Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study.

OBJECTIVE: To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis. DESIGN: A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site. RESULTS: Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features. CONCLUSION: The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption.

The role and contribution of clonality studies in the diagnosis of lymphoproliferative disorders.

OBJECTIVES: To explore the frequency, context and diagnostic impact of B- and T-lymphocyte clonality assay use in the assessment of possible lymphoproliferative disorders at a central haematopathology diagnostics hub. METHODS: All cases reported by haematopathologists over a sixteen-month period were identified, n = 4462, and those which had clonality studies undertaken analysed further. RESULTS: Clonality studies were requested in 9% of cases, directly contributing to a diagnosis being made in 79%. They were most frequently used to help distinguish reactive lymphoid infiltrates from low-grade B-cell lymphomas and in cases of possible T-cell lymphoma, facilitating a diagnosis being made in over 90% of these. In contrast when clonality assays were requested as a diagnostic adjunct in cases with an atypical cutaneous lymphoid infiltrate, and in occasional cases of lymphoid proliferations with Hodgkin-like cells or EBV-driven proliferations, a definitive final diagnosis was possible in less than 60% of cases. CONCLUSIONS: Clonality studies were used in 9% of cases assessed for a possible lymphoproliferative disorder and had a differing impact depending on the differential diagnoses being considered. These findings can be used to guide access to clonality assays by highlighting the likelihood of an informative result in different diagnostic settings.

Development and validation of artificial intelligence-based prescreening of large-bowel biopsies taken in the UK and Portugal: a retrospective cohort study.

BACKGROUND: Histopathological examination is a crucial step in the diagnosis and treatment of many major diseases. Aiming to facilitate diagnostic decision making and improve the workload of pathologists, we developed an artificial intelligence (AI)-based prescreening tool that analyses whole-slide images (WSIs) of large-bowel biopsies to identify typical, non-neoplastic, and neoplastic biopsies. METHODS: This retrospective cohort study was conducted with an internal development cohort of slides acquired from a hospital in the UK and three external validation cohorts of WSIs acquired from two hospitals in the UK and one clinical laboratory in Portugal. To learn the differential histological patterns from digitised WSIs of large-bowel biopsy slides, our proposed weakly supervised deep-learning model (Colorectal AI Model for Abnormality Detection [CAIMAN]) used slide-level diagnostic labels and no detailed cell or region-level annotations. The method was developed with an internal development cohort of 5054 biopsy slides from 2080 patients that were labelled with corresponding diagnostic categories assigned by pathologists. The three external validation cohorts, with a total of 1536 slides, were used for independent validation of CAIMAN. Each WSI was classified into one of three classes (ie, typical, atypical non-neoplastic, and atypical neoplastic). Prediction scores of image tiles were aggregated into three prediction scores for the whole slide, one for its likelihood of being typical, one for its likelihood of being non-neoplastic, and one for its likelihood of being neoplastic. The assessment of the external validation cohorts was conducted by the trained and frozen CAIMAN model. To evaluate model performance, we calculated area under the convex hull of the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and specificity compared with our previously published iterative draw and rank sampling (IDaRS) algorithm. We also generated heat maps and saliency maps to analyse and visualise the relationship between the WSI diagnostic labels and spatial features of the tissue microenvironment. The main outcome of this study was the ability of CAIMAN to accurately identify typical and atypical WSIs of colon biopsies, which could potentially facilitate automatic removing of typical biopsies from the diagnostic workload in clinics. FINDINGS: A randomly selected subset of all large bowel biopsies was obtained between Jan 1, 2012, and Dec 31, 2017. The AI training, validation, and assessments were done between Jan 1, 2021, and Sept 30, 2022. WSIs with diagnostic labels were collected between Jan 1 and Sept 30, 2022. Our analysis showed no statistically significant differences across prediction scores from CAIMAN for typical and atypical classes based on anatomical sites of the biopsy. At 0·99 sensitivity, CAIMAN (specificity 0·5592) was more accurate than an IDaRS-based weakly supervised WSI-classification pipeline (0·4629) in identifying typical and atypical biopsies on cross-validation in the internal development cohort (p<0·0001). At 0·99 sensitivity, CAIMAN was also more accurate than IDaRS for two external validation cohorts (p<0·0001), but not for a third external validation cohort (p=0·10). CAIMAN provided higher specificity than IDaRS at some high-sensitivity thresholds (0·7763 vs 0·6222 for 0·95 sensitivity, 0·7126 vs 0·5407 for 0·97 sensitivity, and 0·5615 vs 0·3970 for 0·99 sensitivity on one of the external validation cohorts) and showed high classification performance in distinguishing between neoplastic biopsies (AUROC 0·9928, 95% CI 0·9927-0·9929), inflammatory biopsies (0·9658, 0·9655-0·9661), and atypical biopsies (0·9789, 0·9786-0·9792). On the three external validation cohorts, CAIMAN had AUROC values of 0·9431 (95% CI 0·9165-0·9697), 0·9576 (0·9568-0·9584), and 0·9636 (0·9615-0·9657) for the detection of atypical biopsies. Saliency maps supported the representation of disease heterogeneity in model predictions and its association with relevant histological features. INTERPRETATION: CAIMAN, with its high sensitivity in detecting atypical large-bowel biopsies, might be a promising improvement in clinical workflow efficiency and diagnostic decision making in prescreening of typical colorectal biopsies. FUNDING: The Pathology Image Data Lake for Analytics, Knowledge and Education Centre of Excellence; the UK Government's Industrial Strategy Challenge Fund; and Innovate UK on behalf of UK Research and Innovation.

Tamoxifen for the treatment of myeloproliferative neoplasms: A Phase II clinical trial and exploratory analysis.

Current therapies for myeloproliferative neoplasms (MPNs) improve symptoms but have limited effect on tumor size. In preclinical studies, tamoxifen restored normal apoptosis in mutated hematopoietic stem/progenitor cells (HSPCs). TAMARIN Phase-II, multicenter, single-arm clinical trial assessed tamoxifen's safety and activity in patients with stable MPNs, no prior thrombotic events and mutated JAK2V617F, CALRins5 or CALRdel52 peripheral blood allele burden ≥20% (EudraCT 2015-005497-38). 38 patients were recruited over 112w and 32 completed 24w-treatment. The study's A'herns success criteria were met as the primary outcome ( ≥ 50% reduction in mutant allele burden at 24w) was observed in 3/38 patients. Secondary outcomes included ≥25% reduction at 24w (5/38), ≥50% reduction at 12w (0/38), thrombotic events (2/38), toxicities, hematological response, proportion of patients in each IWG-MRT response category and ELN response criteria. As exploratory outcomes, baseline analysis of HSPC transcriptome segregates responders and non-responders, suggesting a predictive signature. In responder HSPCs, longitudinal analysis shows high baseline expression of JAK-STAT signaling and oxidative phosphorylation genes, which are downregulated by tamoxifen. We further demonstrate in preclinical studies that in JAK2V617F+ cells, 4-hydroxytamoxifen inhibits mitochondrial complex-I, activates integrated stress response and decreases pathogenic JAK2-signaling. These results warrant further investigation of tamoxifen in MPN, with careful consideration of thrombotic risk.

Semantic annotation for computational pathology: multidisciplinary experience and best practice recommendations.

Recent advances in whole-slide imaging (WSI) technology have led to the development of a myriad of computer vision and artificial intelligence-based diagnostic, prognostic, and predictive algorithms. Computational Pathology (CPath) offers an integrated solution to utilise information embedded in pathology WSIs beyond what can be obtained through visual assessment. For automated analysis of WSIs and validation of machine learning (ML) models, annotations at the slide, tissue, and cellular levels are required. The annotation of important visual constructs in pathology images is an important component of CPath projects. Improper annotations can result in algorithms that are hard to interpret and can potentially produce inaccurate and inconsistent results. Despite the crucial role of annotations in CPath projects, there are no well-defined guidelines or best practices on how annotations should be carried out. In this paper, we address this shortcoming by presenting the experience and best practices acquired during the execution of a large-scale annotation exercise involving a multidisciplinary team of pathologists, ML experts, and researchers as part of the Pathology image data Lake for Analytics, Knowledge and Education (PathLAKE) consortium. We present a real-world case study along with examples of different types of annotations, diagnostic algorithm, annotation data dictionary, and annotation constructs. The analyses reported in this work highlight best practice recommendations that can be used as annotation guidelines over the lifecycle of a CPath project.

Next-Generation Sequencing-Based Clonality Assessment of Ig Gene Rearrangements: A Multicenter Validation Study by EuroClonality-NGS.

Ig gene (IG) clonality analysis has an important role in the distinction of benign and malignant B-cell lymphoid proliferations and is mostly performed with the conventional EuroClonality/BIOMED-2 multiplex PCR protocol and GeneScan fragment size analysis. Recently, the EuroClonality-NGS Working Group developed a method for next-generation sequencing (NGS)-based IG clonality analysis. Herein, we report the results of an international multicenter biological validation of this novel method compared with the gold standard EuroClonality/BIOMED-2 protocol, based on 209 specimens of reactive and neoplastic lymphoproliferations. NGS-based IG clonality analysis showed a high interlaboratory concordance (99%) and high concordance with conventional clonality analysis (98%) for the molecular conclusion. Detailed analysis of the individual IG heavy chain and kappa light chain targets showed that NGS-based clonality analysis was more often able to detect a clonal rearrangement or yield an interpretable result. NGS-based and conventional clonality analysis detected a clone in 96% and 95% of B-cell neoplasms, respectively, and all but one of the reactive cases were scored polyclonal. We conclude that NGS-based IG clonality analysis performs comparable to conventional clonality analysis. We provide critical parameters for interpretation and discuss a first step toward a quantitative scoring approach for NGS clonality results. Considering the advantages of NGS-based clonality analysis, including its high sensitivity and possibilities for accurate clonal comparison, this supports implementation in diagnostic practice.

Genetic modification of primary human B cells to model high-grade lymphoma.

Sequencing studies of diffuse large B cell lymphoma (DLBCL) have identified hundreds of recurrently altered genes. However, it remains largely unknown whether and how these mutations may contribute to lymphomagenesis, either individually or in combination. Existing strategies to address this problem predominantly utilize cell lines, which are limited by their initial characteristics and subsequent adaptions to prolonged in vitro culture. Here, we describe a co-culture system that enables the ex vivo expansion and viral transduction of primary human germinal center B cells. Incorporation of CRISPR/Cas9 technology enables high-throughput functional interrogation of genes recurrently mutated in DLBCL. Using a backbone of BCL2 with either BCL6 or MYC, we identify co-operating genetic alterations that promote growth or even full transformation into synthetically engineered DLBCL models. The resulting tumors can be expanded and sequentially transplanted in vivo, providing a scalable platform to test putative cancer genes and to create mutation-directed, bespoke lymphoma models.

Inhibition of CXCR4-mediated breast cancer metastasis: a potential role for heparinoids?

PURPOSE: The pattern of breast cancer metastasis may be determined by interactions between CXCR4 on breast cancer cells and CXCL12 within normal tissues. Glycosaminoglycans bind chemokines for presentation to responsive cells. This study was designed to test the hypothesis that soluble heparinoid glycosaminoglycan molecules can disrupt the normal response to CXCL12, thereby reducing the metastasis of CXCR4-expressing cancer cells. EXPERIMENTAL DESIGN: Inhibition of the response of CXCR4-expressing Chinese hamster ovary cells to CXCL12 was assessed by measurement of calcium flux and chemotaxis. Radioligand binding was also assessed to quantify the potential of soluble heparinoids to prevent specific receptor ligation. The human breast cancer cell line MDA-MB-231 and a range of sublines were assessed for their sensitivity to heparinoid-mediated inhibition of chemotaxis. A model of hematogenous breast cancer metastasis was established, and the potential of clinically relevant doses of heparinoids to inhibit CXCL12 presentation and metastatic disease was assessed. RESULTS: Unfractionated heparin and the low-molecular-weight heparin tinzaparin inhibited receptor ligation and the response of CXCR4-expressing Chinese hamster ovary cells and human breast cancer cell lines to CXCL12. Heparin also removed CXCL12 from its normal site of expression on the surface of parenchymal cells in the murine lung. Both heparin and two clinically relevant dose regimens of tinzaparin reduced hematogenous metastatic spread of human breast cancer cells to the lung in a murine model. CONCLUSIONS: Clinically relevant concentrations of tinzaparin inhibit the interaction between CXCL12 and CXCR4 and may be useful to prevent chemokine-driven breast cancer metastasis.

PAK4 interacts with p85 alpha: implications for pancreatic cancer cell migration.

It has been reported that p21-activated kinase 4 (PAK4) is amplified in pancreatic cancer tissue. PAK4 is a member of the PAK family of serine/threonine kinases, which act as effectors for several small GTPases, and has been specifically identified to function downstream of HGF-mediated c-Met activation in a PI3K dependent manner. However, the functionality of PAK4 in pancreatic cancer and the contribution made by HGF signalling to pancreatic cancer cell motility remain to be elucidated. We now find that elevated PAK4 expression is coincident with increased expression levels of c-Met and the p85α subunit of PI3K. Furthermore, we demonstrate that pancreatic cancer cells have a specific motility response to HGF both in 2D and 3D physiomimetic organotypic assays; which can be suppressed by inhibition of PI3K. Significantly, we report a specific interaction between PAK4 and p85α and find that PAK4 deficient cells exhibit a reduction in Akt phosphorylation downstream of HGF signalling. These results implicate a novel role for PAK4 within the PI3K pathway via interaction with p85α. Thus, PAK4 could be an essential player in PDAC progression representing an interesting therapeutic opportunity.

A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images.

UNLABELLED: In this paper, we propose a statistical approach for mitosis detection in breast cancer histological images. The proposed algorithm models the pixel intensities in mitotic and non-mitotic regions by a Gamma-Gaussian mixture model (GGMM) and employs a context aware post-processing (CAPP) in order to reduce false positives. Experimental results demonstrate the ability of this simple, yet effective method to detect mitotic cells (MCs) in standard H & E breast cancer histology images. CONTEXT: Counting of MCs in breast cancer histopathology images is one of three components (the other two being tubule formation, nuclear pleomorphism) required for developing computer assisted grading of breast cancer tissue slides. This is very challenging since the biological variability of the MCs makes their detection extremely difficult. In addition, if standard H & E is used (which stains chromatin rich structures, such as nucleus, apoptotic, and MCs dark blue) and it becomes extremely difficult to detect the latter given the fact that former two are densely localized in the tissue sections. AIMS: In this paper, a robust MCs detection technique is developed and tested on 35 breast histopathology images, belonging to five different tissue slides. SETTINGS AND DESIGN: Our approach mimics a pathologists' approach to MCs detections. The idea is (1) to isolate tumor areas from non-tumor areas (lymphoid/inflammatory/apoptotic cells), (2) search for MCs in the reduced space by statistically modeling the pixel intensities from mitotic and non-mitotic regions, and finally (3) evaluate the context of each potential MC in terms of its texture. MATERIALS AND METHODS: Our experimental dataset consisted of 35 digitized images of breast cancer biopsy slides with paraffin embedded sections stained with H and E and scanned at × 40 using an Aperio scanscope slide scanner. STATISTICAL ANALYSIS USED: We propose GGMM for detecting MCs in breast histology images. Image intensities are modeled as random variables sampled from one of the two distributions; Gamma and Gaussian. Intensities from MCs are modeled by a gamma distribution and those from non-mitotic regions are modeled by a gaussian distribution. The choice of Gamma-Gaussian distribution is mainly due to the observation that the characteristics of the distribution match well with the data it models. The experimental results show that the proposed system achieves a high sensitivity of 0.82 with positive predictive value (PPV) of 0.29. Employing CAPP on these results produce 241% increase in PPV at the cost of less than 15% decrease in sensitivity. CONCLUSIONS: In this paper, we presented a GGMM for detection of MCs in breast cancer histopathological images. In addition, we introduced CAPP as a tool to increase the PPV with a minimal loss in sensitivity. We evaluated the performance of the proposed detection algorithm in terms of sensitivity and PPV over a set of 35 breast histology images selected from five different tissue slides and showed that a reasonably high value of sensitivity can be retained while increasing the PPV. Our future work will aim at increasing the PPV further by modeling the spatial appearance of regions surrounding mitotic events.