Classification of neoplastic and inflammatory brain disease using MRI texture analysis in 119 dogs

An Illustrated Scoping Review of the Magnetic Resonance Imaging Characteristics of Canine and Feline Brain Tumors

Magnetic resonance imaging (MRI) is used pervasively in veterinary practice for the antemortem diagnosis of intracranial tumors. Here, we provide an illustrated summary of the published MRI features of primary and secondary intracranial tumors of dogs and cats, following PRISMA scoping review guidelines. The PubMed and Web of Science databases were searched for relevant records, and input from stakeholders was solicited to select data for extraction. Sixty-seven studies of moderate to low-level evidence quality describing the MRI features of pathologically confirmed canine and feline brain tumors met inclusion criteria. Considerable variability in data inclusion and reporting, as well as low case numbers, prohibited comparative data analyses. Available data support a holistic MRI approach incorporating lesion number, location within the brain, shape, intrinsic signal appearances on multiparametric sequences, patterns of contrast enhancement, and associated secondary changes in the brain to prioritize differential imaging diagnoses, and often allows for accurate presumptive diagnosis of common intracranial tumors. Quantitative MRI techniques show promise for improving discrimination of neoplastic from non-neoplastic brain lesions, as well as differentiating brain tumor types and grades, but sample size limitations will likely remain a significant practical obstacle to the design of robustly powered radiomic studies. For many brain tumor variants, particularly in cats, there remains a need for standardized studies that correlate clinicopathologic and neuroimaging data.

The potential application of artificial intelligence in veterinary clinical practice and biomedical research

Artificial intelligence (AI) is a fast-paced technological advancement in terms of its application to various fields of science and technology. In particular, AI has the potential to play various roles in veterinary clinical practice, enhancing the way veterinary care is delivered, improving outcomes for animals and ultimately humans. Also, in recent years, the emergence of AI has led to a new direction in biomedical research, especially in translational research with great potential, promising to revolutionize science. AI is applicable in antimicrobial resistance (AMR) research, cancer research, drug design and vaccine development, epidemiology, disease surveillance, and genomics. Here, we highlighted and discussed the potential impact of various aspects of AI in veterinary clinical practice and biomedical research, proposing this technology as a key tool for addressing pressing global health challenges across various domains.

Chemotherapy for the treatment of intracranial glioma in dogs

Gliomas are the second most common primary brain tumor in dogs and although they are associated with a poor prognosis, limited data are available relating to the efficacy of standard therapeutic options such as surgery, radiation and chemotherapy. Additionally, canine glioma is gaining relevance as a naturally occurring animal model that recapitulates human disease with fidelity. There is an intense comparative research drive to test new therapeutic approaches in dogs and assess if results translate efficiently into human clinical trials to improve the poor outcomes associated with the current standard-of-care. However, the paucity of data and controversy around most appropriate treatment for intracranial gliomas in dogs make comparisons among modalities troublesome. To further inform therapeutic decision-making, client discussion, and future studies evaluating treatment responses, the outcomes of 127 dogs with intracranial glioma, either presumed (n = 49) or histologically confirmed (n = 78), that received chemotherapy as leading or adjuvant treatment are reviewed here. This review highlights the status of current chemotherapeutic approaches to intracranial gliomas in dogs, most notably temozolomide and lomustine; areas of novel treatment currently in development, and difficulties to consensuate and compare different study observations. Finally, suggestions are made to facilitate evidence-based research in the field of canine glioma therapeutics.

Machine learning predicts histologic type and grade of canine gliomas based on MRI texture analysis

Conventional MRI features of canine gliomas subtypes and grades significantly overlap. Texture analysis (TA) quantifies image texture based on spatial arrangement of pixel intensities. Machine learning (ML) models based on MRI-TA demonstrate high accuracy in predicting brain tumor types and grades in human medicine. The aim of this retrospective, diagnostic accuracy study was to investigate the accuracy of ML-based MRI-TA in predicting canine gliomas histologic types and grades. Dogs with histopathological diagnosis of intracranial glioma and available brain MRI were included. Tumors were manually segmented across their entire volume in enhancing part, non-enhancing part, and peri-tumoral vasogenic edema in T2-weighted (T2w), T1-weighted (T1w), FLAIR, and T1w postcontrast sequences. Texture features were extracted and fed into three ML classifiers. Classifiers' performance was assessed using a leave-one-out cross-validation approach. Multiclass and binary models were built to predict histologic types (oligodendroglioma vs. astrocytoma vs. oligoastrocytoma) and grades (high vs. low), respectively. Thirty-eight dogs with a total of 40 masses were included. Machine learning classifiers had an average accuracy of 77% for discriminating tumor types and of 75.6% for predicting high-grade gliomas. The support vector machine classifier had an accuracy of up to 94% for predicting tumor types and up to 87% for predicting high-grade gliomas. The most discriminative texture features of tumor types and grades appeared related to the peri-tumoral edema in T1w images and to the non-enhancing part of the tumor in T2w images, respectively. In conclusion, ML-based MRI-TA has the potential to discriminate intracranial canine gliomas types and grades.

Artificial Intelligence in Veterinary Imaging: An Overview

Artificial intelligence and machine learning have been increasingly used in the medical imaging field in the past few years. The evaluation of medical images is very subjective and complex, and therefore the application of artificial intelligence and deep learning methods to automatize the analysis process would be very beneficial. A lot of researchers have been applying these methods to image analysis diagnosis, developing software capable of assisting veterinary doctors or radiologists in their daily practice. This article details the main methodologies used to develop software applications on machine learning and how veterinarians with an interest in this field can benefit from such methodologies. The main goal of this study is to offer veterinary professionals a simple guide to enable them to understand the basics of artificial intelligence and machine learning and the concepts such as deep learning, convolutional neural networks, transfer learning, and the performance evaluation method. The language is adapted for medical technicians, and the work already published in this field is reviewed for application in the imaging diagnosis of different animal body systems: musculoskeletal, thoracic, nervous, and abdominal.

Artificial intelligence in veterinary diagnostic imaging: A literature review

Artificial intelligence in veterinary medicine is an emerging field. Machine learning, a subfield of artificial intelligence, allows computer programs to analyze large imaging datasets and learn to perform tasks relevant to veterinary diagnostic imaging. This review summarizes the small, yet growing body of artificial intelligence literature in veterinary imaging, provides necessary background to understand these papers, and provides author commentary on the state of the field. To date, less than 40 peer-reviewed publications have utilized machine learning to perform imaging-associated tasks across multiple anatomic regions in veterinary clinical and biomedical research. Major challenges in this field include collection and cleaning of sufficient image data, selection of high-quality ground truth labels, formation of relationships between veterinary and machine learning professionals, and closure of the gap between academic uses of artificial intelligence and currently available commercial products. Further development of artificial intelligence has the potential to help meet the growing need for radiological services through applications in workflow, quality control, and image interpretation for both general practitioners and radiologists.

Radiomics in veterinary medicine: Overview, methods, and applications

Radiomics, or quantitative image analysis from radiographic image data, borrows the suffix from other emerging -omics fields of study, such as genomics, proteomics, and metabolomics. This report provides an overview of the general principles of how radiomic features are computed, describes major types of morphological, first order, and texture features, and the applications, challenges, and opportunities of radiomics as applied in veterinary medicine. Some advantages radiomics has over traditional semantic radiological features include standardized methodology in computing semantic features, the ability to compute features in multi-dimensional images, their newfound associations with genomic and pathological abnormalities, and the number of perceptible and imperceptible features available for regression or classification modeling. Some challenges in deploying radiomics in a clinical setting include sensitivity to image acquisition settings and image artifacts, pre- and post-image reconstruction and calculation settings, variability in feature estimates stemming from inter- and intra-observer contouring errors, and challenges with software and data harmonization and generalizability of findings given the challenges of small sample size and patient selection bias in veterinary medicine. Despite this, radiomics has enormous potential in patient-centric diagnostics, prognosis, and theragnostics. Fully leveraging the utility of radiomics in veterinary medicine will require inter-institutional collaborations, data harmonization, and data sharing strategies amongst institutions, transparent and robust model development, and multi-disciplinary efforts within and outside the veterinary medical imaging community.

A Review of Radiomics and Artificial Intelligence and Their Application in Veterinary Diagnostic Imaging

Simple Summary

The goal of this paper is to provide an overview of current radiomic and AI applications in veterinary diagnostic imaging. We discuss the essential elements of AI for veterinary practitioners with the aim of helping them make informed decisions in applying AI technologies to their practices and that veterinarians will play an integral role in ensuring the appropriate uses and suitable curation of data. The expertise of veterinary professionals will be vital to ensuring suitable data and, subsequently, AI that meets the needs of the profession.

Abstract

Great advances have been made in human health care in the application of radiomics and artificial intelligence (AI) in a variety of areas, ranging from hospital management and virtual assistants to remote patient monitoring and medical diagnostics and imaging. To improve accuracy and reproducibility, there has been a recent move to integrate radiomics and AI as tools to assist clinical decision making and to incorporate it into routine clinical workflows and diagnosis. Although lagging behind human medicine, the use of radiomics and AI in veterinary diagnostic imaging is becoming more frequent with an increasing number of reported applications. The goal of this paper is to provide an overview of current radiomic and AI applications in veterinary diagnostic imaging.

Survival Time after Surgical Debulking and Temozolomide Adjuvant Chemotherapy in Canine Intracranial Gliomas

Simple Summary

Infiltrative brain tumours are common in dogs. Although different treatments have been used, such as surgery, radiotherapy, chemotherapy, or combinations, guidelines for the most effective management are lacking. In this study, we report the effect of combining surgery and chemotherapy on the survival of 14 dogs with infiltrative gliomas. Four dogs were operated on two or three times to remove the tumors, and only one of these dogs died shortly after the second surgery. All tolerated the surgery with minimal or no deterioration, and all were euthanized between 6 months to 2 years after diagnosis due to tumour progression. To conclude, surgery and chemotherapy, although not curative, can prolong survival in dogs with infiltrative brain tumours. This information may help future research into the most appropriate treatment for this debilitating condition.

Abstract

Intracranial gliomas are associated with a poor prognosis, and the most appropriate treatment is yet to be defined. The objectives of this retrospective study are to report the time to progression and survival times of a group of dogs with histologically confirmed intracranial gliomas treated with surgical debulking and adjuvant temozolomide chemotherapy. All cases treated in a single referral veterinary hospital from 2014 to 2021 were reviewed. Inclusion criteria comprised a histopathological diagnosis of intracranial glioma, adjunctive chemotherapy, and follow-up until death. Cases were excluded if the owner declined chemotherapy or there was insufficient follow-up information in the clinical records. Fourteen client-owned dogs were included with a median time to progression (MTP) of 156 days (95% CI 133–320 days) and median survival time (MST) of 240 days (95% CI 149–465 days). Temozolomide was the first-line adjuvant chemotherapy but changed to another chemotherapy agent (lomustine, toceranib phosphate, or melphalan) when tumour relapse was either suspected by clinical signs or confirmed by advanced imaging. Of the fourteen dogs, three underwent two surgical resections and one, three surgeries. Survival times (ST) were 241, 428, and 468 days for three dogs treated twice surgically and 780 days for the dog treated surgically three times. Survival times for dogs operated once was 181 days. One case was euthanized after developing aspiration pneumonia, and all other cases after progression of clinical signs due to suspected or confirmed tumour relapse. In conclusion, the results of this study suggest that debulking surgery and adjuvant chemotherapy are well-tolerated options in dogs with intracranial gliomas in which surgery is a possibility and should be considered a potential treatment option. Repeated surgery may be considered for selected cases.

Detection of blood‐brain barrier dysfunction using advanced imaging methods to predict seizures in dogs with meningoencephalitis of unknown origin

Background

The blood‐brain barrier (BBB), which separates the intravascular and neuropil compartments, characterizes the vascular bed of the brain and is essential for its proper function. Recent advances in imaging techniques have driven the development of methods for quantitative assessment of BBB permeability.

Hypothesis/Objectives

Permeability of the BBB can be assessed quantitatively in dogs with meningoencephalitis of unknown origin (MUO) and its status is associated with the occurrence of seizures.

Animals

Forty dogs with MUO and 12 dogs without MUO.

Methods

Retrospective, prospective cohort study. Both dynamic contrast enhancement (DCE) and subtraction enhancement analysis (SEA) methods were used to evaluate of BBB permeability in affected (DCE, n = 8; SEA, n = 32) and control dogs (DCE, n = 6; SEA, n = 6). Association between BBB dysfunction (BBBD) score and clinical characteristics was examined. In brain regions where BBBD was identified by DCE or SEA magnetic resonance imaging (MRI) analysis, immunofluorescent staining for albumin, glial fibrillary acidic protein, ionized calcium binding adaptor molecule, and phosphorylated mothers against decapentaplegic homolog 2 were performed to detect albumin extravasation, reactive astrocytes, activated microglia, and transforming growth factor beta signaling, respectively.

Results

Dogs with BBBD had significantly higher seizure prevalence (72% vs 19%; P = .01) when compared to MUO dogs with no BBBD. The addition of SEA to routine MRI evaluation increased the identification rate of brain pathology in dogs with MUO from 50% to 72%.

Conclusions and Clinical Importance

Imaging‐based assessment of BBB integrity has the potential to predict risk of seizures in dogs with MUO.

A New Framework for Precise Identification of Prostatic Adenocarcinoma

Prostate cancer, which is also known as prostatic adenocarcinoma, is an unconstrained growth of epithelial cells in the prostate and has become one of the leading causes of cancer-related death worldwide. The survival of patients with prostate cancer relies on detection at an early, treatable stage. In this paper, we introduce a new comprehensive framework to precisely differentiate between malignant and benign prostate cancer. This framework proposes a noninvasive computer-aided diagnosis system that integrates two imaging modalities of MR (diffusion-weighted (DW) and T2-weighted (T2W)). For the first time, it utilizes the combination of functional features represented by apparent diffusion coefficient (ADC) maps estimated from DW-MRI for the whole prostate in combination with texture features with its first- and second-order representations, extracted from T2W-MRIs of the whole prostate, and shape features represented by spherical harmonics constructed for the lesion inside the prostate and integrated with PSA screening results. The dataset presented in the paper includes 80 biopsy confirmed patients, with a mean age of 65.7 years (43 benign prostatic hyperplasia, 37 prostatic carcinomas). Experiments were conducted using different well-known machine learning approaches including support vector machines (SVM), random forests (RF), decision trees (DT), and linear discriminant analysis (LDA) classification models to study the impact of different feature sets that lead to better identification of prostatic adenocarcinoma. Using a leave-one-out cross-validation approach, the diagnostic results obtained using the SVM classification model along with the combined feature set after applying feature selection (88.75% accuracy, 81.08% sensitivity, 95.35% specificity, and 0.8821 AUC) indicated that the system’s performance, after integrating and reducing different types of feature sets, obtained an enhanced diagnostic performance compared with each individual feature set and other machine learning classifiers. In addition, the developed diagnostic system provided consistent diagnostic performance using 10-fold and 5-fold cross-validation approaches, which confirms the reliability, generalization ability, and robustness of the developed system.

Vascular endothelial growth factor concentrations in the cerebrospinal fluid of dogs with neoplastic or inflammatory central nervous system disorders

Background

Vascular endothelial growth factor (VEGF) is a key molecular driver of angiogenesis and vascular permeability and is expressed by a wide variety of neoplasms. Although blood VEGF concentrations have been quantified in intracranial tumors of dogs, cerebrospinal fluid (CSF) VEGF concentration might be a more sensitive biomarker of disease.

Objective

Concentrations of VEGF in CSF are higher in dogs with central nervous system (CNS) neoplasia compared to those with meningoencephalomyelitis and other neurologic disorders.

Animals

One hundred and twenty‐six client‐owned dogs presented to a veterinary teaching hospital.

Methods

Case‐control study. Cerebrospinal fluid was archived from dogs diagnosed with CNS neoplasia and meningoencephalomyelitis. Control dogs had other neurological disorders or diseases outside of the CNS. A commercially available kit was used to determine VEGF concentrations.

Results

Detectable CSF VEGF concentrations were present in 49/63 (77.8%) neoplastic samples, 22/24 (91.7%) inflammatory samples, and 8/39 (20.5%) control samples. The VEGF concentrations were significantly different between groups (P < .0001), and multiple comparison testing showed that both neoplastic and inflammatory groups had significantly higher concentrations than did controls (P < .05), but did not differ from each other. Gliomas and choroid plexus tumors had significantly higher VEGF concentrations than did the control group (P < .05).

Conclusions and Clinical Importance

Cerebrospinal fluid VEGF concentrations may serve as a marker of neoplastic and inflammatory CNS disorders relative to other conditions.