-
The Journal of Pathology. Clinical... Jul 2023The current move towards digital pathology enables pathologists to use artificial intelligence (AI)-based computer programmes for the advanced analysis of whole slide... (Review)
Review
The current move towards digital pathology enables pathologists to use artificial intelligence (AI)-based computer programmes for the advanced analysis of whole slide images. However, currently, the best-performing AI algorithms for image analysis are deemed black boxes since it remains - even to their developers - often unclear why the algorithm delivered a particular result. Especially in medicine, a better understanding of algorithmic decisions is essential to avoid mistakes and adverse effects on patients. This review article aims to provide medical experts with insights on the issue of explainability in digital pathology. A short introduction to the relevant underlying core concepts of machine learning shall nurture the reader's understanding of why explainability is a specific issue in this field. Addressing this issue of explainability, the rapidly evolving research field of explainable AI (XAI) has developed many techniques and methods to make black-box machine-learning systems more transparent. These XAI methods are a first step towards making black-box AI systems understandable by humans. However, we argue that an explanation interface must complement these explainable models to make their results useful to human stakeholders and achieve a high level of causability, i.e. a high level of causal understanding by the user. This is especially relevant in the medical field since explainability and causability play a crucial role also for compliance with regulatory requirements. We conclude by promoting the need for novel user interfaces for AI applications in pathology, which enable contextual understanding and allow the medical expert to ask interactive 'what-if'-questions. In pathology, such user interfaces will not only be important to achieve a high level of causability. They will also be crucial for keeping the human-in-the-loop and bringing medical experts' experience and conceptual knowledge to AI processes.
Topics: Humans; Artificial Intelligence; Pathologists; Algorithms; Image Processing, Computer-Assisted
PubMed: 37045794
DOI: 10.1002/cjp2.322 -
The Journal of Pathology Aug 2023Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence... (Review)
Review
Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists' perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Topics: Humans; Artificial Intelligence; Algorithms; Prognosis; Pathologists; Neoplasms
PubMed: 37580849
DOI: 10.1002/path.6163 -
Cancer Metastasis Reviews Dec 2023Carcinoma of unknown primary (CUP) is a heterogeneous group of metastatic cancers in which the site of origin is not identifiable. These carcinomas have a poor outcome... (Review)
Review
Carcinoma of unknown primary (CUP) is a heterogeneous group of metastatic cancers in which the site of origin is not identifiable. These carcinomas have a poor outcome due to their late presentation with metastatic disease, difficulty in identifying the origin and delay in treatment. The aim of the pathologist is to broadly classify and subtype the cancer and, where possible, to confirm the likely primary site as this information best predicts patient outcome and guides treatment. In this review, we provide histopathologists with diagnostic practice points which contribute to identifying the primary origin in such cases. We present the current clinical evaluation and management from the point of view of the oncologist. We discuss the role of the pathologist in the diagnostic pathway including the control of pre-analytical conditions, assessment of sample adequacy, diagnosis of cancer including diagnostic pitfalls, and evaluation of prognostic and predictive markers. An integrated diagnostic report is ideal in cases of CUP, with results discussed at a forum such as a molecular tumour board and matched with targeted treatment. This highly specialized evolving area ultimately leads to personalized oncology and potentially improved outcomes for patients.
Topics: Humans; Neoplasms, Unknown Primary; Pathologists; Carcinoma; Prognosis
PubMed: 37394540
DOI: 10.1007/s10555-023-10101-6 -
Critical Reviews in Clinical Laboratory... Jun 2024No standard tool to measure pathologist workload currently exists. An accurate measure of workload is needed for determining the number of pathologists to be hired,... (Review)
Review
No standard tool to measure pathologist workload currently exists. An accurate measure of workload is needed for determining the number of pathologists to be hired, distributing the workload fairly among pathologists, and assessing the overall cost of pathology consults. Initially, simple tools such as counting cases or slides were used to give an estimate of the workload. More recently, multiple workload models, including relative value units (RVUs), the Royal College of Pathologists (RCP) point system, Level 4 Equivalent (L4E), Work2Quality (W2Q), and the University of Washington, Seattle (UW) slide count method, have been developed. There is no "ideal" model that is universally accepted. The main differences among the models come from the weights assigned to different specimen types, differential calculations for organs, and the capture of additional tasks needed for safe and timely patient care. Academic centers tend to see more complex cases that require extensive sampling and additional testing, while community-based and private laboratories deal more with biopsies. Additionally, some systems do not account for teaching, participation in multidisciplinary rounds, quality assurance activities, and medical oversight. A successful workload model needs to be continually updated to reflect the current state of practice.Awareness about physician burnout has gained attention in recent years and has been added to the World Health Organization's International Classification of Diseases (World Health Organization, WHO) as an occupational phenomenon. However, the extent to which this affects pathologists is not well understood. According to the WHO, burnout syndrome is diagnosed by the presence of three components: emotional exhaustion, depersonalization from one's work (cynicism related to one's job), and a low sense of personal achievement or accomplishment. Three drivers of burnout are the demand for productivity, lack of recognition, and electronic health records. Prominent consequences of physician burnout are economic and personal costs to the public and to the providers.Wellness is physical and mental well-being that allows individuals to manage stress effectively and to thrive in both their professional and personal lives. To achieve wellness, it is necessary to understand the root causes of burnout, including over-work and working under stressful conditions. Wellness is more than the absence of stress or burnout, and the responsibility of wellness should be shared by pathologists themselves, their healthcare organization, and governing bodies. Each pathologist needs to take their own path to achieve wellness.
Topics: Humans; Workload; Burnout, Professional; Pathologists
PubMed: 38809116
DOI: 10.1080/10408363.2023.2285284 -
Pathology Aug 2023Fusions involving the Neurotrophic tropomyosin receptor kinase (NTRK) gene family (NTRK1, NTRK2 and NTRK3) are targetable oncogenic alterations that are found in a... (Review)
Review
Fusions involving the Neurotrophic tropomyosin receptor kinase (NTRK) gene family (NTRK1, NTRK2 and NTRK3) are targetable oncogenic alterations that are found in a diverse range of tumours. There is an increasing demand to identify tumours which harbour these fusions to enable treatment with selective tyrosine kinase inhibitors such as larotrectinib and entrectinib. NTRK fusions occur in a wide range of tumours including rare tumours such as infantile fibrosarcoma and secretory carcinomas of the salivary gland and breast, as well as at low frequencies in more common tumours including melanoma, colorectal, thyroid and lung carcinomas. Identifying NTRK fusions is a challenging task given the different genetic mechanisms underlying NTRK fusions, their varying frequency across different tumour types, complicated by other factors such as tissue availability, optimal detection methods, accessibility and costs of testing methods. Pathologists play a key role in navigating through these complexities by determining optimal approaches to NTRK testing which has important therapeutic and prognostic implications. This review provides an overview of tumours harbouring NTRK fusions, the importance of identifying these fusions, available testing methods including advantages and limitations, and generalised and tumour-specific approaches to testing.
Topics: Humans; Female; Receptor, trkA; Pathologists; Oncogene Proteins, Fusion; Neoplasms; Breast Neoplasms; Carcinoma; Gene Fusion
PubMed: 37330338
DOI: 10.1016/j.pathol.2023.05.002 -
Radiographics : a Review Publication of... Nov 2023Fibroepithelial lesions (FELs) are among the most common breast masses encountered by breast radiologists and pathologists. They encompass a spectrum of benign and...
Fibroepithelial lesions (FELs) are among the most common breast masses encountered by breast radiologists and pathologists. They encompass a spectrum of benign and malignant lesions, including fibroadenomas (FAs) and phyllodes tumors (PTs). FAs are typically seen in young premenopausal women, with a peak incidence at 20-30 years of age, and have imaging features of oval circumscribed hypoechoic masses. Although some FA variants are especially sensitive to hormonal influences and can exhibit rapid growth (eg, juvenile FA and lactational adenomas), most simple FAs are slow growing and involute after menopause. PTs can be benign, borderline, or malignant and are more common in older women aged 40-50 years. PTs usually manifest as enlarging palpable masses and are associated with a larger size and sometimes with an irregular shape at imaging compared with FAs. Although FA and FA variants are typically managed conservatively unless large and symptomatic, PTs are surgically excised because of the risk of undersampling at percutaneous biopsy and the malignant potential of borderline and malignant PTs. As a result of the overlap in imaging and histologic appearances, FELs can present a diagnostic challenge for the radiologist and pathologist. Radiologists can facilitate accurate diagnosis by supplying adequate tissue sampling and including critical information for the pathologist at the time of biopsy. Understanding the spectrum of FELs can facilitate and guide appropriate radiologic-pathologic correlation and timely diagnosis and management of PTs. Published under a CC BY 4.0 license. Quiz questions for this article are available through the Online Learning Center.
Topics: Female; Humans; Aged; Breast; Fibroadenoma; Phyllodes Tumor; Biopsy; Breast Neoplasms
PubMed: 37856317
DOI: 10.1148/rg.230051 -
Pathology International Sep 2023Morphological and functional heterogeneity are found in tumors, with the latter reflecting the different levels of resistance against antitumor therapies. In a... (Review)
Review
Morphological and functional heterogeneity are found in tumors, with the latter reflecting the different levels of resistance against antitumor therapies. In a therapy-resistant subpopulation, the expression levels of differentiation markers decrease, and those of immature markers increase. In addition, this subpopulation expresses genes involved in drug metabolism, such as aldehyde dehydrogenase 1A1 (ALDH1A1). Because of their similarity to stem cells, cells in the latter therapy-resistant subpopulation are called cancer stem cells (CSCs). Like normal stem cells, CSCs were originally thought not to arise from non-CSCs, but this hierarchical model is too simple. It is now believed that CSCs are generated from non-CSCs. The plasticity of tumor phenotypes between CSCs and non-CSCs causes difficulty in completely curing tumors. In this review, focusing on ALDH1A1 as a marker for CSCs or immature tumor cells, the dynamics of ALDH1A1-expressing tumor cells and their regulatory mechanisms are described, and the plausible regulatory mechanisms of plasticity of ALDH1A1 expression phenotype are discussed. Genetic mutations are a significant factor for tumorigenesis, but non-mutational epigenetic reprogramming factors yielding tumor heterogeneity are also crucial in determining tumor characteristics. Factors influencing non-mutational epigenetic reprogramming in tumors are also discussed.
Topics: Humans; Pathologists; Neoplasms; Carcinogenesis; Cell Transformation, Neoplastic; Mutation
PubMed: 37638598
DOI: 10.1111/pin.13366 -
Gastric Cancer : Official Journal of... Sep 2023The Laurén classification is widely used for Gastric Cancer (GC) histology subtyping. However, this classification is prone to interobserver variability and its...
INTRODUCTION
The Laurén classification is widely used for Gastric Cancer (GC) histology subtyping. However, this classification is prone to interobserver variability and its prognostic value remains controversial. Deep Learning (DL)-based assessment of hematoxylin and eosin (H&E) stained slides is a potentially useful tool to provide an additional layer of clinically relevant information, but has not been systematically assessed in GC.
OBJECTIVE
We aimed to train, test and externally validate a deep learning-based classifier for GC histology subtyping using routine H&E stained tissue sections from gastric adenocarcinomas and to assess its potential prognostic utility.
METHODS
We trained a binary classifier on intestinal and diffuse type GC whole slide images for a subset of the TCGA cohort (N = 166) using attention-based multiple instance learning. The ground truth of 166 GC was obtained by two expert pathologists. We deployed the model on two external GC patient cohorts, one from Europe (N = 322) and one from Japan (N = 243). We assessed classification performance using the Area Under the Receiver Operating Characteristic Curve (AUROC) and prognostic value (overall, cancer specific and disease free survival) of the DL-based classifier with uni- and multivariate Cox proportional hazard models and Kaplan-Meier curves with log-rank test statistics.
RESULTS
Internal validation using the TCGA GC cohort using five-fold cross-validation achieved a mean AUROC of 0.93 ± 0.07. External validation showed that the DL-based classifier can better stratify GC patients' 5-year survival compared to pathologist-based Laurén classification for all survival endpoints, despite frequently divergent model-pathologist classifications. Univariate overall survival Hazard Ratios (HRs) of pathologist-based Laurén classification (diffuse type versus intestinal type) were 1.14 (95% Confidence Interval (CI) 0.66-1.44, p-value = 0.51) and 1.23 (95% CI 0.96-1.43, p-value = 0.09) in the Japanese and European cohorts, respectively. DL-based histology classification resulted in HR of 1.46 (95% CI 1.18-1.65, p-value < 0.005) and 1.41 (95% CI 1.20-1.57, p-value < 0.005), in the Japanese and European cohorts, respectively. In diffuse type GC (as defined by the pathologist), classifying patients using the DL diffuse and intestinal classifications provided a superior survival stratification, and demonstrated statistically significant survival stratification when combined with pathologist classification for both the Asian (overall survival log-rank test p-value < 0.005, HR 1.43 (95% CI 1.05-1.66, p-value = 0.03) and European cohorts (overall survival log-rank test p-value < 0.005, HR 1.56 (95% CI 1.16-1.76, p-value < 0.005)).
CONCLUSION
Our study shows that gastric adenocarcinoma subtyping using pathologist's Laurén classification as ground truth can be performed using current state of the art DL techniques. Patient survival stratification seems to be better by DL-based histology typing compared with expert pathologist histology typing. DL-based GC histology typing has potential as an aid in subtyping. Further investigations are warranted to fully understand the underlying biological mechanisms for the improved survival stratification despite apparent imperfect classification by the DL algorithm.
Topics: Humans; Stomach Neoplasms; Retrospective Studies; Deep Learning; Prognosis; Proportional Hazards Models; Adenocarcinoma
PubMed: 37269416
DOI: 10.1007/s10120-023-01398-x -
Pathologica Dec 2023This work explores the complex field of HER2 testing in the HER2-low breast cancer era, with a focus on methodological aspects. We aim to propose clear positions to... (Review)
Review
This work explores the complex field of HER2 testing in the HER2-low breast cancer era, with a focus on methodological aspects. We aim to propose clear positions to scientific societies, institutions, pathologists, and oncologists to guide and shape the appropriate diagnostic strategies for HER2-low breast cancer. The fundamental question at hand is whether the necessary tools to effectively translate our knowledge about HER2 into practical diagnostic schemes for the lower spectrum of expression are available. Our investigation is centered on the significance of distinguishing between an immunohistochemistry (IHC) score 0 and score 1+ in light of the clinical implications now apparent, as patients with HER2-low breast cancer become eligible for trastuzumab-deruxtecan treatment. Furthermore, we discuss the definition of HER2-low beyond its conventional boundaries and assess the reliability of established diagnostic procedures designed at a time when therapeutic perspectives were non-existent for these cases. In this regard, we examine potential complementary technologies, such as gene expression analysis and liquid biopsy. Ultimately, we consider the potential role of artificial intelligence (AI) in the field of digital pathology and its integration into HER2 testing, with a particular emphasis on its application in the context of HER2-low breast cancer.
Topics: Humans; Female; Artificial Intelligence; Breast Neoplasms; Reproducibility of Results; Pathologists
PubMed: 38180137
DOI: 10.32074/1591-951X-942