Validation of an artificial intelligence platform for the guidance of safe laparoscopic cholecystectomy

Laplante, Simon; Namazi, Babak; Kiani, Parmiss; Hashimoto, Daniel A.; Pasten, Mauricio; Brunt, L. Michael; Gill, Sujata; Davis, Brian R.; Bloom, Matthew B.; Pernar, Luise I.M.; Okrainec, Allan; Madani, Amin

doi:10.1007/s00464-022-09439-9

Cited by 20 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study conducted by Mascagni et al 10 explored the feasibility of an automatic assessment system that can recognize critical view of safety in laparoscopic cholecystectomy with a mean average precision of 0.71. Furthermore, Madani et al 29 developed and trained models to identify safe and dangerous zones of dissection in laparoscopic cholecystectomy and validated the results with an external panel of experts 28,29 . Similarly, recognition of the LAV during left adrenalectomy can potentially help to prevent intraoperative complications, reduce blood loss, and improve postoperative outcomes.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, Madani et al 29 developed and trained models to identify safe and dangerous zones of dissection in laparoscopic cholecystectomy and validated the results with an external panel of experts. 28,29 Similarly, recognition of the LAV during left adrenalectomy can potentially help to prevent intraoperative complications, reduce blood loss, and improve postoperative outcomes. However, it is undeniable that numerous and extensive trials are needed to prove its safety and generalizability before the deployment of such a system.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Minimally Invasive Adrenalectomy: Using Deep Learning to Identify the Left Adrenal Vein

Sengun

İşcan

Özbulak

et al. 2023

Surgical Laparoscopy, Endoscopy &Amp; Percutaneous Techniques

View full text Add to dashboard Cite

Background: Minimally invasive adrenalectomy is the main surgical treatment option for the resection of adrenal masses. Recognition and ligation of adrenal veins are critical parts of adrenal surgery. The utilization of artificial intelligence and deep learning algorithms to identify anatomic structures during laparoscopic and robot-assisted surgery can be used to provide real-time guidance. Methods: In this experimental feasibility study, intraoperative videos of patients who underwent minimally invasive transabdominal left adrenalectomy procedures between 2011 and 2022 in a tertiary endocrine referral center were retrospectively analyzed and used to develop an artificial intelligence model. Semantic segmentation of the left adrenal vein with deep learning was performed. To train a model, 50 random images per patient were captured during the identification and dissection of the left adrenal vein. A randomly selected 70% of data was used to train models while 15% for testing and 15% for validation with 3 efficient stage-wise feature pyramid networks (ESFPNet). Dice similarity coefficient (DSC) and intersection over union scores were used to evaluate segmentation accuracy. Results: A total of 40 videos were analyzed. Annotation of the left adrenal vein was performed in 2000 images. The segmentation network training on 1400 images was used to identify the left adrenal vein in 300 test images. The mean DSC and sensitivity for the highest scoring efficient stage-wise feature pyramid network B-2 network were 0.77 (±0.16 SD) and 0.82 (±0.15 SD), respectively, while the maximum DSC was 0.93, suggesting a successful prediction of anatomy. Conclusions: Deep learning algorithms can predict the left adrenal vein anatomy with high performance and can potentially be utilized to identify critical anatomy during adrenal surgery and provide real-time guidance in the near future.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence in Minimally Invasive Adrenalectomy: Using Deep Learning to Identify the Left Adrenal Vein

Sengun

İşcan

Özbulak

et al. 2023

Surgical Laparoscopy, Endoscopy &Amp; Percutaneous Techniques

View full text Add to dashboard Cite

show abstract

“…78 Real-time intraoperative decision support for laparoscopic cholecystectomy has been recently developed with the participation of a panel of expert surgeons from the Society of American Gastrointestinal and Endoscopic Surgeons Safe Cholecystectomy Task Force. 79 Artificial intelligence is now able to identify safe and dangerous zones of dissection within the surgical field, with high specificity/positive predictive value for "Go zones" and high sensitivity/negative predictive value for "No-Go zones" in the area of Calot's triangle. This technology is promising in minimizing the risk of adverse intraoperative events, especially for surgeons with less experience.…”

Section: Digitalization In Prediction Prevention and Recording Of Com...mentioning

confidence: 99%

Classification of Adverse Events in Adult Surgery

2023

View full text Add to dashboard Cite

Successful surgery combines quality (achievement of a positive outcome) with safety (avoidance of a negative outcome). Outcome assessment serves the purpose of quality improvement in health care by establishing performance indicators and allowing the identification of performance gaps. Novel surgical quality metric tools (benchmark cutoffs and textbook outcomes) provide procedure-specific ideal surgical outcomes in a subgroup of well-defined low-risk patients, with the aim of setting realistic and best achievable goals for surgeons and centers, as well as supporting unbiased comparison of surgical quality between centers and periods of time. Validated classification systems have been deployed to grade adverse events during the surgical journey: (1) the ClassIntra classification for the intraoperative period; (2) the Clavien–Dindo classification for the gravity of single adverse events; and the (3) Comprehensive Complication Index (CCI) for the sum of adverse events over a defined postoperative period. The failure to rescue rate refers to the death of a patient following one or more potentially treatable postoperative adverse event(s) and is a reliable proxy of the institutional safety culture and infrastructure. Complication assessment is undergoing digital transformation to decrease resource-intensity and provide surgeons with real-time pre- or intraoperative decision support. Standardized reporting of complications informs patients on their chances to realize favorable postoperative outcomes and assists surgical centers in the prioritization of quality improvement initiatives, multidisciplinary teamwork, surgical education, and ultimately, in the enhancement of clinical standards.

show abstract

“…Tokuyasu et al [ 23 ] devised a real-time object detection model based on YOLOv3 for identifying four landmarks, which displays the bounding box of the cystic duct, common bile duct, lower edge of the left medial segment, and Rouviere's sulcus on monitors during LC. Additionally, GoNoGoNet [ 24 ], a convolutional neural network model, was introduced to identify safe and unsafe dissection zones by visualizing these areas with topographical heat maps. However, no previous research has specifically addressed the real-time visualization of a guided dissection line using deep learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Development of deep learning framework for anatomical landmark detection and guided dissection line during laparoscopic cholecystectomy

Smithmaitrie,

Khaonualsri,

Sae-Lim

et al. 2024

Heliyon

View full text Add to dashboard Cite

Validation of an artificial intelligence platform for the guidance of safe laparoscopic cholecystectomy

Cited by 20 publications

References 27 publications

Artificial Intelligence in Minimally Invasive Adrenalectomy: Using Deep Learning to Identify the Left Adrenal Vein

Artificial Intelligence in Minimally Invasive Adrenalectomy: Using Deep Learning to Identify the Left Adrenal Vein

Classification of Adverse Events in Adult Surgery

Development of deep learning framework for anatomical landmark detection and guided dissection line during laparoscopic cholecystectomy

Contact Info

Product

Resources

About