Validation of a whole-slide image-based teleconsultation network

Digital Examination of LYmph node CYtopathology Using the Sydney system (DELYCYUS): An international, multi-institutional study

BACKGROUND

After a series of standardized reporting systems in cytopathology, the Sydney system was recently introduced to address the need for reproducibility and standardization in lymph node cytopathology. Since then, the risk of malignancy for the categories of the Sydney system has been explored by several studies, but no studies have yet examined the interobserver reproducibility of the Sydney system.

METHODS

The authors assessed interobserver reproducibility of the Sydney system on 85 lymph node fine-needle aspiration cytology cases reviewed by 15 cytopathologists from 12 institutions in eight different countries, resulting in 1275 diagnoses. In total, 186 slides stained with Diff-Quik, Papanicolaou, and immunocytochemistry were scanned. A subset of the cases included clinical data and results from ultrasound examinations, flow cytometry immunophenotyping, and fluorescence in situ hybridization analysis. The study participants assessed the cases digitally using whole-slide images.

RESULTS

Overall, the authors observed an almost perfect agreement of cytopathologists with the ground truth (median weighted Cohen κ = 0.887; interquartile range, κ = 0.210) and moderate overall interobserver concordance (Fleiss κ = 0.476). There was substantial agreement for the inadequate and malignant categories (κ = 0.794 and κ = 0.729, respectively), moderate agreement for the benign category (κ = 0.490), and very slight agreement for the suspicious (κ = 0.104) and atypical (κ = 0.075) categories.

CONCLUSIONS

The Sydney system for reporting lymph node cytopathology shows adequate interobserver concordance. Digital microscopy is an adequate means to assess lymph node cytopathology specimens.

Clinical Validation of Artificial Intelligence-Augmented Pathology Diagnosis Demonstrates Significant Gains in Diagnostic Accuracy in Prostate Cancer Detection

CONTEXT.—

Prostate cancer diagnosis rests on accurate assessment of tissue by a pathologist. The application of artificial intelligence (AI) to digitized whole slide images (WSIs) can aid pathologists in cancer diagnosis, but robust, diverse evidence in a simulated clinical setting is lacking.

OBJECTIVE.—

To compare the diagnostic accuracy of pathologists reading WSIs of prostatic biopsy specimens with and without AI assistance.

DESIGN.—

Eighteen pathologists, 2 of whom were genitourinary subspecialists, evaluated 610 prostate needle core biopsy WSIs prepared at 218 institutions, with the option for deferral. Two evaluations were performed sequentially for each WSI: initially without assistance, and immediately thereafter aided by Paige Prostate (PaPr), a deep learning-based system that provides a WSI-level binary classification of suspicious for cancer or benign and pinpoints the location that has the greatest probability of harboring cancer on suspicious WSIs. Pathologists' changes in sensitivity and specificity between the assisted and unassisted modalities were assessed, together with the impact of PaPr output on the assisted reads.

RESULTS.—

Using PaPr, pathologists improved their sensitivity and specificity across all histologic grades and tumor sizes. Accuracy gains on both benign and cancerous WSIs could be attributed to PaPr, which correctly classified 100% of the WSIs showing corrected diagnoses in the PaPr-assisted phase.

CONCLUSIONS.—

This study demonstrates the effectiveness and safety of an AI tool for pathologists in simulated diagnostic practice, bridging the gap between computational pathology research and its clinical application, and resulted in the first US Food and Drug Administration authorization of an AI system in pathology.

Stain normalization in digital pathology: Clinical multi-center evaluation of image quality

In digital pathology, the final appearance of digitized images is affected by several factors, resulting in stain color and intensity variation. Stain normalization is an innovative solution to overcome stain variability. However, the validation of color normalization tools has been assessed only from a quantitative perspective, through the computation of similarity metrics between the original and normalized images. To the best of our knowledge, no works investigate the impact of normalization on the pathologist’s evaluation.

The objective of this paper is to propose a multi-tissue (i.e., breast, colon, liver, lung, and prostate) and multi-center qualitative analysis of a stain normalization tool with the involvement of pathologists with different years of experience. Two qualitative studies were carried out for this purpose: (i) a first study focused on the analysis of the perceived image quality and absence of significant image artifacts after the normalization process; (ii) a second study focused on the clinical score of the normalized image with respect to the original one.

The results of the first study prove the high quality of the normalized image with a low impact artifact generation, while the second study demonstrates the superiority of the normalized image with respect to the original one in clinical practice.

The normalization process can help both to reduce variability due to tissue staining procedures and facilitate the pathologist in the histological examination. The experimental results obtained in this work are encouraging and can justify the use of a stain normalization tool in clinical routine.

Virtual Microscopy in Undergraduate Pathology Education: An early transformative experience in clinical reasoning

Objectives

Whole-slide imaging and virtual microscopy (VM) have revolutionised teaching, diagnosis and research in histopathology. This study aimed to establish the feasibility of achieving early integration of clinical reasoning with undergraduate pathology teaching on a VM platform and to determine its student-centricity through student feedback.

Methods

This study was conducted at the Mohammed Bin Rashid University of Medicine and Health Sciences, Dubai, United Arab Emirates, between August and December 2017. A total of 38 VM-centred clinical cases were introduced to 49 students in an integrated undergraduate medical curriculum. The cases were aligned to curricular objectives, reinforced the pathologic basis of disease with critical thinking and were delivered across 15 interactive small-group sessions. A simulated cross-disciplinary integration and judicious choice of pertinent diagnostic investigations were linked to principles of management. Feedback was obtained through a mixed-methods approach.

Results

User-friendliness, gradual learning curve of VM and annotation-capacity were scored as 4–5 (on a Likert scale of 1–5) by 91.84%, 87.76% and 83.67% of the participants, respectively. Most students agreed that the content matched the stage of learning (81.63%), theme of the week (91.84%) and development of a strong clinical foundation (77.55%). Integration (85.71%) and clinico-pathological correlation (83.67%) were the strengths of this educational effort. High student attendance (~100%) and improved assessment scores on critical thinking (80%) were observed. Software lacunae included frequent logouts and lack of note-taking tools. Easy access was a significant student-centric advantage.

Conclusion

A VM-centred approach with a clinico-pathological correlation has been successfully introduced to inculcate integrated learning. Using the pathologic basis of disease as a fulcrum and critical reasoning as an anchor, a digitally-enabled generation of medical students have embraced this educational tool for tutor-guided, student-centred learning.

Recent technical advances in whole slide imaging instrumentation

Microscopic observation of biological specimen smears is the mainstay of diagnostic pathology, as defined by the Digital Pathology Association. Though automated systems for this are commercially available, their bulky size and high cost renders them unusable for remote areas. The research community is investing much effort towards building equivalent but portable, low-cost systems. An overview of such research is presented here, including a comparative analysis of recent reports. This paper also reviews recently reported systems for automated staining and smear formation, including microfluidic devices; and optical and computational automated microscopy systems including smartphone-based devices. Image pre-processing and analysis methods for automated diagnosis are also briefly discussed. It concludes with a set of foreseeable research directions that could lead to affordable, integrated and accurate whole slide imaging systems.

Diagnostic digital pathology implementation: Learning from the digital health experience

Digital Pathology (also referred to as Telepathology and Whole Slide Imaging) is the process of producing high resolution digital images from tissue sections on glass slides. These glass slides are normally examined under a microscope by a pathologist as part of the diagnostic process. The emergence of digital pathology now means that digital images are stored on secure servers and can be viewed on computer monitors; enabling pathologists to work remotely and to collaborate with other colleagues when second opinions are needed. The implementation of digital pathology into clinical practice has many potential benefits. Although this has been long recognised, its adoption as a diagnostic tool remains low and pathologists’ projections about its future deployment are cautious. Notable early digital pathology adopters have led the way. The challenge now is to scale-up digital pathology beyond the relatively few large networks and centres of excellence. Many other areas of healthcare have accumulated experience about optimising approaches to digital health/healthcare technology deployment and sustainability. This has been done in a multi-disciplinary context and has applied theoretical/conceptual frameworks. Thus far there has been little use of similar frameworks in the planning of digital pathology deployment in clinical practice. In this essay, I will explore the scope of digital pathology implementation approaches that have been deployed in clinical practice and examine what can be learned from the wider healthcare experience of adopting, scaling-up and sustaining innovative healthcare solutions.

Digital pathology and computational image analysis in nephropathology

The emergence of digital pathology - an image-based environment for the acquisition, management and interpretation of pathology information supported by computational techniques for data extraction and analysis - is changing the pathology ecosystem. In particular, by virtue of our new-found ability to generate and curate digital libraries, the field of machine vision can now be effectively applied to histopathological subject matter by individuals who do not have deep expertise in machine vision techniques. Although these novel approaches have already advanced the detection, classification, and prognostication of diseases in the fields of radiology and oncology, renal pathology is just entering the digital era, with the establishment of consortia and digital pathology repositories for the collection, analysis and integration of pathology data with other domains. The development of machine-learning approaches for the extraction of information from image data, allows for tissue interrogation in a way that was not previously possible. The application of these novel tools are placing pathology centre stage in the process of defining new, integrated, biologically and clinically homogeneous disease categories, to identify patients at risk of progression, and shifting current paradigms for the treatment and prevention of kidney diseases.

The Role of Telehealth During the COVID-19 Pandemic Across the Interdisciplinary Cancer Team: Implications for Practice

Objective

This literature review aims to explore the role of telehealth during the COVID-19 pandemic across the interdisciplinary cancer care team.

Data Sources

Electronic databases including CINAHL, MEDLINE, PsychINFO, Scopus, and gray literature were searched using Google Scholar up until September 2020.

Conclusion

Although the safe and effective delivery of cancer care via telehealth requires education and training for health care professionals and patients, telehealth has provided a timely solution to the barriers caused by the COVID-19 pandemic on the delivery of interdisciplinary cancer services. Globally, evidence has shown that telehealth in cancer care can leverage an innovative response during the COVID-19 pandemic but may provide a long-lasting solution to enable patients to be treated appropriately in their home environment. Telehealth reduces the travel burden on patients for consultation, affords a timely solution to discuss distressing side effects, initiate interventions, and enable possible treatment additions and/or changes.

Implications for Nursing Practice

Global public health disasters pose significant and unique challenges to the provision of necessary services for people affected by cancer. Oncology nurses can provide a central contribution in the delivery of telehealth through transformational leadership across all domains and settings in cancer care. Oncology nurses provide the “hub of cancer care” safely embedded in the interdisciplinary team. Telehealth provides a solution to the current global health crisis but could also benefit the future provision of services and broad reach clinical trials.

A narrative review of digital pathology and artificial intelligence: focusing on lung cancer

The emergence of whole slide imaging technology allows for pathology diagnosis on a computer screen. The applications of digital pathology are expanding, from supporting remote institutes suffering from a shortage of pathologists to routine use in daily diagnosis including that of lung cancer. Through practice and research large archival databases of digital pathology images have been developed that will facilitate the development of artificial intelligence (AI) methods for image analysis. Currently, several AI applications have been reported in the field of lung cancer; these include the segmentation of carcinoma foci, detection of lymph node metastasis, counting of tumor cells, and prediction of gene mutations. Although the integration of AI algorithms into clinical practice remains a significant challenge, we have implemented tumor cell count for genetic analysis, a helpful application for routine use. Our experience suggests that pathologists often overestimate the contents of tumor cells, and the use of AI-based analysis increases the accuracy and makes the tasks less tedious. However, there are several difficulties encountered in the practical use of AI in clinical diagnosis. These include the lack of sufficient annotated data for the development and validation of AI systems, the explainability of black box AI models, such as those based on deep learning that offer the most promising performance, and the difficulty in defining the ground truth data for training and validation owing to inherent ambiguity in most applications. All of these together present significant challenges in the development and clinical translation of AI methods in the practice of pathology. Additional research on these problems will help in resolving the barriers to the clinical use of AI. Helping pathologists in developing knowledge of the working and limitations of AI will benefit the use of AI in both diagnostics and research.

Pathology Image Exchange: The Dutch Digital Pathology Platform for Exchange of Whole-Slide Images for Efficient Teleconsultation, Telerevision, and Virtual Expert Panels

Among the many uses of digital pathology, remote consultation, remote revision, and virtual slide panels may be the most important ones. This requires basic slide scanner infrastructure in participating laboratories to produce whole-slide images. More importantly, a software platform is needed for exchange of these images and functionality to support the processes around discussing and reporting on these images without breaching patient privacy. This poses high demands on the setup of such a platform, given the inherent complexity of the handling of digital pathology images. In this article, we describe the setup and validation of the Pathology Image Exchange project, which aimed to create a vendor-independent platform for exchange of whole-slide images between Dutch pathology laboratories to facilitate efficient teleconsultation, telerevision, and virtual slide panels. Pathology Image Exchange was released in April 2018 after technical validation, and a first successful validation in real life has been performed for hematopathology cases.

Essential role of laboratory physicians in transformation of laboratory practice and management to a value-based patient-centric model

The laboratory is a vital part of the continuum of patient care. In fact, there are few programs in the healthcare system that do not rely on ready access and availability of complex diagnostic laboratory services. The existing transactional model of laboratory "medical practice" will not be able to meet the needs of the healthcare system as it rapidly shifts toward value-based care and precision medicine, which demands that practice be based on total system indicators, clinical effectiveness, and patient outcomes. Laboratory "value" will no longer be focused primarily on internal testing quality and efficiencies but rather on the relative cost of diagnostic testing compared to direct improvement in clinical and system outcomes. The medical laboratory as a "business" focused on operational efficiency and cost-controls must transform to become an essential clinical service that is a tightly integrated equal partner in direct patient care. We would argue that this paradigm shift would not be necessary if laboratory services had remained a "patient-centric" medical practice throughout the last few decades. This review is focused on the essential role of laboratory physicians in transforming laboratory practice and management to a value-based patient-centric model. Value-based practice is necessary not only to meet the challenges of the new precision medicine world order but also to bring about sustainable healthcare service delivery.

Current opinion, status and future development of digital pathology in Switzerland

AIMS

The transition from analogue to digital pathology (DP) is underway in Switzerland. To assess relevant experiences of pathologists with DP and gauge their outlook towards a digital future, a national survey was conducted by the Swiss Digital Pathology Consortium. Similar surveys were conducted in other countries, enabling a meta-analysis of DP experiences.

METHODS

Pathologists and residents were asked to complete a survey containing 12 questions. Results were compared with similar studies conducted in the United Kingdom, Sweden, Canada, and India.

RESULTS

The estimated response rate among practicing pathologists and trainees nationwide was 39.5%. Of these, 89% have experience with digital slides, mainly for education (61%) and primary diagnostics (20%). Further, 32% have worked with an image analysis programme and 26% use computer-based algorithms weekly. Interestingly, 66% would feel comfortable making a primary diagnosis digitally, while 10% would not. Most respondents believe more standards and regulations are necessary for the clinical employment of DP. Noted advantages include ease of access to slides and the resulting connectivity benefits, namely collaboration with experts across disciplines, off-site work, training purposes, and computational image analysis. Perceived disadvantages include implementation costs and issues associated with IT infrastructure and file formats.

CONCLUSION

The survey results suggest that experiences and perspectives of Swiss pathologists concerning DP is comparable to that of the other reporting countries undergoing transitions to digital workflows. Although more standards and regulations are needed to ensure the safe usage of these technologies, pathologists in Switzerland appear welcoming of this new digital era.