Evaluation of AI-based Gleason grading algorithms "in the wild".

The biopsy Gleason score is an important prognostic marker for prostate cancer patients. It is, however, subject to substantial variability among pathologists. Artificial intelligence (AI)-based algorithms employing deep learning have shown their ability to match pathologists' performance in assigning Gleason scores, with the potential to enhance pathologists' grading accuracy. The performance of Gleason AI algorithms in research is mostly reported on common benchmark datasets or within public challenges. In contrast, many commercial algorithms are evaluated in clinical studies, for which data is not publicly released. As commercial AI vendors typically do not publish performance on public benchmarks, comparison between research and commercial AI is difficult. The aim of this study is to evaluate and compare the performance of top-ranked public and commercial algorithms using real-world data. We curated a diverse dataset of whole-slide prostate biopsy images through crowdsourcing, containing images with a range of Gleason scores and from diverse sources. Predictions were obtained from five top-ranked public algorithms from the PANDA challenge and from two commercial Gleason grading algorithms. Additionally, ten pathologists evaluated the data set in a reader study. Overall, the pairwise quadratic weighted kappa among pathologists ranged from 0.777 to 0.916. Both public and commercial algorithms showed high agreement with pathologists, with quadratic kappa ranging from 0.617 to 0.900. Commercial algorithms performed on par or outperformed top public algorithms.

Artificial Intelligence Helps Pathologists Increase Diagnostic Accuracy and Efficiency in the Detection of Breast Cancer Lymph Node Metastases.

The detection of lymph node metastases is essential for breast cancer staging, although it is a tedious and time-consuming task where the sensitivity of pathologists is suboptimal. Artificial intelligence (AI) can help pathologists detect lymph node metastases, which could help alleviate workload issues. We studied how pathologists' performance varied when aided by AI. An AI algorithm was trained using more than 32 000 breast sentinel lymph node whole slide images (WSIs) matched with their corresponding pathology reports from more than 8000 patients. The algorithm highlighted areas suspicious of harboring metastasis. Three pathologists were asked to review a dataset comprising 167 breast sentinel lymph node WSIs, of which 69 harbored cancer metastases of different sizes, enriched for challenging cases. Ninety-eight slides were benign. The pathologists read the dataset twice, both digitally, with and without AI assistance, randomized for slide and reading orders to reduce bias, separated by a 3-week washout period. Their slide-level diagnosis was recorded, and they were timed during their reads. The average reading time per slide was 129 seconds during the unassisted phase versus 58 seconds during the AI-assisted phase, resulting in an overall efficiency gain of 55% ( P <0.001). These efficiency gains are applied to both benign and malignant WSIs. Two of the 3 reading pathologists experienced significant sensitivity improvements, from 74.5% to 93.5% ( P ≤0.006). This study highlights that AI can help pathologists shorten their reading times by more than half and also improve their metastasis detection rate.

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

CONTEXT.­: Prostate cancer diagnosis rests on accurate assessment of tissue by a pathologist. The application of artificial intelligence (AI) to digitized whole slide images (WSIs) can aid pathologists in cancer diagnosis, but robust, diverse evidence in a simulated clinical setting is lacking. OBJECTIVE.­: To compare the diagnostic accuracy of pathologists reading WSIs of prostatic biopsy specimens with and without AI assistance. DESIGN.­: Eighteen pathologists, 2 of whom were genitourinary subspecialists, evaluated 610 prostate needle core biopsy WSIs prepared at 218 institutions, with the option for deferral. Two evaluations were performed sequentially for each WSI: initially without assistance, and immediately thereafter aided by Paige Prostate (PaPr), a deep learning-based system that provides a WSI-level binary classification of suspicious for cancer or benign and pinpoints the location that has the greatest probability of harboring cancer on suspicious WSIs. Pathologists' changes in sensitivity and specificity between the assisted and unassisted modalities were assessed, together with the impact of PaPr output on the assisted reads. RESULTS.­: Using PaPr, pathologists improved their sensitivity and specificity across all histologic grades and tumor sizes. Accuracy gains on both benign and cancerous WSIs could be attributed to PaPr, which correctly classified 100% of the WSIs showing corrected diagnoses in the PaPr-assisted phase. CONCLUSIONS.­: This study demonstrates the effectiveness and safety of an AI tool for pathologists in simulated diagnostic practice, bridging the gap between computational pathology research and its clinical application, and resulted in the first US Food and Drug Administration authorization of an AI system in pathology.

Artificial Intelligence-assisted Prostate Cancer Diagnosis: Radiologic-Pathologic Correlation.

The classic prostate cancer (PCa) diagnostic pathway that is based on prostate-specific antigen (PSA) levels and the findings of digital rectal examination followed by systematic biopsy has shown multiple limitations. The use of multiparametric MRI (mpMRI) is now widely accepted in men with clinical suspicion for PCa. In addition, clinical information, PSA density, risk calculators, and genomic and other "omics" biomarkers are being used to improve risk stratification. On the basis of mpMRI and MRI-targeted biopsies (MRI-TBx), new diagnostic pathways have been established, aiming to improve the limitations of the classic diagnostic approach. However, these pathways still show limitations associated with mpMRI and MRI-TBx. Definitive PCa diagnosis is made on the basis of histopathologic Gleason grading, which has demonstrated an excellent correlation with clinical outcomes. However, Gleason grading is done subjectively by pathologists and involves poor reproducibility, and PCa may have a heterogeneous distribution of histologic patterns. Thus, important discrepancies persist between biopsy tumor grading and final whole-organ pathologic assessment after radical prostatectomy. PCa offers a unique opportunity to establish a real radiologic-pathologic correlation, as whole-mount radical prostatectomy specimens permit a complete spatial relationship with mpMRI. Artificial intelligence is increasingly being applied to radiologic and pathologic images to improve clinical accuracy and efficiency in PCa diagnosis. This review delineates current PCa diagnostic pathways, with a focus on the role of mpMRI, MRI-TBx, and pathologic analysis. An overview of the expected improvements in PCa diagnosis derived from the use of artificial intelligence, integrated radiologic-pathologic systems, and decision support tools for multidisciplinary teams is provided. An invited commentary by Purysko is available online. Online supplemental material is available for this article. ©RSNA, 2021.

Dissecting the Business Case for Adoption and Implementation of Digital Pathology: A White Paper from the Digital Pathology Association.

We believe the switch to a digital pathology (DP) workflow is imminent and it is essential to understand the economic implications of conversion. Many aspects of the adoption of DP will be disruptive and have a direct financial impact, both in short term costs, such as investment in equipment and personnel, and long term revenue potential, such as improved productivity and novel tests. The focus of this whitepaper is to educate pathologists, laboratorians and other stakeholders about the business and monetary considerations of converting to a digital pathology workflow. The components of a DP business plan will be thoroughly summarized, and guidance will be provided on how to build a case for adoption and implementation as well as a roadmap for transitioning from an analog to a digital pathology workflow in various laboratory settings. It is important to clarify that this publication is not intended to list prices although some financials will be mentioned as examples. The authors encourage readers who are evaluating conversion to a DP workflow to use this paper as a foundational guide for conducting a thorough and complete assessment while incorporating in current market pricing. Contributors to this paper analyzed peer-reviewed literature and data collected from various institutions, some of which are mentioned. Digital pathology will change the way we practice through facilitating patient access to expert pathology services and enabling image analysis tools and assays to aid in diagnosis, prognosis, risk stratification and therapeutic selection. Together, they will result in the delivery of valuable information from which to make better decisions and improve the health of patients.

Complete Digital Pathology for Routine Histopathology Diagnosis in a Multicenter Hospital Network.

CONTEXT.­: Complete digital pathology and whole slide imaging for routine histopathology diagnosis is currently in use in few laboratories worldwide. Granada University Hospitals, Spain, which comprises 4 hospitals, adopted full digital pathology for primary histopathology diagnosis in 2016. OBJECTIVE.­: To describe the methodology adopted and the resulting experience at Granada University Hospitals in transitioning to full digital diagnosis. DESIGN.­: All histopathology glass slides generated for routine diagnosis were digitized at ×40 using the Philips IntelliSite Pathology Solution, which includes an ultrafast scanner and an image management system. All hematoxylin-eosin-stained preparations and immunohistochemistry and histochemistry slides were digitized. The existing sample-tracking software and image management system were integrated to allow data interchange through the Health Level 7 protocol. RESULTS.­: Circa 160 000 specimens have been signed out using digital pathology for primary diagnosis. This comprises more than 800 000 digitized glass slides. The scanning error rate during the implementation phase was below 1.5%, and subsequent workflow optimization rendered this rate negligible. Since implementation, Granada University Hospitals pathologists have signed out 21% more cases per year on average. CONCLUSIONS.­: Digital pathology is an adequate medium for primary histopathology diagnosis. Successful digitization relies on existing sample tracking and integration of the information technology infrastructure. Rapid and reliable scanning at ×40 equivalent was key to the transition to a fully digital workflow. Digital pathology resulted in efficiency gains in the preanalytical and analytical phases, and created the basis for computational pathology: the use of computer-assisted tools to aid diagnosis.

Paquidermodactilia, engrosamiento digital proximal. Pachydermodactyly, digital proximal thickening.

We report a case of pachydermodactyly (PDD). PDD is a benign, asymptomatic soft tissue swelling affecting the skin of the lateral aspects of the proximal interphalangeal joints of the fingers, mostly in young adolescent males. It has often been interpreted as a consequence of tic-like behavior as part of an obsessive-compulsive disorder. Although the diagnosis is essentially clinical, skin biopsy shows compact orthokeratotic hyperkeratosis, increased numbers of collagen fibers and fibroblasts, and no inflammatory changes. A rapid clinical recognition of PDD should avoid many unproductive and expensive diagnostic tests.

Hobnail Hemangioma With an Unusual Clinical Presentation.

Hobnail hemangioma, also known as targetoid hemosiderotic hemangioma, is an uncommon vascular proliferation that clinically presents as a small solitary red to purple papule or macule, located on the limbs or trunk. Multiple lesions and atypical locations have been described. Histopathologically, it exhibits a biphasic pattern, with dilated vessels in the superficial dermis and angulated vessels in the deeper dermis, with endothelial cells that show a hobnail appearance. There is controversy about the histogenetic origin of hobnail hemangioma, although recent studies support that it is a lymphatic malformation. The investigators report the case of a 41-year-old man with an irregular lesion, red to purple in color, with a maximum diameter of 4 cm, on the scalp. The location and in particular the clinical appearance are uncommon. Immunohistochemical analysis showed negativity for WT1 and focal positivity for D2-40. Clinical-pathologic correlation acquires particular importance in the case of lesions with atypical clinical presentation.

Smoothelin and WT-1 expression in glomus tumors and glomuvenous malformations.

BACKGROUND: Smoothelin is a specific marker for smooth muscle cells with contractile capacity which has not been widely studied in glomus lesions. In the same way, the expression for Wilms tumor 1 (WT1) has only been studied occasionally in the endothelial cells of glomovenous malformations and in the glomus cells of glomus tumours. OBJECTIVE: We studied the significance of immunohistochemical expression of smoothelin and WT1 in 25 glomus lesions. METHODS: We assessed 9 cases of solid glomus tumors (SGT), 8 cases of glomus tumors with vascular ectasia (VEGT), 2 cases of glomangiomyomas (GMM) and 6 cases of glomuvenous malformation (GM). Immunohistochemistry was performed, evaluating the expression of WT1, smoothelin, smooth muscle actin (SMA), smooth muscle myosin (SMM), h-caldesmon and desmin. RESULTS: Glomic cells showed cytoplasmic positivity for smoothelin, and WT1 expression was present in all studied cases. SGT showed WT1 positivity in all endothelia. However, in regarding VEGT and GMM, WT1 endothelial expression was positive in some areas, but not in others. GM did not show endothelial cell positivity for WT1. CONCLUSIONS: Smoothelin expression in glomic cells indicates that they are contractile smooth muscle cells, and thus its role in routine diagnosis should be considered. The absence of WT1 expression in the endothelium of the vascular structures of the GM is a differential characteristic between SGT, VEGT and GMM.

Primary cutaneous and subcutaneous leiomyosarcomas: evolution and prognostic factors.

Cutaneous and subcutaneous leiomyosarcomas (LMS) are uncommon neoplasms. We reviewed the MEDLINE database to assess their rates of recurrence and metastasis, mortality and recommended follow-up period. Other prognostic factors were also studied. This review included 112 subcutaneous LMS and 313 cutaneous LMS. In subcutaneous LMS, we observed that rates of recurrence, metastasis and mortality were 36.63%, 43.23% and 37.82%, respectively, after a median follow-up period of 4.40 years, while in cutaneous LMS those figures were 24.40%, 4.22% and 3.33%, respectively, after a median follow-up period of 3.45 years. Although subcutaneous and cutaneous LMS show similar morphologic features, the latter show less tendency to recur and metastasize; in certain cases they both may be the cause of death. For these reasons we suggest avoiding the term "atypical intradermal smooth muscle neoplasm". Location, size and histologic grade are essential prognostic factors for superficial LMS. Recurrence after incomplete excision can be avoided when performed with a surgical margin of at least 1 cm. Follow-up should be at least five years.

Ovarian strumal carcinoid containing appendiceal-type mucinous tumor patterns presenting as pseudomyxoma peritonei.

We report for the first time a case of ovarian strumal carcinoid containing both trabecular carcinoid and mucinous glands lined by both goblet and neuroendocrine cells and a low-grade mucinous neoplasm that presented clinically as pseudomyxoma peritonei in the absence of appendiceal lesion in a 58-yr-old woman. Histologically, there were both a tall columnar cell epithelial component lacking neuroendocrine cells, showing the scalloped contours and subepithelial clefts of low-grade appendiceal-type neoplasms and a mixed goblet cell neuroendocrine element. Characteristically, both reproduced appendiceal neoplastic phenotypes in a teratoid fashion. In addition, we present previously unreported oncocytic and mucinous changes in the thyroideal components of strumal carcinoid. This case represents a rare instance of pseudomyxoma peritonei of primary ovarian origin and is an example of multiple somatic teratoid endodermal differentiations of the different sections of the embryonal gut: foregut represented by thyroid, midgut by both mucinous appendiceal components, and hindgut by trabecular carcinoid.

Ovarian paraganglioma.

A rare case of ovarian paraganglioma was incidentally found as a 1.2-cm intraovarian mass in a 68-year-old hypertensive female operated for an endometrial carcinoma. Histologically, it was arranged in characteristic Zellballen composed of polygonal clear cells with a granular cytoplasm that expressed diffusely CAM5.2 cytokeratin, chromogranin, neuron-specific enolase, synaptophysin, and CD56, while S-100 protein was only present in sustentacular cells. We analyzed differential diagnoses with other rare ovarian tumors such as Sertoli cell tumor, with which it may share an immunophenotype expressing cytokeratins, S-100, and other neural markers, and extra-axial ependymoma, which invariably expresses diffusely GFAP, that may be positive only in the sustentacular cells of paraganglioma. However, on simple hematoxylin-eosin inspection, ovarian paraganglioma displays characteristic Zellballen clusters and cells with a granular cytoplasm but lacks the distinctive Sertoli cell tubules and the characteristic rosettes and fibrillary cytoplasm of ependymoma. Pathologists should be aware of the unusual locations of paraganglioma.

Primary intermediate-grade cardiac myxofibrosarcoma with osseous metaplasia: an extremely rare occurrence with a previously unreported feature.

Primary cardiac myxofibrosarcoma (MFS) is a very rare cardiac tumor with no more than 22 cases reported in the literature, including our case. We report an MFS arising in the left atrium in a 65-year-old woman who presented with pneumonia and cardiac failure. The 9.5-cm mass was diagnosed by echocardiogram. Histopathology examination showed an intermediate-grade MFS with osseous metaplasia, a feature that has not been reported before.

Papillary ependymoma of the endometrium.

AIMS: To report an exceptional case of papillary ependymoma occurring in the endometrium. METHODS AND RESULTS: A clinicopathological study was performed regarding a case of papillary ependymoma occurring in the endometrial cavity of a 61-year-old patient who had presented with a solid-type, stage III anaplastic ependymoma of the ovary, treated with cytoreductive surgery that included total abdominal hysterectomy. The uterus was enlarged and showed a dilated cavity, with broadly implanted papillary excrescences without myometrial invasion that were covered by tall, cylindrical cells. These cells had glial fibrillary acidic protein-expressing cytoplasm that was also positive for cytokeratins 7, 8, 18, and 34ß-E12, epithelial membrane antigen, S100 protein, vimentin, and oestrogen and progesterone receptors. CONCLUSIONS: Pathogenetically, the presence of this uterine ependymoma could represent either an example of multicentricity or a phenomenon of transtubal implantation of the ovarian tumour. Exceptionally, papillary ependymoma can occur in the endometrium, and may prompt differential diagnoses with other papillary endometrial tumours. Pathologists should consider this rare possibility in the differential diagnosis of papillary ovarian and endometrial lesions.