Activity

3%, 88/151), followed by juvenile type (20.5%, 31/151), intermediate type (15.9%, 24/151) and plasmacyte type (5.3%, 8/151). According to the mSMART risk stratification system, the proliferation pattern of myeloma cells in the high-risk group was mainly diffuse type, and the morphology was mainly immature and plasmacyte type. In the middle-risk group, mature type myeloma cells were mainly nodular proliferating. In the low-risk and negative group, mature type myeloma cells were mainly interstitial proliferating. There was no difference in the probability of different proliferation modes of intermediate type plasma cells in each group. Conclusions The proliferation pattern and morphology of plasma cells in bone marrow biopsy combined with cytogenetic markers can more accurately predict the severity and prognosis of MM.Objective To investigate the clinicopathological features, diagnosis and prognosis of polymorphous low-grade neuroepithelial tumor of the young (PLNTY). Methods Two cases of PLNTY diagnosed during January 2016 to December 2019 were collected from Ningbo Diagnostic Pathology Center, Zhejiang, China. The clinical features, histopathological characteristics, immunohistochemical and molecular genetic findings were analyzed and the relevant literature was reviewed. Results The two patients were both female, at the ages of 14 and 25 years, respectively. Both patients presented with seizure attacks. The imaging study showed a mixed signal in the cerebral cortex, located in the occipital and temporal lobes, respectively. Microscopically, the tumors were characterized by the invariable presence of oligodendroglioma-like appearance, often with calcification. Immunohistochemically, the tumors were diffusely and intensely CD34 positive with ramified, CD34-expressing neural elements in regional cortex. The tumors were positive for GFAP, Olig2 and ATRX, and negative for IDH1, Neu N, nestin and EMA. The Ki-67 labeling index was less than 2%. The case number 2 harbored the BRAF V600E mutation, while the case number 1 was negative for both the BRAF V600E mutation and 1p/19q codeletion. Both patients recovered very well and were free of seizures after the following-up of 2 and 24 months, respectively. Conclusions PLNTY is an uncommon neuroepithelial tumor. Histopathologic and immunohistochemical examinations are necessary for establishing the diagnosis and for excluding oligodendroglioma. PLNTY should be considered as a benign tumor corresponding to WHO Grade I. The prognosis is overall good after complete tumor-resection.Objective To investigate the clinicopathological characteristics, immunophenotype, molecular genetic characteristics and prognosis of the metaplastic thymoma (MT). Methods The clinicopathological and follow-up data of five MT cases were collected at Fujian Provincial Hospital from 2008 to 2019. Immunohistochemical staining and MAML2 gene detection were performed, and the relevant literature was reviewed. Results There were 2 males and 3 females, aged 36-64 years (mean age 52 years). The tumors ranged 3.2-7.3 cm in the greatest diameter (average 5.1 cm).Microscopically, the tumor showed a biphasic pattern with epithelial cells merging gradually with the spindle cell component. The two areas transited to each other or had obvious boundary. Both components showed mild atypia. No mitosis was observed in either area, and a small number of lymphocytes were observed in the stroma. Immunohistochemical staining showed that epithelioid cells were positive for CKpan, p63 and E-cadherin. Spindle cells were positive for vimentin and EMA, while the Ki-67 index was less than 5%, and lymphocytes were negative for TdT. MAML2 gene apart signal was detected in two of the cases (2/4) that were tested by FISH. Conclusions MT is a low-grade malignant epithelioid thymic tumor. Its diagnosis and differential diagnosis are dependent on the morphological characteristics, immunohistochemical staining and MAML2 gene detection. The primary treatment option is surgical resection, with an overall good prognosis.Objective To establish an artificial intelligence (AI)-assisted diagnostic system for lung cancer via deep transfer learning. Methods The researchers collected 519 lung pathologic slides from 2016 to 2019, covering various lung tissues, including normal tissues, adenocarcinoma, squamous cell carcinoma and small cell carcinoma, from the Beijing Chest Hospital, the Capital Medical University. The slides were digitized by scanner, and 316 slides were used as training set and 203 as the internal test set. The researchers labeled all the training slides by pathologists and establish a semantic segmentation model based on DeepLab v3 with ResNet-50 to detect lung cancers at the pixel level. To perform transfer learning, the researchers utilized the gastric cancer detection model to initialize the deep neural network parameters. The lung cancer detection convolutional neural network was further trained by fine-tuning of the labeled data. The deep learning model was tested by 203 slides in the internal test set and 1 081 slides obtained from TCIA database, named as the external test set. Results The model trained with transfer learning showed substantial accuracy advantage against the one trained from scratch for the internal test set [area under curve (AUC) 0.988 vs. 0.971, Kappa 0.852 vs. 0.832]. For the external test set, the transferred model achieved an AUC of 0.968 and Kappa of 0.828, indicating superior generalization ability. By studying the predictions made by the model, the researchers obtained deeper understandings of the deep learning model. Conclusions The lung cancer histopathological diagnostic system achieves higher accuracy and superior generalization ability. With the development of histopathological AI, the transfer learning can effectively train diagnosis models and shorten the learning period, and improve the model performance.Objective To study the clinicopathological features and PD-L1 expression of microsatellite instability-high (MSI-H) gastric cancer. Methods The clinicopathological data of the 2 472 patients who had undergone radical surgical resection and been performed immunohistochemical staining of four major mismatch repair (MMR) proteins (MLH1, PMS2, MSH2 and MSH6) from March 2014 to December 2018 at Peking University Cancer Hospital were collected. One hundred and seventy-one patients showed mismatch repair-deficient (dMMR), and microsatellite instability of these patients were detected with polymerase chain reaction (PCR). Then, taken PCR results as the standard, PD-L1 was assessed using immunohistochemistry (IHC) in the MSI-H gastric cancers. Results MSI-H (vs. Y-27632 molecular weight MSI-L) in gastric cancers was associated with female gender, advanced age, gastric-antrum location, intestinal type, lesion diameter exceeding 5 cm, absence of lymph node metastasis and positive PD-L1 expression (P less then 0.05, respectively). Combined positive score (CPS) was an independent risk factor (P=0.