Improving the classification of veterinary thoracic radiographs through inter-species and inter-pathology self-supervised pre-training of deep learning models

The analysis of veterinary radiographic imaging data is an essential step in the diagnosis of many thoracic lesions. Given the limited time that physicians can devote to a single patient, it would be valuable to implement an automated system to help clinicians make faster but still accurate diagnoses. Currently, most of such systems are based on supervised deep learning approaches. However, the problem with these solutions is that they need a large database of labeled data. Access to such data is often limited, as it requires a great investment of both time and money. Therefore, in this work we present a solution that allows higher classification scores to be obtained using knowledge transfer from inter-species and inter-pathology self-supervised learning methods. Before training the network for classification, pretraining of the model was performed using self-supervised learning approaches on publicly available unlabeled radiographic data of human and dog images, which allowed substantially increasing the number of images for this phase. The self-supervised learning approaches included the Beta Variational Autoencoder, the Soft-Introspective Variational Autoencoder, and a Simple Framework for Contrastive Learning of Visual Representations. After the initial pretraining, fine-tuning was performed for the collected veterinary dataset using 20% of the available data. Next, a latent space exploration was performed for each model after which the encoding part of the model was fine-tuned again, this time in a supervised manner for classification. Simple Framework for Contrastive Learning of Visual Representations proved to be the most beneficial pretraining method. Therefore, it was for this method that experiments with various fine-tuning methods were carried out. We achieved a mean ROC AUC score of 0.77 and 0.66, respectively, for the laterolateral and dorsoventral projection datasets. The results show significant improvement compared to using the model without any pretraining approach.

Preliminary Evaluation of Cortical and Medullary Echogenicity in Normal Canine Fetal Kidneys during the Last 10 Days of Pregnancy

The objective of this study was to assess changes in the echogenicity of the cortex and medulla of canine fetal kidneys in relation to days before parturition (dbp), maternal size and litter size. Monitoring of 10 healthy pregnant bitches (2-8 years old, 8.8-40.3 kg bw) was conducted from -10 to 0 dbp using ultrasound. A single renal sonogram was obtained by scanning in a longitudinal section the three most caudal fetuses. The mean gray level (MGL) and SD of a manually drawn region of interest (ROI) in the renal cortex and medulla were measured using the Fiji Image J software (Image J 1.51h, Java 1.6 0_24 64 bit). A linear mixed model taking into account the maternal size as a fixed effect, dbp and litter size as covariates and the bitch as a random and repeated effect was used. The regression coefficients (b) were estimated. Cortical SD (C-SD) and cortico-medullary SD (C/M-SD) were influenced by dbp, with a significant decrease at the approaching day of parturition (b = 0.23 ± 0.06, p < 0.001 and b = 0.5 ± 0.02, p = 0.038, respectively). Maternal size had a significant impact on C/M-MGL with differences observed in large-sized (1.95 ± 0.13) compared to small- (1.41 ± 0.10, p = 0.027) and medium-sized bitches (1.51 ± 0.09, p = 0.016). The C/M-MGL was influenced by litter size, showing a decrease as the number of pups increased (b = -0.08 ± 0.03, p = 0.018). C-SD and C/M-SD were exclusively affected by dbp, and not by maternal and litter size. This suggests their potential as valuable parameters, warranting further investigations in future studies.

An AI-based algorithm for the automatic evaluation of image quality in canine thoracic radiographs

The aim of this study was to develop and test an artificial intelligence (AI)-based algorithm for detecting common technical errors in canine thoracic radiography. The algorithm was trained using a database of thoracic radiographs from three veterinary clinics in Italy, which were evaluated for image quality by three experienced veterinary diagnostic imagers. The algorithm was designed to classify the images as correct or having one or more of the following errors: rotation, underexposure, overexposure, incorrect limb positioning, incorrect neck positioning, blurriness, cut-off, or the presence of foreign objects, or medical devices. The algorithm was able to correctly identify errors in thoracic radiographs with an overall accuracy of 81.5% in latero-lateral and 75.7% in sagittal images. The most accurately identified errors were limb mispositioning and underexposure both in latero-lateral and sagittal images. The accuracy of the developed model in the classification of technically correct radiographs was fair in latero-lateral and good in sagittal images. The authors conclude that their AI-based algorithm is a promising tool for improving the accuracy of radiographic interpretation by identifying technical errors in canine thoracic radiographs.

Development of an artificial intelligence-based method for the diagnosis of the severity of myxomatous mitral valve disease from canine chest radiographs

An algorithm based on artificial intelligence (AI) was developed and tested to classify different stages of myxomatous mitral valve disease (MMVD) from canine thoracic radiographs. The radiographs were selected from the medical databases of two different institutions, considering dogs over 6 years of age that had undergone chest X-ray and echocardiographic examination. Only radiographs clearly showing the cardiac silhouette were considered. The convolutional neural network (CNN) was trained on both the right and left lateral and/or ventro-dorsal or dorso-ventral views. Each dog was classified according to the American College of Veterinary Internal Medicine (ACVIM) guidelines as stage B1, B2 or C + D. ResNet18 CNN was used as a classification network, and the results were evaluated using confusion matrices, receiver operating characteristic curves, and t-SNE and UMAP projections. The area under the curve (AUC) showed good heart-CNN performance in determining the MMVD stage from the lateral views with an AUC of 0.87, 0.77, and 0.88 for stages B1, B2, and C + D, respectively. The high accuracy of the algorithm in predicting the MMVD stage suggests that it could stand as a useful support tool in the interpretation of canine thoracic radiographs.

Contrast-enhanced ultrasound features of adrenal lesions in dogs

BACKGROUND

The contrast-enhanced ultrasound (CEUS) features of adrenal lesions are poorly reported in veterinary literature.

METHODS

Qualitative and quantitative B-mode ultrasound and CEUS features of 186 benign (adenoma) and malignant (adenocarcinoma and pheochromocytoma) adrenal lesions were evaluated.

RESULTS

Adenocarcinomas (n = 72) and pheochromocytomas (n = 32) had mixed echogenicity with B-mode, and a non-homogeneous aspect with a diffused or peripheral enhancement pattern, hypoperfused areas, intralesional microcirculation and non-homogeneous wash-out with CEUS. Adenomas (n = 82) had mixed echogenicity, isoechogenicity or hypoechogenicity with B-mode, and a homogeneous or non-homogeneous aspect with a diffused enhancement pattern, hypoperfused areas, intralesional microcirculation and homogeneous wash-out with CEUS. With CEUS, a non-homogeneous aspect and the presence of hypoperfused areas and intralesional microcirculation can be used to distinguish between malignant (adenocarcinoma and pheochromocytoma) and benign (adenoma) adrenal lesions.

LIMITATIONS

Lesions were characterised only by means of cytology.

CONCLUSIONS

CEUS examination is a valuable tool for distinction between benign and malignant adrenal lesions and can potentially differentiate pheochromocytomas from adenocarcinomas and adenomas. However, cytology and histology are necessary to obtain the final diagnosis.

Contrast-enhanced ultrasound features of focal pancreatic lesions in dogs

BACKGROUND

Contrast-enhanced ultrasound (CEUS) features of pancreatic lesions are poorly reported in veterinary literature.

METHODS

Qualitative and quantitative features of pancreatic benign (nodular hyperplasia [NH], cyst and abscess) and malignant (adenocarcinoma and insulinoma) lesions during B-mode and CEUS examinations are described in 75 dogs.

RESULTS

Adenocarcinomas (n = 23) had mixed echogenicity at B-mode, and they were hypoenhancing or non-enhancing at CEUS, with a non-homogeneous and cystic enhancement pattern. Insulinomas (n = 23) appeared as hypoechoic lesions at B-mode, and as hyperenhancing, homogeneous and solid lesions at CEUS. NH (n = 17) had an constant appearance, being hypoechoic at ultrasound (US) and isoenhancing at CEUS. Cysts (n = 7) were all anechoic, with acoustic enhancement clearly detectable at US, but were non-enhancing at CEUS. Lastly, abscesses (n = 5) had mixed echogenicity, and they showed both hyperenhancement and non-enhancement at CEUS. Hypoenhancement and non-homogeneous appearance had a moderate diagnostic accuracy in the detection of adenocarcinomas. In particular, hyperenhancement was evident only in malignant lesions (adenocarcinomas and insulinomas).

CONCLUSION

CEUS, in combination with B-mode US features, is a valuable tool for distinction of benign and malignant abnormalities of the pancreas and can potentially differentiate insulinomas from adenocarcinomas.

Contrast-enhanced ultrasound features of focal pancreatic lesions in cats

A large overlap in the ultrasound (US) features of focal pancreatic lesions (FPLs) in cats is reported. Furthermore, only a small number of studies describing the contrast-enhanced ultrasound (CEUS) features of FPLs in cats have been conducted today. The aim of this study is to describe the B-mode US and CEUS features of FPLs in cats. Ninety-eight cats cytologically diagnosed with FPL were included. The lesions were classified as adenocarcinoma (n = 40), lymphoma (n = 11), nodular hyperplasia (n = 17), other benign lesion (OBL) (n = 20), cyst (n = 4) or other malignant lesion (OML) (n = 6). Several qualitative and quantitative B-mode and CEUS features were described in each case. OMLs and cysts were not included in the statistical analysis. A decision tree to classify the lesions based on their B-mode and CEUS features was developed. The overall accuracy of the cross-validation of the decision tree was 0.74 (95% CI: 0.63–0.83). The developed decision tree had a very high sensitivity and specificity for nodular hyperplasia (1 and 0.94, respectively) as well as good sensitivity and specificity for both adenocarcinomas (0.85 and 0.77, respectively) and OBLs also (0.70 and 0.93, respectively). The algorithm was unable to detect any specific feature for classifying lymphomas, and almost all the lymphomas were classified as adenocarcinomas. The combination between CEUS and B-mode US is very accurate in the classification of some FPLs, especially nodular hyperplasia and adenocarcinomas. Cytopathology and or histopathology is still a fundamental step FPL diagnostic workflow.

A Machine Learning-Based Approach for Classification of Focal Splenic Lesions Based on Their CT Features

The aim of the study was to describe the CT features of focal splenic lesions (FSLs) in dogs in order to predict lesion histotype. Dogs that underwent a CT scan and had a FSL diagnosis by cytology or histopathology were retrospectively included in the study. For the statistical analysis the cases were divided into four groups, based on the results of cytopatholoy or hystopathology, namely: nodular hyperplasia (NH), other benign lesions (OBLs), sarcoma (SA), round cell tumour (RCT). Several qualitative and quantitative CT features were described for each case. The relationship occurring between each individual CT feature and the histopathological groups was explred by means of c chi-square test for the count data and by means of Kruskal-Wallis or ANOVA for the continuous data. Furthermore, the main features of each group were described using factorial discriminant analysis, and a decision tree for lesion classification was then developed. Sarcomas were characterised by large dimensions, a cystic appearance and an overall low post contrast-enhancement. NH and OBLs were characterised by small dimensions, a solid appearance and a high post-contrast enhancement. OBLs showed higher post-contrast values than NH. Lastly, RCTs did not exhibit any distinctive CT features. The proposed decision tree had a high accuracy for the classification of SA (0.89) and a moderate accuracy for the classification of OBLs and NH (0.79), whereas it was unable to classify RCTs. The results of the factorial analysis and the proposed decision tree could help the clinician in classifying FSLs based on their CT features. A definitive FSL diagnosis can only be obtained by microscopic examination of the spleen.

Undifferentiated laryngeal carcinoma with hyaline bodies in a cat

BACKGROUND

Primary laryngeal neoplasms are rare in cats, with lymphoma and squamous cell carcinoma being the most commonly diagnosed tumour types. These tumours are usually highly aggressive, difficult to treat, and have a poor prognosis. Here an undifferentiated laryngeal carcinoma with hyaline bodies in a cat is reported.

CASE PRESENTATION

A 13-year-old cat was presented for progressive respiratory signs. Diagnostic procedures revealed a partially obstructive laryngeal mass. Cytology was compatible with a poorly differentiated malignant tumour, with neoplastic cells frequently containing large intracytoplasmic hyaline bodies. After 1 month the patient was euthanised due to a worsening clinical condition and submitted for post-mortem examination, which confirmed the presence of two laryngeal masses. Histopathology confirmed the presence of an undifferentiated neoplasm with marked features of malignancy. Strong immunolabelling for pancytokeratin led to a diagnosis of undifferentiated carcinoma, however, histochemical and immunohistochemical investigations could not elucidate the origin of the large intracytoplasmic hyaline bodies observed in tumour cells, which appeared as non-membrane bound deposits of electron-dense material on transmission electron microscopy.

CONCLUSION

This is the first report of primary undifferentiated laryngeal carcinoma in a cat. Our case confirms the clinical features and the short survival that have been reported in other studies describing feline laryngeal tumours. Moreover, for the first time in feline literature, we describe the presence of intracytoplasmic hyaline bodies in neoplastic cells that were compatible with the so-called hyaline granules reported in different human cancers and also in the dog.

Computed tomography features for differentiating malignant and benign focal liver lesions in dogs: A meta-analysis

Computed tomography (CT) is often performed to complement ultrasound following detection of focal liver lesions (FLL). There is no consensus in the literature regarding the CT features that might be helpful in the distinction between benign and malignant FLL. The aim of this meta-analysis was to identify, based on the available literature, the qualitative and quantitative CT features able to distinguish between benign and malignant FLL. Studies on the diagnostic accuracy of CT in characterising FLL were searched in MEDLINE, Web of Science, and Scopus databases. Pooled sensitivity, pooled specificity, diagnostic odds ratio (DOR), receiver operator curve (ROC) area, were calculated for qualitative features. DOR were used to determine which qualitative features were most informative to detect malignancy; quantitative features were selected/identified based on standardised mean difference (SMD). Well-defined margins, presence of a capsule, abnormal lymph nodes, and heterogeneity in the arterial, portal and delayed phase were classified as informative qualitative CT features. The pooled sensitivity ranged from 0.630 (abnormal lymph nodes) to 0.786 (well-defined margins), while pooled specificity ranged from 0.643 (well-defined margins) to 0.816 (heterogeneous in delayed phase). Maximum dimensions, ellipsoid volume, attenuation of the liver in the pre-contrast phase, and attenuation of the liver in the arterial, portal, and delayed phase were found to be informative quantitative CT features. Larger maximum dimensions and volume (positive SMD), and lower attenuation values (negative SMD) were more associated with malignancy. This meta-analysis provides the evidence base for the interpreting CT imaging in the characterization of FLL.

An AI-Based Algorithm for the Automatic Classification of Thoracic Radiographs in Cats

An artificial intelligence (AI)-based computer-aided detection (CAD) algorithm to detect some of the most common radiographic findings in the feline thorax was developed and tested. The database used for training comprised radiographs acquired at two different institutions. Only correctly exposed and positioned radiographs were included in the database used for training. The presence of several radiographic findings was recorded. Consequenly, the radiographic findings included for training were: no findings, bronchial pattern, pleural effusion, mass, alveolar pattern, pneumothorax, cardiomegaly. Multi-label convolutional neural networks (CNNs) were used to develop the CAD algorithm, and the performance of two different CNN architectures, ResNet 50 and Inception V3, was compared. Both architectures had an area under the receiver operating characteristic curve (AUC) above 0.9 for alveolar pattern, bronchial pattern and pleural effusion, an AUC above 0.8 for no findings and pneumothorax, and an AUC above 0.7 for cardiomegaly. The AUC for mass was low (above 0.5) for both architectures. No significant differences were evident in the diagnostic accuracy of either architecture.

Diagnostic Accuracy of Delayed Phase Post Contrast Computed Tomographic Images in the Diagnosis of Focal Liver Lesions in Dogs: 69 Cases

To describe the computed tomographic (CT) features of focal liver lesions (FLLs) in dogs, that could enable predicting lesion histotype. Dogs diagnosed with FLLs through both CT and cytopathology and/or histopathology were retrospectively collected. Ten qualitative and 6 quantitative CT features have been described for each case. Lastly, a machine learning-based decision tree was developed to predict the lesion histotype. Four categories of FLLs - hepatocellular carcinoma (HCC, n = 13), nodular hyperplasia (NH, n = 19), other benign lesions (OBL, n = 18), and other malignant lesions (OML, n = 19) - were evaluated in 69 dogs. Five of the observed qualitative CT features resulted to be statistically significant in the distinction between the 4 categories: surface, appearance, lymph-node appearance, capsule formation, and homogeneity of contrast medium distribution. Three of the observed quantitative CT features were significantly different between the 4 categories: the Hounsfield Units (HU) of the radiologically normal liver parenchyma during the pre-contrast scan, the maximum dimension, and the ellipsoid volume of the lesion. Using the machine learning-based decision tree, it was possible to correctly classify NHs, OBLs, HCCs, and OMLs with an accuracy of 0.74, 0.88, 0.87, and 0.75, respectively. The developed decision tree could be an easy-to-use tool to predict the histotype of different FLLs in dogs. Cytology and histology are necessary to obtain the final diagnosis of the lesions.

Automatic classification of canine thoracic radiographs using deep learning

The interpretation of thoracic radiographs is a challenging and error-prone task for veterinarians. Despite recent advancements in machine learning and computer vision, the development of computer-aided diagnostic systems for radiographs remains a challenging and unsolved problem, particularly in the context of veterinary medicine. In this study, a novel method, based on multi-label deep convolutional neural network (CNN), for the classification of thoracic radiographs in dogs was developed. All the thoracic radiographs of dogs performed between 2010 and 2020 in the institution were retrospectively collected. Radiographs were taken with two different radiograph acquisition systems and were divided into two data sets accordingly. One data set (Data Set 1) was used for training and testing and another data set (Data Set 2) was used to test the generalization ability of the CNNs. Radiographic findings used as non mutually exclusive labels to train the CNNs were: unremarkable, cardiomegaly, alveolar pattern, bronchial pattern, interstitial pattern, mass, pleural effusion, pneumothorax, and megaesophagus. Two different CNNs, based on ResNet-50 and DenseNet-121 architectures respectively, were developed and tested. The CNN based on ResNet-50 had an Area Under the Receive-Operator Curve (AUC) above 0.8 for all the included radiographic findings except for bronchial and interstitial patterns both on Data Set 1 and Data Set 2. The CNN based on DenseNet-121 had a lower overall performance. Statistically significant differences in the generalization ability between the two CNNs were evident, with the CNN based on ResNet-50 showing better performance for alveolar pattern, interstitial pattern, megaesophagus, and pneumothorax.

Training Deep Neural Networks for Small and Highly Heterogeneous MRI Datasets for Cancer Grading

Using medical images recorded in clinical practice has the potential to be a game-changer in the application of machine learning for medical decision support. Thousands of medical images are produced in daily clinical activity. The diagnosis of medical doctors on these images represents a source of knowledge to train machine learning algorithms for scientific research or computer-aided diagnosis. However, the requirement of manual data annotations and the heterogeneity of images and annotations make it difficult to develop algorithms that are effective on images from different centers or sources (scanner manufacturers, protocols, etc.). The objective of this article is to explore the opportunities and the limits of highly heterogeneous biomedical data, since many medical data sets are small and entail a challenge for machine learning techniques. Particularly, we focus on a small data set targeting meningioma grading. Meningioma grading is crucial for patient treatment and prognosis. It is normally performed by histological examination but recent articles showed that it is possible to do it also on magnetic resonance images (MRI), so non-invasive. Our data set consists of 174 T1-weighted MRI images of patients with meningioma, divided into 126 benign and 48 atypical/anaplastic cases, acquired using 26 different MRI scanners and 125 acquisition protocols, which shows the enormous variability in the data set. The performed preprocessing steps include tumor segmentation, spatial image normalization and data augmentation based on color and affine transformations. The preprocessed cases are passed to a carefully trained 2-D convolutional neural network. Accuracy above 74% was obtained, with the high-grade tumor recall above 74%. The results are encouraging considering the limited size and high heterogeneity of the data set. The proposed methodology can be useful for other problems involving classification of small and highly heterogeneous data sets.

Progesterone-responsive vaginal leiomyoma and hyperprogesteronemia due to ovarian luteoma in an older bitch

Background

This is the first report about a vaginal leiomyoma concomitant with an ovarian luteoma in a bitch.

Case presentation

A 11-year-old intact female Labrador retriever was referred because of anuria, constipation and protrusion of a vaginal mass through the vulvar commissure. The bitch had high serum progesterone concentration (4.94 ng/ml). Because of the possibility of progesterone responsiveness causing further increase of the vaginal mass and since the bitch was a poor surgical candidate a 10 mg/kg aglepristone treatment was started SC on referral day 1. A computerized tomography showed a 12.7 × 6.5 × 8.3 cm mass causing urethral and rectal compression, ureteral dilation and hydronephrosis. A vaginal leiomyoma was diagnosed on histology. As serum progesterone concentration kept increasing despite aglepristone treatment, a 0.02 ng/mL twice daily IM alfaprostol treatment was started on day 18. As neither treatment showed remission of clinical signs or luteolysis, ovariohysterectomy was performed on referral day 35. Multiple corpora lutea were found on both ovaries. On histology a luteoma was diagnosed on the left ovary. P4 levels were undetectable 7 days after surgery. Recovery was uneventful and 12 weeks after surgery tomography showed a reduction of 86.7% of the vaginal mass. The bitch has been in good health and able to urinate without any complication ever since.

Conclusions

This case demonstrates the importance of identifying progesterone related conditions as well as the importance of judiciously using a combined medical and surgical approach.

Use of deep learning to detect cardiomegaly on thoracic radiographs in dogs

The purpose of this study was to develop a computer-aided detection (CAD) device based on convolutional neural networks (CNNs) to detect cardiomegaly from plain radiographs in dogs. Right lateral chest radiographs (n = 1465) were retrospectively selected from archives. The radiographs were classified as having a normal cardiac silhouette (No-vertebral heart scale [VHS]-Cardiomegaly) or an enlarged cardiac silhouette (VHS-Cardiomegaly) based on the breed-specific VHS. The database was divided into a training set (1153 images) and a test set (315 images). The diagnostic accuracy of four different CNN models in the detection of cardiomegaly was calculated using the test set. All tested models had an area under the curve >0.9, demonstrating high diagnostic accuracy. There was a statistically significant difference between Model C and the remainder models (Model A vs. Model C, P = 0.0298; Model B vs. Model C, P = 0.003; Model C vs. Model D, P = 0.0018), but there were no significant differences between other combinations of models (Model A vs. Model B, P = 0.395; Model A vs. Model D, P = 0.128; Model B vs. Model D, P = 0.373). Convolutional neural networks could therefore assist veterinarians in detecting cardiomegaly in dogs from plain radiographs.

Correlation between renal histopathology and renal ultrasound in dogs

Fifty-three privately owned dogs were included in the study. Ultrasonography of the kidneys was performed ante mortem. All the dogs died or were euthanized for reasons unrelated to this study. Histopathology of both kidneys was performed, and a degeneration and an inflammation score ranging from zero to two was assigned by consensus between two pathologists. A numerical score based on a three level semi-quantitative scale (0, 0.5, 1) was assigned by consensus between two of the authors to the following ultrasonographic abnormalities: cortico-medullary definition, echogenicity of the renal cortex, echogenicity of the medulla, renal shape, cysts, scars, mineralizations, subcapsular perirenal fluid accumulation, pyelectasia. The scores deriving from the consensus were summed to create a summary index called renal ultrasound score (RUS). Statistically significant differences in cortico-medullary definition, echogenicity of the renal cortex, echogenicity of the medulla, renal shape, scars and pyelectasia were evident between the degeneration score groups. There were significantly different distributions of cortico-medullary definition, renal shape and scars between the inflammatory score groups. There were statistically significant differences in the RUS between the degenerative score groups (F = 24.154, p-value<.001). Post-hoc tests revealed significant differences between all groups. There were no significant differences in the RUS between the inflammatory score groups (F = 1.312, p-value = .264). Post-hoc tests revealed no significant differences between groups. The results of the present study suggest that the number and severity of the ultrasonographic abnormalities are correlated with the severity of the kidney degeneration. On the other hand, inflammation showed poor influence on the ultrasonographic appearance of the kidneys.

A Frailty Index based on clinical data to quantify mortality risk in dogs

Frailty is defined as a decline in an organism’s physiological reserves resulting in increased vulnerability to stressors. In humans, a single continuous variable, the so-called Frailty Index (FI), can be obtained by multidimensionally assessing the biological complexity of an ageing organism. Here, we evaluate this variability in dogs and compare it to the data available for humans. In dogs, there was a moderate correlation between age and the FI, and the distribution of the FI increased with age. Deficit accumulation was strongly related to mortality. The effect of age, when combined with the FI, was negligible. No sex-related differences were evident. The FI could be considered in epidemiological studies and/or experimental trials to account for the potential confounding effects of the health status of individual dogs. The age-related deficit accumulation reported in dogs is similar to that demonstrated in humans. Therefore, dogs might represent an excellent model for human aging studies.

Contrast-enhanced ultrasound features of hepatocellular carcinoma in dogs

Background

This study aimed to describe the contrast-enhanced ultrasound (CEUS) features of canine hepatocellular carcinoma (HCC) in relation to cellular differentiation and lesion size.

Methods

Sixty dogs with a cytological diagnosis of HCC and that underwent a CEUS examination were retrospectively selected. The wash-in and wash-out patterns of contrast enhancement, along with the time to wash-in and the time to wash-out, of each lesion were recorded. A dimensional cut-off value of 3 cm was adopted for classification.

Results

Cellular differentiation had a significant influence on both wash-in (chi-squared=16.99; P<0.001) and wash-out (chi-squared=10.9; P=0.004) patterns of contrast enhancement. Lesion size had a lower, but still significant, influence on both wash-in (chi-squared=12.7; P=0.005) and wash-out (chi-squared=7.42; P=0.024) patterns. A homogeneous hyperenhancement in the arterial phase followed by homogeneous wash-out were suggestive of a well-differentiated HCC. The cellular differentiation of lesions with inhomogeneous hyperenhancement or hypoenhancement/no enhancement as well as an inhomogeneous wash-out or no wash-out could not be inferred.

Conclusions

No significant difference in the time to wash-in and the time to wash-out in relation to cellular differentiation or lesion size was evident. CEUS has the potential to improve efficiency in the diagnosis of HCCs in dogs.

Contrast-enhanced ultrasonography features of hepatobiliary neoplasms in cats

BACKGROUND

Contrast-enhanced ultrasonography (CEUS) features of primary hepatobiliary neoplasms have been reported in dogs but no information is available in cats.

METHODS

Qualitative and quantitative features of bile duct adenomas (BDAs, n=20), bile duct carcinomas (BDCs, n=16), and hepatocellular carcinomas (HCCs, n=8) are described in 44 cats.

RESULTS

There was an overlap in CEUS qualitative features between different histotypes, both in wash-in and wash-out phases. Distinction between different neoplasms based only on the CEUS qualitative features was not possible. At peak of enhancement, the BDAs, BDCs and HCCs showed a large range of echogenicities, from hypoenhancement to hyperenhancement, in comparison to the liver parenchyma. Eight of 20 BDAs showed inhomogeneous hyperenhancement during wash-in, which is a feature reported as typical of malignant lesions in dogs. BDC had a significantly faster wash-in compared with both BDA and HCC but the diagnostic accuracy of all the included quantitative variables was only moderate. No significant differences in the wash-out quantitative features of BDA and BDC were evident.

CONCLUSION

There is poor evidence that CEUS may be used to distinguish between different primary hepatobiliary neoplasms in cats.

Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: A preliminary study

Background

Grading of meningiomas is important in the choice of the most effective treatment for each patient.

Purpose

To determine the diagnostic accuracy of a deep convolutional neural network (DCNN) in the differentiation of the histopathological grading of meningiomas from MR images.

Study Type

Retrospective.

Population

In all, 117 meningioma‐affected patients, 79 World Health Organization [WHO] Grade I, 32 WHO Grade II, and 6 WHO Grade III.

Field Strength/Sequence

1.5 T, 3.0 T postcontrast enhanced T₁ W (PCT₁W), apparent diffusion coefficient (ADC) maps (b values of 0, 500, and 1000 s/mm²).

Assessment

WHO Grade II and WHO Grade III meningiomas were considered a single category. The diagnostic accuracy of the pretrained Inception‐V3 and AlexNet DCNNs was tested on ADC maps and PCT₁W images separately. Receiver operating characteristic curves (ROC) and area under the curve (AUC) were used to asses DCNN performance.

Statistical Test

Leave‐one‐out cross‐validation.

Results

The application of the Inception‐V3 DCNN on ADC maps provided the best diagnostic accuracy results, with an AUC of 0.94 (95% confidence interval [CI], 0.88–0.98). Remarkably, only 1/38 WHO Grade II–III and 7/79 WHO Grade I lesions were misclassified by this model. The application of AlexNet on ADC maps had a low discriminating accuracy, with an AUC of 0.68 (95% CI, 0.59–0.76) and a high misclassification rate on both WHO Grade I and WHO Grade II–III cases. The discriminating accuracy of both DCNNs on postcontrast T₁W images was low, with Inception‐V3 displaying an AUC of 0.68 (95% CI, 0.59–0.76) and AlexNet displaying an AUC of 0.55 (95% CI, 0.45–0.64).

Data Conclusion

DCNNs can accurately discriminate between benign and atypical/anaplastic meningiomas from ADC maps but not from PCT₁W images.

Level of evidence: 2

Technical Efficacy: Stage 2

J. Magn. Reson. Imaging 2019;50:1152–1159.

A methodological approach for deep learning to distinguish between meningiomas and gliomas on canine MR-images

Background

Distinguishing between meningeal-based and intra-axial lesions by means of magnetic resonance (MR) imaging findings may occasionally be challenging. Meningiomas and gliomas account for most of the total primary brain neoplasms in dogs, and differentiating between these two forms is mandatory in choosing the correct therapy. The aims of the present study are: 1) to determine the accuracy of a deep convolutional neural network (CNN, GoogleNet) in discriminating between meningiomas and gliomas in pre- and post-contrast T1 images and T2 images; 2) to develop an image classifier, based on the combination of CNN and MRI sequence displaying the highest accuracy, to predict whether a lesion is a meningioma or a glioma.

Results

Eighty cases with a final diagnosis of meningioma (n = 56) and glioma (n = 24) from two different institutions were included in the study. A pre-trained CNN was retrained on our data through a process called transfer learning. To evaluate CNN accuracy in the different imaging sequences, the dataset was divided into a training, a validation and a test set. The accuracy of the CNN was calculated on the test set. The combination between post-contrast T1 images and CNN was chosen in developing the image classifier (trCNN). Ten images from challenging cases were excluded from the database in order to test trCNN accuracy; the trCNN was trained on the remainder of the dataset of post-contrast T1 images, and correctly classified all the selected images. To compensate for the imbalance between meningiomas and gliomas in the dataset, the Matthews correlation coefficient (MCC) was also calculated. The trCNN showed an accuracy of 94% (MCC = 0.88) on post-contrast T1 images, 91% (MCC = 0.81) on pre-contrast T1-images and 90% (MCC = 0.8) on T2 images.

Conclusions

The developed trCNN could be a reliable tool in distinguishing between different meningiomas and gliomas from MR images.

Normal ultrasonographic reference values for the gastrointestinal tract in developing puppies

Thickness of the individual layers of the wall of the stomach, duodenum, jejunum and colon was assessed by means of ultrasonography in developing puppies at 4, 8 and 16weeks of age. Reference intervals for the thickness of individual ultrasonographic layers of the stomach, duodenum, jejunum and colon at different ages are reported. An increase in wall thickness of all the examined gastro-intestinal tracts in relation to age was recorded. The effect of body-weight was stronger on duodenal and jejunal thickness whereas it resulted lesser on stomach and colon. Correlation between duodenal and jejunal mucosal layer thickness and body weight was strong, while correlation between body weight and the other intestinal wall layers of the duodenum, jejunum and colon ranged from moderate to weak. No effects of gender were detected.

Estimation of fetal lung development using quantitative analysis of ultrasonographic images in normal canine pregnancy

We investigated the quantitative analysis of sonographic images to predict fetal lung maturity of the canine foetus in normal pregnancy. Twelve bitches were recruited in the present study. Serial ultrasonographic exams were performed at three pre-determined time periods corresponding to the pseudoglandular (40-48 days of pregnancy), canalicular (49-56 days of pregnancy) and saccular phase (57-63 days of pregnancy) of lung development. Mean grey level (MGL) and the standard deviation of the histogram (SDH) of fetal lung and liver sonographic images were measured with dedicated software. The lung-to-liver ratio (LLR) for both parameters was also calculated. Measurements were taken on the two caudal-most foetuses and then averaged. SDH did not show any statistically significant difference between the three time periods in the lungs or in the liver. MGL measured in the lungs significantly increased in the first period and reached a plateau during the last two periods. Liver echogenicity was constant during the first two periods and significantly increased during the last week of gestation. The LLR of MGL significantly decreased during the last week of pregnancy. The LLR was a very good test to detect fetal lung maturity (area under the receiver operator curve (AUROC) = 0.875); using a cut-off value of LLR < 1.541, sensitivity was 83.33% and specificity was 83.33%, positive likelihood ratio = 5. LLR of MGL is an accurate test to estimate lung development in normal canine pregnancies.

Relationship of diagnostic accuracy of renal cortical echogenicity with renal histopathology in dogs and cats, a quantitative study

Background

Renal cortical echogenicity is routinely evaluated during ultrasonographic investigation of the kidneys. Both in dog and cat previous ex-vivo studies have revealed a poor correlation between renal echogenicity and corresponding lesions. The aim of this study was to establish the in-vivo relationship between renal cortical echogenicity and renal histopathology.

Results

Thirty-eight dogs and fifteen cats euthanized for critical medical conditions were included in the study. Ultrasonographic images of both kidneys were acquired ante mortem at standardized ultrasonographic settings. The echogenicity was quantified by means of Mean Gray Value (MGV) of the renal cortex measured with ImageJ. A complete histopathological examination of both kidneys was performed. Five kidneys were excluded because histopathology revealed neoplastic lesions. Only samples affected by tubular atrophy showed statistically different values in dog, and histopathology explained 13% of the total variance. MGV was not correlated neither to the degeneration nor to the inflammation scores. However, significant differences were identified between mildly and severely degenerated samples. Overall, the classification efficiency of MGV to detect renal lesions was poor with a sensitivity of 39% and a specificity of 86%.

In cats, samples affected by both tubular vacuolar degeneration and interstitial nephritis were statistically different and histopathology explained 44% of the total variance. A linear correlation was evident between degeneration and MGV, whereas no correlation with inflammation was found. Statistically significant differences were evident only between normal and severely degenerated samples with a sensitivity of 54.17% and a specificity of 83.3% and MGV resulted scarce to discriminate renal lesions in this species.

Conclusions

Renal cortical echogenicity shows low relevance in detecting chronic renal disease in dog whereas it results worth to identify severe renal damage in cat.

Normal computed tomographic features and reference values for the coelomic cavity in pet parrots

Background

The increasing popularity gained by pet birds over recent decades has highlighted the role of avian medicine and surgery in the global veterinary scenario; such a need for speciality avian medical practice reflects the rising expectation for high-standard diagnostic imaging procedures. The aim of this study is to provide an atlas of matched anatomical cross-sections and contrast-enhanced CT images of the coelomic cavity in three highly diffused psittacine species.

Results

Contrast-enhanced computed tomographic studies of the coelomic cavity were performed in 5 blue-and-gold macaws, 4 African grey parrots and 6 monk parakeets by means of a 4-multidetector-row CT scanner. Both pre- and post-contrast scans were acquired. Anatomical reference cross-sections were obtained from 5 blue-and-gold macaw, 7 African grey parrot, and 9 monk parakeet cadavers. The specimens were stored in a −20 °C freezer until completely frozen and then sliced at 5-mm intervals by means of a band saw. All the slices were photographed on both sides. Individual anatomical structures were identified by means of the available literature. Pre- and post-contrast attenuation reference values for the main coelomic organs are reported in Hounsfield units (HU).

Conclusions

The results provide an atlas of matched anatomical cross-sections and contrast-enhanced CT images of the coelomic cavity in three highly diffused psittacine species.

Texture analysis of B-mode ultrasound images to stage hepatic lipidosis in the dairy cow: A methodological study

Hepatic lipidosis is the most diffused hepatic disease in the lactating cow. A new methodology to estimate the degree of fatty infiltration of the liver in lactating cows by means of texture analysis of B-mode ultrasound images is proposed. B-mode ultrasonography of the liver was performed in 48 Holstein Friesian cows using standardized ultrasound parameters. Liver biopsies to determine the triacylglycerol content of the liver (TAGqa) were obtained from each animal. A large number of texture parameters were calculated on the ultrasound images by means of a free software. Based on the TAGqa content of the liver, 29 samples were classified as mild (TAGqa<50mg/g), 6 as moderate (50mg/g<TAGqa>100mg/g) and 13 as severe (TAG>100mg/g) in steatosis. Stepwise linear regression analysis was performed to predict the TAGqa content of the liver (TAGpred) from the texture parameters calculated on the ultrasound images. A five-variable model was used to predict the TAG content from the ultrasound images. The regression model explained 83.4% of the variance. An area under the curve (AUC) of 0.949 was calculated for <50mg/g vs >50mg/g of TAGqa; using an optimal cut-off value of 72mg/g TAGpred had a sensitivity of 86.2% and a specificity of 84.2%. An AUC of 0.978 for <100mg/g vs >100mg/g of TAGqa was calculated; using an optimal cut-off value of 89mg/g, TAGpred sensitivity was 92.3% and specificity was 88.6%. Texture analysis of B-mode ultrasound images may therefore be used to accurately predict the TAG content of the liver in lactating cows.

Correlation of renal histopathology with renal echogenicity in dogs and cats: an ex-vivo quantitative study

Background

Increased cortical or cortical and medullary echogenicity is one of the most common signs of chronic or acute kidney disease in dogs and cats. Subjective evaluation of the echogenicity is reported to be unreliable. Patient and technical-related factors affect in-vivo quantitative evaluation of the echogenicity of parenchymal organs. The aim of the present study is to investigate the relationship between histopathology and ex-vivo renal cortical echogenicity in dogs and cats devoid of any patient and technical-related biases.

Results

Kidney samples were collected from 68 dog and 32 cat cadavers donated by the owners to the Veterinary Teaching Hospital of the University of Padua and standardized ultrasonographic images of each sample were collected. The echogenicity of the renal cortex was quantitatively assessed by means of mean gray value (MGV), and then histopathological analysis was performed. Statistical analysis to evaluate the influence of histological lesions on MGV was performed. The differentiation efficiency of MGV to detect pathological changes in the kidneys was calculated for dogs and cats. Statistical analysis revealed that only glomerulosclerosis was an independent determinant of echogenicity in dogs whereas interstitial nephritis, interstitial necrosis and fibrosis were independent determinants of echogenicity in cats. The global influence of histological lesions on renal echogenicity was higher in cats (23%) than in dogs (12%).

Conclusions

Different histopathological lesions influence the echogenicity of the kidneys in dogs and cats. Moreover, MGV is a poor test for distinguishing between normal and pathological kidneys in the dog with a sensitivity of 58.3% and specificity of 59.8%. Instead, it seems to perform globally better in the cat, resulting in a fair test, with a sensitivity of 80.6% and a specificity of 56%.

Evaluation of three medetomidine-based protocols for chemical restraint and sedation for non-painful procedures in companion rats (Rattus norvegicus)

Three medetomidine-based protocols were evaluated for sedation in companion rats undergoing diagnostic procedures. Group Me received medetomidine at 150 μg/kg intramuscularly (IM); group Me-Bu received medetomidine 100 μg/kg IM and butorphanol 2 mg/kg IM, and group Me-Bu-Mi received medetomidine 50 μg/kg IM, butorphanol 2 mg/kg IM and midazolam 1 mg/kg IM. The righting reflex disappeared more quickly in the Me-Bu-Mi group, but recovery after atipamezole was longer. In group Me, a palpebral reflex was present throughout sedation in more rats than in the other two groups. Pulse and respiratory rates were higher when lower doses of medetomidine were used, although arterial haemoglobin O2 saturation was similar among groups. All protocols tested produced adequate sedation lasting 25 min.

Comparative evaluation of the cadaveric, radiographic and computed tomographic anatomy of the heads of green iguana (Iguana iguana), common tegu (Tupinambis merianae) and bearded dragon (Pogona vitticeps)

Background

Radiology and computed tomography are the most commonly available diagnostic tools for the diagnosis of pathologies affecting the head and skull in veterinary practice. Nevertheless, accurate interpretation of radiographic and CT studies requires a thorough knowledge of the gross and the cross-sectional anatomy. Despite the increasing success of reptiles as pets, only a few reports over their normal imaging features are currently available. The aim of this study is to describe the normal cadaveric, radiographic and computed tomographic features of the heads of the green iguana, tegu and bearded dragon.

Results

6 adult green iguanas, 4 tegus, 3 bearded dragons, and, the adult cadavers of : 4 green iguana, 4 tegu, 4 bearded dragon were included in the study. 2 cadavers were dissected following a stratigraphic approach and 2 cadavers were cross-sectioned for each species. These latter specimens were stored in a freezer (−20°C) until completely frozen. Transversal sections at 5 mm intervals were obtained by means of an electric band-saw. Each section was cleaned and photographed on both sides. Radiographs of the head of each subject were obtained. Pre- and post- contrast computed tomographic studies of the head were performed on all the live animals. CT images were displayed in both bone and soft tissue windows. Individual anatomic structures were first recognised and labelled on the anatomic images and then matched on radiographs and CT images. Radiographic and CT images of the skull provided good detail of the bony structures in all species. In CT contrast medium injection enabled good detail of the soft tissues to be obtained in the iguana whereas only the eye was clearly distinguishable from the remaining soft tissues in both the tegu and the bearded dragon.

Conclusions

The results provide an atlas of the normal anatomical and in vivo radiographic and computed tomographic features of the heads of lizards, and this may be useful in interpreting any imaging modality involving these species.

Evaluation of radiographic, computed tomographic, and cadaveric anatomy of the head of boa constrictors

OBJECTIVE

To evaluate the radiographic, computed tomographic (CT), and cadaveric anatomy of the head of boa constrictors.

ANIMALS

4 Boa constrictor imperator cadavers.

PROCEDURES

Cadavers weighed 3.4 to 5.6 kg and had a body length ranging from 189 to 221 cm. Radiographic and CT images were obtained with a high-detail screen-film combination, and conventional CT was performed with a slice thickness of 1.5 mm. Radiographic images were obtained in ventrodorsal, dorsoventral, and left and right laterolateral recumbency; CT images were obtained with the animals positioned in ventral recumbency directly laying on a plastic support. At the end of the radiographic and CT imaging session, 2 heads were sectioned following a stratigraphic approach; the other 2, carefully maintained in the same position on the plastic support, were moved into a freezer (-20°C) until completely frozen and then sectioned into 3-mm slices, respecting the imaging protocol. The frozen sections were cleaned and then photographed on each side. Anatomic structures were identified and labeled on gross anatomic images and on the corresponding CT or radiographic image with the aid of available literature.

RESULTS

Radiographic and CT images provided high detail for visualization of bony structures; soft tissues were not easily identified on radiographic and CT images.

CONCLUSIONS AND CLINICAL RELEVANCE

Results provide an atlas of stratigraphic and cross-sectional gross anatomy and radiographic and CT anatomy of the heads of boa constrictors that might be useful in the interpretation of any imaging modality in this species.

Cross-sectional anatomy of the rabbit neck and trunk: comparison of computed tomography and cadaver anatomy

Computed tomographic images of the neck, thorax and abdomen in four healthy adult rabbits were obtained with a conventional CT using a slice-thickness of 5mm. CT images were obtained with the animals positioned in sternal recumbency on a removable plastic support directly laying on the CT-table. At the end of the CT session, each rabbit was euthanized and, while carefully maintaining the same position on the plastic support, the animal was moved into a -20 degrees C freezer until completely frozen. Each cadaver was then sectioned at 10mm slices, with the first section starting at the tip of the nose, respecting the imaging protocol. The frozen sections were cleaned and then photographed on each side. Anatomic structures were identified and labeled first on each side of the frozen section and then on the corresponding CT image with the aid of the available literature. Results from our study provide an atlas of normal cross-sectional gross and CT anatomy of the rabbit neck, thorax and abdomen, useful in the interpretation of any cross-sectional imaging modality in this species.