Experts’ labels were used as ground truth to train the semantic segmentation. Veterinary radiologists in SNU-VMTH manually generated contour labels of heart and T4 vertebrae body with the “labelme opensource tool” 8. Contrast Limit Adaptive Histogram Equalization (CLAHE) 6 was applied using the OpenCV library 7 in Python to mitigate variability in exposure level and enhance the contrast of images. Image preprocessing and ground truth establishmentĪll images were center cropped with Pillow library in Python and resized to 256 × 256. Clinical information such as sex, age, breed, radiologic report, and manually measured VHS was also collected. Some disease conditions that interrupt heart margin were excluded, including pleural effusion, overlying mediastinal nodules, and lung mass superimposed over the heart.
The purpose of this study is 1) to develop a method that automatically measures and a new cardiac index from a simple X-ray and 2) to compare the performance of a new method versus the current standard method in predicting clinically proven cardiomegaly.Īfter an initial quality check, image data were selected inadequately positioned or exposed radiographs were excluded by manual inspection of veterinary radiologists. The deep learning (DL) algorithms automate the measures and enable two-dimensional measurement of the heart area. We propose a new automated cardiac index for dogs to improve the VHS index, adjusted heart volume index (aHVI). Because of its relative simplicity, the VHS is the most widely used index of cardiac enlargement, at the cost of involving efforts and possible measurement errors. For measuring VHS, the longest axis and its perpendicular axis of the cardiac silhouette from a simple canine chest X-ray are summed and then divided by the length of the mid-thoracic vertebral body, starting at the cranial edge of T4. VHS is an index of normalized heart size to body size using mid-thoracic vertebrae for adjustment. In the ACVIM consensus guideline, vertebral heart score (VHS) 5 larger than 11.5 from lateral thoracic radiograph is suggested as radiographic evidence of cardiomegaly alone without echocardiographic measurements. The American College of Veterinary Internal Medicine Veterinarian (ACVIM) guideline for staging MMVD 2 is widely used for diagnosing cardiac enlargement. Since cardiac enlargement ensues pharmacological intervention to prevent fatal heart failure, early detection of cardiac enlargement is a priority healthcare issue for dogs. The progression of MR results in left heart overload, with signs of left atrial and left ventricular enlargement (LAE and LVE) 3, 4. The MMVD is characterized by progressive deformation of the valve structure, resulting in mitral valve regurgitation (MR). About 75 ~ 80% of small-breed dogs (< 15 kg) over 13 years of age are reported to have degenerative heart diseases 2.
Unlike humans, where coronary heart diseases are predominant, myxomatous mitral valve disease (MMVD) is the most common type of heart disease in dogs, with its prevalence increasing markedly with age. With improved care and increased life span, it is estimated that approximately 10% of dogs represented in primary care veterinary practices have heart disease 2. Cohabitating dogs are often regarded as family members, with growing vigilance on their healthcare. The global population of dogs was estimated to be around 900 million in 2013, and 20% of them cohabitate with humans 1. The aHVI outperformed the current clinical standard in predicting cardiac enlargement, a common but often fatal health condition for small old dogs. The tversky loss functions with multiple hyperparameters were used to capture the size-unbalanced regions of heart and T4. For semantic segmentation, we used 1000 dogs’ radiographic images taken between Jan 2018 and Aug 2020 at Seoul National University Veterinary Medicine Teaching Hospital. The algorithms consist of segmentation and measurements. The proposed “adjusted heart volume index” (aHVI) was calculated as the total area of the heart multiplied by the heart’s height and divided by the fourth thoracic vertebral body (T4) length from simple lateral X-rays.
In this study, we developed a new deep learning-based radiographic index quantifying canine heart size using retrospective data. Since most of degenerative canine heart diseases accompany cardiomegaly, early detection of cardiac enlargement is main priority healthcare issue for dogs.