Chinedu Innocent Nwoye
A5018519401- Surgical Simulation and Training
- Anatomy and Medical Technology
- Artificial Intelligence in Healthcare and Education
- Digital Imaging in Medicine
- Augmented Reality Applications
- Cardiac, Anesthesia and Surgical Outcomes
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Domain Adaptation and Few-Shot Learning
- Colorectal Cancer Screening and Detection
- 3D Shape Modeling and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Biomedical Text Mining and Ontologies
- Enhanced Recovery After Surgery
- Digital Communication and Language
- Advanced X-ray and CT Imaging
- Advanced Authentication Protocols Security
- Biomedical and Engineering Education
- User Authentication and Security Systems
- Biometric Identification and Security
- Medical Imaging and Analysis
- Face recognition and analysis
- Robotics and Sensor-Based Localization
- Chaos-based Image/Signal Encryption
Laboratoire des Sciences de l'Ingénieur, de l'Informatique et de l'Imagerie
2019-2024
Institut de Recherche contre les Cancers de l’Appareil Digestif
2024
Hôpital Civil, Strasbourg
2023
Université de Strasbourg
2018-2023
Centre National de la Recherche Scientifique
2018-2023
Institut de Chirurgie Guidée par l'Image
2022
Hôpitaux Universitaires de Strasbourg
2019
University of Nigeria
2016
Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase safety operation through context-sensitive warnings semi-autonomous robotic or improve training surgeons via data-driven feedback. In up to 91% average precision has been reported phase recognition on an open data single-center video dataset. this work we investigated generalizability algorithms in a multicenter setting including more...
The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts annotated data, imposing a prohibitively high cost; especially clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction general community, represent potential solution these annotation costs, allowing learn useful...
Acquiring and annotating surgical data is often resource-intensive, ethical constraining, requiring significant expert involvement. While generative AI models like text-to-image can alleviate scarcity, incorporating spatial annotations, such as segmentation masks, crucial for precision-driven applications, simulation, education. This study introduces both a novel task method, SimGen, Simultaneous Image Mask Generation. SimGen diffusion model based on the DDPM framework Residual U-Net,...
The number of international benchmarking competitions is steadily increasing in various fields machine learning (ML) research and practice. So far, however, little known about the common practice as well bottlenecks faced by community tackling questions posed. To shed light on status quo algorithm development specific field biomedical imaging analysis, we designed an survey that was issued to all participants challenges conducted conjunction with IEEE ISBI 2021 MICCAI conferences (80 total)....
In addition to generating data and annotations, devising sensible splitting strategies evaluation metrics is essential for the creation of a benchmark dataset. This practice ensures consensus on usage data, homogeneous assessment, uniform comparison research methods study focuses CholecT50, which 50 video surgical dataset that formalizes activities as triplets <instrument, verb, target>. this paper, we introduce standard splits CholecT50 CholecT45 datasets show how they compare with existing...
The ability to automatically detect and track surgical instruments in endoscopic videos can enable transformational interventions. Assessing performance efficiency, identifying skilled tool use choreography, planning operational logistical aspects of OR resources are just a few the applications that could benefit. Unfortunately, obtaining annotations needed train machine learning models identify localize tools is difficult task. Annotating bounding boxes frame-by-frame tedious...
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 cataRACT Surgery (CATARACTS) released 50 cataract surgery videos accompanied by usage annotations. These annotations included frame-level presence information. 2020, we pixel-wise semantic instruments 4670 images sampled from 25 of CATARACTS training set. The 2020...
PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase safety operation through context-sensitive warnings semi-autonomous robotic or improve training surgeons via data-driven feedback. In up to 91% average precision has been reported phase recognition on an open data single-center dataset. this work we investigated generalizability algorithms in a multi-center setting including more...
The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts annotated data, imposing a prohibitively high cost; especially clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction general community, represent potential solution these annotation costs, allowing learn useful...
Tool tracking in surgical videos is vital computer-assisted intervention for tasks like surgeon skill assessment, safety zone estimation, and human-machine collaboration during minimally invasive procedures. The lack of large-scale datasets hampers Artificial Intelligence implementation this domain. Current exhibit overly generic formalization, often lacking context: a deficiency that becomes evident when tools move out the camera's scope, resulting rigid trajectories hinder realistic...
Accurate tool tracking is essential for the success of computer-assisted intervention. Previous efforts often modeled trajectories rigidly, overlooking dynamic nature surgical procedures, especially scenarios like out-of-body and out-of-camera views. Addressing this limitation, new CholecTrack20 dataset provides detailed labels that account multiple in three perspectives: (1) intraoperative, (2) intracorporeal, (3) visibility, representing different types temporal duration tracks. These...