Video feedback provides a wealth of information about surgical procedures and is the main sensory cue for surgeons. Scene understanding is crucial to computer assisted interventions (CAI) and to post-operative analysis of the surgical procedure. A fundamental building block of such capabilities is the identification and localization of surgical instruments and anatomical structures through semantic segmentation. Deep learning has advanced semantic segmentation techniques in the recent years but is inherently reliant on the availability of labelled datasets for model training. This paper introduces a dataset for semantic segmentation of cataract surgery videos complementing the publicly available CATARACTS challenge dataset. In addition, we benchmark the performance of several state-of-the-art deep learning models for semantic segmentation on the presented dataset. The dataset is publicly available at https://cataracts-semantic-segmentation2020.grand-challenge.org/.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.media.2021.102053 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Social inequalities in green exposure in small- and medium-sized U.S. cities: A mobility-based approach.
Soc Sci Res
March 2025
Department of Geography, Virginia Tech, Blacksburg, VA 24061, USA. Electronic address:
Background: Green space exposure has been considered essential for people's physical and mental health. Researchers have investigated uneven exposure to green space based on individuals' home locations, which may exacerbate health disparities. A mobility-based approach enables a more accurate assessment of green exposure in daily activity patterns.
View Article and Find Full Text PDFHWA-ResMamba: automatic segmentation of coronary arteries based on residual Mamba with high-order wavelet-enhanced convolution and attention feature aggregation.
Phys Med Biol
March 2025
Northeastern University, Baita Street, Hunnan District, Shenyang, Liaoning Province，China, Shenyang, Liaoning, 110169, CHINA.
Automatic segmentation of coronary arteries is a crucial prerequisite in assisting in the diagnosis of coronary artery disease. However, due to the fuzzy boundaries, small-slender branches, and significant individual variations, automatic segmentation of coronary arteries is extremely challenging. To address these challenges, this study proposes a residual Mamba with high-order wavelet-enhanced convolution and attention feature aggregation (HWA-ResMamba).
View Article and Find Full Text PDFPatho-Net: enhancing breast cancer classification using deep learning and explainable artificial intelligence.
Am J Cancer Res
February 2025
Department of Computer Science and Engineering, K.S.R. College of Engineering (Autonomous) Tiruchengode, Namakkal, Tamilnadu, India.
Breast cancer is a disorder affecting women globally, and hence an early and precise classification is the best possible treatment to increase the survival rate. However, the breast cancer classification faced difficulties in scalability, fixed-size input images, and overfitting on limited datasets. To tackle these issues, this work proposes a Patho-Net model for breast cancer classification that overcomes the problems of scalability in color normalization, integrates the Gated Recurrent Unit (GRU) network with the U-Net architecture to process images without the need for resizing and computational efficiency, and addresses the overfitting problems.
View Article and Find Full Text PDFComparative Study of Deep Transfer Learning Models for Semantic Segmentation of Human Mesenchymal Stem Cell Micrographs.
Int J Mol Sci
March 2025
V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
The aim of this study is to conduct a comparative assessment of the effectiveness of neural network models-U-Net, DeepLabV3+, SegNet and Mask R-CNN-for the semantic segmentation of micrographs of human mesenchymal stem cells (MSCs). A dataset of 320 cell micrographs annotated by cell biology experts was created. The models were trained using a transfer learning method based on ImageNet pre-trained weights.
View Article and Find Full Text PDFUnsupervised semantic label generation in agricultural fields.
Front Robot AI
February 2025
Center for Robotics, University of Bonn, Bonn, Germany.
Robust perception systems allow farm robots to recognize weeds and vegetation, enabling the selective application of fertilizers and herbicides to mitigate the environmental impact of traditional agricultural practices. Today's perception systems typically rely on deep learning to interpret sensor data for tasks such as distinguishing soil, crops, and weeds. These approaches usually require substantial amounts of manually labeled training data, which is often time-consuming and requires domain expertise.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!