Deepak Alapatt
YOU?
Author Swipe
View article: Current validation practice undermines surgical AI development
Current validation practice undermines surgical AI development Open
Surgical data science (SDS) is rapidly advancing, yet clinical adoption of artificial intelligence (AI) in surgery remains severely limited, with inadequate validation emerging as a key obstacle. In fact, existing validation practices ofte…
View article: The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment
The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment Open
Advances in artificial intelligence (AI) for surgical quality assessment promise to democratize access to expertise, with applications in training, guidance, and accreditation. This study presents the SAGES Critical View of Safety (CVS) Ch…
View article: Endoscapes, a critical view of safety and surgical scene segmentation dataset for laparoscopic cholecystectomy
Endoscapes, a critical view of safety and surgical scene segmentation dataset for laparoscopic cholecystectomy Open
View article: Analyzing the impact of surgical technique on intraoperative adverse events in laparoscopic Roux-en-Y gastric bypass surgery by video-based assessment
Analyzing the impact of surgical technique on intraoperative adverse events in laparoscopic Roux-en-Y gastric bypass surgery by video-based assessment Open
Background Despite high-level evidence that variations of surgical technique in laparoscopic Roux-en-Y gastric bypass (LRYGB) are correlated with postoperative outcomes and might be linked to intraoperative adverse events (iAEs), there are…
View article: Optimizing Latent Graph Representations of Surgical Scenes for Zero-Shot Domain Transfer
Optimizing Latent Graph Representations of Surgical Scenes for Zero-Shot Domain Transfer Open
Purpose: Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera s…
View article: The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark
The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark Open
This technical report provides a detailed overview of Endoscapes, a dataset of laparoscopic cholecystectomy (LC) videos with highly intricate annotations targeted at automated assessment of the Critical View of Safety (CVS). Endoscapes com…
View article: Jumpstarting Surgical Computer Vision
Jumpstarting Surgical Computer Vision Open
Consensus amongst researchers and industry points to a lack of large, representative annotated datasets as the biggest obstacle to progress in the field of surgical data science. Advances in Self-Supervised Learning (SSL) represent a solut…
View article: Latent Graph Representations for Critical View of Safety Assessment
Latent Graph Representations for Critical View of Safety Assessment Open
Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality…
View article: CholecTriplet2022: Show me a tool and tell me the triplet — An endoscopic vision challenge for surgical action triplet detection
CholecTriplet2022: Show me a tool and tell me the triplet — An endoscopic vision challenge for surgical action triplet detection Open
View article: CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition Open
View article: CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection Open
Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more…
View article: Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning
Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning Open
View article: Biomedical image analysis competitions: The state of current participation practice
Biomedical image analysis competitions: The state of current participation practice Open
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the c…
View article: Real-Time Artificial Intelligence Assistance for Safe Laparoscopic Cholecystectomy: Early-Stage Clinical Evaluation
Real-Time Artificial Intelligence Assistance for Safe Laparoscopic Cholecystectomy: Early-Stage Clinical Evaluation Open
Artificial intelligence is set to be deployed in operating rooms to improve surgical care. This early-stage clinical evaluation shows the feasibility of concurrently attaining real-time, high-quality predictions from several deep neural ne…
View article: Latent Graph Representations for Critical View of Safety Assessment
Latent Graph Representations for Critical View of Safety Assessment Open
Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality…
View article: Federated Cycling (FedCy): Semi-Supervised Federated Learning of Surgical Phases
Federated Cycling (FedCy): Semi-Supervised Federated Learning of Surgical Phases Open
Recent advancements in deep learning methods bring computer-assistance a step closer to fulfilling promises of safer surgical procedures. However, the generalizability of such methods is often dependent on training on diverse datasets from…
View article: Computer vision in surgery: from potential to clinical value
Computer vision in surgery: from potential to clinical value Open
View article: Dissecting Self-Supervised Learning Methods for Surgical Computer Vision
Dissecting Self-Supervised Learning Methods for Surgical Computer Vision Open
The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity of deep neural network-based methods. However, standard fully-supervised approaches for training such models require …
View article: CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition Open
Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, s…
View article: Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation
Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation Open
A major obstacle to building models for effective semantic segmentation, and particularly video semantic segmentation, is a lack of large and well annotated datasets. This bottleneck is particularly prohibitive in highly specialized and re…
View article: 2020 CATARACTS Semantic Segmentation Challenge
2020 CATARACTS Semantic Segmentation Challenge Open
Surgical scene segmentation is essential for anatomy and instrument localization which can be further used to assess tissue-instrument interactions during a surgical procedure. In 2017, the Challenge on Automatic Tool Annotation for cataRA…
View article: Surgical data science for safe cholecystectomy: a protocol for segmentation of hepatocystic anatomy and assessment of the critical view of safety
Surgical data science for safe cholecystectomy: a protocol for segmentation of hepatocystic anatomy and assessment of the critical view of safety Open
Minimally invasive image-guided surgery heavily relies on vision. Deep learning models for surgical video analysis could therefore support visual tasks such as assessing the critical view of safety (CVS) in laparoscopic cholecystectomy (LC…
View article: Endoscopic Vision Challenge 2021
Endoscopic Vision Challenge 2021 Open
Minimally invasive surgery using cameras to observe the internal anatomy is the preferred approach to many surgical procedures. Furthermore, other surgical disciplines rely on microscopic images or use flexible endoscopes for diagnostic pu…
View article: Artificial Intelligence in Surgery: Neural Networks and Deep Learning
Artificial Intelligence in Surgery: Neural Networks and Deep Learning Open
Deep neural networks power most recent successes of artificial intelligence, spanning from self-driving cars to computer aided diagnosis in radiology and pathology. The high-stake data intensive process of surgery could highly benefit from…