Skip to content
#edge computing Editorial Open access

Editorial: Outstanding advances in veterinary diagnostic ultrasonography: novel milestones in disease detection, prediction, and treatment, volume II

Sep 2026 · Frontiers in Veterinary Science

Abstract

Currently, ultrasonography (US) is widely used in a broad range of animals as an efficient diagnostic tool in veterinary practice. It exhibited superiority to radiography in visualizing the internal organs clearly and detecting diverse affections. This enabled precise assessment of the anatomy and function of various body organs under health and illness conditions. Furthermore, US could be used efficiently to provide qualitative evaluation and quantitative scoring of the healing following surgeries. In addition, color Doppler US has been utilized to assess the function of different organs through evaluation of their vascular hemodynamics. Engagement of novel technologies in US presented a novel milestone that extended its uses to early detection and even prediction of many diseases especially cardiac ones. That consequently aids to design and assess prompt therapeutic protocols and minimize the possible deaths.The present research topic aimed to highlight the existing progress of the diagnostic US with emphasis on its wide and promising applications in veterinary practice. It joined the most substantial and recent research conducted on diverse large and small animal models as well as implementation of artificial intelligence in advancement of diagnostic imaging. The present research topic comprised 6 published articles focusing these aimed strategies. Park J. et al.foot_0 evaluated the utility of US in the assessment of adrenal glands in 38 clinically normal Korean raccoon dogs (Nyctereutes procyonoides koreensis). They aimed to establish species-specific reference values for the adrenal gland measures in these dogs, which are important for veterinary practice and wildlife medicine. A retrospective analysis of sagittal US included adrenal length, height of the cranial pole, and height of the caudal pole of both left and right glands was performed. Moreover, the morphology and corticomedullary distinction were visually evaluated. Ultrasonogrphy enabled clear visualization of the adrenal glands without sedation. In conclusion, this study presented the first ultrasonographic reference values for the adrenal glands in clinically health Korean raccoon dogs. The morphology and adrenal size were consistent across sex and body weight, supporting the use of a single reference range for adults. These findings will improve the diagnostic precision of US in veterinary imaging and support species-specific evaluation in wildlife medicine.Martinez R. et al. 2 studied the feasibility of deep learning AI models to assist in the diagnosis of life-threatening conditions -specifically effusions (fluid accumulation) and pneumothorax (PTX, air in the chest cavity)-in dogs using point-of-care ultrasound (POCUS). They aimed to improve the diagnostic accuracy, particularly in settings where expert operators are unavailable, such as military or remote environments. A total of 25 dogs diagnosed with PTX were enrolled in this investigation. Ultrasound clips were collected from diverse anatomical areas using standardized protocols. Then, the images were reviewed curated and labeled by experts. To develop the AI model, multiple convolutional neural network (CNN) architectures were trained using transfer learning from large pre-existing medical imaging datasets. The models were optimized and evaluated using a leave-one-subject-out crossvalidation approach to confirm generalizability. Moreover, to address dataset limitation, image augmentation and class balancing techniques were applied. Conclusively, AI-assisted ultrasound interpretation is feasible and presents potential promises for augmenting veterinary emergency triage, especially in military and remote applications. With further development, these AI models could help first responders and less experienced practitioners detect life-threatening conditions in dogs, improving early intervention and outcomes.Transducer (probe) selection is often operator-dependent, with limited evidence-based guideline in veterinary practice. Granger Jr K. L. et al.foot_2 provided an evidence-based review article on the optimized selection of the US transducers for the diagnosis of alveolarinterstitial syndrome (AIS), a common lung ultrasound (LUS) finding in small animals with various pulmonary diseases (e.g., pulmonary edema, pneumonia, contusions, acute respiratory distress syndrome (ARDS)). They discussed the present literature in human and animal medicine to investigate how the probe choice can affect the diagnosis and depiction of the AIS in dogs and cats. They found that all major transducer types can detect AIS in small animals, however the selection should be adjusted to the patient size, clinical objective, and the available machine. Microconvex probes are generally preferred for versatility, meanwhile the linear probes are best for detailed pleural imaging. Moreover, it was concluded that consistency in transducer use is crucial for monitoring disease progression. Standardization and further studies will enhance the accuracy of diagnosis and the patient outcomes in vetetrinary emergency and critical care.Injuries of intermediate patellar ligament (IPL) in horses present a high clinical significance and traditional US often yields nonspecific findings. Hence, Straticò P. et al.foot_3 investigated the use of two advanced US techniques; strain elastography (SE) and two-dimensional shear wave elastography (2D-SWE) to assess the IPL in horses. Longitudinal and transverse SE scans to measure the strain ratio (SR) between the IPL and the infrapatellar fat pad and the elasticity index of the IPL (EIIPL), in addition to 2D-SWE scans to measure the Young's modulus (kPa) and shear wave velocity (m/s) were used to assess the IPLs in sound and lame horses. Evaluation of the same region of interest (ROI) revealed that both techniques were feasible. They concluded that SE and 2D-SWE could efficiently study equine IPL and can be potentially employed together with the conventionally used techniques such as x-ray and US.Moreover, these tools could differentiate the elastic characters of equine IPLs under normal and chronic injury conditions. However, marked limitations of this study is still to be addressed in future investigations including the employment of Doppler US to further investigate the vascular structure of the ligaments on a larger number of studied animals.Conventional echocardiography was utilized to provide quantitative evaluation of the severity of mitral regurgitation (MR) in dogs with myxomatous mitral valve disease (MMVD), Kawai S. et al.foot_4 provided a retrospective study of 167 MMVD small-breed dogs categorized based on the staging system of the American College of Veterinary Internal Medicine (ACVIM). They found that quantitative indices such as regurgitant volume normalized to the body weight (RVol/kg) and regurgitant fraction (RF) were significantly correlated with conventional echocardiography measures of MMVD dogs. Moreover, They could provide valuable insights on the severity of MR, structural evaluation, and staging of the disease. Furthermore, mitral-aortic velocity-time integral (VTI) ratio was strongly associated with regurgitation measures and provided outstanding ability to diagnose and define the severity of MR. The authors concluded that conventional echocardiography combined with calculation of quantitative regurgitation indices provided a promising tool to evaluate MR, even though further investigations are still required to validate these outcomes.In an exciting case report, Tsuka T. et al. 6 used US in combination with computed tomography (CT) to study one of the rare vascular anomalies named Juvenile angiomatosis in the bovine practice for the first time. The four-days-old, male Japanese-Black calf was presented with different swollen lesions on the dorsal and ventral aspects of the thoracic skin of the left side. Examination using US showed presence of structures with homogeneous echogenicity in the subcutaneous space with poor vasculature confirmed with Doppler US. The findings were confirmed and counted and characterized using CT. Moreover, the structure of the masses was finely assessed with histopathology and immunohistochemistry using von Willebrand factor and alpha-smooth muscle actin. Despite, US and CT provided a preliminary diagnosis lacking detailed characterization of the masses. The combinatory diagnosis scheme including US, CT, Histopathology, and immunostaining could provide a detailed examination and definitive diagnosis of such rare cases.Combined, the articles in the present research topic provide a coherent and proactive perspective on US as a key element of veterinary diagnostic imaging. They show that US is a potent diagnostic tool for diverse affections in different body organs and systems of various animal species. The field is moving toward a more thorough and integrative diagnostic model by connecting imaging results to outcomes, utilizing cutting-edge technology, and modifying methods for underrepresented species. Moreover, integration of AI in the future investigations will open the doors to further outstanding advancements.

Read PDF

Similar papers

#computer vision Review Sep 2017

Agile Software Development Methods: Review and Analysis

This publication proposes a definition and a classification of agile software development approaches and analyses ten software development methods that can be characterized as being "agile" against the defined criterion.

P. Abrahamsson, O. Salo, Jussi Ronkainen et al. · 727 citations · ⚡54
#computer vision Jun 2008

The impact of agile practices on communication in software development

The study shows that agile practices improve both informal and formal communication, but indicates that, in larger development situations involving multiple external stakeholders, a mismatch of adequate communication mechanisms can sometimes even hinder the communication.

M. Pikkarainen, Jukka Haikara, O. Salo et al. · 401 citations · ⚡48
#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54

Related blog posts

Microsoft Research Blog Oct 6, 2026

What AI gets wrong and what failure teaches us

Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.  The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.