Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists.

The Gleason score is the most important prognostic marker for prostate cancer patients, but it suffers from significant observer variability. Artificial intelligence (AI) systems based on deep learning can achieve pathologist-level performance at Gleason grading. However, the performance of such systems can degrade in the presence of artifacts, foreign tissue, or other anomalies. Pathologists integrating their expertise with feedback from an AI system could result in a synergy that outperforms both the individual pathologist and the system. Despite the hype around AI assistance, existing literature on this topic within the pathology domain is limited. We investigated the value of AI assistance for grading prostate biopsies. A panel of 14 observers graded 160 biopsies with and without AI assistance. Using AI, the agreement of the panel with an expert reference standard increased significantly (quadratically weighted Cohen's kappa, 0.799 vs. 0.872; p = 0.019). On an external validation set of 87 cases, the panel showed a significant increase in agreement with a panel of international experts in prostate pathology (quadratically weighted Cohen's kappa, 0.733 vs. 0.786; p = 0.003). In both experiments, on a group-level, AI-assisted pathologists outperformed the unassisted pathologists and the standalone AI system. Our results show the potential of AI systems for Gleason grading, but more importantly, show the benefits of pathologist-AI synergy.

Isolated Scapular Metastasis in a Patient with Malignant Struma Ovarii: A Case Report.

CASE: We report the case of a 38-year-old woman who presented with a lytic bone lesion in the left scapula. A biopsy showed a tumor with the histologic appearance of thyroid tissue. She also was found to have a thyroid nodule and an enlarged ovary, both of which were excised. The thyroid nodule turned out to be a benign colloid nodule, and the ovary contained a monodermal teratoma composed of thyroid tissue (struma ovarii). The lesion in the scapula eventually was proven to be metastatic malignant struma ovarii. CONCLUSION: Malignant struma ovarii with bone metastases is very rare, and its diagnosis is a challenge. There are some documented cases with bone metastases, mostly to the thoracic and lumbar spine. The optimal treatment of choice for the bone lesion is unknown because of the rarity of its presentation.

Double-hit lymphomas: clinical, morphological, immunohistochemical and cytogenetic study in a series of Brazilian patients with high-grade non-Hodgkin lymphoma.

BACKGROUND: Double-hit lymphomas (DHL) are rare high-grade neoplasms characterized by two translocations: one involving the gene MYC and another involving genes BCL2 or BCL6, whose diagnosis depends on cytogenetic examination. This research studied DHL and morphological and/or immunophenotypic factors associated with the detection of these translocations in a group of high-grade non-Hodgkin lymphoma cases. METHOD: Clinical and morphological reviews of 120 cases diagnosed with diffuse large B-cell lymphoma and Burkitt lymphoma were conducted. Immunohistochemistry (CD20, CD79a, PAX5, CD10, Bcl6, Bcl2, MUM1, TDT and Myc) and fluorescence in situ hybridization for detection of MYC, BCL2 and BCL6 gene translocations were performed in a tissue microarray platform. RESULTS: Three cases of DHL were detected: two with translocations of MYC and BCL2 and one with translocations of MYC and BCL6, all leading to death in less than six months. Among 90 cytogenetically evaluable biopsies, associations were determined between immunohistochemistry and fluorescence in situ hybridization for MYC (p = 0.036) and BCL2 (p = 0.001). However, these showed only regular agreement, indicated by Kappa values of 0.23 [0.0;0.49] and 0.35 [0.13;0.56], respectively. "Starry sky" morphology was strongly associated with MYC positivity (p = 0.01). The detection of three cases of DHL, all resulting in death, confirms the rarity and aggressiveness of this neoplasm. CONCLUSIONS: The "starry sky" morphological pattern and immunohistochemical expression of Myc and Bcl2 represent possible selection factors for additional cytogenetic diagnostic testing.