Artificial intelligence in surgery

Nature Medicine, Journal Year: 2024, Volume and Issue: 30(5), P. 1257 - 1268

Published: May 1, 2024

Artificial intelligence (AI) is rapidly emerging in healthcare, yet applications surgery remain relatively nascent. Here we review the integration of AI field surgery, centering our discussion on multifaceted improvements surgical care preoperative, intraoperative and postoperative space. The emergence foundation model architectures, wearable technologies improving data infrastructures enabling rapid advances interventions utility. We discuss how maturing methods hold potential to improve patient outcomes, facilitate education optimize care. current deep learning approaches outline a vision for future through multimodal models. This Review outlines state art artificial settings, where it has enormous system efficiencies.

Language: Английский

---

Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions

Cancer Discovery, Journal Year: 2024, Volume and Issue: 14(5), P. 711 - 726

Published: March 21, 2024

Artificial intelligence (AI) in oncology is advancing beyond algorithm development to integration into clinical practice. This review describes the current state of field, with a specific focus on integration. AI applications are structured according cancer type and domain, focusing four most common cancers tasks detection, diagnosis, treatment. These encompass various data modalities, including imaging, genomics, medical records. We conclude summary existing challenges, evolving solutions, potential future directions for field.

Language: Английский

---

Dissecting self-supervised learning methods for surgical computer vision

Medical Image Analysis, Journal Year: 2023, Volume and Issue: 88, P. 102844 - 102844

Published: May 24, 2023

The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts annotated data, imposing a prohibitively high cost; especially clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction general community, represent potential solution these annotation costs, allowing learn useful representations from only unlabeled data. Still, effectiveness SSL methods more complex and impactful domains, as medicine surgery, remains limited unexplored. In this work, we address critical need by investigating four state-of-the-art (MoCo v2, SimCLR, DINO, SwAV) context vision. We present an extensive analysis performance on Cholec80 dataset two fundamental popular tasks understanding, phase recognition tool presence detection. examine their parameterization, then behavior respect data quantities semi-supervised settings. Correct transfer described conducted leads substantial gains over generic uses – up 7.4% 20% detection well 14%. Further results obtained highly diverse selection datasets exhibit strong generalization properties. code is available at https://github.com/CAMMA-public/SelfSupSurg.

Language: Английский

---

Practical Guide to Machine Learning and Artificial Intelligence in Surgical Education Research

JAMA Surgery, Journal Year: 2024, Volume and Issue: 159(4), P. 455 - 455

Published: Jan. 3, 2024

This Guide to Statistics and Methods gives an overview of artificial intelligence techniques tools in surgical education research.

Language: Английский

---

Continuous Intraoperative AI Monitoring of Surgical Technical Skills Using Computer Vision

The American Journal of Surgery, Journal Year: 2025, Volume and Issue: unknown, P. 116248 - 116248

Published: Feb. 1, 2025

Language: Английский

---

Endoscapes, a critical view of safety and surgical scene segmentation dataset for laparoscopic cholecystectomy

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Feb. 25, 2025

Minimally invasive image-guided surgery heavily relies on vision. Deep learning models for surgical video analysis can support surgeons in visual tasks such as assessing the critical view of safety (CVS) laparoscopic cholecystectomy, potentially contributing to and efficiency. However, performance, reliability, reproducibility are deeply dependent availability data with high-quality annotations. To this end, we release Endoscapes2023, a dataset comprising 201 cholecystectomy videos regularly spaced frames annotated segmentation masks instruments hepatocystic anatomy, well assessments criteria defining CVS by three trained following public protocol. Endoscapes2023 enables development object detection, semantic instance segmentation, prediction, safe cholecystectomy.

Language: Английский

---

Continuous patient monitoring with AI: real-time analysis of video in hospital care settings

Frontiers in Imaging, Journal Year: 2025, Volume and Issue: 4

Published: March 10, 2025

Introduction This study introduces an AI-driven platform for continuous and passive patient monitoring in hospital settings, developed by LookDeep Health. Leveraging advanced computer vision, the provides real-time insights into behavior interactions through video analysis, securely storing inference results cloud retrospective evaluation. Methods The AI system detects key components rooms, including individuals' presence roles, furniture location, motion magnitude, boundary crossings. Inference are stored dataset, compiled with 11 partners, includes over 300 high-risk fall patients spans more than 1,000 days of inference. An anonymized subset is publicly available to foster innovation reproducibility at lookdeep/ai-norms-2024 . Results Performance evaluation demonstrates strong accuracy object detection (macro F1-score = 0.92) patient-role classification (F1-score 0.98). reliably tracks “patient alone” metric (mean logistic regression 0.82 ± 0.15), enabling isolation, wandering, unsupervised movement-key indicators risk adverse events. Discussion work establishes benchmarks monitoring, highlighting platform's potential enhance safety continuous, data-driven interactions.

Language: Английский

---

Artificial Intelligence for context-aware surgical guidance in complex robot-assisted oncological procedures: An exploratory feasibility study

European Journal of Surgical Oncology, Journal Year: 2023, Volume and Issue: 50(12), P. 106996 - 106996

Published: July 28, 2023

Complex oncological procedures pose various surgical challenges including dissection in distinct tissue planes and preservation of vulnerable anatomical structures throughout different phases. In rectal surgery, violation increases the risk local recurrence autonomous nerve damage resulting incontinence sexual dysfunction. This work explores feasibility phase recognition target structure segmentation robot-assisted resection (RARR) using machine learning.A total 57 RARR were recorded subsets these annotated with respect to phases exact locations (anatomical structures, types, static areas). For recognition, three learning models trained: LSTM, MSTCN, Trans-SVNet. Based on pixel-wise annotations 9037 images, individual based DeepLabv3 trained. Model performance was evaluated F1 score, Intersection-over-Union (IoU), accuracy, precision, recall, specificity.The best results for achieved MSTCN model (F1 score: 0.82 ± 0.01, accuracy: 0.84 0.03). Mean IoUs ranged from 0.14 0.22 0.80 organs types 0.11 0.44 0.30 areas. Image quality, distorting factors (i.e. blood, smoke), technical lack depth perception) considerably impacted performance.Machine learning-based selected are feasible RARR. future, such functionalities could be integrated into a context-aware guidance system surgery.

Language: Английский

---

Computer image analysis with artificial intelligence: a practical introduction to convolutional neural networks for medical professionals

Postgraduate Medical Journal, Journal Year: 2023, Volume and Issue: 99(1178), P. 1287 - 1294

Published: Oct. 4, 2023

Abstract Artificial intelligence tools, particularly convolutional neural networks (CNNs), are transforming healthcare by enhancing predictive, diagnostic, and decision-making capabilities. This review provides an accessible practical explanation of CNNs for clinicians highlights their relevance in medical image analysis. have shown themselves to be exceptionally useful computer vision, a field that enables machines ‘see’ interpret visual data. Understanding how these models work can help leverage full potential, especially as artificial continues evolve integrate into healthcare. already demonstrated efficacy diverse fields, including radiology, histopathology, photography. In been used automate the assessment conditions such pneumonia, pulmonary embolism, rectal cancer. assess classify colorectal polyps, gastric epithelial tumours, well assist multiple malignancies. photography, retinal diseases skin conditions, detect polyps during endoscopic procedures. surgical laparoscopy, they may provide intraoperative assistance surgeons, helping anatomy demonstrate safe dissection zones. The integration analysis promises enhance diagnostic accuracy, streamline workflow efficiency, expand access expert-level analysis, contributing ultimate goal delivering further improvements patient outcomes.

Language: Английский

---

The digital transformation of surgery

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: May 31, 2023

Rapid advances in digital technology and artificial intelligence recent years have already begun to transform many industries, are beginning make headway into healthcare. There is tremendous potential for new technologies improve the care of surgical patients. In this piece, we highlight work being done advance using machine learning, computer vision, wearable devices, remote patient monitoring, virtual augmented reality. We describe ways these can be used practice surgery, discuss opportunities challenges their widespread adoption use operating rooms at bedside.

Language: Английский

---