Histomorphological and molecular profiling: friends not foes! Morpho-molecular analysis reveals agreement between histological and molecular profiling

Analysing cerebrospinal fluid with explainable deep learning: From diagnostics to insights

AIM

Analysis of cerebrospinal fluid (CSF) is essential for diagnostic workup of patients with neurological diseases and includes differential cell typing. The current gold standard is based on microscopic examination by specialised technicians and neuropathologists, which is time-consuming, labour-intensive and subjective.

METHODS

We, therefore, developed an image analysis approach based on expert annotations of 123,181 digitised CSF objects from 78 patients corresponding to 15 clinically relevant categories and trained a multiclass convolutional neural network (CNN).

RESULTS

The CNN classified the 15 categories with high accuracy (mean AUC 97.3%). By using explainable artificial intelligence (XAI), we demonstrate that the CNN identified meaningful cellular substructures in CSF cells recapitulating human pattern recognition. Based on the evaluation of 511 cells selected from 12 different CSF samples, we validated the CNN by comparing it with seven board-certified neuropathologists blinded for clinical information. Inter-rater agreement between the CNN and the ground truth was non-inferior (Krippendorff's alpha 0.79) compared with the agreement of seven human raters and the ground truth (mean Krippendorff's alpha 0.72, range 0.56-0.81). The CNN assigned the correct diagnostic label (inflammatory, haemorrhagic or neoplastic) in 10 out of 11 clinical samples, compared with 7-11 out of 11 by human raters.

CONCLUSIONS

Our approach provides the basis to overcome current limitations in automated cell classification for routine diagnostics and demonstrates how a visual explanation framework can connect machine decision-making with cell properties and thus provide a novel versatile and quantitative method for investigating CSF manifestations of various neurological diseases.

[Artificial intelligence: a solution for the lack of pathologists?]

Given the rapid developments, there is no doubt that artificial intelligence (AI) will substantially impact pathological diagnostics. However, it remains an open question if AI will primarily be another diagnostic tool, such as immunohistochemistry, or if AI will also be able to replace human expertise. Most current studies on AI in histopathology deal with relatively simple diagnostic problems and are not yet capable of coping with the complexity of routine diagnostics. While some methods in molecular pathology would already be unthinkable without AI, it remains to be shown how AI will also be able to help with difficult histomorphological differential diagnoses in the future.

Lobular Breast Cancer: Histomorphology and Different Concepts of a Special Spectrum of Tumors

Simple Summary

Invasive lobular breast cancer (ILC) is a special type of breast cancer (BC) that was first described in 1941. The diagnosis of ILC is made by microscopy of tumor specimens, which reveals a distinct morphology. This review recapitulates the developments in the microscopic assessment of ILC from 1941 until today. We discuss different concepts of ILC, provide an overview on ILC variants, and highlight advances which have contributed to a better understanding of ILC as a special histologic spectrum of tumors.

Abstract

Invasive lobular breast cancer (ILC) is the most common special histological type of breast cancer (BC). This review recapitulates developments in the histomorphologic assessment of ILC from its beginnings with the seminal work of Foote and Stewart, which was published in 1941, until today. We discuss different concepts of ILC and their implications. These concepts include (i) BC arising from mammary lobules, (ii) BC growing in dissociated cells and single files, and (iii) BC defined as a morpho-molecular spectrum of tumors with distinct histological and molecular characteristics related to impaired cell adhesion. This review also provides a comprehensive overview of ILC variants, their histomorphology, and differential diagnosis. Furthermore, this review highlights recent advances which have contributed to a better understanding of the histomorphology of ILC, such as the role of the basal lamina component laminin, the molecular specificities of triple-negative ILC, and E-cadherin to P-cadherin expression switching as the molecular determinant of tubular elements in CDH1-deficient ILC. Last but not least, we provide a detailed account of the tumor microenvironment in ILC, including tumor infiltrating lymphocyte (TIL) levels, which are comparatively low in ILC compared to other BCs, but correlate with clinical outcome. The distinct histomorphology of ILC clearly reflects a special tumor biology. In the clinic, special treatment strategies have been established for triple-negative, HER2-positive, and ER-positive BC. Treatment specialization for patients diagnosed with ILC is just in its beginnings. Accordingly, ILC deserves greater attention as a special tumor entity in BC diagnostics, patient care, and cancer research.

Artificial Intelligence in Pathology

BACKGROUND

Increasing digitalization enables the use of artificial intelligence (AI) and machine learning in pathology. However, these technologies have only just begun to be implemented, and no randomized prospective trials have yet shown a benefit of AI-based diagnosis. In this review, we present current concepts, illustrate them with examples from representative publications, and discuss the possibilities and limitations of their use.

METHODS

This article is based on the results of a search in PubMed for articles published between January 1950 and January 2020 containing the searching terms "artificial intelligence," "deep learning," and "digital pathology," as well as the authors' own research findings.

RESULTS

Current research on AI in pathology focuses on supporting routine diagnosis and on prognostication, particularly for patients with cancer. Initial data indicate that pathologists can arrive at a diagnosis faster and more accurately with the aid of a computer. In a pilot study on the diagnosis of breast cancer, involving 70 patients, sensitivity for the detection of micrometastases rose from 83.3% (by a pathologist alone) to 91.2% (by a pathologist combined with a computer algorithm). The evidence likewise suggests that AI applied to histomorphological properties of cells during microscopy may enable the inference of certain genetic properties, such as mutations in key genes and deoxyribonucleic acid (DNA) methylation profiles.

CONCLUSION

Initial proof-of-concept studies for AI in pathology are now available. Randomized, prospective studies are now needed so that these early findings can be confirmed or falsified.

Artificial intelligence and pathology: From principles to practice and future applications in histomorphology and molecular profiling

The complexity of diagnostic (surgical) pathology has increased substantially over the last decades with respect to histomorphological and molecular profiling. Pathology has steadily expanded its role in tumor diagnostics and beyond from disease entity identification via prognosis estimation to precision therapy prediction. It is therefore not surprising that pathology is among the disciplines in medicine with high expectations in the application of artificial intelligence (AI) or machine learning approaches given their capabilities to analyze complex data in a quantitative and standardized manner to further enhance scope and precision of diagnostics. While an obvious application is the analysis of histological images, recent applications for the analysis of molecular profiling data from different sources and clinical data support the notion that AI will enhance both histopathology and molecular pathology in the future. At the same time, current literature should not be misunderstood in a way that pathologists will likely be replaced by AI applications in the foreseeable future. Although AI will transform pathology in the coming years, recent studies reporting AI algorithms to diagnose cancer or predict certain molecular properties deal with relatively simple diagnostic problems that fall short of the diagnostic complexity pathologists face in clinical routine. Here, we review the pertinent literature of AI methods and their applications to pathology, and put the current achievements and what can be expected in the future in the context of the requirements for research and routine diagnostics.

The Role of the Pathologist in the Next-Generation Era of Tumor Molecular Characterization

Current pathology practice is being shaped by the increasing complexity of modern medicine, in particular of precision oncology, and major technological advances. In the "next-generation technologies era", the pathologist has become the person responsible for the integration and interpretation of morphologic and molecular information and for the delivery of critical answers to diagnostic, prognostic and predictive queries, acquiring a prominent position in the molecular tumor boards.