Grading laryngeal squamous cell carcinoma (LSCC) based on histopathological images is a clinically significant yet challenging task. However, more low-effect background semantic information appeared in the feature maps, feature channels, and class activation maps, which caused a serious impact on the accuracy and interpretability of LSCC grading. While the traditional transformer block makes extensive use of parameter attention, the model overlearns the low-effect background semantic information, resulting in ineffectively reducing the proportion of background semantics. Therefore, we propose an end-to-end network with transformers constrained by learned-parameter-free attention (LA-ViT), which improve the ability to learn high-effect target semantic information and reduce the proportion of background semantics. Firstly, according to generalized linear model and probabilistic, we demonstrate that learned-parameter-free attention (LA) has a stronger ability to learn highly effective target semantic information than parameter attention. Secondly, the first-type LA transformer block of LA-ViT utilizes the feature map position subspace to realize the query. Then, it uses the feature channel subspace to realize the key, and adopts the average convergence to obtain a value. And those construct the LA mechanism. Thus, it reduces the proportion of background semantics in the feature maps and feature channels. Thirdly, the second-type LA transformer block of LA-ViT uses the model probability matrix information and decision level weight information to realize key and query, respectively. And those realize the LA mechanism. So, it reduces the proportion of background semantics in class activation maps. Finally, we build a new complex semantic LSCC pathology image dataset to address the problem, which is less research on LSCC grading models because of lacking clinically meaningful datasets. After extensive experiments, the whole metrics of LA-ViT outperform those of other state-of-the-art methods, and the visualization maps match better with the regions of interest in the pathologists' decision-making. Moreover, the experimental results conducted on a public LSCC pathology image dataset show that LA-ViT has superior generalization performance to that of other state-of-the-art methods.

Purpose: To observe the clinicopathological, immunohistochemical, and molecular genetic features of epithelioid glioblastoma (E-GBM), and identify tumor-associated prognostic factors. Patients and Methods: The clinical and radiological data of fifteen cases of E-GBM were collected, and their pathological, immunohistochemical, and molecular features were examined. A 1p/19q analysis via FISH, MGMT promoter methylation by MS-PCR, and IDH1 and BRAF V600E mutation analysis by HRM-PCR were performed. The level of EZH2 expression was valuated by immunohistochemistry in 15 E-GBM cases, and the prognostic factors were analyzed in E-GBM patients. Fifteen non-E-GBM cases were used as a control. Results: The fifteen cases of E-GBM included twelve males and three females, with fourteen cases supratentorially located. Headache was the main symptom. Microscopy revealed that the tumors were composed of epithelioid cells and some rhabdoid cells. The epithelioid and rhabdoid cells displayed focal discohesion, scant intervening neuropil, a distinct cell membrane, eosinophilic cytoplasm, and a laterally positioned nucleus. Most tumors showed high mitosis, zonal necrosis, and microvascular hyperplasia. Immunohistochemical findings included epithelioid cells positive for GFAP, vimentin, nestin, S-100, and INI-1. The molecular findings included no deletions of 1p/19q, EGFR amplifications, or IDH1 mutations in any case, a methylated MGMT promoter in 46.7% (7/15) cases, and a BRAFV600E mutation in 46.7% (7/15) cases. EZH2 overexpression occurred in 60.0% (9/15) of E-GBM cases. E-GBM patients with OS (≤ 12 months) exhibited extensive necrosis (6/6), EZH2 overexpression (6/6), MGMT promoter unmethylation (5/6), BRAFV600E mutation (3/6), and treatment (surgery4/6). E-GBM patients with OS (> 12 months) exhibited focal or limited necrosis, low or negative EZH2 expression, MGMT promoter methylation (2/3), BRAFV600E mutation (3/3), and treatment (surgery+radiotherapy/chemo-radiotherapy, 2/3). Conclusion: E-GBM was a rare variant of glioblastoma, with histological epithelioid features and poor prognosis. Extensive necrosis, MGMT promoter unmethylation, EZH2 overexpression, and lack of adjuvant chemo-radiotherapy may indicate a poor prognosis.

The discovery of the fusion gene echinodermmicro tubule associated proteinlike 4-anaplastic lymphoma kinase, EML4-ALK, in patients with non-small-cell lung cancer has led to the remarkable development of anaplastic lymphoma kinase inhibitors, such as crizotinib. Consequently, the clinical outcomes of these patients have improved dramatically. Herein, we report the case of a woman with ALK gene translocation-squamous cell lung cancer who experienced a remarkable tumor response to crizotinib after two courses of failed chemotherapy.