Histopathological Classification of Canine Cutaneous Round Cell Tumors Using Deep Learning: A Multi-Center Study

Cutaneous plasmacytoma with Mott cell differentiation in a dog

Cytologic evaluation of aspirate slides from a small, <1-cm, interdigital mass on a 9-y-old, spayed female Yorkshire Terrier revealed a proliferation of discrete, round cells containing few-to-many, variably sized, round, eosinophilic, cytoplasmic inclusions. The top differentials based on the cytologic findings were either a plasma cell tumor or a B-cell lymphoma with Mott cell differentiation. The unencapsulated, well-demarcated, multilobulated round-cell neoplasm was completely excised. Immunohistochemical stains were performed to further characterize the neoplasm, which had immunolabeling for multiple myeloma oncogene 1 and vimentin, but did not react with CD3, CD20, melan A, or ionized calcium-binding adapter molecule 1, nor with a Giemsa special stain. Ultrastructurally, the cytoplasmic granules had Russell body-like morphology. A solitary, cutaneous plasmacytoma with Mott cell differentiation has not been described previously in veterinary medicine, to our knowledge.

All you need is data preparation: A systematic review of image harmonization techniques in Multi-center/device studies for medical support systems

BACKGROUND AND OBJECTIVES

Artificial intelligence (AI) models trained on multi-centric and multi-device studies can provide more robust insights and research findings compared to single-center studies. However, variability in acquisition protocols and equipment can introduce inconsistencies that hamper the effective pooling of multi-source datasets. This systematic review evaluates strategies for image harmonization, which standardizes appearances to enable reliable AI analysis of multi-source medical imaging.

METHODS

A literature search using PRISMA guidelines was conducted to identify relevant papers published between 2013 and 2023 analyzing multi-centric and multi-device medical imaging studies that utilized image harmonization approaches.

RESULTS

Common image harmonization techniques included grayscale normalization (improving classification accuracy by up to 24.42 %), resampling (increasing the percentage of robust radiomics features from 59.5 % to 89.25 %), and color normalization (enhancing AUC by up to 0.25 in external test sets). Initially, mathematical and statistical methods dominated, but machine and deep learning adoption has risen recently. Color imaging modalities like digital pathology and dermatology have remained prominent application areas, though harmonization efforts have expanded to diverse fields including radiology, nuclear medicine, and ultrasound imaging. In all the modalities covered by this review, image harmonization improved AI performance, with increasing of up to 24.42 % in classification accuracy and 47 % in segmentation Dice scores.

CONCLUSIONS

Continued progress in image harmonization represents a promising strategy for advancing healthcare by enabling large-scale, reliable analysis of integrated multi-source datasets using AI. Standardizing imaging data across clinical settings can help realize personalized, evidence-based care supported by data-driven technologies while mitigating biases associated with specific populations or acquisition protocols.

Improved assessment of donor liver steatosis using Banff consensus recommendations and deep learning algorithms

BACKGROUND & AIMS

The Banff Liver Working Group recently published consensus recommendations for steatosis assessment in donor liver biopsy, but few studies reported their use and no automated deep-learning algorithms based on the proposed criteria have been developed so far. We evaluated Banff recommendations on a large monocentric series of donor liver needle biopsies by comparing pathologists' scores with those generated by convolutional neural networks (CNNs) we specifically developed for automated steatosis assessment.

METHODS

We retrospectively retrieved 292 allograft liver needle biopsies collected between January 2016 and January 2020 and performed steatosis assessment using a former intra-institution method (pre-Banff method) and the newly introduced Banff recommendations. Scores provided by pathologists and CNN models were then compared, and the degree of agreement was measured with the intraclass correlation coefficient (ICC).

RESULTS

Regarding the pre-Banff method, poor agreement was observed between the pathologist and CNN models for small droplet macrovesicular steatosis (ICC: 0.38), large droplet macrovesicular steatosis (ICC: 0.08), and the final combined score (ICC: 0.16) evaluation, but none of these reached statistically significance. Interestingly, significantly improved agreement was observed using the Banff approach: ICC was 0.93 for the low-power score (p <0.001), 0.89 for the high-power score (p <0.001), and 0.93 for the final score (p <0.001). Comparing the pre-Banff method with the Banff approach on the same biopsy, pathologist and CNN model assessment showed a mean (±SD) percentage of discrepancy of 26.89 (±22.16) and 1.20 (±5.58), respectively.

CONCLUSIONS

Our findings support the use of Banff recommendations in daily practice and highlight the need for a granular analysis of their effect on liver transplantation outcomes.

IMPACT AND IMPLICATIONS

We developed and validated the first automated deep-learning algorithms for standardized steatosis assessment based on the Banff Liver Working Group consensus recommendations. Our algorithm provides an unbiased automated evaluation of steatosis, which will lay the groundwork for granular analysis of steatosis's short- and long-term effects on organ viability, enabling the identification of clinically relevant steatosis cut-offs for donor organ acceptance. Implementing our algorithm in daily clinical practice will allow for a more efficient and safe allocation of donor organs, improving the post-transplant outcomes of patients.

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.

Quantitative analysis of prion disease using an AI-powered digital pathology framework

Prion disease is a fatal neurodegenerative disorder characterized by accumulation of an abnormal prion protein (PrPSc) in the central nervous system. To identify PrPSc aggregates for diagnostic purposes, pathologists use immunohistochemical staining of prion protein antibodies on tissue samples. With digital pathology, artificial intelligence can now analyze stained slides. In this study, we developed an automated pipeline for the identification of PrPSc aggregates in tissue samples from the cerebellar and occipital cortex. To the best of our knowledge, this is the first framework to evaluate PrPSc deposition in digital images. We used two strategies: a deep learning segmentation approach using a vision transformer, and a machine learning classification approach with traditional classifiers. Our method was developed and tested on 64 whole slide images from 41 patients definitively diagnosed with prion disease. The results of our study demonstrated that our proposed framework can accurately classify WSIs from a blind test set. Moreover, it can quantify PrPSc distribution and localization throughout the brain. This could potentially be extended to evaluate protein expression in other neurodegenerative diseases like Alzheimer's and Parkinson's. Overall, our pipeline highlights the potential of AI-assisted pathology to provide valuable insights, leading to improved diagnostic accuracy and efficiency.

Canine Mammary Tumor Histopathological Image Classification via Computer-Aided Pathology: An Available Dataset for Imaging Analysis

Histopathology, the gold-standard technique in classifying canine mammary tumors (CMTs), is a time-consuming process, affected by high inter-observer variability. Digital (DP) and Computer-aided pathology (CAD) are emergent fields that will improve overall classification accuracy. In this study, the ability of the CAD systems to distinguish benign from malignant CMTs has been explored on a dataset-namely CMTD-of 1056 hematoxylin and eosin JPEG images from 20 benign and 24 malignant CMTs, with three different CAD systems based on the combination of a convolutional neural network (VGG16, Inception v3, EfficientNet), which acts as a feature extractor, and a classifier (support vector machines (SVM) or stochastic gradient boosting (SGB)), placed on top of the neural net. Based on a human breast cancer dataset (i.e., BreakHis) (accuracy from 0.86 to 0.91), our models were applied to the CMT dataset, showing accuracy from 0.63 to 0.85 across all architectures. The EfficientNet framework coupled with SVM resulted in the best performances with an accuracy from 0.82 to 0.85. The encouraging results obtained by the use of DP and CAD systems in CMTs provide an interesting perspective on the integration of artificial intelligence and machine learning technologies in cancer-related research.

Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning

Background

Radiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task.

Purpose

The purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC.

Materials and methods

Contrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient (Dice), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs.

Results

CNN models trained from scratch on canine data or by using transfer learning obtained mean test set Dice scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean Dice performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set Dice scores of 0.69 for both approaches.

Conclusion

In conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients.

Comparative Evaluation of Tumor-Infiltrating Lymphocytes in Companion Animals: Immuno-Oncology as a Relevant Translational Model for Cancer Therapy

Simple Summary

Laboratory experiments studying solid tumors are limited by the inability to adequately model the tumor microenvironment and important immune interactions. Immune cells that infiltrate the tumor bed or periphery have been documented as reliable biomarkers in human studies. Veterinary oncology provides a naturally occurring cancer model that could complement biomarker discovery, clinical trials, and drug development.

Abstract

Despite the important role of preclinical experiments to characterize tumor biology and molecular pathways, there are ongoing challenges to model the tumor microenvironment, specifically the dynamic interactions between tumor cells and immune infiltrates. Comprehensive models of host-tumor immune interactions will enhance the development of emerging treatment strategies, such as immunotherapies. Although in vitro and murine models are important for the early modelling of cancer and treatment-response mechanisms, comparative research studies involving veterinary oncology may bridge the translational pathway to human studies. The natural progression of several malignancies in animals exhibits similar pathogenesis to human cancers, and previous studies have shown a relevant and evaluable immune system. Veterinary oncologists working alongside oncologists and cancer researchers have the potential to advance discovery. Understanding the host-tumor-immune interactions can accelerate drug and biomarker discovery in a clinically relevant setting. This review presents discoveries in comparative immuno-oncology and implications to cancer therapy.

Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset

Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.

Measurement(s)	canine cutaneous tissue
Technology Type(s)	bright-field microscopy • H&E slide staining • whole slide scanning
Sample Characteristic - Organism	Canis

Qualitative Histopathological Classification of Primary Bone Tumors Using Deep Learning: A Pilot Study

Background

Histopathological diagnosis of bone tumors is challenging for pathologists. We aim to classify bone tumors histopathologically in terms of aggressiveness using deep learning (DL) and compare performance with pathologists.

Methods

A total of 427 pathological slides of bone tumors were produced and scanned as whole slide imaging (WSI). Tumor area of WSI was annotated by pathologists and cropped into 716,838 image patches of 256 × 256 pixels for training. After six DL models were trained and validated in patch level, performance was evaluated on testing dataset for binary classification (benign vs. non-benign) and ternary classification (benign vs. intermediate vs. malignant) in patch-level and slide-level prediction. The performance of four pathologists with different experiences was compared to the best-performing models. The gradient-weighted class activation mapping was used to visualize patch’s important area.

Results

VGG-16 and Inception V3 performed better than other models in patch-level binary and ternary classification. For slide-level prediction, VGG-16 and Inception V3 had area under curve of 0.962 and 0.971 for binary classification and Cohen’s kappa score (CKS) of 0.731 and 0.802 for ternary classification. The senior pathologist had CKS of 0.685 comparable to both models (p = 0.688 and p = 0.287) while attending and junior pathologists showed lower CKS than the best model (each p < 0.05). Visualization showed that the DL model depended on pathological features to make predictions.

Conclusion

DL can effectively classify bone tumors histopathologically in terms of aggressiveness with performance similar to senior pathologists. Our results are promising and would help expedite the future application of DL-assisted histopathological diagnosis for bone tumors.