A research group led by Prof. Jia Fucang from the Shenzhen Institute of Advanced Technology (SIAT) of the Chinese Academy of Sciences has proposed a multi-task fine-grained spatiotemporal model that can effectively identify action triplets in laparoscopic gallbladder removal surgery videos.
In this study, the researchers developed a novel model for surgical action triplet recognition. This model consists of two key components: acapable of handling multiple tasks simultaneously in surgical video, and a loss function designed for multiple similar labels."Both spatial and temporal features within surgical videos are considered by our framework, a departure from previous methods that predominantly focused on spatial features alone," said Prof. Jia.
The proposed model outperformed existing methods, including Triplet, Attention Triplet, and Rendezvous approaches. Compared to the state-of-the-art Rendezvous method, the model achieved average precision improvements of 4.6%, 4.0%, and 7.8% in instrument, action, and organ recognition tasks, reaching 82.1%, 51.5%, and 45.5%, respectively. In the overall triplets' recognition task, the proposed model also improved by 3.1% in average precision, reaching 35.8%.
"In future work, we aim to enhance recognition accuracy based on the proposed model framework," said Prof. Jia.Yuchong Li et al, MT-FiST: A Multi-Task Fine-grained Spatial-Temporal Framework for Surgical Action Triplet Recognition,
United Kingdom Latest News, United Kingdom Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Researchers develop AI model to improve tumor removal accuracy during breast cancer surgeryArtificial intelligence (AI) and machine learning tools have received a lot of attention recently, with the majority of discussions focusing on proper use. However, this technology has a wide range of practical applications, from predicting natural disasters to addressing racial inequalities and now, assisting in cancer surgery.
Read more »
Medical researchers tackle immune rejection of biomedical implantsTo learn more about what causes the body to reject biomedical implants, a team at the University of Arizona College of Medicine-Tucson identified a protein that appears to help drive this response, and hopes their discoveries will improve the design and safety of biomedical implants. The findings were published today in Nature Biomedical Engineering.
Read more »
Researchers find contaminated water in fast-food soda fountainsLoma Linda University (LLU) researchers found microbial contamination in common sources of drinking water in the Eastern Coachella Valley, including soda fountains at fast-food restaurants. Their findings revealed that 41% of the water samples researchers collected from these soda fountains contained total coliforms, an indicator of water contamination.
Read more »
Researchers describe clinical experiences of transgender people, recommend new strategiesMany transgender people experience mistreatment in health care encounters, which can include harassment, assault and denial of care. A new paper published in the September/October 2023 issue of Annals of Family Medicine describes the clinical experiences of transgender people. Study authors also present short-term and long-term strategies towards reducing oppression and its health consequences among this patient population.
Read more »
Researchers identify important strategies for diabetes care and quality improvements in the primary care settingA qualitative study published in the Annals of Family Medicine considers how the strategies used by high-performing primary care practices to improve diabetes care might play a role in successfully managing practice change.
Read more »