ABSTRACT
Previous navigation systems can determine the position of the "tracked" surgical instrument in CT images in the context of functional endoscopic sinus surgery (FESS), but do not provide any assistance directly in the video endoscopic image of the surgeon. Developing this direct assistance for intraoperative orientation and risk reduction was the goal of the BIOPASS project (Bild Ontologie und prozessgestütztes Assistenzsystem). The Project pursues the development of a novel navigation system for FESS without markers. BIOPASS describes a hybrid system that integrates various sensor data and makes it available. The goal is to abandon tracking and exclusively provide navigation information directly in the video image. This paper describes the first step of the development by collecting and structuring the surgical phases (workflows), the video endoscopic landmarks and a first clinical evaluation of the model version. The results provide the important basis and platform for the next step of the project.
Subject(s)
Surgeons , Surgery, Computer-Assisted , Humans , Endoscopy , Surgical InstrumentsABSTRACT
The disease and treatment of patients with head and neck cancer can lead to multiple late and long-term sequelae. Especially pain, psychosocial problems, and voice issues can have a high impact on patients' health-related quality of life. The aim was to show the feasibility of implementing an electronic Patient-Reported Outcome Measure (PROM) in patients with head and neck cancer (HNC). Driven by our department's intention to assess Patient-Reported Outcomes (PRO) based on the International Classification of Functioning during tumor aftercare, the program "OncoFunction" has been implemented and continuously refined in everyday practice. The new version of "OncoFunction" was evaluated by 20 head and neck surgeons and radiation oncologists in an interview. From 7/2013 until 7/2017, 846 patients completed the PROM during 2,833 of 3,610 total visits (78.5%). The latest software version implemented newly developed add-ins and increased the already high approval ratings in the evaluation as the number of errors and the time required decreased (6 vs. 0 errors, 1.35 vs. 0.95 min; p<0.01). Notably, patients had different requests using PRO in homecare use. An additional examination shows that only 59% of HNC patients use the world wide web. Using OncoFunction for online-recording and interpretation of PROM improved data acquisition in daily HNC patients' follow-up. An accessory timeline grants access to former consultations and their visualization supported and simplified structured examinations. This provides an easy-to-use representation of the patient's functional outcome supporting comprehensive aftercare, considering all aspects of the patient's life.
ABSTRACT
PURPOSE: In the context of aviation and automotive navigation technology, assistance functions are associated with predictive planning and wayfinding tasks. In endoscopic minimally invasive surgery, however, assistance so far relies primarily on image-based localization and classification. We show that navigation workflows can be described and used for the prediction of navigation steps. METHODS: A natural description vocabulary for observable anatomical landmarks in endoscopic images was defined to create 3850 navigation workflow sentences from 22 annotated functional endoscopic sinus surgery (FESS) recordings. Resulting FESS navigation workflows showed an imbalanced data distribution with over-represented landmarks in the ethmoidal sinus. A transformer model was trained to predict navigation sentences in sequence-to-sequence tasks. The training was performed with the Adam optimizer and label smoothing in a leave-one-out cross-validation study. The sentences were generated using an adapted beam search algorithm with exponential decay beam rescoring. The transformer model was compared to a standard encoder-decoder-model, as well as HMM and LSTM baseline models. RESULTS: The transformer model reached the highest prediction accuracy for navigation steps at 0.53, followed by 0.35 of the LSTM and 0.32 for the standard encoder-decoder-network. With an accuracy of sentence generation of 0.83, the prediction of navigation steps at sentence-level benefits from the additional semantic information. While standard class representation predictions suffer from an imbalanced data distribution, the attention mechanism also considered underrepresented classes reasonably well. CONCLUSION: We implemented a natural language-based prediction method for sentence-level navigation steps in endoscopic surgery. The sentence-level prediction method showed a potential that word relations to navigation tasks can be learned and used for predicting future steps. Further studies are needed to investigate the functionality of path prediction. The prediction approach is a first step in the field of visuo-linguistic navigation assistance for endoscopic minimally invasive surgery.
Subject(s)
Minimally Invasive Surgical Procedures/methods , Surgery, Computer-Assisted/methods , Algorithms , Anatomic Landmarks , Endoscopy , Humans , WorkflowABSTRACT
INTRODUCTION: An increased psychosocial workload can have an negative impact on health. An effective way to record this is the effort reward imbalance model postulated by Siegrist. Values on this topic from ENT residents are missing, which is why the concept and corresponding questions were included in the survey on the current situation in further education. MATERIAL AND METHODS: An online survey on the current situation of the ENT residency including the recording of psychosocial workload was developed by ENT physicians on the basis of a well-known questionnaire of colleagues of the Alliance of Young Physicians. The short version of the validated questionnaire on the effort reward imbalance model according to Siegrist with 16 items was used. An online survey was carried out addressing all ENT residents in Germany known to the German society of Oto-Rhino-Laryngology, Head and Neck surgery. The survey was sent by e-mail and was available from April 1st to July 31st in 2019. RESULTS: 92,3â% of the participants had an effort-reward imbalance. The mean value of effort reward imbalance was 1.57â± 0.43, adjusted 2.16â±â1.36. The effort scale was 10.71â±â1.40 (3-12), adjusted 85.72â±â15.52, reward scale 16.58â±â2.86 (7-28), adjusted 45.61â±â13.63, over commitment 17â±â3.37, adjusted 61.14â±â18.73. A high effort reward imbalance had positive significant correlations with regard to the duration of residency, the number of working hours per week and the number of duty hours per month. CONCLUSION: The effort and reward imbalance is comparable to other specialty physicians in residency. It is related to working hours, services and the progress of training. It can be improved through personal initiative and could be supplemented with the support of the hospital's internal stakeholders.
Subject(s)
Internship and Residency , Otolaryngology , Germany , Humans , Reward , Stress, Psychological , Surveys and Questionnaires , WorkloadABSTRACT
BACKGROUND: Residents of ENT were asked about their situation in residency. A good and well structured training is the key for an attractive residency. METHODS: Between April 25-August 1, 2019, 691 residents registered with the German Society of Otorhinolaryngology, Head- and Neck Surgery ENT society were invited to anonymously participate in an online survey using SurveyMonkey® on the situation of the education in ENT and their working conditions. 25 of 80 questions were asked on the topics of structure and quality of the education in residency. RESULTS: The response rate was 36â% (nâ=â249). The participants attested their further training an average result. Mainly they see deficits in the further education and training structure and culture with a desire for improved feedback and improved surgical training. Participants were more dissatisfied with advanced further training time, regardless of ownership of the institution and level of care. CONCLUSIONS: The survey proposes concrete advice for improvement of ENT medical training in Germany. Suggestions for improvement are further development of the associated training and continuing education programs in cooperation with professional associations, structured feedback and supervision as well as transparent rotation plans and reliable working conditions.
Subject(s)
Internship and Residency , Otolaryngology , Germany , Humans , Otolaryngology/education , Surveys and QuestionnairesABSTRACT
OBJECTIVE: Interactive e-learning-platforms may replace the classical textbook in the future. Such media have the possible advantage of including video and audio files in a more comprehensive way, but ENT-specific platforms do not currently exist. So far, the actual needs and wishes of ENT residents are unclear and may be affected by the so called digital revolution. MATERIAL AND METHODS: An online survey was carried out addressing all ENT residents in Germany known to the German society of oto-rhino-laryngology, head and neck surgery. A 17-items survey was developed by ENT doctors receiving and providing training and distributed by e-mail. The survey was available to answer in April and May 2019. RESULTS: A total of 150 out of 671 ENT specialists and residents took part in the study. Of these, 80â% were residents and 20â% were ENT specialists. 63-80â% of the respondents already use online media in general at work, in preparation for the ENT specialist examination, for training purposes and for support as a clinician. 92-95â% of the participants indicated the willingness to use an interactive platform for their ENT specialist examination preparation and further training. On average, e-learning media are used by the responders to prepare for the ENT specialist examination or in clinical everyday life and for further training 108 or 130âmin/week. The desire for surgical instruction videos is also very high. CONCLUSION: There is a high demand for a structured e-learning-platform especially for ENT. An interactive e-learning-platform would ensure, supplement and support qualified education and training.
