AI Tool RadAnalyzer Aids Veterinarians in Tracking Canine Heart Disease

A new AI tool developed by researchers at Texas A&M University's College of Veterinary Medicine and Biomedical Sciences could revolutionize the way veterinarians track heart disease in dogs. RadAnalyzer, a web- and smartphone-based application, automates the measurement of heart size on chest x-rays, providing results as accurate as those obtained by trained specialists. This innovation could significantly improve the monitoring of canine heart conditions, particularly in primary care settings where specialist access is limited.

## How RadAnalyzer Works

RadAnalyzer calculates two standard measurements used to track heart enlargement in dogs: vertebral heart size and vertebral left atrial size. These measurements are crucial for determining whether a dog's heart is changing over time and whether treatment should begin. The tool was tested on over 1000 canine radiographs, and its measurements were found to closely match those of a highly trained observer, indicating its reliability.

Chest radiographs are a common tool for monitoring heart disease due to their affordability and widespread availability, unlike echocardiography, which is the gold standard but requires specialized equipment. Manually measuring heart size on radiographs involves identifying anatomical landmarks, placing markers, and calculating values by hand-a process that can vary among clinicians. RadAnalyzer eliminates this variability by providing consistent measurements each time it evaluates an image.

## Addressing Specialist Shortages and Improving Treatment Decisions

The measurements provided by RadAnalyzer are particularly relevant for monitoring myxomatous mitral valve disease, a common condition in older, small-breed dogs. Many dogs develop heart murmurs before showing other signs of illness, and tracking chamber enlargement over time helps veterinarians decide when to start treatment. With only about 400 veterinary cardiologists practicing in the US, primary care veterinarians often make these decisions.

Sonya Gordon, DVSc, DACVIM (Cardiology), the study's principal investigator, emphasized that tools like RadAnalyzer can ease the burden on primary care veterinarians. The radiographs are already being taken, and reviewing automated measurements takes less time than performing them manually. The measurements can help identify when a dog's heart is enlarged enough to benefit from pimobendan, a medication shown to delay the onset of clinical symptoms and extend symptom-free survival by an average of 60%, or more than a year for most dogs.

## Reducing Measurement Variability

One of the key advantages of RadAnalyzer is its consistency. Prior research from Gordon's group found that variability among clinicians decreases with experience but does not disappear entirely. RadAnalyzer, by contrast, produces the same result each time it evaluates a given image, reducing measurement variability to essentially zero.

This consistency is particularly important when veterinarians are watching for small changes in heart size over months or years, as a modest increase can signal that treatment should begin. Gordon noted that as AI applications become more common in veterinary medicine, rigorous validation studies will be necessary to confirm that the tools perform as intended. The goal of such technology is to support a veterinarian’s judgment rather than replace it.

"If people think of AI as something that's making us obsolete, they're looking at it the wrong way," Gordon said. "It's making us better."