Veterinary College, University of Prince Edward Island, from 1988 through 2003 were reviewed to identify dogs with CT attributable to PE. Dogs with available thoracicradiographic images (≥ 1 lateral projection and a dorsoventral or ventrodorsal projection
for detection of pulmonary metastatic disease in small animals 6,7,13,14 ; however, reports 8,13,14 quantitatively addressing the benefit of CT, compared with thoracicradiography in dogs, for pulmonary metastases detection are few. The 2 main
,20,22 Survey thoracicradiography remains a useful imaging technique for the evaluation of intrathoracic disorders because it is relatively inexpensive, widely available, and easy to perform. 23
To our knowledge, reports of systematic studies aimed at
Objective—To compare results of thoracic radiography,
cytologic evaluation of bronchoalveolar lavage
(BAL) fluid, and histologic evaluation of biopsy and
necropsy specimens in dogs with respiratory tract
disease and to determine whether histologic evaluation
provides important diagnostic information not
attainable by the other methods.
Procedure—BAL fluid was classified as normal, neutrophilic,
eosinophilic, mononuclear, mixed, neoplastic,
or nondiagnostic. Radiographic abnormalities
were classified as interstitial, bronchial, bronchointerstitial,
or alveolar. Histologic lesions were classified as
inflammatory, fibrotic, or neoplastic, and the predominant
site of histologic lesions was classified as the
alveoli, interstitium, or airway.
Results—The predominant radiographic location of
lesions correlated with the histologic location in 8
dogs. Of 11 dogs with histologic evidence of inflammatory
disease, 8 had inflammatory BAL fluid. Of the
2 dogs with histologic evidence of neoplasia, 1 had
BAL fluid suggestive of neoplasia, and the other had
BAL fluid consistent with septic purulent inflammation.
Two dogs without any histologic abnormalities
had mononuclear or nondiagnostic BAL fluid. Two
dogs with histologic evidence of fibrosis had mononuclear
or mixed inflammatory BAL fluid.
Conclusions and Clinical Relevance—Results suggest
that although thoracic radiography, cytologic
evaluation of BAL fluid, and histologic evaluation of
lung specimens are complementary, each method
has limitations in regard to how well results reflect
the underlying disease process in dogs with respiratory
tract disease. Lung biopsy should be considered
in cases where results of radiography and cytology
are nondiagnostic. (J Am Vet Med Assoc 2001;218:
species, improved veterinary care is paramount to increased longevity with higher standards for diagnostic and therapeutic options.
Electrocardiography and thoracicradiography are 2 noninvasive diagnostic tools for evaluation of cardiothoracic
, weight, and breed were recorded. The following clinical information associated with the baseline evaluation was extracted when available: clinical signs (type and duration), medications, respiratory rate, and temperature.
To determine the feasibility of machine learning algorithms for the classification of appropriate collimation of the cranial and caudal borders in ventrodorsal and dorsoventral thoracic radiographs.
900 ventrodorsal and dorsoventral canine and feline thoracic radiographs were retrospectively acquired from the Picture Archiving and Communication system (PACs) system of the Ontario Veterinary College.
Radiographs acquired from April 2020 to May 2021 were labeled by 1 radiologist in Summer of 2022 as either appropriately or inappropriately collimated for the cranial and caudal borders. A machine learning model was trained to identify the appropriate inclusion of the entire lung field at both the cranial and caudal borders. Both individual models and a combined overall inclusion model were assessed based on the combined results of both the cranial and caudal border assessments.
The combined overall inclusion model showed a precision of 91.21% (95% CI [91, 91.4]), accuracy of 83.17% (95% CI [83, 83.4]), and F1 score of 87% (95% CI [86.8, 87.2]) for classification when compared with the radiologist’s quality assessment. The model took on average 6 ± 1 second to run.
Deep learning-based methods can classify small animal thoracic radiographs as appropriately or inappropriately collimated. These methods could be deployed in a clinical setting to improve the diagnostic quality of thoracic radiographs in small animal practice.
fluoroscopy during the period from February 6, 2001, to February 6, 2006. Only those dogs for which at least 1 lateral thoracicradiographic view (including the cervical portion of the trachea) was available were included in the study. Fluoroscopic images were
Emergency diagnosis of congestive heart failure can be challenging, particularly when a dog or cat has respiratory distress that limits the diagnostic evaluation. Thoracicradiography is considered a fairly high-yield test for identifying CPE
and accurate diagnosis and emergency care are required.
Auscultation and thoracicradiography are standard methods for the detection of CPE in dogs. Auscultation allows evaluation of heart murmurs as well as the presence or absence of pulmonary edema