Cytologic scoring of equine exercise-induced pulmonary hemorrhage: Performance of human experts and a deep learning-based algorithm

Jugular venous thrombosis as a risk factor for exercise-induced pulmonary hemorrhage in thoroughbred racehorses

Background

Exercise-induced pulmonary hemorrhage (EIPH) is one of the most commonly diagnosed disorders in racehorses. Many EIPH risk factors such as breed, age, high or low environmental temperature, and distance of the race have been studied in racehorses.

Aim

The aim of this study was to study the relationship between EIPH and the presence of jugular vein thrombose in racehorses.

Methods

Forty-eight thoroughbred racehorses randomly selected from animals with exercise intolerance due to respiratory disorders were enrolled in the present study. Clinical and tracheobronchoscopy examinations were done for EIPH grading. In addition, both jugular veins were examined using ultrasonography for vein thrombosis.

Results

It was noted during endoscopy that many cases suffered from laryngeal paralysis, and we were not able to assess the degree of laryngeal paralysis under sedation. About 40% of horses with exercise intolerance suffered from EIPH of varying degrees. Most cases of jugular vein thrombosis were of the chronic type, as local heat and pain were not observed. About 42% of the exercise-intolerant horses had jugular vein thrombose with most jugular vein thrombosis on the left side. Combined jugular veins thrombose and EIPH were found in about 25% of exercise intolerance horses, while 17% showed jugular vein thrombose without EIPH, and 41% showed no EIPH with the absence of jugular vein thrombose.

Conclusion

The present study revealed that jugular vein thrombosis may cause disorders-associated damage to the vessels and anatomical structures close to it, such as the trachea causing EIPH.

Comparison of veterinarians and a deep learning tool in the diagnosis of equine ophthalmic diseases

BACKGROUND/OBJECTIVES

The aim was to compare ophthalmic diagnoses made by veterinarians to a deep learning (artificial intelligence) software tool which was developed to aid in the diagnosis of equine ophthalmic diseases. As equine ophthalmology is a very specialised field in equine medicine, the tool may be able to help in diagnosing equine ophthalmic emergencies such as uveitis.

STUDY DESIGN

In silico tool development and assessment of diagnostic performance.

METHODS

A deep learning tool which was developed and trained for classification of equine ophthalmic diseases was tested with 40 photographs displaying various equine ophthalmic diseases. The same data set was shown to different groups of veterinarians (equine, small animal, mixed practice, other) using an opinion poll to compare the results and evaluate the performance of the programme. Convolutional Neural Networks (CNN) were trained on 2346 photographs of equine eyes, which were augmented to 9384 images. Two hundred and sixty-one separate unmodified images were used to evaluate the trained network. The trained deep learning tool was used on 40 photographs of equine eyes (10 healthy, 12 uveitis, 18 other diseases). An opinion poll was used to evaluate the diagnostic performance of 148 veterinarians in comparison to the software tool.

RESULTS

The probability for the correct answer was 93% for the AI programme. Equine veterinarians answered correctly in 76%, whereas other veterinarians reached 67% probability for the correct diagnosis.

MAIN LIMITATIONS

Diagnosis was solely based on images of equine eyes without the possibility to evaluate the inner eye.

CONCLUSIONS

The deep learning tool proved to be at least equivalent to veterinarians in assessing ophthalmic diseases in photographs. We therefore conclude that the software tool may be useful in detecting potential emergency cases. In this context, blindness in horses may be prevented as the horse can receive accurate treatment or can be sent to an equine hospital. Furthermore, the tool gives less experienced veterinarians the opportunity to differentiate between uveitis and other ocular anterior segment disease and to support them in their decision-making regarding treatment.

Respiratory oscillometry testing in relation to exercise in healthy and asthmatic Thoroughbreds

BACKGROUND

Racehorses may experience exercise-induced bronchodilation or bronchoconstriction, with potential differences between healthy and asthmatic individuals.

OBJECTIVES

To identify exercise-related lung function variations by oscillometry in racehorses, compare lung function between healthy and mild equine asthma (MEA) horses, assess oscillometry's potential as a predictor of racing fitness.

STUDY DESIGN

Prospective case-control clinical study.

METHODS

Fourteen Thoroughbred racehorses (5 healthy, 9 MEA) underwent a protocol including respiratory oscillometry at rest, exercise with fitness monitoring, oscillometry at 15 and 45 min post-exercise, and bronchoalveolar lavage fluid (BALf) cytology. Oscillometry parameters (resistance [Rrs] and reactance [Xrs]) were compared within and between healthy and MEA groups at different timepoints. Associations between Rrs and Xrs at rest and 15 min post-exercise and BALf cytology and fitness indices were evaluated.

RESULTS

MEA horses showed higher Rrs at 15 min post-exercise (0.6 ± 0.2 cmH2 O/L/s) than healthy horses (0.3 ± 0.1 cmH2 O/L/s) (p < 0.01). In healthy horses, Rrs decreased at 15 min post-exercise compared with resting values (0.5 ± 0.1 cmH2 O/L/s) (p = 0.04). In MEA horses, oscillometry parameters did not vary with time. Post-exercise Xrs inversely correlated with total haemosiderin score (p < 0.01, r2  = 0.51). Resting Rrs inversely correlated with speed at 200 bpm (p = 0.03, r2  = -0.61), and Xrs with maximum heart rate (HR) during exercise (p = 0.02, r2  = -0.62). Post-exercise Rrs inversely correlated with mean (p = 0.04, r2  = -0.60) and maximum speed (p = 0.04, r2  = -0.60), and HR variability (p < 0.01, r2  = -0.74).

MAIN LIMITATIONS

Small sample size, oscillometry repeatability not assessed, potential interference of upper airway obstructions, external variables influencing fitness indices.

CONCLUSIONS

Oscillometry identified lung function differences between healthy and MEA horses at 15 min post-exercise. Only healthy horses exhibited exercise-induced bronchodilation. Oscillometry showed potential in predicting subclinical airway obstruction.

Histological classification of canine and feline lymphoma using a modular approach based on deep learning and advanced image processing

Histopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users' trust in computer-assisted image classification.

Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images

Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training, n = 245 whole-slide images (WSIs), validation (n = 35 WSIs), and test sets (n = 70 WSIs). Full annotations included the 7 tumor classes and 6 normal skin structures. The data set was used to train a convolutional neural network (CNN) for the automatic segmentation of tumor and nontumor classes. Subsequently, the detected tumor regions were classified patch-wise into 1 of the 7 tumor classes. A majority of patches-approach led to a tumor classification accuracy of the network on the slide-level of 95% (133/140 WSIs), with a patch-level precision of 85%. The same 140 WSIs were provided to 6 experienced pathologists for diagnosis, who achieved a similar slide-level accuracy of 98% (137/140 correct majority votes). Our results highlight the feasibility of artificial intelligence-based methods as a support tool in diagnostic oncologic pathology with future applications in other species and tumor types.