Medical Surgery Stream Segmentation to Detect and Track Robotic Tools

Published: Feb. 5, 2024

This paper presents a real-time image segmentation and tracking system that can operate on continuous stream of endoscopic surgical videos. Such find several valuable applications in the medical field, such as building augmentations to assist with robotic surgeries, training residents, summarizing surgery videos generate reports having whole understanding procedure. We have formulated technique requires minimal supervision provides objects. The results from evaluation our approach indicate even annotated data surgeons, we achieve good segmentation. reduces need for extensive expensive collection annotation processes surgery. evaluated two datasets, EndoVis 2017 2018, dataset Robotic Instrument sub-challenge MICCAI 2018. Our are par state-of-the-art methods EndoVis-17 EndoVis-18 binary meanIoU 92.26% 82.40% respectively, case multi-class, do it achieving 74.43% averaged over all classes video sequences. main contribution is give streaming data.

Language: Английский

---

Human-Centered Edge Artificial Intelligence for Smart Factory Applications in Industry 5.0: A Review and Perspective

Springer series in reliability engineering, Journal Year: 2024, Volume and Issue: unknown, P. 79 - 100

Published: Jan. 1, 2024

Language: Английский

---

IG-Net: An Instrument-guided real-time semantic segmentation framework for prostate dissection during surgery for low rectal cancer

Computer Methods and Programs in Biomedicine, Journal Year: 2024, Volume and Issue: 257, P. 108443 - 108443

Published: Sept. 28, 2024

Language: Английский

---

Exploring the Effect of Dataset Diversity in Self-supervised Learning for Surgical Computer Vision

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 43 - 53

Published: Oct. 24, 2024

Language: Английский

---

SnapSeek 2.0 at Video Browser Showdown 2025

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 339 - 346

Published: Dec. 31, 2024

Language: Английский

---