Key Points: A BCL2 IHC score is a strong prognostic factor independent of the IPI and MYC protein/rearrangement status in DLBCL treated with R-CHOP. The BCL2 scoring system we propose is a simple, at-a-glance, and highly reliable system, which was confirmed by an image analysis.

Primary effusion-based lymphoma (EBL) presents as a malignant effusion in a body cavity. The clinicopathologic features and prognosis of primary human herpesvirus 8 (HHV8)–negative EBL remain unclear. We therefore conducted a retrospective study of 95 patients with EBL, regardless of HHV8 status, in Japan. Of 69 patients with EBL tested for HHV8, a total of 64 were negative. The median age of patients with primary HHV8-negative EBL at diagnosis was 77 years (range, 57-98 years); all 58 tested patients were negative for HIV. Primary HHV8-negative EBL was most commonly diagnosed in pleural effusion (77%). Expression of at least 1 pan B-cell antigen (CD19, CD20, or CD79a) was observed in all cases. According to the Hans algorithm, 30 of the 38 evaluated patients had nongerminal center B-cell (non-GCB) tumors. Epstein-Barr virus–encoded small RNA was positive in 6 of 45 patients. In 56 of 64 HHV8-negative patients, systemic therapy was initiated within 3 months after diagnosis. Cyclophosphamide, doxorubicin, vincristine, and prednisolone (CHOP) or CHOP-like regimens with or without rituximab (n = 48) were the most common primary treatments. The overall response and complete response rates were 95% and 73%, respectively. Three patients did not progress without systemic treatment for a median of 24 months. With a median 25-month follow-up, the 2-year overall survival and progression-free survival rates were 84.7% and 73.8%. Sixteen patients died; 12 were lymphoma-related deaths. Thus, most EBL cases in Japan are HHV8-negative and affect elderly patients. The non-GCB subtype is predominant. Overall, primary HHV8-negative EBL exhibits a favorable prognosis after anthracycline-based chemotherapy.

Clinical and prognostic significance of aberrant T-cell marker expression in 225 cases of de novo diffuse large B-cell lymphoma and 276 cases of other B-cell lymphomas Clinical and prognostic significance of aberrant T-cell marker expression in 225 cases of de novo diffuse large B-cell lymphoma and 276 cases of other B-cell lymphomas

Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology.