Latent Graph Representations for Critical View of Safety Assessment DOI Creative Commons
Aditya Murali, Deepak Alapatt, Pietro Mascagni

et al.

arXiv (Cornell University), Journal Year: 2022, Volume and Issue: unknown

Published: Jan. 1, 2022

Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization key anatomical structures, reasoning about their geometric relationships to one another, determining quality exposure. Prior works have approached this task by including semantic segmentation as an intermediate step, using predicted masks then predict CVS. While these methods are effective, they rely on extremely expensive ground-truth annotations tend fail when is incorrect, limiting generalization. In work, we propose a method for CVS prediction wherein first represent surgical image disentangled latent scene graph, process representation graph neural network. Our representations explicitly encode information - object location, class information, relations improve anatomy-driven reasoning, well visual features retain differentiability thereby provide robustness errors. Finally, address annotation cost, train our only bounding box annotations, incorporating auxiliary reconstruction objective learn fine-grained boundaries. We show that not outperforms several baseline trained with but also scales effectively masks, maintaining state-of-the-art performance.

Language: Английский

Artificial Intelligence in Colorectal Cancer Surgery: Present and Future Perspectives DOI Open Access
Giuseppe Quero, Pietro Mascagni, Fiona R. Kolbinger

et al.

Cancers, Journal Year: 2022, Volume and Issue: 14(15), P. 3803 - 3803

Published: Aug. 4, 2022

Artificial intelligence (AI) and computer vision (CV) are beginning to impact medicine. While evidence on the clinical value of AI-based solutions for screening staging colorectal cancer (CRC) is mounting, CV AI applications enhance surgical treatment CRC still in their early stage. This manuscript introduces key concepts a audience, illustrates fundamental steps develop applications, provides comprehensive overview state-of-the-art CRC. Notably, studies show that can be trained automatically recognize phases actions with high accuracy even complex procedures such as transanal total mesorectal excision (TaTME). In addition, models were interpret fluorescent signals correct dissection planes during (TME), suggesting potentially valuable tool intraoperative decision-making guidance. Finally, could have role training, providing automatic skills assessment operating room. promising, these proofs concept require further development, validation multi-institutional data, confirm treatment.

Language: Английский

Citations

30
Role of artificial intelligence in risk prediction, prognostication, and therapy response assessment in colorectal cancer: current state and future directions DOI Creative Commons
Arian Mansur,

Zain Saleem,

Tarig Elhakim

et al.

Frontiers in Oncology, Journal Year: 2023, Volume and Issue: 13

Published: Jan. 25, 2023

Artificial Intelligence (AI) is a branch of computer science that utilizes optimization, probabilistic and statistical approaches to analyze make predictions based on vast amount data. In recent years, AI has revolutionized the field oncology spearheaded novel in management various cancers, including colorectal cancer (CRC). Notably, applications diagnose, prognosticate, predict response therapy CRC, gaining traction proving be promising. There have also been several advancements technologies help metastases CRC Computer-Aided Detection (CAD) Systems improve miss rates for neoplasia. This article provides comprehensive review role predicting risk, prognosis, therapies among patients with CRC.

Language: Английский

Citations

20
The use and future perspective of Artificial Intelligence—A survey among German surgeons DOI Creative Commons
Mathieu Pecqueux, Carina Riediger, Marius Distler

et al.

Frontiers in Public Health, Journal Year: 2022, Volume and Issue: 10

Published: Oct. 5, 2022

Clinical abundance of artificial intelligence has increased significantly in the last decade. This survey aims to provide an overview current state knowledge and acceptance AI applications among surgeons Germany.

Language: Английский

Citations

23
Anatomy segmentation in laparoscopic surgery: comparison of machine learning and human expertise – an experimental study DOI Creative Commons
Fiona R. Kolbinger,

Franziska M. Rinner,

Alexander C. Jenke

et al.

International Journal of Surgery, Journal Year: 2023, Volume and Issue: unknown

Published: Aug. 1, 2023

Lack of anatomy recognition represents a clinically relevant risk in abdominal surgery. Machine learning (ML) methods can help identify visible patterns and structures; however, their practical value remains largely unclear.Based on novel dataset 13 195 laparoscopic images with pixel-wise segmentations 11 anatomical structures, we developed specialized segmentation models for each structure combined all structures using two state-of-the-art model architectures (DeepLabv3 SegFormer) compared performance algorithms to cohort 28 physicians, medical students, laypersons the example pancreas segmentation.Mean Intersection-over-Union semantic intra-abdominal ranged from 0.28 0.83 0.23 0.77 DeepLabv3-based structure-specific models, 0.31 0.85 0.26 0.67 SegFormer-based respectively. Both are capable near-real-time operation, while not. All four outperformed at least 26 out human participants segmentation.These results demonstrate that ML have potential provide assistance minimally invasive surgery near-real-time. Future research should investigate educational subsequent clinical impact respective systems.

Language: Английский

Citations

14
Opportunities for Artificial Intelligence in Oncology: From the Lens of Clinicians and Patients DOI
Krunal Pandav, Sahar Almahfouz Nasser,

Kristen H. Kimball

et al.

JCO Oncology Practice, Journal Year: 2025, Volume and Issue: unknown

Published: March 13, 2025

Much work has been published on artificial intelligence (AI) and oncology, with many focusing an algorithm perspective. However, very few perspective articles have explicitly discussed the role of AI in oncology from perspectives stakeholders—the clinicians patients. In this article, we delve into opportunities clinician's patient's lens. From perspective, discuss reducing burnout, enhancing decision making, leveraging vast data sets to provide evidence-based recommendations, eventually affecting diagnostic accuracy treatment planning. virtual concierge, which could improve cancer care journey by facilitating patient education, mental health support, personalized lifestyle wellness recommendations promoting a holistic approach care. We aim highlight stakeholders' unmet needs guide institutions create innovative solutions oncology. By addressing these perspectives, our article aims bridge gap between technological research advancements their real-world AI-focused clinical applications Understanding prioritizing stakeholders will foster development impactful tools intentional utilization such technology, for implementation integration workflows.

Language: Английский

Citations

0
The application of augmented reality in robotic general surgery: A mini-review DOI Creative Commons
Gian Luigi Canu, Fabio Medas,

Eleonora Noli

et al.

Open Medicine, Journal Year: 2025, Volume and Issue: 20(1)

Published: Jan. 1, 2025

Abstract In robotic surgery, surgical planning and navigation represent two crucial elements, allowing surgeons to maximize outcomes while minimizing the risk of complications. this context, an emerging imaging technology, namely augmented reality (AR), can a powerful tool create integration preoperative 3D models into live intraoperative view, providing interactive visual interface rather than simple operative field. way, be guided by during operation. This makes procedure more accurate safer, leading so-called “precision surgery”. article aims provide overview developments in application AR general surgery. The technology field is showing promising results. main benefits include improved oncological reduced occurrence addition, its may also important for education. However, we are still initial phase experience some limitations remain. Moreover, our knowledge, date, reports literature regarding surgery very limited. To improve application, close collaboration between engineers, software developers, mandatory.

Language: Английский

Citations

0
Vision techniques for anatomical structures in laparoscopic surgery: a comprehensive review DOI Creative Commons
Ru Zhou, Dan Wang, Hanwei Zhang

et al.

Frontiers in Surgery, Journal Year: 2025, Volume and Issue: 12

Published: April 14, 2025

Laparoscopic surgery is the method of choice for numerous surgical procedures, while it confronts a lot challenges. Computer vision exerts vital role in addressing these challenges and has become research hotspot, especially classification, segmentation, target detection abdominal anatomical structures. This study presents comprehensive review last decade this area. At first, categorized overview core subtasks presented regarding their relevance applicability to real-world medical scenarios. Second, dataset used experimental validation statistically analyzed. Subsequently, technical approaches trends tasks are explored detail, highlighting advantages, limitations, practical implications. Additionally, evaluation methods three types discussed. Finally, gaps current identified. Meanwhile, great potential development area emphasized.

Language: Английский

Citations

0
AI-Driven Decision-Making in Healthcare Information Systems: A Comprehensive Review DOI
Zahra Mohtasham‐Amiri,

Ali Taghavirashidizadeh,

Parsa Khorrami

et al.

Journal of Systems and Software, Journal Year: 2025, Volume and Issue: unknown, P. 112470 - 112470

Published: April 1, 2025

Language: Английский

Citations

0
Ai-Driven Decision-Making in Healthcare Information Systems: A Comprehensive Review DOI
Zahra Mohtasham‐Amiri

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

Citations

2
Performance evaluation and future prospects of capsule robot localization technology DOI Creative Commons
Yan Xu, Peng Zhang, Lei Wang

et al.

Geo-spatial Information Science, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 31

Published: May 28, 2024

Capsule Robot Endoscope (CRE), as one of the widely used methods gastrointestinal medical examination, has characteristics painless, non-cross infection, and no movement restriction, compared with other traditional endoscopes. To obtain precise location lesion, positioning capsule robot in digestive tract become a hot research topic related fields. In recent decades, rapid advancement indoor outdoor technologies, several well-established have emerged that enable acquisition high-precision real-time spatiotemporal integration data. These hold great potential for interdisciplinary applications services across various domains. The manuscript aims to draw inspiration from surveying mapping techniques by reviewing existing microspace technologies overcome inherent technical challenges. This article reviewed more than 100 pieces literature at home abroad four major academic search engines further studied state art commonly used. Microspace technology robots is evaluated eight factors: accuracy, power consumption, portability, comfort, complexity, robustness, extensibility, cost. We summarize challenges associated each technology's limitations, finally proffering prospective avenues future research. Our investigation reveals six identified distinct advantages disadvantages. Among these, magnetic field-based exhibited superior overall performance gradually advancing toward commercialization. Vision-based technology, while significantly contributing applications, particularly enhancing augmented reality surgical navigation, faces weak-textured non-rigid environment. Additionally, limitation posed size energy consumption make difficulties single-source techniques. proposed promising directions considering robot's current technological advancements cutting-edge technologies. include exploring new sources, integrating multiple sensor fusion, developing three-dimensional models. approaches are expected enhance safety reliability technology. They can potentially promote development provide support diagnosing treating diseases.

Language: Английский

Citations

2