Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917884439035904 |
|---|---|
| author | Sinha, Sanya Balazia, Michal Bremond, Francois |
| author_facet | Sinha, Sanya Balazia, Michal Bremond, Francois |
| contents | Instructional cataract surgery videos are crucial for ophthalmologists and trainees to observe surgical details repeatedly. This paper presents a deep learning model for real-time identification of surgical instruments in these videos, using a custom dataset scraped from open-access sources. Inspired by the architecture of YOLOV9, the model employs a Programmable Gradient Information (PGI) mechanism and a novel Generally-Optimized Efficient Layer Aggregation Network (Go-ELAN) to address the information bottleneck problem, enhancing Minimum Average Precision (mAP) at higher Non-Maximum Suppression Intersection over Union (NMS IoU) scores. The Go-ELAN YOLOV9 model, evaluated against YOLO v5, v7, v8, v9 vanilla, Laptool and DETR, achieves a superior mAP of 73.74 at IoU 0.5 on a dataset of 615 images with 10 instrument classes, demonstrating the effectiveness of the proposed model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02618 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network Sinha, Sanya Balazia, Michal Bremond, Francois Computer Vision and Pattern Recognition 68T05, 68T10 I.5 Instructional cataract surgery videos are crucial for ophthalmologists and trainees to observe surgical details repeatedly. This paper presents a deep learning model for real-time identification of surgical instruments in these videos, using a custom dataset scraped from open-access sources. Inspired by the architecture of YOLOV9, the model employs a Programmable Gradient Information (PGI) mechanism and a novel Generally-Optimized Efficient Layer Aggregation Network (Go-ELAN) to address the information bottleneck problem, enhancing Minimum Average Precision (mAP) at higher Non-Maximum Suppression Intersection over Union (NMS IoU) scores. The Go-ELAN YOLOV9 model, evaluated against YOLO v5, v7, v8, v9 vanilla, Laptool and DETR, achieves a superior mAP of 73.74 at IoU 0.5 on a dataset of 615 images with 10 instrument classes, demonstrating the effectiveness of the proposed model. |
| title | Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network |
| topic | Computer Vision and Pattern Recognition 68T05, 68T10 I.5 |
| url | https://arxiv.org/abs/2501.02618 |