Analysis of 3D pathology samples using weakly supervised AI.

Human tissue, which is inherently three-dimensional (3D), is traditionally examined through standard-of-care histopathology as limited two-dimensional (2D) cross-sections that can insufficiently represent the tissue due to sampling bias. To holistically characterize histomorphology, 3D imaging modalities have been developed, but clinical translation is hampered by complex manual evaluation and lack of computational platforms to distill clinical insights from large, high-resolution datasets. We present TriPath, a deep-learning platform for processing tissue volumes and efficiently predicting clinical outcomes based on 3D morphological features. Recurrence risk-stratification models were trained on prostate cancer specimens imaged with open-top light-sheet microscopy or microcomputed tomography. By comprehensively capturing 3D morphologies, 3D volume-based prognostication achieves superior performance to traditional 2D slice-based approaches, including clinical/histopathological baselines from six certified genitourinary pathologists. Incorporating greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, further emphasizing the value of capturing larger extents of heterogeneous morphology.

Spatially resolved clonal copy number alterations in benign and malignant tissue.

Defining the transition from benign to malignant tissue is fundamental to improving early diagnosis of cancer1. Here we use a systematic approach to study spatial genome integrity in situ and describe previously unidentified clonal relationships. We used spatially resolved transcriptomics2 to infer spatial copy number variations in >120,000 regions across multiple organs, in benign and malignant tissues. We demonstrate that genome-wide copy number variation reveals distinct clonal patterns within tumours and in nearby benign tissue using an organ-wide approach focused on the prostate. Our results suggest a model for how genomic instability arises in histologically benign tissue that may represent early events in cancer evolution. We highlight the power of capturing the molecular and spatial continuums in a tissue context and challenge the rationale for treatment paradigms, including focal therapy.

A New Hierarchy of Research Evidence for Tumor Pathology: A Delphi Study to Define Levels of Evidence in Tumor Pathology.

The hierarchy of evidence is a fundamental concept in evidence-based medicine, but existing models can be challenging to apply in laboratory-based health care disciplines, such as pathology, where the types of evidence and contexts are significantly different from interventional medicine. This project aimed to define a comprehensive and complementary framework of new levels of evidence for evaluating research in tumor pathology-introducing a novel Hierarchy of Research Evidence for Tumor Pathology collaboratively designed by pathologists with help from epidemiologists, public health professionals, oncologists, and scientists, specifically tailored for use by pathologists-and to aid in the production of the World Health Organization Classification of Tumors (WCT) evidence gap maps. To achieve this, we adopted a modified Delphi approach, encompassing iterative online surveys, expert oversight, and external peer review, to establish the criteria for evidence in tumor pathology, determine the optimal structure for the new hierarchy, and ascertain the levels of confidence for each type of evidence. Over a span of 4 months and 3 survey rounds, we collected 1104 survey responses, culminating in a 3-day hybrid meeting in 2023, where a new hierarchy was unanimously agreed upon. The hierarchy is organized into 5 research theme groupings closely aligned with the subheadings of the WCT, and it consists of 5 levels of evidence-level P1 representing evidence types that merit the greatest level of confidence and level P5 reflecting the greatest risk of bias. For the first time, an international collaboration of pathology experts, supported by the International Agency for Research on Cancer, has successfully united to establish a standardized approach for evaluating evidence in tumor pathology. We intend to implement this novel Hierarchy of Research Evidence for Tumor Pathology to map the available evidence, thereby enriching and informing the WCT effectively.

Moving Forward on Tumor Pathology Research Reporting: A Guide for Pathologists From the World Health Organization Classification of Tumors Living Evidence Gap Map by Tumour Type Group.

Evidence-based medicine (EBM) can be an unfamiliar territory for those working in tumor pathology research, and there is a great deal of uncertainty about how to undertake an EBM approach to planning and reporting histopathology-based studies. In this article, reviewed and endorsed by the Word Health Organization International Agency for Research on Cancer's International Collaboration for Cancer Classification and Research, we aim to help pathologists and researchers understand the basics of planning an evidence-based tumor pathology research study, as well as our recommendations on how to report the findings from these. We introduce some basic EBM concepts, a framework for research questions, and thoughts on study design and emphasize the concept of reporting standards. There are many study-specific reporting guidelines available, and we provide an overview of these. However, existing reporting guidelines perhaps do not always fit tumor pathology research papers, and hence, here, we collate the key reporting data set together into one generic checklist that we think will simplify the task for pathologists. The article aims to complement our recent hierarchy of evidence for tumor pathology and glossary of evidence (study) types in tumor pathology. Together, these articles should help any researcher get to grips with the basics of EBM for planning and publishing research in tumor pathology, as well as encourage an improved standard of the reports available to us all in the literature.

First-in-man study of the PSMA Minibody IR800-IAB2M for molecularly targeted intraoperative fluorescence guidance during radical prostatectomy.

PURPOSE: Prostate-specific membrane antigen (PSMA) is increasingly used to image prostate cancer in clinical practice. We sought to develop and test a humanised PSMA minibody IAB2M conjugated to the fluorophore IRDye 800CW-NHS ester in men undergoing robot-assisted laparoscopic radical prostatectomy (RARP) to image prostate cancer cells during surgery. METHODS: The minibody was evaluated pre-clinically using PSMA positive/negative xenograft models, following which 23 men undergoing RARP between 2018 and 2020 received between 2.5 mg and 20 mg of IR800-IAB2M intravenously, at intervals between 24 h and 17 days prior to surgery. At every step of the procedure, the prostate, pelvic lymph node chains and extra-prostatic surrounding tissue were imaged with a dual Near-infrared (NIR) and white light optical platform for fluorescence in vivo and ex vivo. Histopathological evaluation of intraoperative and postoperative microscopic fluorescence imaging was undertaken for verification. RESULTS: Twenty-three patients were evaluated to optimise both the dose of the reagent and the interval between injection and surgery and secure the best possible specificity of fluorescence images. Six cases are presented in detail as exemplars. Overall sensitivity and specificity in detecting non-lymph-node extra-prostatic cancer tissue were 100% and 65%, and 64% and 64% respectively for lymph node positivity. There were no side-effects associated with administration of the reagent. CONCLUSION: Intraoperative imaging of prostate cancer tissue is feasible and safe using IR800-IAB2M. Further evaluation is underway to assess the benefit of using the technique in improving completion of surgical excision during RARP. REGISTRATION: ISCRCTN10046036: https://www.isrctn.com/ISRCTN10046036 .

Spatial transcriptomic analysis of virtual prostate biopsy reveals confounding effect of tissue heterogeneity on genomic signatures.

Genetic signatures have added a molecular dimension to prognostics and therapeutic decision-making. However, tumour heterogeneity in prostate cancer and current sampling methods could confound accurate assessment. Based on previously published spatial transcriptomic data from multifocal prostate cancer, we created virtual biopsy models that mimic conventional biopsy placement and core size. We then analysed the gene expression of different prognostic signatures (OncotypeDx®, Decipher®, Prostadiag®) using a step-wise approach with increasing resolution from pseudo-bulk analysis of the whole biopsy, to differentiation by tissue subtype (benign, stroma, tumour), followed by distinct tumour grade and finally clonal resolution. The gene expression profile of virtual tumour biopsies revealed clear differences between grade groups and tumour clones, compared to a benign control, which were not reflected in bulk analyses. This suggests that bulk analyses of whole biopsies or tumour-only areas, as used in clinical practice, may provide an inaccurate assessment of gene profiles. The type of tissue, the grade of the tumour and the clonal composition all influence the gene expression in a biopsy. Clinical decision making based on biopsy genomics should be made with caution while we await more precise targeting and cost-effective spatial analyses.

Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies.

The use of immunohistochemistry in the reporting of prostate biopsies is an important adjunct when the diagnosis is not definite on haematoxylin and eosin (H&E) morphology alone. The process is however inherently inefficient with delays while waiting for pathologist review to make the request and duplicated effort reviewing a case more than once. In this study, we aimed to capture the workflow implications of immunohistochemistry requests and demonstrate a novel artificial intelligence tool to identify cases in which immunohistochemistry (IHC) is required and generate an automated request. We conducted audits of the workflow for prostate biopsies in order to understand the potential implications of automated immunohistochemistry requesting and collected prospective cases to train a deep neural network algorithm to detect tissue regions that presented ambiguous morphology on whole slide images. These ambiguous foci were selected on the basis of the pathologist requesting immunohistochemistry to aid diagnosis. A gradient boosted trees classifier was then used to make a slide-level prediction based on the outputs of the neural network prediction. The algorithm was trained on annotations of 219 immunohistochemistry-requested and 80 control images, and tested by threefold cross-validation. Validation was conducted on a separate validation dataset of 222 images. Non IHC-requested cases were diagnosed in 17.9 min on average, while IHC-requested cases took 33.4 min over multiple reporting sessions. We estimated 11 min could be saved on average per case by automated IHC requesting, by removing duplication of effort. The tool attained 99% accuracy and 0.99 Area Under the Curve (AUC) on the test data. In the validation, the average agreement with pathologists was 0.81, with a mean AUC of 0.80. We demonstrate the proof-of-principle that an AI tool making automated immunohistochemistry requests could create a significantly leaner workflow and result in pathologist time savings.

Noninvasive assessment of steatosis and viability of cold-stored human liver grafts by MRI.

PURPOSE: A shortage of suitable donor livers is driving increased use of higher risk livers for transplantation. However, current biomarkers are not sensitive and specific enough to predict posttransplant liver function. This is limiting the expansion of the donor pool. Therefore, better noninvasive tests are required to determine which livers will function following implantation and hence can be safely transplanted. This study assesses the temperature sensitivity of proton density fat fraction and relaxometry parameters and examines their potential for assessment of liver function ex vivo. METHODS: Six ex vivo human livers were scanned during static cold storage following normothermic machine perfusion. Proton density fat fraction, T1 , T2 , and T2∗ were measured repeatedly during cooling on ice. Temperature corrections were derived from these measurements for the parameters that showed significant variation with temperature. RESULTS: Strong linear temperature sensitivities were observed for proton density fat fraction (R2 = 0.61, P < .001) and T1 (R2 = 0.78, P < .001). Temperature correction according to a linear model reduced the coefficient of repeatability in these measurements by 41% and 36%, respectively. No temperature dependence was observed in T2 or T2∗ measurements. Comparing livers deemed functional and nonfunctional during normothermic machine perfusion by hemodynamic and biochemical criteria, T1 differed significantly: 516 ± 50 ms for functional versus 679 ± 60 ms for nonfunctional, P = .02. CONCLUSION: Temperature correction is essential for robust measurement of proton density fat fraction and T1 in cold-stored human livers. These parameters may provide a noninvasive measure of viability for transplantation.

Validation of grading of non-invasive urothelial carcinoma by digital pathology for routine diagnosis.

BACKGROUND: Pathological grading of non-invasive urothelial carcinoma has a direct impact upon management. This study evaluates the reproducibility of grading these tumours on glass slides and digital pathology. METHODS: Forty eight non-invasive urothelial bladder carcinomas were graded by three uropathologists on glass and on a digital platform using the 1973 WHO and 2004 ISUP/WHO systems. RESULTS: Consensus grades for glass and digital grading gave Cohen's kappa scores of 0.78 (2004) and 0.82 (1973). Of 142 decisions made on the key therapeutic borderline of low grade versus high grade urothelial carcinoma (2004) by the three pathologists, 85% were in agreement. For the 1973 grading system, agreement overall was 90%. CONCLUSIONS: Agreement on grading on glass slide and digital screen assessment is similar or in some cases improved, suggesting at least non-inferiority of DP for grading of non-invasive urothelial carcinoma.

Artificial intelligence in digital pathology: a roadmap to routine use in clinical practice.

The use of artificial intelligence will transform clinical practice over the next decade and the early impact of this will likely be the integration of image analysis and machine learning into routine histopathology. In the UK and around the world, a digital revolution is transforming the reporting practice of diagnostic histopathology and this has sparked a proliferation of image analysis software tools. While this is an exciting development that could discover novel predictive clinical information and potentially address international pathology workforce shortages, there is a clear need for a robust and evidence-based framework in which to develop these new tools in a collaborative manner that meets regulatory approval. With these issues in mind, the NCRI Cellular Molecular Pathology (CM-Path) initiative and the British In Vitro Diagnostics Association (BIVDA) have set out a roadmap to help academia, industry, and clinicians develop new software tools to the point of approved clinical use. © 2019 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

CM-Path Molecular Diagnostics Forum-consensus statement on the development and implementation of molecular diagnostic tests in the United Kingdom.

BACKGROUND: Pathology has evolved from a purely morphological description of cellular alterations in disease to our current ability to interrogate tissues with multiple 'omics' technologies. By utilising these techniques and others, 'molecular diagnostics' acts as the cornerstone of precision/personalised medicine by attempting to match the underlying disease mechanisms to the most appropriate targeted therapy. METHODS: Despite the promises of molecular diagnostics, significant barriers have impeded its widespread clinical adoption. Thus, the National Cancer Research Institute (NCRI) Cellular Molecular Pathology (CM-Path) initiative convened a national Molecular Diagnostics Forum to facilitate closer collaboration between clinicians, academia, industry, regulators and other key stakeholders in an attempt to overcome these. RESULTS: We agreed on a consensus 'roadmap' that should be followed during development and implementation of new molecular diagnostic tests. We identified key barriers to efficient implementation and propose possible solutions to these. In addition, we discussed the recent reconfiguration of molecular diagnostic services in NHS England and its likely impacts. CONCLUSIONS: We anticipate that this consensus statement will provide practical advice to those involved in the development of novel molecular diagnostic tests. Although primarily focusing on test adoption within the United Kingdom, we also refer to international guidelines to maximise the applicability of our recommendations.

Intraoperative identification and analysis of lymph nodes at laparoscopic colorectal cancer surgery using fluorescence imaging combined with rapid OSNA pathological assessment.

BACKGROUND: Standard surgical practice for colorectal cancer involves resection of the primary lesion and all draining lymph nodes. Accurate intraoperative assessment of nodal status could allow stratified resectional extent. One-step nucleic acid (OSNA) can provide a rapid method of interrogating nodal tissue, whilst near-infrared (NIR) laparoscopy together with indocyanine green (ICG) can identify relevant nodal tissue intraoperatively. METHODS: ICG was administered around the tumour endoscopically prior to the operation. Fluorescent nodes identified by NIR were marked and submitted for whole-node OSNA analysis. Further fresh lymph nodes dissected from the standard resection specimen were examined and analysed by both conventional histology and OSNA. In addition, the status of the fluorescent nodes was compared to that of non-ICG nodes to assess their predictive value. RESULTS: Sixteen patients were recruited with a total final lymph node count of 287. 78 fresh lymph nodes were identified on fresh dissection for both histological and OSNA assessment with an analytical concordance rate of 98.7% (77/78). OSNA sensitivity was 1 (0.81-1, 95% CI) and specificity 0.98 (0.91-1, 95% CI). Six patients had a total of nine nodes identified intraoperatively by ICG fluorescence. Of these nine nodes, one was positive for metastasis on OSNA. OSNA analysis of the ICG-labelled node matched the final histological nodal stage in 3/6 patients (two being N0 and one N1). The final pathological nodal stage of the other three was N1 or N2, while the ICG nodes were negative. CONCLUSION: OSNA is highly concordant with standard histology, although only a minority of nodes identifiable by full pathological analysis were found for OSNA on fresh dissection. OSNA can be combined with NIR and ICG lymphatic mapping to provide intraoperative assessment of nodal tissue in patients with colorectal cancer.

Mucin-rich variant of traditional serrated adenoma: a distinct morphological variant.

AIMS: Traditional serrated adenomas (TSAs) account for 5% of serrated polyps, and have a villiform architecture, eosinophilic cells with a brush border, and indented, flat-topped luminal serrations. However, some are composed of mucin-filled goblet cells (GCs): mucin-rich TSA (MrTSA). The aim of this study was to determine whether this variant has unique features as compared with classic TSA (cTSA). METHODS AND RESULTS: One hundred and fifty-six TSAs were retrieved from the period 2010-2016. Patient demographics, site of polyps and 16 microscopic variables were evaluated. TSAs containing ≥50% GCs were classified as MrTSAs. Ectopic crypt foci (ECFs) were quantified as low (1-10) or high (>10), counted at ×200 magnification, and the average was taken for 10 fields. Twenty-four fulfilled the criteria for MrTSA. In males, MrTSAs (65%) were more prevalent than cTSAs (55%). There was no age difference, and both variants had a predilection for the left colon, although, in the right colon, MrTSAs were more frequent (39%) than cTSAs (10%) (P = 0.012). Adenomatous dysplasia was present in four of 24 MrTSAs (low grade, 3; high grade, 1). The most distinctive features of MrTSAs were: a variable growth pattern [endophytic (9%), mixed (30%), or villiform/exophytic (61%)], and a lower frequency of ECFs (P = 0.001) and more intraepithelial lymphocytes (P < 0.05) than in cTSAs. MrTSAs retain characteristic luminal serrations, at least focally. Inflamed MrTSAs can mimic inflammatory polyps and hamartomatous polyps (when there are >95% GCs). CONCLUSIONS: MrTSA is characterized by >50% GCs, and fewer ECFs than cTSA, but with preservation of archetypal luminal serrations. Awareness of this variant will prevent misdiagnosis, given the association of TSA with the accelerated pathway to colorectal cancer.

Bile duct basement membrane thickening in primary sclerosing cholangitis.

AIMS: Primary sclerosing cholangitis (PSC) is characterized histologically by portal inflammation, bile duct injury and regeneration and concentric periductal fibrosis. Although seen commonly in our experience, the significance of histological thickening of the bile duct basement membrane on periodic acid Schiff (PAS)-positive, diastase-resistant (DPAS) staining has never been analysed formally. In this paper we provide an evidence-based assessment of basement membrane thickening (BMT) reproducibility and diagnostic accuracy. METHODS AND RESULTS: A total of 128 archived medical liver core biopsies were retrieved and blinded for review by two independent histopathologists. BMT was assessed and designated as absent or present with a grade (G) of G1-G3. The sensitivity of any BMT for PSC was good at 77%, with moderate specificity at 61%. When only G3 BMT was considered positive, the specificity was high at 95% but the sensitivity was poor at 16%. The interobserver agreement (0.69) and consistency (0.72) were good. CONCLUSIONS: Basement membrane thickening is a reproducible predictor for PSC with good sensitivity and specificity. The presence of G2 and especially G3 BMT showed high specificity and could be regarded as highly predictive of PSC. The presence of more than G1 BMT should be reported and the possibility of PSC should be raised in the differential diagnosis.

Histological overlap between colorectal villous/tubulovillous and traditional serrated adenomas.

AIMS: To ascertain the degree of histological overlap between conventional villous/tubulovillous (VA/TVAs) and traditional serrated adenomas (TSA). METHODS AND RESULTS: A total of 180 polyps from the left colon/rectum diagnosed as VA/TVAs were retrieved randomly and reviewed by five pathologists looking specifically at luminal serration, cytoplasmic eosinophilia and the presence of ectopic crypt foci (ECF). For comparative purposes, 100 tubular adenomas and 80 TSAs were also examined. Twenty VA/TVAs were reclassified as TSA. Luminal serration as noted in TSA was not seen in any of the remaining 160 polyps, ECFs were noted in 55 of the 160 VA/TVAs (34%), while cytoplasmic eosinophilia (constituting <50% of the adenoma) was noted in only 10 of 160 cases (6.2%). CONCLUSIONS: Ectopic crypt foci and cytoplasmic eosinophilia are encountered in sporadic VA/TVAs but not to the same extent and degree as in TSA. ECFs were found in one-third of cases, but cytoplasmic eosinophilia is rare. The pattern of luminal serration in TSA is very characteristic and not recapitulated in VA/TVA. The occurrence of all three histological features together occurs only in TSA. ECFs are not a sine qua non for TSA and are encountered commonly in VA/TVAs. VA/TVAs often contain occasional glands typical of TSA.

Artificial Intelligence-Based Quality Assessment of Histopathology Whole-Slide Images within a Clinical Workflow: Assessment of 'PathProfiler' in a Diagnostic Pathology Setting.

Digital pathology continues to gain momentum, with the promise of artificial intelligence to aid diagnosis and for assessment of features which may impact prognosis and clinical management. Successful adoption of these technologies depends upon the quality of digitised whole-slide images (WSI); however, current quality control largely depends upon manual assessment, which is inefficient and subjective. We previously developed PathProfiler, an automated image quality assessment tool, and in this feasibility study we investigate its potential for incorporation into a diagnostic clinical pathology setting in real-time. A total of 1254 genitourinary WSI were analysed by PathProfiler. PathProfiler was developed and trained on prostate tissue and, of the prostate biopsy WSI, representing 46% of the WSI analysed, 4.5% were flagged as potentially being of suboptimal quality for diagnosis. All had concordant subjective issues, mainly focus-related, 54% severe enough to warrant remedial action which resulted in improved image quality. PathProfiler was less reliable in assessment of non-prostate surgical resection-type cases, on which it had not been trained. PathProfiler shows potential for incorporation into a digitised clinical pathology workflow, with opportunity for image quality improvement. Whilst its reliability in the current form appears greatest for assessment of prostate specimens, other specimen types, particularly biopsies, also showed benefit.

Engineering the future of 3D pathology.

In recent years, technological advances in tissue preparation, high-throughput volumetric microscopy, and computational infrastructure have enabled rapid developments in nondestructive 3D pathology, in which high-resolution histologic datasets are obtained from thick tissue specimens, such as whole biopsies, without the need for physical sectioning onto glass slides. While 3D pathology generates massive datasets that are attractive for automated computational analysis, there is also a desire to use 3D pathology to improve the visual assessment of tissue histology. In this perspective, we discuss and provide examples of potential advantages of 3D pathology for the visual assessment of clinical specimens and the challenges of dealing with large 3D datasets (of individual or multiple specimens) that pathologists have not been trained to interpret. We discuss the need for artificial intelligence triaging algorithms and explainable analysis methods to assist pathologists or other domain experts in the interpretation of these novel, often complex, large datasets.

Impact of the transition to digital pathology in a clinical setting on histopathologists in training: experiences and perceived challenges within a UK training region.

AIMS: With increasing utility of digital pathology (DP), it is important to consider the experiences of histopathologists in training, particularly in view of the varied access to DP across a training region and the consequent need to remain competent in reporting on glass slides (GS), which is also relevant for the Fellowship of the Royal College of Pathologists part 2 examination. Understanding the impact of DP on training is limited but could aid development of guidance to support the transition. We sought to investigate the perceptions of histopathologists in training around the introduction of DP for clinical diagnosis within a training region, and the potential training benefits and challenges. METHODS: An anonymous online survey was circulated to 24 histopathologists in training within a UK training region, including a hospital which has been fully digitised since summer 2020. RESULTS: 19 of 24 histopathologists in training responded (79%). The results indicate that DP offers many benefits to training, including ease of access to cases to enhance individual learning and teaching in general. Utilisation of DP for diagnosis appears variable; almost half of the (10 of 19) respondents with DP experience using it only for ancillary purposes such as measurements, reporting varying levels of confidence in using DP clinically. For those yet to undergo the transition, there was a perceived anxiety regarding digital reporting despite experience with DP in other contexts. CONCLUSIONS: The survey evidences the need for provision of training and support for histopathologists in training during the transition to DP, and for consideration of their need to maintain competence and confidence with GS reporting.