RESUMO
BACKGROUND: Laparoscopic cholecystectomy is a very frequent surgical procedure. However, in an ageing society, less surgical staff will need to perform surgery on patients. Collaborative surgical robots (cobots) could address surgical staff shortages and workload. To achieve context-awareness for surgeon-robot collaboration, the intraoperative action workflow recognition is a key challenge. METHODS: A surgical process model was developed for intraoperative surgical activities including actor, instrument, action and target in laparoscopic cholecystectomy (excluding camera guidance). These activities, as well as instrument presence and surgical phases were annotated in videos of laparoscopic cholecystectomy performed on human patients (n = 10) and on explanted porcine livers (n = 10). The machine learning algorithm Distilled-Swin was trained on our own annotated dataset and the CholecT45 dataset. The validation of the model was conducted using a fivefold cross-validation approach. RESULTS: In total, 22,351 activities were annotated with a cumulative duration of 24.9 h of video segments. The machine learning algorithm trained and validated on our own dataset scored a mean average precision (mAP) of 25.7% and a top K = 5 accuracy of 85.3%. With training and validation on our dataset and CholecT45, the algorithm scored a mAP of 37.9%. CONCLUSIONS: An activity model was developed and applied for the fine-granular annotation of laparoscopic cholecystectomies in two surgical settings. A machine recognition algorithm trained on our own annotated dataset and CholecT45 achieved a higher performance than training only on CholecT45 and can recognize frequently occurring activities well, but not infrequent activities. The analysis of an annotated dataset allowed for the quantification of the potential of collaborative surgical robots to address the workload of surgical staff. If collaborative surgical robots could grasp and hold tissue, up to 83.5% of the assistant's tissue interacting tasks (i.e. excluding camera guidance) could be performed by robots.
Assuntos
Colecistectomia Laparoscópica , Aprendizado de Máquina , Procedimentos Cirúrgicos Robóticos , Colecistectomia Laparoscópica/métodos , Procedimentos Cirúrgicos Robóticos/métodos , Humanos , Suínos , Animais , Algoritmos , Gravação em Vídeo , Fluxo de TrabalhoRESUMO
BACKGROUND: Laparoscopic videos are increasingly being used for surgical artificial intelligence (AI) and big data analysis. The purpose of this study was to ensure data privacy in video recordings of laparoscopic surgery by censoring extraabdominal parts. An inside-outside-discrimination algorithm (IODA) was developed to ensure privacy protection while maximizing the remaining video data. METHODS: IODAs neural network architecture was based on a pretrained AlexNet augmented with a long-short-term-memory. The data set for algorithm training and testing contained a total of 100 laparoscopic surgery videos of 23 different operations with a total video length of 207 h (124 min ± 100 min per video) resulting in 18,507,217 frames (185,965 ± 149,718 frames per video). Each video frame was tagged either as abdominal cavity, trocar, operation site, outside for cleaning, or translucent trocar. For algorithm testing, a stratified fivefold cross-validation was used. RESULTS: The distribution of annotated classes were abdominal cavity 81.39%, trocar 1.39%, outside operation site 16.07%, outside for cleaning 1.08%, and translucent trocar 0.07%. Algorithm training on binary or all five classes showed similar excellent results for classifying outside frames with a mean F1-score of 0.96 ± 0.01 and 0.97 ± 0.01, sensitivity of 0.97 ± 0.02 and 0.0.97 ± 0.01, and a false positive rate of 0.99 ± 0.01 and 0.99 ± 0.01, respectively. CONCLUSION: IODA is able to discriminate between inside and outside with a high certainty. In particular, only a few outside frames are misclassified as inside and therefore at risk for privacy breach. The anonymized videos can be used for multi-centric development of surgical AI, quality management or educational purposes. In contrast to expensive commercial solutions, IODA is made open source and can be improved by the scientific community.
Assuntos
Inteligência Artificial , Laparoscopia , Humanos , Privacidade , Laparoscopia/métodos , Algoritmos , Redes Neurais de Computação , Gravação em VídeoRESUMO
For the reproduction of healthy society, it is necessary to pay special attention to self-preserving behavior of population, since health is not only medical, but also and social category. The health acts both as result of interaction of individual and the social environment, and as key condition for successful implementation of social statuses and roles, viability of social system as a whole. The spontaneous "health-saving" socialization, and, as a result, lacking of formation of behavioral patterns related to maintaining and strengthening health, imitation practices of self-care, which are demonstrated by different social demographic groups, especially young population, form danger of development of chronic diseases, further deterioration of national health indices, including decreasing reproductive potential of the state and increasing risks of for demographic policy in the future. This dictate needs for systematic analysis of factors and causes that lead to weak behavioral activity of Russian population in matters of "health-saving", determining their significance and relationship with health indices. The expert survey was carried out that allowed to identify configuration of main factors and risks in the system "environment - health", significantly affecting development of patterns of behavior in relation to it. The participation of experts representing various areas of professional activity (health care, physical education, ecology, state and municipal administration, education and science) proves high reliability of results and makes it possible to consider localization of main external dangers with highest rates of negative impact on development of self-preservation attitudes. The overall pattern of significance of various factors determining possible variations and main line of behavior of population of the central regions of Russia in context of health conservation allows to bring to foreground personal factors associated with willingness to ensure reproduction of one's own health, infrastructural and socio-economic factors that determine individual and group opportunities for Russia population to use potential of "health-saving" attitudes as well as factors of trust acting as an impulse, activating relationship of population and health care system.
Assuntos
Atitude Frente a Saúde , Nível de Saúde , Humanos , Reprodutibilidade dos Testes , Federação Russa , Inquéritos e QuestionáriosRESUMO
The article elaborates on research tasks determining the vector trends and key risks of actual models of self-preserving behavior of population in Russia on scale of national security level and searching the means of increasing effectiveness of regional demographic policy in area of developing effective self-preserving choices of life-style strategies. The results of sociological survey of the aspects of self-preserving behavior of residents of the central regions of the Russian Federation (the study was carried out on a quota sample, n = 1060) are analyzed. The study made it possible to answer the questions about the importance of health and to assess it identifying the groups of relative and absolute risk. The study provided following results: the importance factors affecting development of self-preserving behavioral patterns and choice trajectories among respondents, as well as motivation for health protection and for refusal to live longer. The most important factors turned out to be personal resources and family upbringing. The most powerful motivation was the desire for well-being, participation in children's lives and self-fulfillment. The results of the study made it possible to identify self-preserving perimeter of residents of the central part of Russia. Though being aware of and understanding the importance and priority of health, almost half of the respondents waive their responsibility for their own well-being and life expectancy and at the same time displaying a clear distrust of medical institutions. Such a position of non-resource situation foregrounds all the possible risks associated with both loss of health and the failure to maintain it at satisfactory level. The results of study confirm the research hypothesis that the groups of relative and absolute risk correlate with the groups choosing external locus of control over their health. The obtained data is the basis for empirical verification of the indices of self-preserving strategies and the starting point for forecast calculations of possible risks of national demographic policy.