Reliability and Influence on Decision Making of fully-automated vs. semi-automated Software Packages for Procedural Planning in TAVI

A fully automated artificial intelligence-driven software for planning of transcatheter aortic valve replacement

BACKGROUND

Transcatheter aortic valve replacement (TAVR) is increasingly performed for the treatment of aortic stenosis. Computed tomography (CT) analysis is essential for pre-procedural planning. Currently available software packages for TAVR planning require substantial human interaction. We describe development and validation of an artificial intelligence (AI) powered software to automatically rend anatomical measurements and other information required for TAVR planning and implantation.

METHODS

Automated measurements from 100 CTs were compared to measurements from three expert clinicians and TAVR operators using commercially available software packages. Correlation coefficients and mean differences were calculated to assess precision and accuracy.

RESULTS

AI-generated annular measurements had excellent agreements with manual measurements by expert operators yielding correlation coefficients of 0.97 for both perimeter and area. There was no relevant bias with a mean difference of -0.07 mm and - 1.4 mm2 for perimeter and area, respectively. For the ascending aorta measured 5 cm above the annular plane, correlation coefficient was 0.95 and mean difference was 1.4 mm. Instruction for use-based sizing yielded agreement with the effective implant size in 87-88 % of patients for self-expanding valves (perimeter-based sizing) and in 88 % for balloon-expandable valves (area-based sizing).

CONCLUSIONS

A fully automated software enables accurate and precise anatomical segmentation and measurements required for TAVR planning without human interaction and with high reliability.

Transcatheter Aortic Valve Replacement and Coronary Protection Guided by Deep Learning and 3-Dimensional Printing

OBJECTIVE

In this case report, the auxiliary role of deep learning and 3-dimensional printing technology in the perioperative period was discussed to guide transcatheter aortic valve replacement and coronary stent implantation simultaneously.

CASE PRESENTATION

A 68-year-old man had shortness of breath and chest tightness, accompanied by paroxysmal nocturnal dyspnea, 2 weeks before presenting at our hospital. Echocardiography results obtained in the outpatient department showed severe aortic stenosis combined with regurgitation and pleural effusion. The patient was first treated with closed thoracic drainage. After 800 mL of pleural effusion was collected, the patient's symptoms were relieved and he was admitted to the hospital. Preoperative transthoracic echocardiography showed severe bicuspid aortic valve stenosis combined with calcification and aortic regurgitation (mean pressure gradient, 42 mmHg). Preoperative computed tomography results showed a type I bicuspid aortic valve with severe eccentric calcification. The leaflet could be seen from the left coronary artery plane, which indicated an extremely high possibility of coronary obstruction. After preoperative imaging assessment, deep learning and 3-dimensional printing technology were used for evaluation and simulation. Guided transcatheter aortic valve replacement and a coronary stent implant were completed successfully. Postoperative digital subtraction angiography showed that the bioprosthesis and the chimney coronary stent were in ideal positions. Transesophageal echocardiography showed normal morphology without paravalvular regurgitation.

CONCLUSION

The perioperative guidance of deep learning and 3-dimensional printing are of great help for surgical strategy formulation in patients with severe bicuspid aortic valve stenosis with calcification and high-risk coronary obstruction.

Pre-TAVI aortic annulus sizing: comparison between manual and semi-automated new generation software measurements in operators with different experience

OBJECTIVES

Aim of the study is to compare manual and semi-automatic measurements for aortic annulus assessment among different operators.

METHODS

Eighty patients who underwent TAVI were retrospectively enrolled. The measurements manually performed by an experienced reader for aortic annulus (minimum and maximum diameters, perimeter, area), annulus-to-coronary ostia distance and time needed for the whole evaluation, were collected. The same operator (observer 1) and two less experienced readers (observer 2 and 3, with >5 years and 1 year of experience, respectively) assessed the same measurements using a semi-automatic software. Differences between manual and semi-automatic measurements, reading time and suggested valves size derived by CT were compared.

RESULTS

Very good correlations were found between manual and software-aided measurements for aortic annulus area and perimeter in comparison with standard measurements for the three readers (ICC range 0.81-0.98). Good correlations were found for the distance with coronary ostia(0.75-0.79). The same area-derived prosthesis size for manual and semi-automatic measurements was selected in 96% of cases for observer 1; very good correlations were also found for observer 2 and 3 (ICC = 0.89 and 0.88, respectively). Using semi-automatic measurements, the mean time needed for CT images was significantly lower for observers 1 and 2 (1.50 and 1.72versus 3.14 min), respectively.

CONCLUSIONS

Pre-TAVI CT using semi-automatic software allows accurate and reproducible measurements, reducing reconstruction time up to 50% and is reliable even for operators with different experience.

ADVANCES IN KNOWLEDGE

The use of semi-automatic dedicated software for CT in TAVI planning is reliable even for operators without long time experience and allows accurate and reproducible measurements improving pre-TAVI workflow.

Computed tomography angiography/magnetic resonance imaging-based preprocedural planning and guidance in the interventional treatment of structural heart disease

Preprocedural planning and periprocedural guidance based on image fusion are widely established techniques supporting the interventional treatment of structural heart disease. However, these two techniques are typically used independently. Previous works have already demonstrated the benefits of integrating planning details into image fusion but are limited to a few applications and the availability of the proprietary tools used. We propose a vendor-independent approach to integrate planning details into periprocedural image fusion facilitating guidance during interventional treatment. In this work, we demonstrate the feasibility of integrating planning details derived from computer tomography and magnetic resonance imaging into periprocedural image fusion with open-source and commercially established tools. The integration of preprocedural planning details into periprocedural image fusion has the potential to support safe and efficient interventional treatment of structural heart disease.

Use of virtual reality for procedural planning of transcatheter aortic valve replacement

This study sought to evaluate the impact of virtual reality (VR) tools in procedural planning of transcatheter aortic valve replacement. A prospective study involving 11 patients referred for transcatheter aortic valve replacement was conducted. A multidetector computed tomography was used to acquire and segment the anatomy of the access route and landing zone. From the information obtained with the multidetector computed tomography in DICOM format, we built a virtual platform (VisuaMed, Techer Team, Valencia, Spain) that contains all the clinical information of the patients and a virtualized model of their anatomy. Wearing VR devices, the professional was able to 'walk inside' the anatomy in an interactive and immersive way. Decisions after the evaluation of routine clinical images were compared with those after experience with VR models and intraprocedural findings.

Technical Aspects and Development of Transcatheter Aortic Valve Implantation

Aortic stenosis is the most common valve disease requiring surgery or percutaneous treatment. Since the first-in-man implantation in 2002 we have witnessed incredible progress in transcatheter aortic valve implantation (TAVI). In this article, we review the technical aspects of TAVI development with a look at the future. Durability, low thrombogenicity, good hydrodynamics, biocompatibility, low catheter profile, and deployment stability are the attributes of an ideal TAVI device. Two main design types exist-balloon-expandable and self-expanding prostheses. Balloon-expandable prostheses use a cobalt-chromium alloy frame providing high radial strength and radiopacity, while the self-expanding prostheses use a nickel-titanium (Nitinol) alloy frame, which expands to its original shape once unsheathed and heated to the body temperature. The valve is sewn onto the frame and consists of the porcine or bovine pericardium, which is specially treated to prevent calcinations and prolong durability. The lower part of the frame can be covered by polyethylene terephthalate fabric or a pericardial skirt, providing better sealing between the frame and aortic annulus. The main future challenges lie in achieving lower rates of paravalvular leaks and new pacemaker implantations following the procedure, lower delivery system profiles, more precise positioning, longer durability, and a good hemodynamic profile. Patient-specific design and the use of autologous tissue might solve these issues.

Aortic valve replacement via right anterolateral minithoracotomy: preventing adverse events during the initial learning curve

BACKGROUND

Despite excellent outcomes and reduced invasiveness, the right anterolateral thoracotomy approach for aortic valve replacement (RALT-AVR) has not been broadly adopted. This study provides results regarding the initial experience and learning curve of a single surgeon performing this procedure.

METHODS

Periprocedural details and postoperative outcomes of the first 100 consecutive patients who underwent RALT-AVR at our institution were retrospectively analyzed. We conducted a cumulative sum analysis of surgical failure, defined as occurrence of 30-day-mortality, surgical revision for bleeding, conversion to sternotomy, 3^rd degree heart block, paravalvular leakage, postoperative stroke or mean transvalvular gradient >20 mmHg.

RESULTS

The cohort was of low surgical risk (mean EuroSCORE II 1.31%±0.85, mean STS PROM 1.45%±0.97), 58% were males. Median cross-clamp time was 67.5 (57.8-76) min, median CPB time 105 (91.8-119) min, and median operation time 164.5 (144.5-183.2) min. There were no conversions to full sternotomy, 4 cases of revision for bleeding and 2 pacemaker implantations for 3^rd degree heart block. Prosthesis function was good (median ΔPmean 10.9 [7.4-13.6] mmHg). Thirty-day-mortality was 0%. The log-likelihood graph never crossed the upper boundary, and after a steady decrease, crossed the lower boundary at 93 patients.

CONCLUSIONS

RALT-AVR can be performed with acceptable procedural times and satisfactory outcomes. For a well-trained surgeon, adapting to this new procedure does not expose patients to an increased risk, when patient selection and procedural planning are applied appropriately. Cumulative sum failure analysis is an appropriate tool to monitor the transition from standard AVR to the technically more demanding RALT-AVR.

Cascaded neural network-based CT image processing for aortic root analysis

Purpose

Careful assessment of the aortic root is paramount to select an appropriate prosthesis for transcatheter aortic valve implantation (TAVI). Relevant information about the aortic root anatomy, such as the aortic annulus diameter, can be extracted from pre-interventional CT. In this work, we investigate a neural network-based approach for segmenting the aortic root as a basis for obtaining these parameters.

Methods

To support valve prosthesis selection, geometric measures of the aortic root are extracted from the patient’s CT scan using a cascade of convolutional neural networks (CNNs). First, the image is reduced to the aortic root, valve, and left ventricular outflow tract (LVOT); within that subimage, the aortic valve and ascending aorta are segmented; and finally, the region around the aortic annulus. From the segmented annulus region, we infer the annulus orientation using principal component analysis (PCA). The area-derived diameter of the annulus is approximated based on the segmentation of the aortic root and LVOT and the plane orientation resulting from the PCA.

Results

The cascade of CNNs was trained using 90 expert-annotated contrast-enhanced CT scans routinely acquired for TAVI planning. Segmentation of the aorta and valve within the region of interest achieved an F1 score of 0.94 on the test set of 36 patients. The area-derived diameter within the annulus region was determined with a mean error below 2 mm between the automatic measurement and the diameter derived from annotations. The calculated diameters and resulting errors are comparable to published results of alternative approaches.

Conclusions

The cascaded neural network approach enabled the assessment of the aortic root with a relatively small training set. The processing time amounts to 30 s per patient, facilitating time-efficient, reproducible measurements. An extended training data set, including different levels of calcification or special cases (e.g., pre-implanted valves), could further improve this method’s applicability and robustness.

Mitral valve surgery: current status and future prospects of the minimally invasive approach

Introduction: During the past five years the approach to procedural planning, operative techniques and perfusion strategies for minimally invasive mitral valve surgery (MIMVS) has evolved. With the goal to provide a maximum of patient safety the procedure has been modified according to individual patient characteristics and is largely based on preoperative imaging.Areas covered: In this review article we describe the important factors in image based therapy planning and simulation, different access strategies, the operative key-steps, a rationale use of devices, and highlight a few future developments in the field of MIMVS. Published studies were identified through pearl growing, citation chasing, a search of PubMed using the systematic review methods filter, and the authors' topic knowledge.Expert opinion: With the help of expert teams including surgeons specialized in mitral repair, anesthesiologists and perfusionists a broad spectrum of mitral valve pathologies and related pathologies can be treated with excellent functional outcomes. Avoiding procedure related complications is the key for success for any MIMVS program.