CAMUS Cardiac Ultrasound Image Dataset

CAMUS (Cardiac Acquisitions for Multi-structure Ultrasound Segmentation) is a 2019 public cardiac ultrasound image dataset created specifically to support cardiac structure segmentation and related medical image analysis tasks.Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography”, has been published in the IEEE TMI journal.

The dataset contains two-dimensional apical four-chamber and two-chamber view sequences obtained from 500 patients. The data was collected at the University Hospital of Saint-Etienne in France and has been completely anonymized to ensure patient privacy and data compliance. Each image has been accurately annotated by professional medical personnel, covering the contour information of the left ventricular endocardium, left ventricular epicardium, and left atrium. These detailed annotations provide researchers with rich training and verification resources.

The design of the dataset fully considers the diversity and complexity of clinical practice. It not only contains samples with good and medium image quality, but also specially includes 84 samples with poor image quality to reflect the various situations that may be encountered in daily clinical work. This diverse data collection setting enables the CAMUS dataset to better simulate real-world medical image analysis scenarios, providing researchers with a very challenging and practical research platform.

In terms of data organization, CAMUS is divided into a training set and a test set, where the training set contains data from 450 patients and the test set contains data from 50 patients. This division is designed to provide researchers with sufficient data for model training and optimization, while also retaining a portion of independent data for model performance verification and evaluation. In this way, researchers can more accurately measure the performance of their algorithms on unseen data, thereby promoting the development of cardiac ultrasound image segmentation technology.