Automated quality assessment (AQA) in transoesophageal echocardiography (TEE) contributes to accurate diagnosis and echocardiographers' training, providing direct feedback for the development of dexterous skills. However, prior works only perform AQA on simulated TEE data due to the scarcity of real data, which lacks applicability in the real world. Considering the cost and limitations of collecting TEE data from real cases, exploiting the readily available simulated data for AQA in real-world TEE is desired. In this paper, we construct the first simulation-to-real TEE dataset, and propose a novel Simulation-to-Real network (SR-AQA) with unsupervised domain adaptation for this problem. It is based on uncertainty-aware feature stylization (UFS), incorporating style consistency learning (SCL) and task-specific learning (TL), to achieve high generalizability. Concretely, UFS estimates the uncertainty of feature statistics in the real domain and diversifies simulated images with style variants extracted from the real images, alleviating the domain gap. We enforce SCL and TL across different real-stylized variants to learn domain-invariant and task-specific representations. Experimental results demonstrate that our SR-AQA outperforms state-of-the-art methods with 3.02% and 4.37% performance gain in two AQA regression tasks, by using only 10% unlabelled real data. Our code and dataset are available at https://doi.org/10.5522/04/23699736.

Transoesophageal echocardiography (TEE) is a valuable diagnostic and monitoring imaging modality. Proper image acquisition is essential for diagnosis, yet current assessment techniques are solely based on manual expert review. This paper presents a supervised deep learn ing framework for automatically evaluating and grading the quality of TEE images. To obtain the necessary dataset, 38 participants of varied experience performed TEE exams with a high-fidelity virtual reality (VR) platform. Two Convolutional Neural Network (CNN) architectures, AlexNet and VGG, structured to perform regression, were finetuned and validated on manually graded images from three evaluators. Two different scoring strategies, a criteria-based percentage and an overall general impression, were used. The developed CNN models estimate the average score with a root mean square accuracy ranging between 84%-93%, indicating the ability to replicate expert valuation. Proposed strategies for automated TEE assessment can have a significant impact on the training process of new TEE operators, providing direct feedback and facilitating the development of the necessary dexterous skills.

This paper presents a novel approach for evaluating technical skills in Transoesophageal Echocardiography (TEE). Our core assumption is that operational competency can be objectively expressed by specific motion-based measures. TEE experiments were carried out with an augmented reality simulation platform involving both novice trainees and expert radiologists. Probe motion data were collected and used to formulate various kinematic parameters. Subsequent analysis showed that statistically significant differences exist among the two groups for the majority of the metrics investigated. Experts exhibited lower completion times and higher average velocity and acceleration, attributed to their refined ability for efficient and economical probe manipulation. In addition, their navigation pattern is characterised by increased smoothness and fluidity, evaluated through the measures of dimensionless jerk and spectral arc length. Utilised as inputs to well-known clustering algorithms, the derived metrics are capable of discriminating experience levels with high accuracy (>84

A 74-year-old woman, who had previously been fit and well, presented to the emergency department in September 2001 after a self-terminating episode of palpitations lasting 30 minutes. This was not associated with chest pain or shortness of breath. There was no history suggestive of embolic phenomena. The history was otherwise unremarkable. Examination revealed a soft systolic murmur in the mitral area with no tumor “plop” heard. The electrocardiogram showed lateral T-wave depression but no other abnormalities. The chest radiograph, troponin T, and creatine kinase were normal. An outpatient transthoracic echocardiogram was performed and showed a 4 cm × 6 cm mass in the left atrium that appeared to be attached to the interatrial septum. Flow through the mitral valve was not obstructed, nor did the tumor prolapse through it. The valves and ventricles appeared normal. A presumptive diagnosis of a left atrial myxoma was made, and she was admitted for surgery. After an uneventful induction of anesthesia and intubation, a transesophageal echocardiogram (TEE) probe was inserted without difficulty. This confirmed the presence of a left atrial mass attached to the interatrial septum, which is best seen in the midesophageal bicaval view (Fig 1.). A midline sternotomy was made, and after aortic and superior and inferior vena caval cannulation, cardiopulmonary bypass (CPB) was instituted. Cold blood cardioplegia was used, and the patient was cooled to 32°C. Surgical access to the left atrium was gained via the right atrium, and the tumor appeared to be removed in its entirety. The left atrial appendage and pulmonary veins were flushed with saline. The interatrial septum and right atrium were closed. The heart was refilled and deairing was performed and checked using TEE. However, after the removal of the aortic cross-clamp and reinstitution of mechanical ventilation before discontinuation of CPB, 2 free fragments of tumor were noted on TEE. They appeared to enter the left atrium from the right lower pulmonary vein. One fragment rapidly descended into the left ventricle and was seen disappearing up the left ventricular outflow tract before rapid replacement of the aortic cross-clamp. Ventricular fibrillation was induced, and a mass was then seen in a midesophageal long-axis view to lie trapped between the cross-clamp and the aortic valve (Fig 2).The aorta was opened, and cardioplegia was given via the coronary ostia. A 1 cm × 2 cm mass was removed from the aortic root. The second mass of similar size was removed by opening the left atrium and flushing out the left ventricle with saline. Discontinuation of CPB was achieved without difficulty, and the patient was successfully extubated 6 hours later in the intensive care unit. There was no apparent neurologic deficit, and her recovery was uneventful. The clinical indications for transesophageal echocardiography include aortic dissection, dysfunction of valvular prosthesis, detection of an intracardiac source of embolism, assessment of infective endocarditis, congenital and valvular heart disease, and evaluation of cardiac masses.1Lesbre JP The main indications for transesophageal echocardiography.Ann Cardiol Angeiol. 1995; 44: 547-551PubMed Google Scholar Intraoperative echocardiography (IOE) has been shown to be of use in confirming diagnoses, altering surgical management plans, and achieving stable hemodynamic variables by the use of fluid challenges and inotropic support.2Couture P Denault AY McKenty S et al.Impact of routine use of intraoperative transesophageal echocardiography during cardiac surgery.Can J Anaesth. 2000; 47: 20-26Crossref PubMed Scopus (90) Google Scholar, 3Hodgins L Kisslo JA Mark JB Perioperative transesophageal echocardiography: the anesthesiologist as cardiac diagnostician.Anesth Analg. 1995; 80: 4-6PubMed Google Scholar, 4Kolev N Brase R Swanevelder J et al.The influence of transoesophageal echocardiography on intraoperative decision-making. A European multicentre study.Anaesthesia. 1998; 53 (European Perioperative TOE Research Group): 767-773Crossref PubMed Scopus (82) Google Scholar, 5Sousa RC Garcia-Fernandez MA Moreno M et al.The contribution and usefulness of routine intraoperative transesophageal echocardiography in cardiac surgery. An analysis of 130 consecutive cases.Revista Portuguesa Cardiologia. 1995; 14: 15-27PubMed Google Scholar The impact on clinical decision-making, which has been reported to be as high as 50% in some series,6Schmidlin D Bettex D Bernard E et al.Transoesophageal echocardiography in cardiac and vascular surgery: implications and observer variability.Br J Anaesth. 2001; 86: 497-505Crossref PubMed Scopus (29) Google Scholar has been used to justify the considerable outlay cost of buying the machine and probe.7Murphy PM Pro: Intraoperative transesophageal echocardiography is a cost-effective strategy for cardiac surgical procedures.J Cardiothorac Vasc Anesth. 1997; 11: 246-249Abstract Full Text PDF PubMed Scopus (22) Google Scholar Transesophageal echocardiography, however, is not without risk, and these risks have to be balanced against the potential benefits. In view of this, the ASA/SCA has drawn up guidelines for indications for intraoperative echocardiography. These guidelines place the removal of cardiac tumors in class 11a (ie, weight of evidence/opinion is in favor of usefulness/efficacy). Our case illustrates that without the benefit of IOE, this woman would have suffered 2 tumor emboli with potentially fatal or severe complications, adding evidence in favor of intracardiac tumors stepping up into class 1 (ie, conditions for which there is evidence and or general agreement that a given procedure or treatment is useful and effective). We would recommend that IOE is used in the removal of intracardiac tumors to confirm the diagnosis and tumor position, aid the surgeon in his/her approach to tumor removal, and lastly to assist in deairing and prevention of tumor embolization. doi: 10.1053/jcan.2003.30