Federated Synthetic Learning from Multi-institutional and Heterogeneous Medical Data

Statistically and information-wise adequate data plays a critical role in training a robust deep learning model. However, collecting sufficient medical data to train a centralized model is still challenging due to various constraints such as privacy regulations and security. In this work, we develop a novel privacy-preserving federated-discriminator GAN, named FedD-GAN, that can learn and synthesize high-quality and various medical images regardless of their type, from heterogeneous datasets residing in multiple data centers whose data cannot be transferred or shared. We trained and evaluated FedD-GAN on three essential classes of medical data, each involving different types of medical images: cardiac CTA, brain MRI, and histopathology. We show that the synthesized images using our method have better quality than using a standard federated learning method and are realistic and accurate enough to train accurate segmentation models in downstream tasks. The segmentation model trained on the synthetic data only is comparable to that trained on an all-in-one real-image dataset shared from multiple data centers if possible. FedD-GAN can learn to generate a scalable and diverse synthetic database without compromising data privacy. This synthetic database could help to boost machine learning techniques in medical data analytics.

Bicuspid aortic valve annulus: assessment of geometry and size changes during the cardiac cycle as measured with a standardized method to define the annular plane

Purpose Bicuspid aortic valve (BAV) is a complex malformation affecting not merely the aortic valve. However, little is known regarding the dynamic physiology of the aortic annulus in these patients and whether it is similar to tricuspid aortic valves (TAV). Determining the BAV annular plane is more challenging than for TAV. Our aim was to present a standardized methodology to determine BAV annulus and investigate its changes in shape and dimensions during the cardiac cycle. Methods BAV patients were prospectively included and underwent an ECG-gated cardiac CTA. The annulus plane was manually identified on reconstructions at 5% intervals of the cardiac cycle with a new standardized method for different BAV types. Based on semi-automatically defined contours, maximum and minimum diameter, area, area-derived diameter, perimeter, asymmetry ratio (AR), and relative area were calculated. Differences of dynamic annular parameters were assessed also per BAV type. Results Of the 55 patients included (38.4 ± 13.3 years; 58% males), 38 had BAV Sievers type 1, 10 type 0, and 7 type 2. The minimum diameter, perimeter, area, and area-derived diameter were significantly higher in systole than in diastole with a relative change of 13.7%, 4.8%, 13.7%, and 7.2% respectively (all p < 0.001). The AR was ≥ 1.1 in all phases, indicating an elliptic shape, with more pronounced flattening in diastole (p < 0.001). Different BAV types showed comparable dynamic changes. Conclusions BAV annulus undergo significant changes in shape during the cardiac cycle with a wider area in systole and a more elliptic conformation in diastole regardless of valve type. Key Points • A refined method for the identification of the annulus plane on CT scans of patients with bicuspid aortic valves, tailored for the specific anatomy of each valve type, is proposed. • The annulus of patients with bicuspid aortic valves undergoes significant changes during the cardiac cycle with a wider area and more circular shape in systole regardless of valve type. • As compared to previously published data, the bicuspid aortic valve annulus has physiological dynamics similar to that encountered in tricuspid valves but with overall larger dimensions.

Bayesian Estimation of Geometric Morphometric Landmarks for Simultaneous Localization of Multiple Anatomies in Cardiac CT Images

We propose a robust method to simultaneously localize multiple objects in cardiac computed tomography angiography (CTA) images. The relative prior distributions of the multiple objects in the three-dimensional (3D) space can be obtained through integrating the geometric morphological relationship of each target object to some reference objects. In cardiac CTA images, the cross-sections of ascending and descending aorta can play the role of the reference objects. We employed the maximum a posteriori (MAP) estimator that utilizes anatomic prior knowledge to address this problem of localizing multiple objects. We propose a new feature for each pixel using the relative distances, which can define any objects that have unclear boundaries. Our experimental results targeting four pulmonary veins (PVs) and the left atrial appendage (LAA) in cardiac CTA images demonstrate the robustness of the proposed method. The method could also be extended to localize other multiple objects in different applications.

Non-invasive quantitative characterization of aortic valve tissue composition from computed tomography angiography improves patient risk stratification in transcatheter aortic valve implantation

Background Computed tomography angiography (CTA) performed for procedural planning of transcatheter aortic valve implantation (TAVI) can be used for a more complete characterization of aortic valve tissue beyond calcium assessment. Combining quantitative data on both noncalcified and calcified tissues may improve differentiation of aortic stenosis (AS) subtypes and prognostication post-TAVI. Purpose We sought to noninvasively assess aortic valve tissue composition with quantitative cardiac CTA in patients with AS and its prognostic vaalue in those who underwent TAVI. Methods In 185 consecutive AS patients in a prospective registry who underwent cardiac CTA before TAVR and 90 matched controls with normal aortic valves, non-luminal aortic valve tissue were identified using semi-automated software as non-calcified (low-attenuation [−30 to 30 Hounsfield Units (HU)], fibro-fatty (31 to 130 HU), fibrous (131 to 350 HU) and calcified (&gt;650 HU) tissue; with total tissue as (non-calcified + calcified components). Volumes of each component and composition [(tissue component volume/total tissue volume) ×100%] were quantified. The association of aortic valve composition and clinical outcomes post-TAVI including all-cause mortality was evaluated using Valve Academic Research Consortium (VARC)-2 definitions. Results AS patients had greater aortic valve tissue volume (median 2000.2, vs 527.8 mm3, p&lt;0.001) with a higher calcified tissue composition (41.8% vs 3.4%, p&lt;0.001) compared to controls. Total aortic valve tissue (noncalcified and calcified) volume yielded the highest area under the operating curve (AUC) for diagnosing severe AS (0.93,95% CI:0.93–0.99) as compared to calcified tissue volume alone (0.87,95% CI:0.81–0.94, p=0.002). Low-flow low-gradient AS was associated with increase in total tissue volume compared to controls (1515.3 vs 527.8 mm3, p&lt;0.001), with lower volumes of calcified tissue than high-gradient AS (412.5 vs 829.6 mm3, p&lt;0.001). Device success was achieved in 88% (164 of 185) patients and prevalence of moderate or severe paravalvular leak was 3.8%, however no differences between in aortic valve composition were observed in patients with and without device success. Early safety endpoints occurred in 16.1% (29 of 180) patients and 30-day all-cause mortality was 4.4%. Whereas only calcified tissue volume was related to VARC-2 early safety, AUC for prediction of 30-day mortality post-TAVI was 0.793 (95% CI:0.685–0.901) for total tissue volume and 0.776 (95% CI:0.676–0.876) for calcified tissue volume. Conclusions Quantitative CTA assessment of aortic valve tissue volume and composition can improve identification of high-gradient AS and low-flow low-gradient AS patients referred for TAVI and predict 30-day mortality post-TAVI. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): National Heart, Lung, and Blood Institute (NHLBI)