Digital Pathology Research Articles

Role of artificial intelligence in haematolymphoid diagnostics.

The advent of digital pathology and the deployment of high-throughput molecular techniques are generating an unprecedented mass of data. Thanks to advances in computational sciences, artificial intelligence (AI) approaches represent a promising avenue for extracting relevant information from complex data structures. From diagnostic assistance to powerful research tools, the potential fields of application of machine learning techniques in pathology are vast and constitute the subject of considerable research work. The aim of this article is to provide an overview of the potential applications of AI in the field of haematopathology and to define the role that these emerging technologies could play in our laboratories in the short to medium term.

AnVILWorkflow: A runnable workflow package for Cloud-implemented bioinformatics analysis pipelines

Advancements in sequencing technologies and the development of new data collection methods produce large volumes of biological data. The Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL) provides a cloud-based platform for democratizing access to large-scale genomics data and analysis tools. However, utilizing the full capabilities of AnVIL can be challenging for researchers without extensive bioinformatics expertise, especially for executing complex workflows. We present the AnVILWorkflow R package, which enables the convenient execution of bioinformatics workflows hosted on AnVIL directly from an R environment. AnVILWorkflow simplifies the setup of the cloud computing environment, input data formatting, workflow submission, and retrieval of results through intuitive functions. We demonstrate the utility of AnVILWorkflow for three use cases: bulk RNA-seq analysis with Salmon, metagenomics analysis with bioBakery, and digital pathology image processing with PathML. The key features of AnVILWorkflow include user-friendly browsing of available data and workflows, seamless integration of R and non-R tools within a reproducible analysis pipeline, and accessibility to scalable computing resources without direct management overhead. AnVILWorkflow lowers the barrier to utilizing AnVIL’s resources, especially for exploratory analyses or bulk processing with established workflows. This empowers a broader community of researchers to leverage the latest genomics tools and datasets using familiar R syntax. This package is distributed through the Bioconductor project (https://bioconductor.org/packages/AnVILWorkflow), and the source code is available through GitHub (https://github.com/shbrief/AnVILWorkflow).

Correlation of low numbers of intratumoral FOXP3+ cells with worse progression-free survival in angioimmunoblastic T cell lymphoma

AimsAngioimmunoblastic T cell lymphoma (AITL) is a T cell lymphoma with aberrant immune activity. It is characterised by inflammatory and immune reactions. However, the impact of regulatory T (Treg) cells...

Transforming Diagnostics: A Comprehensive Review of Advances in Digital Pathology

Transforming Diagnostics: A Comprehensive Review of Advances in Digital Pathology

The Role of Affective Labour in Expertise: Bringing Emotions Back into Expert Practices

In recent years, a lot of scholarly attention has been devoted to how practices of digitalisation and datafication require medical professionals to work together with different stakeholders, and to how such collaborations shape expertise (Stevens, Wehrens, and de Bont 2020; Carboni et al. 2024). STS scholars have generally approached expertise as an epistemic and social endeavor, but they have tended to neglect the role affects and emotions play in its development and performance. In this paper, we provide a theoretical reflection on the relation between affective labour and expertise building upon Egher’s (2023) conceptualisation of expertise as a practical achievement realised through coordination and affective labour. Based on ethnographic fieldwork conducted in various medical settings, including digital pathology, psychiatry, and datafication in intensive care, we explore what types of affective labour are conducted in digital healthcare, by whom, and with what consequences. We show how affective labour mediates both epistemic and relational practices. We argue that different affects and emotions are mobilised in these practices, which impacts the development and effective performance of expertise.

A hierarchical data partitioning strategy for irregular applications: a case study in digital pathology

A hierarchical data partitioning strategy for irregular applications: a case study in digital pathology

Assessment of PD-L1 expression and tumour infiltrating lymphocytes in early-stage non-small cell lung carcinoma with artificial intelligence algorithms

AimsTo study programmed death ligand 1 (PD-L1) expression and tumour infiltrating lymphocytes (TILs) in patients with early-stage non-small cell lung carcinoma (NSCLC) with artificial intelligence (AI) algorithms.MethodsThe study included samples...

Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology

The incorporation of digital pathology in clinical practice will require the training of pathologists in digital skills. Our study aimed to assess the reliability among pathologists in determining tumor percentage in whole slide images (WSI) of non-small cell lung cancer (NSCLC) using digital image analysis, and study how the results correlate with the molecular findings. Pathologists from nine centers were trained to quantify epithelial tumor cells, tumor-associated stromal cells, and non-neoplastic cells from NSCLC WSI using QuPath. Then, we conducted two consecutive ring trials. In the first trial, analyzing four WSI, reliability between pathologists in the assessment of tumor cell percentage was poor (intraclass correlation coefficient (ICC) 0.09). After performing the first ring trial pathologists received feedback. The second trial, comprising 10 WSI with paired next-generation sequencing results, also showed poor reliability (ICC 0.24). Cases near the recommended 20% visual threshold for molecular techniques exhibited higher values with digital analysis. In the second ring trial reliability slightly improved and human errors were reduced from 5.6% to 1.25%. Most discrepancies arose from subjective tasks, such as the annotation process, suggesting potential improvement with future artificial intelligence solutions.

Neural network analysis as a novel skin outcome in a trial of belumosudil in patients with systemic sclerosis.

Background The modified Rodnan skin score (mRSS), used to measure dermal thickness in patients with systemic sclerosis (SSc), is agnostic to inflammation and vasculopathy. Previously, we demonstrated the potential of neural network-based digital pathology applied to stained skin biopsies from SSc patients as a quantitative outcome. We leveraged deep learning and histologic analyses of clinical trial biopsies to decipher SSc skin features 'seen' by artificial intelligence (AI). Methods Adults with diffuse cutaneous SSc (disease duration ≤ 6 years) enrolled in an open-label trial evaluating belumosudil underwent serial mRSS assessment and dorsal arm biopsies at week 0, 24 and 52/end of trial. Two blinded dermatopathologists independently scored stained sections [Masson's trichrome, hematoxylin and eosin (H&E), CD3, CD34, CD8, α smooth muscle actin (αSMA)] for 16 published SSc dermal pathological parameters. We applied our previously published deep learning model to generate QIF signatures/biopsy and generated Fibrosis Scores. Associations between Fibrosis Score and mRSS (Spearman correlation); and between Fibrosis Score mRSS versus histologic parameters [odds ratios (OR)] were determined. Results Only ten patients were enrolled because the sponsor terminated the trial early. Median, interquartile range (IQR) for mRSS change (0-52 weeks) for the five participants with paired biopsies was - 2.5 (-11-7.5), and for the ten participants was - 2 (-9-7.5). The correlation between Fibrosis Score and mRSS was R = 0.3; p = 0.674. Per 1-unit mRSS change (0-52W), histologic parameters with the greatest associated changes were (OR, p-value): telangiectasia (2.01, 0.001), perivascular CD3+ (1.03, 0.015), and % of CD8 + among CD3+ (1.08, 0.031). Likewise, per 1-unit Fibrosis Score change, parameters with greatest changes were (OR, p-value): hyalinized collagen (1.1, < 0.001), subcutaneous (SC) fat loss (1.47, < 0.001), thickened intima (1.21, 0.005), and eccrine entrapment (1.14, 0.046). Conclusions Belumosudil was associated with a non-clinically meaningful improvement in mRSS. Fibrosis Score changes correlated with histologic feature changes ( e.g. , hyalinized collagen, SC fat loss) that were distinct from those associated with mRSS changes ( e.g. , telangiectasia, perivascular CD3+, and % of CD8 + among CD3+). These data suggest that AI applied to SSc biopsies may be useful for quantifying pathologic features of SSc beyond skin thickness.

Image Analysis in Histopathology and Cytopathology: From Early Days to Current Perspectives.

Both pathology and cytopathology still rely on recognizing microscopical morphologic features, and image analysis plays a crucial role, enabling the identification, categorization, and characterization of different tissue types, cell populations, and disease states within microscopic images. Historically, manual methods have been the primary approach, relying on expert knowledge and experience of pathologists to interpret microscopic tissue samples. Early image analysis methods were often constrained by computational power and the complexity of biological samples. The advent of computers and digital imaging technologies challenged the exclusivity of human eye vision and brain computational skills, transforming the diagnostic process in these fields. The increasing digitization of pathological images has led to the application of more objective and efficient computer-aided analysis techniques. Significant advancements were brought about by the integration of digital pathology, machine learning, and advanced imaging technologies. The continuous progress in machine learning and the increasing availability of digital pathology data offer exciting opportunities for the future. Furthermore, artificial intelligence has revolutionized this field, enabling predictive models that assist in diagnostic decision making. The future of pathology and cytopathology is predicted to be marked by advancements in computer-aided image analysis. The future of image analysis is promising, and the increasing availability of digital pathology data will invariably lead to enhanced diagnostic accuracy and improved prognostic predictions that shape personalized treatment strategies, ultimately leading to better patient outcomes.

Relationship between the expressions of DLL3, ASC1, TTF-1 and Ki-67: First steps of precision medicine at SCLC.

This study presents an observational, cross-sectional analysis of 64 patients diagnosed with small cell lung cancer (SCLC) at a reference laboratory for thoracic pathology between 2022 and 2024. The primary objective was to evaluate the expression of Delta-like ligand 3 (DLL3) and other neuroendocrine markers such as Chromogranin, and Synaptophysin, utilizing both traditional immunohistochemistry and digital pathology tools. Patients were primarily older adults, with a median age of over 71, and most biopsies were obtained from lung parenchyma. Immunohistochemistry (IHC) was performed using specific monoclonal antibodies, with DLL3 showing variable expression across the samples. Notably, DLL3 was expressed in 72.3% of the cases, with varied intensities and a semi-quantitative H-score applied for more nuanced analysis. ASCL1 was expressed in 97% of cases, with the majority considered low-expressors. Only 11% had high expression. TTF-1, traditionally not a conventional marker for the diagnosis of SCLC, was positive in half of the cases, suggesting its potential as a biomarker. The study underscores the significant variability in the expression of neuroendocrine markers in SCLC, with implications for both diagnosis and potential therapeutic targeting. DLL3, particularly, shows promise as a therapeutic target due to its high expression rate in the cohort. The use of digital pathology software QuPath enhanced the accuracy and depth of analysis, allowing for detailed morphometric analysis and potentially informing more personalized treatment approaches. The findings emphasize the need for further research into the role of these markers in the management and treatment of SCLC, considering the poor prognosis and high mortality rate observed in the cohort.

Characterizing alcohol-related and metabolic dysfunction-associated steatotic liver disease cirrhosis via fibrotic pattern analysis

This study aimed to address the diagnostic challenges in distinguishing between alcohol-related liver disease (ALD) and metabolic dysfunction-associated steatotic liver disease (MASLD). We utilized whole-slide imaging technology to conduct a comprehensive digital analysis of liver specimens collected from patients undergoing transplantation. This study included 36 and 17 patients with ALD and MASLD cirrhosis, respectively, who underwent transplantation at our institution. Digital slides were analyzed for fibrosis patterns using FibroNest™. Patient background characteristics were comparable between ALD (n = 36) and MASLD (n = 17) groups, except for sex. The ALD group exhibited thicker collagen per strand, longer and more flexural fibrosis, and a more heterogeneous distribution than the MASLD group. In patients with ALD and concomitant metabolic dysfunction, fiber distribution became relatively uniform, resembling MASLD. Application of the phenotypic fibrosis composite score achieved 100% sensitivity and specificity for ALD/MASLD diagnosis. Digital pathological analysis of the fibrosis patterns showed morphological differences between ALD and MASLD. This approach holds promise for histological differentiation, providing valuable insights beyond the current definitions based solely on alcohol intake. This study emphasizes the potential of digital pathology in refining the diagnostic criteria for hepatic disorders.

Self-Supervised Learning for Feature Extraction from Glomerular Images and Disease Classification with Minimal Annotations.

Deep learning has great potential in digital kidney pathology. However, its effectiveness depends heavily on the availability of extensively labeled datasets, which are often limited due to the specialized knowledge and time required for their creation. This limitation hinders the widespread application of deep learning for the analysis of kidney biopsy images. We applied self-distillation with no labels (DINO), a self-supervised learning method, to a dataset of 10,423 glomerular images obtained from 384 PAS-stained kidney biopsy slides. Glomerular features extracted from the DINO-pretrained backbone were visualized using principal component analysis (PCA). We then performed classification tasks by adding either k-nearest neighbor (kNN) classifiers or linear head layers to the DINO-pretrained or ImageNet-pretrained backbones. These models were trained on our labeled classification dataset. Performance was evaluated using metrics such as the area under the receiver operating characteristic curve (ROC-AUC). The classification tasks encompassed four disease categories (minimal change disease, mesangial proliferative glomerulonephritis, membranous nephropathy, and diabetic nephropathy) as well as clinical parameters such as hypertension, proteinuria, and hematuria. PCA visualization revealed distinct principal components corresponding to different glomerular structures, demonstrating the capability of the DINO-pretrained backbone to capture morphological features. In disease classification, the DINO-pretrained transferred model (ROC-AUC = 0.93) outperformed the ImageNet-pretrained fine-tuned model (ROC-AUC = 0.89). When the labeled data were limited, the ImageNet-pretrained fine-tuned model's ROC-AUC dropped to 0.76 (95% confidence interval [CI], 0.72-0.80), whereas the DINO-pretrained transferred model maintained superior performance (ROC-AUC 0.88, 95% CI 0.86-0.90). The DINO-pretrained transferred model also exhibited higher AUCs for the classification of several clinical parameters. External validation using two independent datasets confirmed DINO pre-training's superiority, particularly when labeled data were limited. The application of DINO to unlabeled PAS-stained glomerular images facilitated the extraction of histological features that can be effectively utilized for disease classification.

A New Generation of Pathologists: Addressing Modern Curriculum and Educational Scholarship for Pathology Educators and Trainees After the End of the COVID-19 Pandemic.

The COVID-19 pandemic irreversibly altered the pathology education landscape. It exacerbated workforce shortages, restricted in-person activities, and highlighted critical means in curricula evaluation to limit the expansion of medical knowledge gaps in postpandemic society. Training enacted swift changes toward online learning (e-learning) practices to minimize potential deficiencies in pathology education. Today, a breadth of widely available online pathology curricular tools, including e-learning and digital pathology, are increasingly being used by medical students, trainees, and pathologists worldwide. To critically address the continued role of e-learning and digital pathology in postpandemic pathology education and scholarship, as a current paucity of literature exists and lingering workflow effects of this pandemic affecting many anatomic and clinical pathology departments globally persist. A qualitative review of relevant literature is synthesized to create a timely, narrative discussion to bridge this literature gap. Peer-reviewed sources and other original or primary documents will be assessed. Because of the subjective nature of curricular development and defining what constitutes scholarship, no widely established consensus is present, though it has been touched on in previous literature. It may be years until we better understand how e-learning and digital pathology shape curricular practices, scholarship production, and patient-care delivery, though recent studies support sustained blended curricula beyond the COVID-19 pandemic. The education landscape continues to become increasingly digitalized, and infrastructures may soon be able to support complete digital pathology practice as the education norm. Future and theoretical insight for pathology and laboratory departments globally are provided.

A deep learning approach to case prioritisation of colorectal biopsies.

To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis). Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)-stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision-making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow. Validation of the model was conducted on two cohorts: the first, on 100 single-slide cases, achieved micro-average model specificity of 0.984, micro-average model sensitivity of 0.949 and micro-average model F1 score of 0.949 across all classes. A secondary multi-institutional validation cohort, of 101 single-slide cases, achieved micro-average model specificity of 0.978, micro-average model sensitivity of 0.931 and micro-average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities. We have developed a high-performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non-neoplastic biopsies.

Validation of large language models for detecting pathologic complete response in breast cancer using population-based pathology reports

AimsThe primary goal of this study is to evaluate the capabilities of Large Language Models (LLMs) in understanding and processing complex medical documentation. We chose to focus on the identification of pathologic complete response (pCR) in narrative pathology reports. This approach aims to contribute to the advancement of comprehensive reporting, health research, and public health surveillance, thereby enhancing patient care and breast cancer management strategies.MethodsThe study utilized two analytical pipelines, developed with open-source LLMs within the healthcare system’s computing environment. First, we extracted embeddings from pathology reports using 15 different transformer-based models and then employed logistic regression on these embeddings to classify the presence or absence of pCR. Secondly, we fine-tuned the Generative Pre-trained Transformer-2 (GPT-2) model by attaching a simple feed-forward neural network (FFNN) layer to improve the detection performance of pCR from pathology reports.ResultsIn a cohort of 351 female breast cancer patients who underwent neoadjuvant chemotherapy (NAC) and subsequent surgery between 2010 and 2017 in Calgary, the optimized method displayed a sensitivity of 95.3% (95%CI: 84.0–100.0%), a positive predictive value of 90.9% (95%CI: 76.5–100.0%), and an F1 score of 93.0% (95%CI: 83.7–100.0%). The results, achieved through diverse LLM integration, surpassed traditional machine learning models, underscoring the potential of LLMs in clinical pathology information extraction.ConclusionsThe study successfully demonstrates the efficacy of LLMs in interpreting and processing digital pathology data, particularly for determining pCR in breast cancer patients post-NAC. The superior performance of LLM-based pipelines over traditional models highlights their significant potential in extracting and analyzing key clinical data from narrative reports. While promising, these findings highlight the need for future external validation to confirm the reliability and broader applicability of these methods.

Evaluation of a Task-Specific Self-Supervised Learning Framework in Digital Pathology Relative to Transfer Learning Approaches and Existing Foundation Models

An integral stage in typical digital pathology workflows involves deriving specific features from tiles extracted from a tessellated whole-slide image. Notably, various computer vision neural network architectures, particularly the ImageNet pretrained, have been extensively used in this domain. This study critically analyzes multiple strategies for encoding tiles to understand the extent of transfer learning and identify the most effective approach. The study categorizes neural network performance into 3 weight initialization methods: random, ImageNet-based, and self-supervised learning. Additionally, we propose a framework based on task-specific self-supervised learning, which introduces a shallow feature extraction method, employing a spatial-channel attention block to glean distinctive features optimized for histopathology intricacies. Across 2 different downstream classification tasks (patch classification and weakly supervised whole-slide image classification) with diverse classification data sets, including colorectal cancer histology, Patch Camelyon, prostate cancer detection, The Cancer Genome Atlas, and CIFAR-10, our task-specific self-supervised encoding approach consistently outperforms other convolutional neural network–based encoders. The better performances highlight the potential of task-specific attention-based self-supervised training in tailoring feature extraction for histopathology, indicating a shift from using pretrained models originating outside the histopathology domain. Our study supports the idea that task-specific self-supervised learning allows domain-specific feature extraction, encouraging a more focused analysis.

Reproducibility and explainability in digital pathology: The need to make black-box artificial intelligence systems more transparent

Artificial intelligence (AI), and more specifically Machine Learning (ML) and Deep learning (DL), has permeated the digital pathology field in recent years, with many algorithms successfully applied as new advanced tools to analyze pathological tissues. The introduction of high-resolution scanners in histopathology services has represented a real revolution for pathologists, allowing the analysis of digital whole-slide images (WSI) on a screen without a microscope at hand. However, it means a transition from microscope to algorithms in the absence of specific training for most pathologists involved in clinical practice. The WSI approach represents a major transformation, even from a computational point of view. The multiple ML and DL tools specifically developed for WSI analysis may enhance the diagnostic process in many fields of human pathology. AI-driven models allow the achievement of more consistent results, providing valid support for detecting, from H&amp;E-stained sections, multiple biomarkers, including microsatellite instability, that are missed by expert pathologists.

Corrigendum to “Quantitative scoring of progression in transplant glomerulopathy using digital pathology may be superior to Banff cg scoring.” Kidney International 2023;103:365–377

Corrigendum to “Quantitative scoring of progression in transplant glomerulopathy using digital pathology may be superior to Banff cg scoring.” Kidney International 2023;103:365–377

Nuclei Detection and Segmentation of Histopathological Images Using a Feature Pyramidal Network Variant of a Mask R-CNN.

Cell nuclei interpretation is crucial in pathological diagnostics, especially in tumor specimens. A critical step in computational pathology is to detect and analyze individual nuclear properties using segmentation algorithms. Conventionally, a semantic segmentation network is used, where individual nuclear properties are derived after post-processing a segmentation mask. In this study, we focus on showing that an object-detection-based instance segmentation network, the Mask R-CNN, after integrating it with a Feature Pyramidal Network (FPN), gives mature and reliable results for nuclei detection without the need for additional post-processing. The results were analyzed using the Kumar dataset, a public dataset with over 20,000 nuclei annotations from various organs. The dice score of the baseline Mask R-CNN improved from 76% to 83% after integration with an FPN. This was comparable with the 82.6% dice score achieved by modern semantic-segmentation-based networks. Thus, evidence is provided that an end-to-end trainable detection-based instance segmentation algorithm with minimal post-processing steps can reliably be used for the detection and analysis of individual nuclear properties. This represents a relevant task for research and diagnosis in digital pathology, which can improve the automated analysis of histopathological images.