Assessment of mitotic activity in breast cancer: revisited in the digital pathology era

CNMI-YOLO: Domain Adaptive and Robust Mitosis Identification in Digital Pathology

In digital pathology, accurate mitosis detection in histopathological images is critical for cancer diagnosis and prognosis. However, this remains challenging due to the inherent variability in cell morphology and the domain shift problem. This study introduces CNMI-YOLO (ConvNext Mitosis Identification-YOLO), a new two-stage deep learning method that uses the YOLOv7 architecture for cell detection and the ConvNeXt architecture for cell classification. The goal is to improve the identification of mitosis in different types of cancer. We utilized the MIDOG 2022 dataset in the experiments to ensure the model's robustness and success across various scanners, species, and cancer types. The CNMI-YOLO model demonstrates superior performance in accurately detecting mitotic cells, significantly outperforming existing models in terms of precision, recall, and F1-score. The CNMI-YOLO model achieved an F1-score of 0.795 on the MIDOG 2022 and demonstrated robust generalization with F1-scores of 0.783 and 0.759 on the external melanoma and sarcoma test sets, respectively. Additionally, the study included ablation studies to evaluate various object detection and classification models, such as Faster R-CNN and Swin Transformer. Furthermore, we assessed the model's robustness performance on unseen data, confirming its ability to generalize and its potential for real-world use in digital pathology, using soft tissue sarcoma and melanoma samples not included in the training dataset.

Domain generalization across tumor types, laboratories, and species - Insights from the 2022 edition of the Mitosis Domain Generalization Challenge

Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking.

Mitosis detection, fast and slow: Robust and efficient detection of mitotic figures

Counting of mitotic figures is a fundamental step in grading and prognostication of several cancers. However, manual mitosis counting is tedious and time-consuming. In addition, variation in the appearance of mitotic figures causes a high degree of discordance among pathologists. With advances in deep learning models, several automatic mitosis detection algorithms have been proposed but they are sensitive to domain shift often seen in histology images. We propose a robust and efficient two-stage mitosis detection framework, which comprises mitosis candidate segmentation (Detecting Fast) and candidate refinement (Detecting Slow) stages. The proposed candidate segmentation model, termed EUNet, is fast and accurate due to its architectural design. EUNet can precisely segment candidates at a lower resolution to considerably speed up candidate detection. Candidates are then refined using a deeper classifier network, EfficientNet-B7, in the second stage. We make sure both stages are robust against domain shift by incorporating domain generalization methods. We demonstrate state-of-the-art performance and generalizability of the proposed model on the three largest publicly available mitosis datasets, winning the two mitosis domain generalization challenge contests (MIDOG21 and MIDOG22). Finally, we showcase the utility of the proposed algorithm by processing the TCGA breast cancer cohort (1,124 whole-slide images) to generate and release a repository of more than 620K potential mitotic figures (not exhaustively validated).

Invisible for a few but essential for many: the role of Histotechnologists in the establishment of digital pathology

Digital pathology (DP) is indisputably the future for histopathology laboratories. The process of digital implementation requires deep workflow reorganisation which involves an interdisciplinary team. This transformation may have the greatest impact on the Histotechnologist (HTL) profession. Our review of the literature has clearly revealed that the role of HTLs in the establishment of DP is being unnoticed and guidance is limited. This article aims to bring HTLs from behind-the-scenes into the spotlight. Our objective is to provide them guidance and practical recommendations to successfully contribute to the implementation of a new digital workflow. Furthermore, it also intends to contribute for improvement of study programs, ensuring the role of HTL in DP is addressed as part of graduate and post-graduate education. In our review, we report on the differences encountered between workflow schemes and the limitations observed in this process. The authors propose a digital workflow to achieve its limitless potential, focusing on the HTL's role. This article explores the novel responsibilities of HTLs during specimen gross dissection, embedding, microtomy, staining, digital scanning, and whole slide image quality control. Furthermore, we highlight the benefits and challenges that DP implementation might bring the HTLs career. HTLs have an important role in the digital workflow: the responsibility of achieving the perfect glass slide.

Artificial Intelligence-Based Mitosis Scoring in Breast Cancer: Clinical Application

In recent years, artificial intelligence (AI) has demonstrated exceptional performance in mitosis identification and quantification. However, the implementation of AI in clinical practice needs to be evaluated against the existing methods. This study is aimed at assessing the optimal method of using AI-based mitotic figure scoring in breast cancer (BC). We utilized whole slide images from a large cohort of BC with extended follow-up comprising a discovery (n = 1715) and a validation (n = 859) set (Nottingham cohort). The Cancer Genome Atlas of breast invasive carcinoma (TCGA-BRCA) cohort (n = 757) was used as an external test set. Employing automated mitosis detection, the mitotic count was assessed using 3 different methods, the mitotic count per tumor area (MCT; calculated by dividing the number of mitotic figures by the total tumor area), the mitotic index (MI; defined as the average number of mitotic figures per 1000 malignant cells), and the mitotic activity index (MAI; defined as the number of mitotic figures in 3 mm2 area within the mitotic hotspot). These automated metrics were evaluated and compared based on their correlation with the well-established visual scoring method of the Nottingham grading system and Ki67 score, clinicopathologic parameters, and patient outcomes. AI-based mitotic scores derived from the 3 methods (MCT, MI, and MAI) were significantly correlated with the clinicopathologic characteristics and patient survival (P < .001). However, the mitotic counts and the derived cutoffs varied significantly between the 3 methods. Only MAI and MCT were positively correlated with the gold standard visual scoring method used in Nottingham grading system (r = 0.8 and r = 0.7, respectively) and Ki67 scores (r = 0.69 and r = 0.55, respectively), and MAI was the only independent predictor of survival (P < .05) in multivariate Cox regression analysis. For clinical applications, the optimum method of scoring mitosis using AI needs to be considered. MAI can provide reliable and reproducible results and can accurately quantify mitotic figures in BC.

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.

A novel dilated contextual attention module for breast cancer mitosis cell detection

Background and object: Mitotic count (MC) is a critical histological parameter for accurately assessing the degree of invasiveness in breast cancer, holding significant clinical value for cancer treatment and prognosis. However, accurately identifying mitotic cells poses a challenge due to their morphological and size diversity. Objective: We propose a novel end-to-end deep-learning method for identifying mitotic cells in breast cancer pathological images, with the aim of enhancing the performance of recognizing mitotic cells. Methods: We introduced the Dilated Cascading Network (DilCasNet) composed of detection and classification stages. To enhance the model's ability to capture distant feature dependencies in mitotic cells, we devised a novel Dilated Contextual Attention Module (DiCoA) that utilizes sparse global attention during the detection. For reclassifying mitotic cell areas localized in the detection stage, we integrate the EfficientNet-B7 and VGG16 pre-trained models (InPreMo) in the classification step. Results: Based on the canine mammary carcinoma (CMC) mitosis dataset, DilCasNet demonstrates superior overall performance compared to the benchmark model. The specific metrics of the model's performance are as follows: F1 score of 82.9%, Precision of 82.6%, and Recall of 83.2%. With the incorporation of the DiCoA attention module, the model exhibited an improvement of over 3.5% in the F1 during the detection stage. Conclusion: The DilCasNet achieved a favorable detection performance of mitotic cells in breast cancer and provides a solution for detecting mitotic cells in pathological images of other cancers.

Single-cell DNA replication dynamics in genomically unstable cancers

Dysregulated DNA replication is both a cause and a consequence of aneuploidy, yet the dynamics of DNA replication in aneuploid cell populations remains understudied. We developed a new method, PERT, for inferring cell-specific DNA replication states from single-cell whole genome sequencing, and investigated clone-specific DNA replication dynamics in >50,000 cells obtained from a collection of aneuploid and clonally heterogeneous cell lines, xenografts and primary cancer tissues. Clone replication timing (RT) profiles correlated with future copy number changes in serially passaged cell lines. Cell type was the strongest determinant of RT heterogeneity, while whole genome doubling and mutational process were associated with accumulation of late S-phase cells and weaker RT associations. Copy number changes affecting chromosome X had striking impact on RT, with loss of the inactive X allele shifting replication earlier, and loss of inactive Xq resulting in reactivation of Xp. Finally, analysis of time series xenografts illustrate how cell cycle distributions approximate clone proliferation, recapitulating expected relationships between proliferation and fitness in treatment-naive and chemotherapeutic contexts.

A comprehensive multi-domain dataset for mitotic figure detection

The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species.

Update on C-Cell Neuroendocrine Neoplasm: Prognostic and Predictive Histopathologic and Molecular Features of Medullary Thyroid Carcinoma

Medullary thyroid carcinoma (MTC) is a C-cell-derived epithelial neuroendocrine neoplasm. With the exception of rare examples, most are well-differentiated epithelial neuroendocrine neoplasms (also known as neuroendocrine tumors in the taxonomy of the International Agency for Research on Cancer [IARC] of the World Health Organization [WHO]). This review provides an overview and recent evidence-based data on the molecular genetics, disease risk stratification based on clinicopathologic variables including molecular profiling and histopathologic variables, and targeted molecular therapies in patients with advanced MTC. While MTC is not the only neuroendocrine neoplasm in the thyroid gland, other neuroendocrine neoplasms in the thyroid include intrathyroidal thymic neuroendocrine neoplasms, intrathyroidal parathyroid neoplasms, and primary thyroid paragangliomas as well as metastatic neuroendocrine neoplasms. Therefore, the first responsibility of a pathologist is to distinguish MTC from other mimics using appropriate biomarkers. The second responsibility includes meticulous assessment of the status of angioinvasion (defined as tumor cells invading through a vessel wall and forming tumor-fibrin complexes, or intravascular tumor cells admixed with fibrin/thrombus), tumor necrosis, proliferative rate (mitotic count and Ki67 labeling index), and tumor grade (low- or high-grade) along with the tumor stage and the resection margins. Given the morphologic and proliferative heterogeneity in these neoplasms, an exhaustive sampling is strongly recommended. Routine molecular testing for pathogenic germline RET variants is typically performed in all patients with a diagnosis of MTC; however, multifocal C-cell hyperplasia in association with at least a single focus of MTC and/or multifocal C-cell neoplasia are morphological harbingers of germline RET alterations. It is of interest to assess the status of pathogenic molecular alterations involving genes other than RET like the MET variants in MTC families with no pathogenic germline RET variants. Furthermore, the status of somatic RET alterations should be determined in all advanced/progressive or metastatic diseases, especially when selective RET inhibitor therapy (e.g., selpercatinib or pralsetinib) is considered. While the role of routine SSTR2/5 immunohistochemistry remains to be further clarified, evidence suggests that patients with somatostatin receptor (SSTR)-avid metastatic disease may also benefit from the option of ¹⁷⁷Lu-DOTATATE peptide radionuclide receptor therapy. Finally, the authors of this review make a call to support the nomenclature change of MTC to C-cell neuroendocrine neoplasm to align this entity with the IARC/WHO taxonomy since MTCs represent epithelial neuroendocrine neoplasms of endoderm-derived C-cells.

Expression, assessment and significance of Ki67 expression in breast cancer: an update

Ki67 expression is one of the most important and cost-effective surrogate markers to assess for tumour cell proliferation in breast cancer (BC). The Ki67 labelling index has prognostic and predictive value in patients with early-stage BC, particularly in the hormone receptor-positive, HER2 (human epidermal growth factor receptor 2)-negative (luminal) tumours. However, many challenges exist in using Ki67 in routine clinical practice and it is still not universally used in the clinical setting. Addressing these challenges can potentially improve the clinical utility of Ki67 in BC. In this article, we review the function, immunohistochemical (IHC) expression, methods for scoring and interpretation of results as well as address several challenges of Ki67 assessment in BC. The prodigious attention associated with use of Ki67 IHC as a prognostic marker in BC resulted in high expectation and overestimation of its performance. However, the realisation of some pitfalls and disadvantages, which are expected with any similar markers, resulted in an increasing criticism of its clinical use. It is time to consider a pragmatic approach and weigh the benefits against the weaknesses and identify factors to achieve the best clinical utility. Here we highlight the strengths of its performance and provide some insights to overcome the existing challenges.

Improving mitotic cell counting accuracy and efficiency using phosphohistone-H3 (PHH3) antibody counterstained with haematoxylin and eosin as part of breast cancer grading

BACKGROUND

Mitotic count in breast cancer is an important prognostic marker. Unfortunately, substantial inter- and intraobserver variation exists when pathologists manually count mitotic figures. To alleviate this problem, we developed a new technique incorporating both haematoxylin and eosin (H&E) and phosphorylated histone H3 (PHH3), a marker highly specific to mitotic figures, and compared it to visual scoring of mitotic figures using H&E only.

METHODS

Two full-face sections from 97 cases were cut, one stained with H&E only, and the other was stained with PHH3 and counterstained with H&E (PHH3-H&E). Counting mitoses using PHH3-H&E was compared to traditional mitoses scoring using H&E in terms of reproducibility, scoring time, and the ability to detect mitosis hotspots. We assessed the agreement between manual and image analysis-assisted scoring of mitotic figures using H&E and PHH3-H&E-stained cells. The diagnostic performance of PHH3 in detecting mitotic figures in terms of sensitivity and specificity was measured. Finally, PHH3 replaced the mitosis score in a multivariate analysis to assess its significance.

RESULTS

Pathologists detected significantly higher mitotic figures using the PHH3-H&E (median ± SD, 20 ± 33) compared with H&E alone (median ± SD, 16 ± 25), P < 0.001. The concordance between pathologists in identifying mitotic figures was highest when using the dual PHH3-H&E technique; in addition, it highlighted mitotic figures at low power, allowing better agreement on choosing the hotspot area (k = 0.842) in comparison with standard H&E (k = 0.625). A better agreement between image analysis-assisted software and the human eye was observed for PHH3-stained mitotic figures. When the mitosis score was replaced with PHH3 in a Cox regression model with other grade components, PHH3 was an independent predictor of survival (hazard ratio [HR] 5.66, 95% confidence interval [CI] 1.92-16.69; P = 0.002), and even showed a more significant association with breast cancer-specific survival (BCSS) than mitosis (HR 3.63, 95% CI 1.49-8.86; P = 0.005) and Ki67 (P = 0.27).

CONCLUSION

Using PHH3-H&E-stained slides can reliably be used in routine scoring of mitotic figures and integrating both techniques will compensate for each other's limitations and improve diagnostic accuracy, quality, and precision.

An international unified approach to reporting and grading invasive breast cancer. An overview of the International Collaboration on Cancer Reporting (ICCR) initiative

Standardised reporting of breast cancer key pathology data has become the norm in some parts of the world, but are based on national or regional guidelines that differ in certain aspects, resulting in divergent reporting practices and a lack of comparability of data internationally. The International Collaboration on Cancer Reporting (ICCR), a global alliance of major (inter-)national pathology and cancer organizations, have recently produced a new international dataset for the pathology reporting of breast cancer, including resection specimens with invasive cancer and ductal carcinoma in situ (DCIS) of the breast. This initiative aims at providing an international unified approach to reporting cancer. The guidance was prepared by an international expert panel consisting of experienced breast pathologists, a surgeon, and an oncologist. The dataset includes core (essential) and noncore (optional) data items based on a critical review and discussion of current evidence. Commentary is provided for each data item to explain the rationale for selection, its clinical relevance, and to highlight potential areas of disagreement or lack of evidence, in which case a consensus position was formulated. The process concludes with international public consultation, before ratification and publication on the free open access ICCR website, with a synoptic reporting guide. The key aim is to promote high-quality, standardised pathology reporting that can be used worldwide. Histological grade, tumour size, and oestrogen receptor status are used in this article to illustrate this process and the detail provided to support its inclusion.

Artificial intelligence-based multi-omics analysis fuels cancer precision medicine

With biotechnological advancements, innovative omics technologies are constantly emerging that have enabled researchers to access multi-layer information from the genome, epigenome, transcriptome, proteome, metabolome, and more. A wealth of omics technologies, including bulk and single-cell omics approaches, have empowered to characterize different molecular layers at unprecedented scale and resolution, providing a holistic view of tumor behavior. Multi-omics analysis allows systematic interrogation of various molecular information at each biological layer while posing tricky challenges regarding how to extract valuable insights from the exponentially increasing amount of multi-omics data. Therefore, efficient algorithms are needed to reduce the dimensionality of the data while simultaneously dissecting the mysteries behind the complex biological processes of cancer. Artificial intelligence has demonstrated the ability to analyze complementary multi-modal data streams within the oncology realm. The coincident development of multi-omics technologies and artificial intelligence algorithms has fuelled the development of cancer precision medicine. Here, we present state-of-the-art omics technologies and outline a roadmap of multi-omics integration analysis using an artificial intelligence strategy. The advances made using artificial intelligence-based multi-omics approaches are described, especially concerning early cancer screening, diagnosis, response assessment, and prognosis prediction. Finally, we discuss the challenges faced in multi-omics analysis, along with tentative future trends in this field. With the increasing application of artificial intelligence in multi-omics analysis, we anticipate a shifting paradigm in precision medicine becoming driven by artificial intelligence-based multi-omics technologies.

Multiparametric Classification of Non-Muscle Invasive Papillary Urothelial Neoplasms: Combining Morphological, Phenotypical, and Molecular Features for Improved Risk Stratification

Diagnosis and grading of non-invasive papillary urothelial tumors according to the current WHO classification poses some challenges for pathologists. The diagnostic reproducibility of separating low-grade and high-grade lesions is low, which impacts their clinical management. Whereas papillary urothelial neoplasms with low malignant potential (PUN-LMP) and low-grade papillary non-invasive carcinoma (LG-PUC) are comparable and show frequent local recurrence but rarely metastasize, high-grade papillary non-invasive carcinoma (HG-PUC) has a poor prognosis. The main objective of this work is to develop a multiparametric classification to unambiguously distinguish low-grade and high-grade tumors, considering immunohistochemical stains for p53, FGFR3, CK20, MIB-1, p16, p21 and p-HH3, and pathogenic mutations in TP53, FGFR3, TP53, ERCC2, PIK3CA, PTEN and STAG2. We reviewed and analyzed the clinical and histological data of 45 patients with a consensus diagnosis of PUN-LMP (n = 8), non-invasive LG-PUC (n = 23), and HG-PUC (n = 14). The proliferation index and mitotic count assessed with MIB-1 and P-HH3 staining, respectively correlated with grading and clinical behavior. Targeted sequencing confirmed frequent FGFR3 mutations in non-invasive papillary tumors and identified mutations in TP53 as high-risk. Cluster analysis of the different immunohistochemical and molecular parameters allowed a clear separation in two different clusters: cluster 1 corresponding to PUN-LMP and LG-PUC (low MIB-1 and mitotic count/FGFR3 and STAG2 mutations) and cluster 2, HG-PUC (high MIB-1 and mitosis count/CK20 +++ expression, FGFR3 WT and TP53 mutation). Further analysis is required to validate and analyze the reproducibility of these clusters and their biological and clinical implication.

The characteristics and clinical significance of atypical mitosis in breast cancer

Atypical mitosis is considered a feature of malignancy, however, its significance in breast cancer (BC) remains elusive. Here, we aimed to assess the clinical value of atypical mitoses in BC and to explore their underlying molecular features. Atypical and typical mitotic figures were quantified and correlated with clinicopathological variables in a large cohort of primary BC tissue sections (n = 846) using digitalized hematoxylin and eosin whole-slide images (WSIs). In addition, atypical mitoses were assessed in The Cancer Genome Atlas (TCGA) BC dataset (n = 1032) and were linked to the genetic alterations and pathways. In this study, the median of typical mitoses was 17 per 3 mm² (range 0-120 mitoses), while the median of atypical mitoses was 4 (range 0-103 mitoses). High atypical mitoses were significantly associated with parameters characteristic of aggressive tumor behavior. The total number of mitoses, and a high atypical-to-typical mitoses ratio (>0.27) were associated with poor BC specific survival (BCSS), (p = 0.04 and 0.01, respectively). The atypical-to-typical mitoses ratio dichotomized triple negative-BC (TNBC) patients into two distinct groups in terms of the association with the outcome, while the overall number of mitoses was not. Moreover, TNBC patients with high atypical-to-typical mitoses ratio treated with adjuvant chemotherapy were associated with shorter survival (p = 0.003). Transcriptomic analysis of the TCGA-BRCA cohort dichotomized based on atypical mitoses identified 2494 differentially expressed genes. These included genes linked to pathways involved in chromosomal localization and segregation, centrosome assembly, spindle and microtubule formation, regulation of cell cycle and DNA repair. To conclude, the atypical-to-typical mitoses ratio has prognostic value independent of the overall mitotic count in BC patients and could predict the response to chemotherapy in TNBC.