Supervised Domain Adaptation for Automated Semantic Segmentation of the Atrial Cavity

Abstract

Atrial fibrillation (AF) is the most common cardiac arrhythmia. At present, cardiac ablation is the main treatment procedure for AF. To guide and plan this procedure, it is essential for clinicians to obtain patient-specific 3D geometrical models of the atria. For this, there is an interest in automatic image segmentation algorithms, such as deep learning (DL) methods, as opposed to manual segmentation, an error-prone and time-consuming method. However, to optimize DL algorithms, many annotated examples are required, increasing acquisition costs. The aim of this work is to develop automatic and high-performance computational models for left and right atrium (LA and RA) segmentation from a few labelled MRI volumetric images with a 3D Dual U-Net algorithm. For this, a supervised domain adaptation (SDA) method is introduced to infer knowledge from late gadolinium enhanced (LGE) MRI volumetric training samples (80 LA annotated samples) to a network trained with balanced steady-state free precession (bSSFP) MR images of limited number of annotations (19 RA and LA annotated samples). The resulting knowledge-transferred model SDA outperformed the same network trained from scratch in both RA (Dice equals 0.9160) and LA (Dice equals 0.8813) segmentation tasks.

Aligning Small Datasets Using Domain Adversarial Learning: Applications in Automated in Vivo Oral Cancer Diagnosis

“…The goal of domain adaptation is to mitigate the mismatch between domains. Multiple domain adaptation techniques have been proposed, including using fine-tuning [10], generative adversarial network (GAN) [12], gradient reversal [20], transformation of data between domains [11], and augmentation methods [21].…”

“…Several studies have used a fine-tuning, transfer learning approach when at least some labels are present for both source and target data sets [5], [6], [10]. In these methods, a base classifier was trained using a source data set.…”