hard to apply to different tasks (classification, detection, segmentation). Following the work in Differentiable NAS (DNAS), we present a simple and efficient NAS method, Differentiable Parallel Operation (DIPO), that constructs a local search space in the form of a DIPO block, and can easily be applied to any convolutional network by injecting it in-place of the convolutions. The DIPO block's internal architecture and parameters are automatically optimised end-to-end for each task. We demonstrate the flexibility of our approach by applying DIPO to 4 model architectures (U-Net, HRNET, KAPAO and YOLOX) across different surgical tasks (surgical scene segmentation, surgical instrument detection, and surgical instrument pose estimation) and evaluated across 5 datasets. Results show significant improvements in surgical scene segmentation (+10.5% in CholecSeg8K, +13.2% in CaDIS), instrument detection (+1.5% in ROBUST-MIS, +5.3% in RoboKP), and instrument pose estimation (+9.8% in RoboKP).
- Open Access
Self-Knowledge Distillation for Surgical Phase Recognition
Purpose: Advances in surgical phase recognition are generally led by training deeper networks. Rather than going further with a more complex solution, we believe that current models can be exploited better. We propose a self-knowledge distillation framework that can be integrated into current state-of-the-art (SOTA) models without requiring any extra complexity to the models or annotations. Methods: Knowledge distillation is a framework for network regularization where knowledge is distilled from a teacher network to a student network. In self-knowledge distillation, the student model becomes the teacher such that the network learns from itself. Most phase recognition models follow an encoder-decoder framework. Our framework utilizes self-knowledge distillation in both stages. The teacher model guides the training process of the student model to extract enhanced feature representations from the encoder and build a more robust temporal decoder to tackle the over-segmentation problem. Results: We validate our proposed framework on the public dataset Cholec80. Our framework is embedded on top of four popular SOTA approaches and consistently improves their performance. Specifically, our best GRU model boosts performance by +3.33% accuracy and +3.95% F1-score over the same baseline model. Conclusion: We embed a self-knowledge distillation framework for the first time in the surgical phase recognition training pipeline. Experimental results demonstrate that our simple yet powerful framework can improve performance of existing phase recognition models. Moreover, our extensive experiments show that even with 75% of the training set we still achieve performance on par with the same baseline model trained on the full set.
Open AccessSelf-Knowledge Distillation for Surgical Phase Recognition
Purpose: Advances in surgical phase recognition are generally led by training deeper networks. Rather than going further with a more complex solution, we believe that current models can be exploited better. We propose a self-knowledge distillation framework that can be integrated into current state-of-the-art (SOTA) models without requiring any extra complexity to the models or annotations. Methods: Knowledge distillation is a framework for network regularization where knowledge is distilled from a teacher network to a student network. In self-knowledge distillation, the student model becomes the teacher such that the network learns from itself. Most phase recognition models follow an encoder-decoder framework. Our framework utilizes self-knowledge distillation in both stages. The teacher model guides the training process of the student model to extract enhanced feature representations from the encoder and build a more robust temporal decoder to tackle the over-segmentation problem. Results: We validate our proposed framework on the public dataset Cholec80. Our framework is embedded on top of four popular SOTA approaches and consistently improves their performance. Specifically, our best GRU model boosts performance by +3.33% accuracy and +3.95% F1-score over the same baseline model. Conclusion: We embed a self-knowledge distillation framework for the first time in the surgical phase recognition training pipeline. Experimental results demonstrate that our simple yet powerful framework can improve performance of existing phase recognition models. Moreover, our extensive experiments show that even with 75% of the training set we still achieve performance on par with the same baseline model trained on the full set.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2384-2393
ASPnet: Action Segmentation with Shared-Private Representation of Multiple Data Sources
Most state-of-the-art methods for action segmentation are based on single input modalities or naïve fusion of multiple data sources. However, effective fusion of complementary information can potentially strengthen segmentation models and make them more robust to sensor noise and more accurate with smaller training datasets. In order to improve multimodal representation learning for action segmentation, we propose to disentangle hidden features of a multi-stream segmentation model into modality-shared components, containing common information across data sources, and private components; we then use an attention bottleneck to capture long-range temporal dependencies in the data while preserving disentanglement in consecutive processing layers. Evaluation on 50salads, Breakfast and RARP45 datasets shows that our multimodal approach outperforms different data fusion baselines on both multiview and multimodal data sources, obtaining competitive or better results compared with the state-of-the-art. Our model is also more robust to additive sensor noise and can achieve performance on par with strong video baselines even with less training data.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2384-2393
ASPnet: Action Segmentation with Shared-Private Representation of Multiple Data Sources
Most state-of-the-art methods for action segmentation are based on single input modalities or naïve fusion of multiple data sources. However, effective fusion of complementary information can potentially strengthen segmentation models and make them more robust to sensor noise and more accurate with smaller training datasets. In order to improve multimodal representation learning for action segmentation, we propose to disentangle hidden features of a multi-stream segmentation model into modality-shared components, containing common information across data sources, and private components; we then use an attention bottleneck to capture long-range temporal dependencies in the data while preserving disentanglement in consecutive processing layers. Evaluation on 50salads, Breakfast and RARP45 datasets shows that our multimodal approach outperforms different data fusion baselines on both multiview and multimodal data sources, obtaining competitive or better results compared with the state-of-the-art. Our model is also more robust to additive sensor noise and can achieve performance on par with strong video baselines even with less training data.
- Open Access
- 2 December 2020
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 9 (3) , 286-293
Towards video-based surgical workflow understanding in open orthopaedic surgery
Safe and efficient surgical training and workflow management play a critical role in clinical competency and ultimately, patient outcomes. Video data in minimally invasive surgery (MIS) have enabled opportunities for vision-based artificial intelligence (AI) systems to improve surgical skills training and assurance through post-operative video analysis and development of real-time computer-assisted interventions (CAI). Despite the availability of mounted cameras for the operating room (OR), similar capabilities are much more complex to develop for recording open surgery procedures, which has resulted in a shortage of exemplar video-based training materials. In this paper, we present a potential solution to record open surgical procedures using head-mounted cameras. Recorded videos were anonymised to remove patient and staff identifiable information using a machine learning algorithm that achieves state-of-the-art results on the OR Face dataset. We then propose a CNN-LSTM-based model to automatically segment videos into different surgical phases, which has never been previously demonstrated in open procedures. The redacted videos, along with the automatically predicted phases, are then available for surgeons and their teams for post-operative review and analysis. To our knowledge, this is the first demonstration of the feasibility of deploying camera recording systems and developing machine learning-based workflow analysis solutions for open surgery, particularly in orthopaedics.
- 2 December 2020
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 9 (3) , 286-293
Open AccessTowards video-based surgical workflow understanding in open orthopaedic surgery
Safe and efficient surgical training and workflow management play a critical role in clinical competency and ultimately, patient outcomes. Video data in minimally invasive surgery (MIS) have enabled opportunities for vision-based artificial intelligence (AI) systems to improve surgical skills training and assurance through post-operative video analysis and development of real-time computer-assisted interventions (CAI). Despite the availability of mounted cameras for the operating room (OR), similar capabilities are much more complex to develop for recording open surgery procedures, which has resulted in a shortage of exemplar video-based training materials. In this paper, we present a potential solution to record open surgical procedures using head-mounted cameras. Recorded videos were anonymised to remove patient and staff identifiable information using a machine learning algorithm that achieves state-of-the-art results on the OR Face dataset. We then propose a CNN-LSTM-based model to automatically segment videos into different surgical phases, which has never been previously demonstrated in open procedures. The redacted videos, along with the automatically predicted phases, are then available for surgeons and their teams for post-operative review and analysis. To our knowledge, this is the first demonstration of the feasibility of deploying camera recording systems and developing machine learning-based workflow analysis solutions for open surgery, particularly in orthopaedics.