Whole-slide imaging, tissue image analysis, and artificial intelligence in veterinary pathology: An updated introduction and review.

Since whole-slide imaging has been commercially available for over 2 decades, digital pathology has become a constantly expanding aspect of the pathology profession that will continue to significantly impact how pathologists conduct their craft. While some aspects, such as whole-slide imaging for archiving, consulting, and teaching, have gained broader acceptance, other facets such as quantitative tissue image analysis and artificial intelligence-based assessments are still met with some reservations. While most vendors in this space have focused on diagnostic applications, that is, viewing one or few slides at a time, some are developing solutions tailored more specifically to the various aspects of veterinary pathology including updated diagnostic, discovery, and research applications. This has especially advanced the use of digital pathology in toxicologic pathology and drug development, for primary reads as well as peer reviews. It is crucial that pathologists gain a deeper understanding of digital pathology and tissue image analysis technology and their applications in order to fully use these tools in a way that enhances and improves the pathologist's assessment as well as work environment. This review focuses on an updated introduction to the basics of digital pathology and image analysis and introduces emerging topics around artificial intelligence and machine learning.

Tissue Multiplex Analyte Detection in Anatomic Pathology - Pathways to Clinical Implementation.

Background: Multiplex tissue analysis has revolutionized our understanding of the tumor microenvironment (TME) with implications for biomarker development and diagnostic testing. Multiplex labeling is used for specific clinical situations, but there remain barriers to expanded use in anatomic pathology practice. Methods: We review immunohistochemistry (IHC) and related assays used to localize molecules in tissues, with reference to United States regulatory and practice landscapes. We review multiplex methods and strategies used in clinical diagnosis and in research, particularly in immuno-oncology. Within the framework of assay design and testing phases, we examine the suitability of multiplex immunofluorescence (mIF) for clinical diagnostic workflows, considering its advantages and challenges to implementation. Results: Multiplex labeling is poised to radically transform pathologic diagnosis because it can answer questions about tissue-level biology and single-cell phenotypes that cannot be addressed with traditional IHC biomarker panels. Widespread implementation will require improved detection chemistry, illustrated by InSituPlex technology (Ultivue, Inc., Cambridge, MA) that allows coregistration of hematoxylin and eosin (H&E) and mIF images, greater standardization and interoperability of workflow and data pipelines to facilitate consistent interpretation by pathologists, and integration of multichannel images into digital pathology whole slide imaging (WSI) systems, including interpretation aided by artificial intelligence (AI). Adoption will also be facilitated by evidence that justifies incorporation into clinical practice, an ability to navigate regulatory pathways, and adequate health care budgets and reimbursement. We expand the brightfield WSI system "pixel pathway" concept to multiplex workflows, suggesting that adoption might be accelerated by data standardization centered on cell phenotypes defined by coexpression of multiple molecules. Conclusion: Multiplex labeling has the potential to complement next generation sequencing in cancer diagnosis by allowing pathologists to visualize and understand every cell in a tissue biopsy slide. Until mIF reagents, digital pathology systems including fluorescence scanners, and data pipelines are standardized, we propose that diagnostic labs will play a crucial role in driving adoption of multiplex tissue diagnostics by using retrospective data from tissue collections as a foundation for laboratory-developed test (LDT) implementation and use in prospective trials as companion diagnostics (CDx).

Domain Adaptation-Based Deep Learning for Automated Tumor Cell (TC) Scoring and Survival Analysis on PD-L1 Stained Tissue Images.

We report the ability of two deep learning-based decision systems to stratify non-small cell lung cancer (NSCLC) patients treated with checkpoint inhibitor therapy into two distinct survival groups. Both systems analyze functional and morphological properties of epithelial regions in digital histopathology whole slide images stained with the SP263 PD-L1 antibody. The first system learns to replicate the pathologist assessment of the Tumor Cell (TC) score with a cut-point for positivity at 25% for patient stratification. The second system is free from assumptions related to TC scoring and directly learns patient stratification from the overall survival time and event information. Both systems are built on a novel unpaired domain adaptation deep learning solution for epithelial region segmentation. This approach significantly reduces the need for large pixel-precise manually annotated datasets while superseding serial sectioning or re-staining of slides to obtain ground truth by cytokeratin staining. The capacity of the first system to replicate the TC scoring by pathologists is evaluated on 703 unseen cases, with an addition of 97 cases from an independent cohort. Our results show Lin's concordance values of 0.93 and 0.96 against pathologist scoring, respectively. The ability of the first and second system to stratify anti-PD-L1 treated patients is evaluated on 151 clinical samples. Both systems show similar stratification powers (first system: HR = 0.539, p = 0.004 and second system: HR = 0.525, p = 0.003) compared to TC scoring by pathologists (HR = 0.574, p = 0.01).

Mini Review: The Last Mile-Opportunities and Challenges for Machine Learning in Digital Toxicologic Pathology.

The 2019 manuscript by the Special Interest Group on Digital Pathology and Image Analysis of the Society of Toxicologic pathology suggested that a synergism between artificial intelligence (AI) and machine learning (ML) technologies and digital toxicologic pathology would improve the daily workflow and future impact of toxicologic pathologists globally. Now 2 years later, the authors of this review consider whether, in their opinion, there is any evidence that supports that thesis. Specifically, we consider the opportunities and challenges for applying ML (the study of computer algorithms that are able to learn from example data and extrapolate the learned information to unseen data) algorithms in toxicologic pathology and how regulatory bodies are navigating this rapidly evolving field. Although we see similarities with the "Last Mile" metaphor, the weight of evidence suggests that toxicologic pathologists should approach ML with an equal dose of skepticism and enthusiasm. There are increasing opportunities for impact in our field that leave the authors cautiously excited and optimistic. Toxicologic pathologists have the opportunity to critically evaluate ML applications with a "call-to-arms" mentality. Why should we be late adopters? There is ample evidence to encourage engagement, growth, and leadership in this field.

Proof of Concept for a Deep Learning Algorithm for Identification and Quantification of Key Microscopic Features in the Murine Model of DSS-Induced Colitis.

Inflammatory bowel disease (IBD) is a complex disease which leads to life-threatening complications and decreased quality of life. The dextran sulfate sodium (DSS) colitis model in mice is known for rapid screening of candidate compounds. Efficacy assessment in this model relies partly on microscopic semiquantitative scoring, which is time-consuming and subjective. We hypothesized that deep learning artificial intelligence (AI) could be used to identify acute inflammation in H&E-stained sections in a consistent and quantitative manner. Training sets were established using ×20 whole slide images of the entire colon. Supervised training of a Convolutional Neural Network (CNN) was performed using a commercial AI platform to detect the entire colon tissue, the muscle and mucosa layers, and 2 categories within the mucosa (normal and acute inflammation E1). The training sets included slides of naive, vehicle-DSS and cyclosporine A-DSS mice. The trained CNN was able to segment, with a high level of concordance, the different tissue compartments in the 3 groups of mice. The segmented areas were used to determine the ratio of E1-affected mucosa to total mucosa. This proof-of-concept work shows promise to increase efficiency and decrease variability of microscopic scoring of DSS colitis when screening candidate compounds for IBD.

Developing a Qualification and Verification Strategy for Digital Tissue Image Analysis in Toxicological Pathology.

Digital tissue image analysis is a computational method for analyzing whole-slide images and extracting large, complex, and quantitative data sets. However, as with any analysis method, the quality of generated results is dependent on a well-designed quality control system for the entire digital pathology workflow. Such system requires clear procedural controls, appropriate user training, and involvement of specialists to oversee key steps of the workflow. The toxicologic pathologist is responsible for reporting data obtained by digital image analysis and therefore needs to ensure that it is correct. To accomplish that, they must understand the main parameters of the quality control system and should play an integral part in its conception and implementation. This manuscript describes the most common digital tissue image analysis end points and potential sources of analysis errors. In addition, it outlines recommended approaches for ensuring quality and correctness of results for both classical and machine-learning based image analysis solutions, as adapted from a recently proposed Food and Drug Administration regulatory framework for modifications to artificial intelligence/machine learning-based software as a medical device. These approaches are beneficial for any type of toxicopathologic study which uses the described end points and can be adjusted based on the intended use of the image analysis solution.

Detection of MCPG metabolites in horses with atypical myopathy.

Atypical myopathy (AM) in horses is caused by ingestion of seeds of the Acer species (Sapindaceae family). Methylenecyclopropylacetyl-CoA (MCPA-CoA), derived from hypoglycin A (HGA), is currently the only active toxin in Acer pseudoplatanus or Acer negundo seeds related to AM outbreaks. However, seeds or arils of various Sapindaceae (e.g., ackee, lychee, mamoncillo, longan fruit) also contain methylenecyclopropylglycine (MCPG), which is a structural analogue of HGA that can cause hypoglycaemic encephalopathy in humans. The active poison formed from MCPG is methylenecyclopropylformyl-CoA (MCPF-CoA). MCPF-CoA and MCPA-CoA strongly inhibit enzymes that participate in ß-oxidation and energy production from fat. The aim of our study was to investigate if MCPG is involved in Acer seed poisoning in horses. MCPG, as well as glycine and carnitine conjugates (MCPF-glycine, MCPF-carnitine), were quantified using high-performance liquid chromatography-tandem mass spectrometry of serum and urine from horses that had ingested Acer pseudoplatanus seeds and developed typical AM symptoms. The results were compared to those of healthy control horses. For comparison, HGA and its glycine and carnitine derivatives were also measured. Additionally, to assess the degree of enzyme inhibition of ß-oxidation, several acyl glycines and acyl carnitines were included in the analysis. In addition to HGA and the specific toxic metabolites (MCPA-carnitine and MCPA-glycine), MCPG, MCPF-glycine and MCPF-carnitine were detected in the serum and urine of affected horses. Strong inhibition of ß-oxidation was demonstrated by elevated concentrations of all acyl glycines and carnitines, but the highest correlations were observed between MCPF-carnitine and isobutyryl-carnitine (r = 0.93) as well as between MCPA- (and MCPF-) glycine and valeryl-glycine with r = 0.96 (and r = 0.87). As shown here, for biochemical analysis of atypical myopathy of horses, it is necessary to take MCPG and the corresponding metabolites into consideration.

Deep Semi Supervised Generative Learning for Automated Tumor Proportion Scoring on NSCLC Tissue Needle Biopsies.

The level of PD-L1 expression in immunohistochemistry (IHC) assays is a key biomarker for the identification of Non-Small-Cell-Lung-Cancer (NSCLC) patients that may respond to anti PD-1/PD-L1 treatments. The quantification of PD-L1 expression currently includes the visual estimation by a pathologist of the percentage (tumor proportional scoring or TPS) of tumor cells showing PD-L1 staining. Known challenges like differences in positivity estimation around clinically relevant cut-offs and sub-optimal quality of samples makes visual scoring tedious and subjective, yielding a scoring variability between pathologists. In this work, we propose a novel deep learning solution that enables the first automated and objective scoring of PD-L1 expression in late stage NSCLC needle biopsies. To account for the low amount of tissue available in biopsy images and to restrict the amount of manual annotations necessary for training, we explore the use of semi-supervised approaches against standard fully supervised methods. We consolidate the manual annotations used for training as well the visual TPS scores used for quantitative evaluation with multiple pathologists. Concordance measures computed on a set of slides unseen during training provide evidence that our automatic scoring method matches visual scoring on the considered dataset while ensuring repeatability and objectivity.

Bovine Neonatal Pancytopenia - correlation between clinical symptoms, hematological parameters and lifespan.

OBJECTIVE: To compare the hematological parameters and clinical symptoms between Bovine Neonatal Pancytopenia (BNP) diseased calves dying before and after 14 days of life. MATERIAL AND METHODS: Clinical observations included 47 calves from dams which underwent a 3-year vaccination program with the inactivated PregSure® BVD vaccine. In 25 of these 47 BNP affected calves blood examinations were performed and in 22 dead calves diagnosis was mainly based on post-mortem findings. RESULTS: Cutaneous bleeding was the predominant clinical manifestation in 32 from 47 calves (68.1%). Seven from 47 calves (14.9%) developed cutaneous bleeding as the only symptom and 17 from 47 calves (36.2%) demonstrated these alterations in combination with hemorrhagic lesions of the oral mucosa. In 66.0% (31/47) of calves petechiae of the oral mucosa were seen and petechiation without any other BNP related symptoms occurred in eight from 47 calves (17.0%). The hematological analysis revealed thrombocytopenia in all 25 cases (n = 23: PLT < 60 x 109/l, n = 2: PLT 139-164 x 109/l). Nineteen from 25 calves (76.0%) developed thrombocytopenia and leukocytopenia (WBC < 3.5 x 109/l). In nine of them a decrease of erythrocyte count (RBC < 4.5 x 109/l), hemoglobin concentration (Hb < 8 g/dl) and packed cell volume (PCV < 24%) was measured. Three BNP affected calves without clinical symptoms were identified by hematological examination. The average life time of BNP affected calves was 14.7 ± 6.2 days. Clinical findings, especially multifocal cutaneous hemorrhages were more frequently recognized in calves living longer than 14 days. CONCLUSION AND CLINICAL RELEVANCE: At the time of falling ill with BNP, older calves displayed more numerous symptoms, especially bleeding in the skin. Thrombocytopenia and erythropenia occur as well as a decreased hemoglobin concentration and a low PCV. The time between outbreak of symptoms and death of calves which fell ill later, did not differ from the survival time of BNP calves, which displayed symptoms at a younger age. A decrease of thrombocytes was the cardinal laboratory finding.

Novel Immunomodulatory Flagellin-Like Protein FlaC in Campylobacter jejuni and Other Campylobacterales.

The human diarrheal pathogens Campylobacter jejuni and Campylobacter coli interfere with host innate immune signaling by different means, and their flagellins, FlaA and FlaB, have a low intrinsic property to activate the innate immune receptor Toll-like receptor 5 (TLR5). We have investigated here the hypothesis that the unusual secreted, flagellin-like molecule FlaC present in C. jejuni, C. coli, and other Campylobacterales might activate cells via TLR5 and interact with TLR5. FlaC shows striking sequence identity in its D1 domains to TLR5-activating flagellins of other bacteria, such as Salmonella, but not to nonstimulating Campylobacter flagellins. We overexpressed and purified FlaC and tested its immunostimulatory properties on cells of human and chicken origin. Treatment of cells with highly purified FlaC resulted in p38 activation. FlaC directly interacted with TLR5. Preincubation with FlaC decreased the responsiveness of chicken and human macrophage-like cells toward the bacterial TLR4 agonist lipopolysaccharide (LPS), suggesting that FlaC mediates cross-tolerance. C. jejuni flaC mutants induced an increase of cell responses in comparison to those of the wild type, which was suppressed by genetic complementation. Supplementing excess purified FlaC likewise reduced the cellular response to C. jejuni. In vivo, the administration of ultrapure FlaC led to a decrease in cecal interleukin 1ß (IL-1ß) expression and a significant change of the cecal microbiota in chickens. We propose that Campylobacter spp. have evolved a novel type of secreted immunostimulatory flagellin-like effector in order to specifically modulate host responses, for example toward other pattern recognition receptor (PRR) ligands, such as LPS. IMPORTANCE Flagellins not only are important for bacterial motility but are major bacterial proteins that can modulate host responses via Toll-like receptor 5 (TLR5) or other pattern recognition receptors. Campylobacterales colonizing the intestinal tracts of different host species harbor a gene coding for an unusual flagellin, FlaC, that is not involved in motility but is secreted and possesses a chimeric amino acid sequence composed of TLR5-activating and non-TLR5-activating flagellin sequences. Campylobacter jejuni FlaC activates cells to increase in cytokine expression in chicken and human cells, promotes cross-tolerance to TLR4 ligands, and alters chicken cecal microbiota. We propose that FlaC is a secreted effector flagellin that has specifically evolved to modulate the immune response in the intestinal tract in the presence of the resident microbiota and may contribute to bacterial persistence. The results also strengthen the role of the flagellar type III apparatus as a functional secretion system for bacterial effector proteins.

Rapid diagnosis of hypoglycin A intoxication in atypical myopathy of horses.

Hypoglycin A (2-amino-3-(2-methylidenecyclopropyl)propanoic acid) is the plant toxin shown to cause atypical myopathy in horses. It is converted in vivo to methylenecyclopropyl acetic acid, which is transformed to a coenzyme A ester that subsequently blocks beta oxidation of fatty acids. Methylenecyclopropyl acetic acid is also conjugated with carnitine and glycine. Acute atypical myopathy may be diagnosed by quantifying the conjugates of methylenecyclopropyl acetic acid plus a selection of acyl conjugates in urine and serum. We describe a new mass spectrometric method for sample volumes of <0.5 mL. Samples were extracted with methanol containing 5 different internal standards. Extracts were analyzed by ultra-high-performance liquid chromatography-tandem mass spectrometry focusing on 11 metabolites. The total preparation time for a series of 20 samples was 100 min. Instrument run time was 14 min per sample. For the quantification of carnitine and glycine conjugates of methylenecyclopropyl acetic acid in urine, the coefficients of variation for intraday quantification were 2.9% and 3.0%, respectively. The respective values for interday were 9.3% and 8.0%. Methylenecyclopropyl acetyl carnitine was detected as high as 1.18 µmol/L in serum (median: 0.46 µmol/L) and 1.98 mmol/mol creatinine in urine (median: 0.79 mmol/mol creatinine) of diseased horses, while the glycine derivative accumulated up to 1.97 mmol/mol creatinine in urine but was undetectable in most serum samples. In serum samples from horses with atypical myopathy, the intraday coefficients of variation for C4-C8 carnitines and glycines were ≤4.5%. Measured concentrations exceeded those in healthy horses by ~10 to 1,400 times.

No evidence of Sarcocystis calchasi involvement in mammalian meningoencephalitis of unknown origin.

Sarcocystis calchasi has recently been identified as the cause of pigeon protozoal encephalitis, PPE, a lethal brain disease in pigeons and parrots. While only avian species have been identified so far to be susceptible to this pathogen as definitive or intermediate hosts, we speculated whether mammals may be susceptible as well, as in Sarcocystis neurona and other related apicomplexan parasites. Specifically, we hypothesized its involvement in mammalian meningoencephalitis of unknown origin, MUO. A total of 143 archived formalin fixed, paraffin embedded brain samples with MUO from dogs, cats, pigs, cattle, sheep, guinea pigs, horses, goats, mice, raccoon, ferret, hamster, mink and maned wolf were examined pathohistologically and by PCR for parasitic stages or DNA, respectively, of Sarcocystis calchasi or other apicomplexan parasites. All samples had non-suppurative, lymphoplasmacytic and/or granulomatous encephalitis or meningoencephalitis typical of MUO with many similarities to PPE in pigeons. However, neither parasitic structures nor DNA of Sarcocystis calchasi or other apicomplexan parasites were detected. It thus appears that, despite histological similarities between mammalian MUO and pigeon PPE and despite seemingly high prevalence of PPE and a persistent threat by Sarcocystis calchasi in pigeons, based on histopathology and PCR there is no evidence for a role of this parasite in MUO in mammals as intermediate or aberrant hosts.