Artificial intelligence algorithm accurately assesses oestrogen receptor immunohistochemistry in metastatic breast cancer cytology specimens: A pilot study.

OBJECTIVE: The Visiopharm artificial intelligence (AI) algorithm for oestrogen receptor (ER) immunohistochemistry (IHC) in whole slide images (WSIs) has been successfully validated in surgical pathology. This study aimed to assess its efficacy in cytology specimens. METHODS: The study cohort comprised 105 consecutive cytology specimens with metastatic breast carcinoma. ER IHC WSIs were seamlessly integrated into the Visiopharm platform from the Image Management System (IMS) during our routine digital workflow, and an AI algorithm was employed for analysis. ER AI scores were compared with pathologists' manual consensus scores. Optimization steps were implemented and evaluated to reduce discordance. RESULTS: The overall concordance between pathologists' scores and AI scores was excellent (99/105, 94.3%). Six cases exhibited discordant results, including two false-negative (FN) cases due to abundant histiocytes incorrectly counted as negatively stained tumour cells by AI, two FN cases owing to weak staining, and two false-positive (FP) cases where pigmented macrophages were erroneously counted as positively stained tumour cells by AI. The Pearson correlation coefficient of ER-positive percentages between pathologists' and AI scores was 0.8483. Optimization steps, such as lowering the cut-off threshold and additional training using higher input magnification, significantly improved accuracy. CONCLUSIONS: The automated ER AI algorithm demonstrated excellent concordance with pathologists' assessments and accurately differentiated ER-positive from ER-negative metastatic breast carcinoma cytology cases. However, precision in identifying tumour cells in cytology specimens requires further enhancement.

A visual-language foundation model for computational pathology.

The accelerated adoption of digital pathology and advances in deep learning have enabled the development of robust models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain, and a model's usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text and, notably, over 1.17 million image-caption pairs through task-agnostic pretraining. Evaluated on a suite of 14 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving histopathology images and/or text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, and text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning.

Artificial intelligence's impact on breast cancer pathology: a literature review.

This review discusses the profound impact of artificial intelligence (AI) on breast cancer (BC) diagnosis and management within the field of pathology. It examines the various applications of AI across diverse aspects of BC pathology, highlighting key findings from multiple studies. Integrating AI into routine pathology practice stands to improve diagnostic accuracy, thereby contributing to reducing avoidable errors. Additionally, AI has excelled in identifying invasive breast tumors and lymph node metastasis through its capacity to process large whole-slide images adeptly. Adaptive sampling techniques and powerful convolutional neural networks mark these achievements. The evaluation of hormonal status, which is imperative for BC treatment choices, has also been enhanced by AI quantitative analysis, aiding interobserver concordance and reliability. Breast cancer grading and mitotic count evaluation also benefit from AI intervention. AI-based frameworks effectively classify breast carcinomas, even for moderately graded cases that traditional methods struggle with. Moreover, AI-assisted mitotic figures quantification surpasses manual counting in precision and sensitivity, fostering improved prognosis. The assessment of tumor-infiltrating lymphocytes in triple-negative breast cancer using AI yields insights into patient survival prognosis. Furthermore, AI-powered predictions of neoadjuvant chemotherapy response demonstrate potential for streamlining treatment strategies. Addressing limitations, such as preanalytical variables, annotation demands, and differentiation challenges, is pivotal for realizing AI's full potential in BC pathology. Despite the existing hurdles, AI's multifaceted contributions to BC pathology hold great promise, providing enhanced accuracy, efficiency, and standardization. Continued research and innovation are crucial for overcoming obstacles and fully harnessing AI's transformative capabilities in breast cancer diagnosis and assessment.

Artificial Intelligence-Enabled Prostate Cancer Diagnosis and Prognosis: Current State and Future Implications.

In this modern era of digital pathology, artificial intelligence (AI)-based diagnostics for prostate cancer has become a hot topic. Multiple retrospective studies have demonstrated the benefits of AI-based diagnostic solutions for prostate cancer that includes improved prostate cancer detection, quantification, grading, interobserver concordance, cost and time savings, and a potential to reduce pathologists' workload and enhance pathology laboratory workflow. One of the major milestones is the Food and Drug Administration approval of Paige prostate AI for a second review of prostate cancer diagnosed using core needle biopsies. However, implementation of these AI tools for routine prostate cancer diagnostics is still lacking. Some of the limiting factors include costly digital pathology workflow, lack of regulatory guidelines for deployment of AI, and lack of prospective studies demonstrating the actual benefits of AI algorithms. Apart from diagnosis, AI algorithms have the potential to uncover novel insights into understanding the biology of prostate cancer and enable better risk stratification, and prognostication. This article includes an in-depth review of the current state of AI for prostate cancer diagnosis and highlights the future prospects of AI in prostate pathology for improved patient care.

Artificial intelligence-assisted digital pathology for non-alcoholic steatohepatitis: current status and future directions.

The worldwide prevalence of non-alcoholic steatohepatitis (NASH) is increasing, causing a significant medical burden, but no approved therapeutics are currently available. NASH drug development requires histological analysis of liver biopsies by expert pathologists for trial enrolment and efficacy assessment, which can be hindered by multiple issues including sample heterogeneity, inter-reader and intra-reader variability, and ordinal scoring systems. Consequently, there is a high unmet need for accurate, reproducible, quantitative, and automated methods to assist pathologists with histological analysis to improve the precision around treatment and efficacy assessment. Digital pathology (DP) workflows in combination with artificial intelligence (AI) have been established in other areas of medicine and are being actively investigated in NASH to assist pathologists in the evaluation and scoring of NASH histology. DP/AI models can be used to automatically detect, localise, quantify, and score histological parameters and have the potential to reduce the impact of scoring variability in NASH clinical trials. This narrative review provides an overview of DP/AI tools in development for NASH, highlights key regulatory considerations, and discusses how these advances may impact the future of NASH clinical management and drug development. This should be a high priority in the NASH field, particularly to improve the development of safe and effective therapeutics.

Evaluation of programmed cell death ligand 1 expression in a contemporary cohort of penile squamous cell carcinoma and its correlation with clinicopathologic and survival parameters: A study of 134 patients.

OBJECTIVES: Penile squamous cell carcinomas (PCs) are rare malignancies with a dismal prognosis in a metastatic setting; therefore, novel immunotherapeutic modalities are an unmet need. One such modality is the immune checkpoint molecule programmed cell death ligand 1 (PD-L1). We sought to analyze PD-L1 expression and its correlation with various clinicopathologic parameters in a contemporary cohort of 134 patients with PC. METHODS: A cohort of 134 patients with PC was studied for PD-L1 immunohistochemistry. The PD-L1 expression was evaluated using a combined proportion score with a cutoff of 1 or higher to define positivity. The results were correlated with various clinicopathologic parameters. RESULTS: Overall, 77 (57%) patients had positive PD-L1 expression. Significantly high PD-L1 expression was observed in high-grade tumors (P = .006). We found that 37% of human papillomavirus (HPV)-associated subtypes and 73% of other histotype tumors expressed PD-L1, while 63% of HPV-associated tumors and 27% of other histotype tumors did not (odds ratio, 1.35; P = .002 when compared for HPV-associated groups vs all others). Similarly, PD-L1-positive tumors had a 3.61-times higher chance of being node positive than PD-L1-negative tumors (P = .0009). In addition, PD-L1 high-positive tumors had a 5-times higher chance of being p16ink4a negative than PD-L1 low-positive tumors (P = .004). The PD-L1-positive tumors had a lower overall survival and cancer-specific survival than PD-L1-negative tumors. CONCLUSIONS: Overall, PD-L1 expression is associated with high-grade and metastatic tumors. Lower PD-L1 expression is observed more frequently in HPV-associated (warty or basaloid) subtypes than in other, predominantly HPV-independent types. As a result, PD-L1 positivity, including higher expression, portends lower overall and cancer-specific survival. These data provide a rational for further investigating PD-L1-based immunotherapeutics in PC.

Digital cytology part 1: digital cytology implementation for practice: a concept paper with review and recommendations from the American Society of Cytopathology Digital Cytology Task Force.

Digital cytology and artificial intelligence (AI) are gaining greater adoption in the cytopathology laboratory. However, peer-reviewed real-world data and literature are lacking regarding the current clinical landscape. The American Society of Cytopathology in conjunction with the International Academy of Cytology and the Digital Pathology Association established a special task force comprising 20 members with expertise and/or interest in digital cytology. The aim of the group was to investigate the feasibility of incorporating digital cytology, specifically cytology whole slide scanning and AI applications, into the workflow of the laboratory. In turn, the impact on cytopathologists, cytologists (cytotechnologists), and cytology departments were also assessed. The task force reviewed existing literature on digital cytology, conducted a worldwide survey, and held a virtual roundtable discussion on digital cytology and AI with multiple industry corporate representatives. This white paper, presented in 2 parts, summarizes the current state of digital cytology and AI practice in global cytology practice. Part 1 of the white paper presented herein is a review and offers best practice recommendations for incorporating digital cytology into practice. Part 2 of the white paper provides a comprehensive review of AI in cytology practice along with best practice recommendations and legal considerations. Additionally, the results of a global survey regarding digital cytology are highlighted.

Digital cytology part 2: artificial intelligence in cytology: a concept paper with review and recommendations from the American Society of Cytopathology Digital Cytology Task Force.

Digital cytology and artificial intelligence (AI) are gaining greater adoption in the cytology laboratory. However, peer-reviewed real-world data and literature are lacking in regard to the current clinical landscape. The American Society of Cytopathology in conjunction with the International Academy of Cytology and the Digital Pathology Association established a special task force comprising 20 members with expertise and/or interest in digital cytology. The aim of the group was to investigate the feasibility of incorporating digital cytology, specifically cytology whole slide scanning and AI applications, into the workflow of the laboratory. In turn, the impact on cytopathologists, cytologists (cytotechnologists), and cytology departments were also assessed. The task force reviewed existing literature on digital cytology, conducted a worldwide survey, and held a virtual roundtable discussion on digital cytology and AI with multiple industry corporate representatives. This white paper, presented in 2 parts, summarizes the current state of digital cytology and AI practice in global cytology practice. Part 1 of the white paper is presented as a separate paper which details a review and best practice recommendations for incorporating digital cytology into practice. Part 2 of the white paper presented here provides a comprehensive review of AI in cytology practice along with best practice recommendations and legal considerations. Additionally, the cytology global survey results highlighting current AI practices by various laboratories, as well as current attitudes, are reported.

Cytomorphology of papillary renal neoplasm with reverse polarity.

Papillary renal neoplasm with reverse nuclear polarity (PRNRP) is an emerging oncocytic renal tumor. Cytomorphologic features of this tumor have not been described in the literature before. The objective of this study was to review the cytomorphology of a case PRNRP and compare with cytomorphologic features of papillary renal cell carcinomas (pRCCs) reported in the literature. 1 case of core needle biopsy (CNB) with touch preparation (TP) of a renal mass diagnosed as PRNRP was reviewed retrospectively. Clinical presentation, cytomorphologic features, ancillary tests and histopathology results were analyzed. The touch preparation was cellular and showed tight 3-D clusters of cuboidal epithelial cells with variable presence of fibrovascular cores (FC), granular eosinophilic cytoplasm, round apically located grade 1 nuclei compared to cases of pRCC that consistently showed presence of FCs lined by cuboidal to columnar epithelial cells with variable degree of cytologic atypia. Features characteristic of pRCC like foamy macrophages, hemosiderin laden macrophages, nuclear grooves or psammoma bodies were not present. No necrosis or mitosis were identified. By immunohistochemistry (IHC) the tumor cells were positive for cytokeratin 7, GATA-3 and AMACR (focal) and negative for CA-IX, CD117 and vimentin. Cytomorphologic features of PRNRP are unique and characterized by tight 3-D clusters (with or without FCs) of cuboidal cells with small round apically located nuclei and finely granular oncocytic cytoplasm. Specific diagnosis of PRNRP on cytology or CNB is feasible along with use of ancillary tests IHC and /or molecular tests.

New Therapies in Melanoma: Current Trends, Evolving Paradigms, and Future Perspectives.

Melanoma is an aggressive skin cancer with increasing incidence and mortality worldwide. For many years the therapeutic strategies were limited to surgery, radiotherapy, and chemotherapy. Recent advances in immunology and cancer biology have led to the discovery and development of novel therapeutics, such as immune checkpoint inhibitors (ICIs) and targeted therapies, which have revolutionized the clinical care of patients with metastatic melanoma. Despite recent successes with ICIs, many melanoma patients do not experience long-term benefits from ICI therapies, highlighting the need for alternative treatments with novel targets such as lymphocyte-activated gene 3 (LAG-3). In this review, we explore new therapeutic agents and novel combinations that are being tested in early-phase clinical trials. We discuss newer promising tools such as nanotechnology to develop nanosystems that act as drug carriers and/or light absorbents to potentially improve therapy outcomes. Finally, we also highlight challenges such as management after resistance and intervention with novel immunotherapies and the lack of predictive biomarkers to stratify patients to targeted treatments after primary treatment failure.

Artificial intelligence in diagnostic pathology.

Digital pathology (DP) is being increasingly employed in cancer diagnostics, providing additional tools for faster, higher-quality, accurate diagnosis. The practice of diagnostic pathology has gone through a staggering transformation wherein new tools such as digital imaging, advanced artificial intelligence (AI) algorithms, and computer-aided diagnostic techniques are being used for assisting, augmenting and empowering the computational histopathology and AI-enabled diagnostics. This is paving the way for advancement in precision medicine in cancer. Automated whole slide imaging (WSI) scanners are now rendering diagnostic quality, high-resolution images of entire glass slides and combining these images with innovative digital pathology tools is making it possible to integrate imaging into all aspects of pathology reporting including anatomical, clinical, and molecular pathology. The recent approvals of WSI scanners for primary diagnosis by the FDA as well as the approval of prostate AI algorithm has paved the way for starting to incorporate this exciting technology for use in primary diagnosis. AI tools can provide a unique platform for innovations and advances in anatomical and clinical pathology workflows. In this review, we describe the milestones and landmark trials in the use of AI in clinical pathology with emphasis on future directions.

Comparison of four different displays for identification of select pathologic features extracted from whole slide images of surgical pathology cases.

BACKGROUND: The establishment of minimum standards for display selection for the whole slide image (WSI) interpretation has not been fully defined. Recently, pathologists have increasingly preferred using remote displays for clinical diagnostics. Our study aims to assess and compare the performance of three fixed work displays and one remote personal display in accurately identifying ten selected pathologic features integrated into WSIs. DESIGN: Hematoxylin and eosin-stained glass slides were digitized using Philips scanners. Seven practicing pathologists and three residents reviewed ninety WSIs to identify ten pathologic features using the LG, Dell, and Samsung and an optional consumer-grade display. Ten pathologic features included eosinophils, neutrophils, plasma cells, granulomas, necrosis, mucin, hemosiderin, crystals, nucleoli, and mitoses. RESULTS: The accuracy of the identification of ten features on different types of displays did not significantly differ among the three types of "fixed" workplace displays. The highest accuracy was observed for the identification of neutrophils, eosinophils, plasma cells, granuloma, and mucin. On the other hand, a lower accuracy was observed for the identification of crystals, mitoses, necrosis, hemosiderin, and nucleoli. Participant pathologists and residents preferred the use of larger displays (>30″) with a higher pixel count, resolution, and luminance. CONCLUSION: Most features can be identified using any display. However, certain features posed more challenges across the three fixed display types. Furthermore, the use of a remote personal consumer-grade display chosen according to the pathologists' preference showed similar feature identification accuracy. Several factors of display characteristics seemed to influence pathologists' display preferences such as the display size, color, contrast ratio, pixel count, and luminance calibration. This study supports the use of standard "unlocked" vendor-agnostic displays for clinical digital pathology workflow rather than purchasing "locked" and more expensive displays that are part of a digital pathology system.

Weakly Supervised AI for Efficient Analysis of 3D Pathology Samples.

Human tissue consists of complex structures that display a diversity of morphologies, forming a tissue microenvironment that is, by nature, three-dimensional (3D). However, the current standard-of-care involves slicing 3D tissue specimens into two-dimensional (2D) sections and selecting a few for microscopic evaluation1,2, with concomitant risks of sampling bias and misdiagnosis3-6. To this end, there have been intense efforts to capture 3D tissue morphology and transition to 3D pathology, with the development of multiple high-resolution 3D imaging modalities7-18. However, these tools have had little translation to clinical practice as manual evaluation of such large data by pathologists is impractical and there is a lack of computational platforms that can efficiently process the 3D images and provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy12-14 or microcomputed tomography15,16 and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting that there is value in capturing larger extents of spatially heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, MAMBA provides a general and efficient framework for 3D weakly supervised learning for clinical decision support and can help to reveal novel 3D morphological biomarkers for prognosis and therapeutic response.

Whole Slide Imaging Technology and Its Applications: Current and Emerging Perspectives.

Background. Whole slide imaging (WSI) represents a paradigm shift in pathology, serving as a necessary first step for a wide array of digital tools to enter the field. It utilizes virtual microscopy wherein glass slides are converted into digital slides and are viewed by pathologists by automated image analysis. Its impact on pathology workflow, reproducibility, dissemination of educational material, expansion of service to underprivileged areas, and institutional collaboration exemplifies a significant innovative movement. The recent US Food and Drug Administration approval to WSI for its use in primary surgical pathology diagnosis has opened opportunities for wider application of this technology in routine practice. Main Text. The ongoing technological advances in digital scanners, image visualization methods, and the integration of artificial intelligence-derived algorithms with these systems provide avenues to exploit its applications. Its benefits are innumerable such as ease of access through the internet, avoidance of physical storage space, and no risk of deterioration of staining quality or breakage of slides to name a few. Although the benefits of WSI to pathology practices are many, the complexities of implementation remain an obstacle to widespread adoption. Some barriers including the high cost, technical glitches, and most importantly professional hesitation to adopt a new technology have hindered its use in routine pathology. Conclusions. In this review, we summarize the technical aspects of WSI, its applications in diagnostic pathology, training, and research along with future perspectives. It also highlights improved understanding of the current challenges to implementation, as well as the benefits and successes of the technology. WSI provides a golden opportunity for pathologists to guide its evolution, standardization, and implementation to better acquaint them with the key aspects of this technology and its judicial use. Also, implementation of routine digital pathology is an extra step requiring resources which (currently) does not usually result increased efficiency or payment.

Multifaceted Spindle Cell/Sclerosing Rhabdomyosarcoma With Role of Immunohistochemistry in Avoiding Misdiagnosis: A Multi-Institutional Study of 45 Distinct Tumors.

Background. Spindle cell/sclerosing rhabdomyosarcoma is a rare neoplasm and has an aggressive clinical course. Because of its rarity, we performed a multi-institutional collaboration to comprehend the overarching clinical, histopathological, and immunohistochemical characteristics of a cohort of spindle cell/sclerosing rhabdomyosarcoma. Materials and Methods. Forty-five patients with spindle cell/sclerosing rhabdomyosarcoma were identified. Demographics, clinical, histopathological, and immunohistochemistry data were reviewed and recorded. Results. The patients' age ranged from 1 to 85 years with a male to female ratio of 1.2:1. There were 15 children/adolescents and 30 adults. Eighteen (40%) tumors were located in the head and neck region. Twenty-four (53%) tumors displayed a bimorphic cellular arrangement with hypercellular areas having short, long, and sweeping fascicular and herringbone pattern, and hypocellular areas with stromal sclerosis and associated hyalinized and/or chondromyxoid matrix. Histomorphological differentials considered were leiomyosarcoma, malignant peripheral nerve sheath tumor, fibrosarcoma, nodular fasciitis, liposarcoma, synovial sarcoma, sarcomatoid carcinoma, solitary fibrous tumor, dermatofibrosarcoma protuberans, and schwannoma. Six tumors exhibited marked stromal sclerosis. The myogenic nature was confirmed by immunohistochemistry. Positivity for at least one skeletal muscle-associated marker (MyoD1 and/or myogenin) was observed. Conclusion. Spindle cell/sclerosing rhabdomyosarcoma diagnosis can be challenging as a number of malignant spindle cell neoplasm mimic this entity. Thus a correct diagnosis requires immunohistochemical work up with a broad panel of antibodies. In view of rarity of this neoplasm, further studies on a large cohort of patients with clinical follow-up data are needed for a better understanding of this tumor.

Diagnostic Utility of GATA3 and ISL1 in Differentiating Neuroblastoma From Other Pediatric Malignant Small Round Blue Cell Tumors.

Accurate diagnosis of neuroblastoma may be challenging, especially with limited or inadequate specimen and at the metastatic sites due to overlapping imaging, histopathologic, and immunohistochemical (immunohistochemistry [IHC]; infidelity among various lineage-associated transcription factors eg FLI1, transducin-like enhancer 1, etc) features. GATA3 and ISL1 have recently been described as markers of neuroblastic differentiation. This study aims at determining the diagnostic utility of GATA3 and ISL1 in differentiating neuroblastoma from other pediatric malignant small round blue cell tumors.We evaluated GATA3 and ISL1 expression in 74 pediatric small round blue cell tumors that included 23 NMYC-amplified neuroblastomas, 11 EWSR1-rearranged round cell sarcomas, 7 SYT::SSX1-rearranged synovial sarcomas, 5 embryonal rhabdomyosarcomas, 10 Wilms tumors (nephroblastomas), 7 lymphoblastic lymphoma, 7 medulloblastoma, and 4 desmoplastic small round cell tumor.All 23 neuroblastomas (moderate to strong staining in >50% of the tumor cells), 5 T-lymphoblastic lymphomas (moderate to strong staining in 40%-90% of the tumor cells), and 2 desmoplastic small round cell tumors (weak to moderate staining in 20%-30% of the tumor cells) expressed GATA3, while other tumors were negative. ISL1 immunoreactivity was observed in 22 (96%) neuroblastomas (strong staining in in >50% of the tumor cells, n = 17; moderate to strong staining in 26%-50% of the tumor cells, n = 5), 3 embryonal rhabdomyosarcoma (moderate to strong staining in 30%-85% of the tumor cells), 1 synovial sarcoma (weak staining in 20% of the tumor cells), and 7 medulloblastoma (strong staining in 60%-90% of the tumor cells). Other tumors were negative. Overall, GATA3 showed 86% specificity, 100% sensitivity, and 90% accuracy for neuroblastoma, with a positive predictive value (PPV) and negative predictive value (NPV) of 77% and 100%, respectively. ISLI showed 72% specificity, 96% sensitivity, and 81% accuracy for neuroblastoma, with a PPV and NPV of 67% and 97%, respectively. After the exclusion of T-lymphoblastic lymphoma and desmoplastic small round cell tumors, GATA3 had 100% specificity, sensitivity, accuracy, and PPV and NPV for neuroblastoma. Similarly, in pediatric small round blue cell tumors, ISL1 had 100% specificity, sensitivity, accuracy, PPV, and NPV for neuroblastoma, after embryonal rhabdomyosarcoma, synovial sarcoma, and medulloblastoma were excluded. CONCLUSIONS: GATA3 and ISL1 may be valuable in the diagnostic work-up of neuroblastoma and may reliably be used to support the neuroblastic lineage of pediatric small round blue cell tumors. Furthermore, dual positivity helps in challenging scenarios, when there is equivocal imaging, overlapping IHC features, limited specimen, and the lack of facility for a molecular work up.

SOX17 is a highly sensitive and specific marker for metastatic ovarian and endometrial carcinomas in cytology cell block specimens.

BACKGROUND: SOX17 (SRY-box transcription factor 17) was recently identified as a highly sensitive and specific marker for ovarian and endometrial carcinomas in surgical specimens. In this study, validation of the utility of SOX17 immunohistochemistry (IHC) in diagnosing metastatic gynecologic carcinomas in cytology specimens was sought. METHODS: The study cohort included 84 cases of metastatic carcinomas that included 29 metastatic gynecologic carcinomas (24 ovarian high-grade serous carcinomas, two endometrial serous carcinomas, one low-grade serous carcinoma, one ovarian clear cell carcinoma, and one endometrial endometrioid carcinoma) and 55 cases of metastatic nongynecologic carcinomas (10 clear cell renal cell carcinomas, 10 papillary thyroid carcinomas, 11 gastrointestinal adenocarcinomas, 10 breast carcinomas, 10 lung adenocarcinomas, and four urothelial carcinomas). Cytology specimen types included peritoneal fluid (n = 44), pleural fluid (n = 25), and fine-needle aspiration (n = 15). SOX17 IHC was performed on the cell block sections. The intensity of staining and percent positivity of the tumor cells were evaluated. RESULTS: SOX17 was highly expressed in all tested metastatic gynecologic carcinomas with diffuse and strong nuclear expression (29 of 29; 100%). SOX17 was negative in other metastatic nongynecologic carcinomas (54 of 55; 98.18%) except for one papillary thyroid carcinoma that showed low positivity (<10%). CONCLUSIONS: SOX17 is a highly sensitive (100%) and specific (98.2%) marker for the differential diagnosis of metastatic gynecologic carcinomas in cytology specimens. Therefore, SOX17 IHC should be included in the workup of differential diagnosis of metastatic gynecologic carcinomas in cytology specimens.

Artificial Intelligence-Aided Diagnosis of Breast Cancer Lymph Node Metastasis on Histologic Slides in a Digital Workflow.

Identifying lymph node (LN) metastasis in invasive breast carcinoma can be tedious and time-consuming. We investigated an artificial intelligence (AI) algorithm to detect LN metastasis by screening hematoxylin and eosin (H&E) slides in a clinical digital workflow. The study included 2 sentinel LN (SLN) cohorts (a validation cohort with 234 SLNs and a consensus cohort with 102 SLNs) and 1 nonsentinel LN cohort (258 LNs enriched with lobular carcinoma and postneoadjuvant therapy cases). All H&E slides were scanned into whole slide images in a clinical digital workflow, and whole slide images were automatically batch-analyzed using the Visiopharm Integrator System (VIS) metastasis AI algorithm. For the SLN validation cohort, the VIS metastasis AI algorithm detected all 46 metastases, including 19 macrometastases, 26 micrometastases, and 1 with isolated tumor cells with a sensitivity of 100%, specificity of 41.5%, positive predictive value of 29.5%, and negative predictive value (NPV) of 100%. The false positivity was caused by histiocytes (52.7%), crushed lymphocytes (18.2%), and others (29.1%), which were readily recognized during pathologists' reviews. For the SLN consensus cohort, 3 pathologists examined all VIS AI annotated H&E slides and cytokeratin immunohistochemistry slides with similar average concordance rates (99% for both modalities). However, the average time consumed by pathologists using VIS AI annotated slides was significantly less than using immunohistochemistry slides (0.6 vs 1.0 minutes, P = .0377). For the nonsentinel LN cohort, the AI algorithm detected all 81 metastases, including 23 from lobular carcinoma and 31 from postneoadjuvant chemotherapy cases, with a sensitivity of 100%, specificity of 78.5%, positive predictive value of 68.1%, and NPV of 100%. The VIS AI algorithm showed perfect sensitivity and NPV in detecting LN metastasis and less time consumed, suggesting its potential utility as a screening modality in routine clinical digital pathology workflow to improve efficiency.

Incidence, Clinicopathologic Features, HER2 Fluorescence In Situ Hybridization Profile, and Oncotype DX Results of Human Epidermal Growth Factor Receptor 2-Low Breast Cancers: Experience From a Single Academic Center.

Human epidermal growth factor receptor 2 (HER2)-low breast cancer, defined by an immunohistochemical (IHC) score of 1+ or 2+ with negative in situ hybridization, is emerging as a predictive marker for the use of the antibody-drug conjugate. To understand how this category differs from HER2-zero cases, we investigated clinicopathological characteristics and HER2 fluorescence in situ hybridization results in a large cohort of 1309 continuous HER2-negative invasive breast carcinomas from 2018 to 2021 evaluated by the Food and Drug Administration-approved HER2 IHC test. Additionally, we compared Oncotype DX recurrence scores and HER2 mRNA expression between HER-low and HER2-zero cases in a separate cohort of 438 estrogen receptor-positive (ER+) early-stage breast carcinoma cases from 2014 to 2016. Based on the cohort from 2018 to 2021, the incidence of HER2-low breast cancers was approximately 54%. HER2-low cases had less frequent grade 3 morphology, less frequent triple-negative results, ER and progesterone receptor negativity, and a higher mean HER2 copy number and HER2/CEP17 ratio than HER2-zero cases (P < .0001). Among ER+ cases, HER2-low cases showed significantly less frequent Nottingham grade 3 tumors. In the cohort from 2014 to 2016, HER2-low cases showed significantly higher ER+ percentages, fewer progesterone receptor-negative cases, lower Oncotype DX recurrence scores, and higher HER2 mRNA expression scores than HER2-zero cases. In summary, this is the first study, to our knowledge, using a large cohort of continuous cases evaluated by the Food and Drug Administration-approved HER2 IHC companion diagnostic test for HER2-low expression and HER2 fluorescence in situ hybridization profile in a real-world setting. Although HER2-low cases showed a higher HER2 copy number, ratio, and mRNA level than HER2-zero cases statistically, such small differences are unlikely to be biologically or clinically meaningful. However, our study suggests that HER2-low/ER+ early-stage breast carcinoma may represent a less aggressive group of breast carcinoma, given its association with a lower Nottingham grade and Oncotype DX recurrence score.