Artificial intelligence-based automated laparoscopic cholecystectomy surgical phase recognition and analysis

Cheng, Ke; You, Jiaying; Wu, Shangdi; Chen, Zixin; Zhou, Zijian; Guan, Jingye; Peng, Bing; Wang, Xin

doi:10.1007/s00464-021-08619-3

Cited by 41 publications

(21 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies [4,7,13,15,[29][30][31] used a variety of methods to improve the degree of accuracy in the online use of deep learning models, such as the recognition information of surgical tools, LSTM, and the hidden Markov model. Certainly, LSTM and the hidden Markov model are effective for LC videos that proceed according to a standardized operation procedure; in other words, the transition pattern of the surgical phase is fixed to some extent [5].…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, the possibilities of SPM will expand with the advanced image recognition of deep learning [1]. Recognition technology for surgical phases using deep learning has been used in a variety of cases; for instance, predicting an operation's end time with an image of the surgical field, supporting surgeons' intraoperative decision-making [1][2][3], indexing surgical videos in a database [4,5], and assessing operation skill using videos. Notably, it is necessary that a deep learning model used in an operation room has high versatility for an unknown image.…”

mentioning

confidence: 99%

“…In our research, surgical phase recognition based on deep learning has been applied to laparoscopic cholecystectomy [4,7] and laparoscopic sigmoidectomy [8,9]. In both cases, and Other Interventional Techniques the technology recognized the surgical phases of each operation with high accuracy, especially the surgical tools, which were important factors to increase the degree of recognition accuracy [7].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence software available for medical devices: surgical phase recognition in laparoscopic cholecystectomy

et al. 2022

View full text Add to dashboard Cite

Background Surgical process modeling automatically identifies surgical phases, and further improvement in recognition accuracy is expected with deep learning. Surgical tool or time series information has been used to improve the recognition accuracy of a model. However, it is difficult to collect this information continuously intraoperatively. The present study aimed to develop a deep convolution neural network (CNN) model that correctly identifies the surgical phase during laparoscopic cholecystectomy (LC). Methods We divided LC into six surgical phases (P1–P6) and one redundant phase (P0). We prepared 115 LC videos and converted them to image frames at 3 fps. Three experienced doctors labeled the surgical phases in all image frames. Our deep CNN model was trained with 106 of the 115 annotation datasets and was evaluated with the remaining datasets. By depending on both the prediction probability and frequency for a certain period, we aimed for highly accurate surgical phase recognition in the operation room. Results Nine full LC videos were converted into image frames and were fed to our deep CNN model. The average accuracy, precision, and recall were 0.970, 0.855, and 0.863, respectively. Conclusion The deep learning CNN model in this study successfully identified both the six surgical phases and the redundant phase, P0, which may increase the versatility of the surgical process recognition model for clinical use. We believe that this model can be used in artificial intelligence for medical devices. The degree of recognition accuracy is expected to improve with developments in advanced deep learning algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence software available for medical devices: surgical phase recognition in laparoscopic cholecystectomy

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Videos with a Parkland score ≥3 were assigned to the inflammatory group, whereas videos with a Parkland score <3 were assigned to the non-inflammatory group. The LC procedure was divided into seven surgical phases—establish access (EA), adhesion lysis (AL), mobilize hepatocystic triangle (MHT), dissect gallbladder from liver bed (DGB), extract the gallbladder (EG), clear the operative region (COR), and idle time (ID)—based on our previous study ( 29 ). The ID was defined as the period when the camera was aimed away from the abdomen or indicated no action in the abdomen.…”

Section: Methodsmentioning

confidence: 99%

Critical view of safety in laparoscopic cholecystectomy: A prospective investigation from both cognitive and executive aspects

Jin

Liu²,

Chen

et al. 2022

Front. Surg.

Self Cite

View full text Add to dashboard Cite

BackgroundThe achievement rate of the critical view of safety during laparoscopic cholecystectomy is much lower than expected. This original study aims to investigate and analyze factors associated with a low critical view of safety achievement.Materials and MethodsWe prospectively collected laparoscopic cholecystectomy videos performed from September 2, 2021, to September 19, 2021, in Sichuan Province, China. The artificial intelligence system, SurgSmart, analyzed videos under the necessary corrections undergone by expert surgeons. Also, we distributed questionnaires to surgeons and analyzed them along with surgical videos simultaneously.ResultsWe collected 169 laparoscopic cholecystectomy surgical videos undergone by 124 surgeons, among which 105 participants gave valid answers to the questionnaire. Excluding those who conducted the bail-out process directly, the overall critical view of safety achievement rates for non-inflammatory and inflammatory groups were 18.18% (18/99) and 9.84% (6/61), respectively. Although 80.95% (85/105) of the surgeons understood the basic concept of the critical view of safety, only 4.76% (5/105) of the respondents commanded all three criteria in an error-free way. Multivariate logistic regression results showed that an unconventional surgical workflow (OR:12.372, P < 0.001), a misunderstanding of the 2nd (OR: 8.917, P < 0.05) and 3rd (OR:8.206, P < 0.05) criterion of the critical view of safety, and the don't mistake “fundus-first technique” as one criterion of the critical view of safety (OR:0.123, P < 0.01) were associated with lower and higher achievements of the critical view of safety, respectively.ConclusionsThe execution and cognition of the critical view of safety are deficient, especially the latter one. Thus, increasing the critical view of safety surgical awareness may effectively improve its achievement rate.

show abstract

“…AI has been employed in various areas in the field of surgery, as a mean to optimize the management of patients and surgical techniques and as a support to training. AI is currently being tested in clinical practice to aid preoperative diagnosis and staging and to help predict response to treatment, particularly in the field of surgical oncology [11,12] . Moreover, some models have been developed with the aim to support clinical decision-making during surgery.…”

Section: How Technology Can Help Female Surgeonsmentioning

confidence: 99%

Statement on artificial intelligence surgery by women-in-surgery - Italia: can artificial intelligence be the great equalizer in surgery?

Spolverato¹,

Capelli²,

Majidi³

et al. 2021

AIS

View full text Add to dashboard Cite

Artificial intelligence-based automated laparoscopic cholecystectomy surgical phase recognition and analysis

Cited by 41 publications

References 31 publications

Artificial intelligence software available for medical devices: surgical phase recognition in laparoscopic cholecystectomy

Artificial intelligence software available for medical devices: surgical phase recognition in laparoscopic cholecystectomy

Critical view of safety in laparoscopic cholecystectomy: A prospective investigation from both cognitive and executive aspects

Statement on artificial intelligence surgery by women-in-surgery - Italia: can artificial intelligence be the great equalizer in surgery?

Contact Info

Product

Resources

About