Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval.

Large-scale digital whole slide image (WSI) datasets analysis have gained significant attention in computer-aided cancer diagnosis. Content-based histopathological image retrieval (CBHIR) is a technique that searches a large database for data samples matching input objects in both details and semantics, offering relevant diagnostic information to pathologists. However, the current methods are limited by the difficulty of gigapixels, the variable size of WSIs, and the dependence on manual annotations. In this work, we propose a novel histopathology language-image representation learning framework for fine-grained digital pathology cross-modal retrieval, which utilizes paired diagnosis reports to learn fine-grained semantics from the WSI. An anchor-based WSI encoder is built to extract hierarchical region features and a prompt-based text encoder is introduced to learn fine-grained semantics from the diagnosis reports. The proposed framework is trained with a multivariate cross-modal loss function to learn semantic information from the diagnosis report at both the instance level and region level. After training, it can perform four types of retrieval tasks based on the multi-modal database to support diagnostic requirements. We conducted experiments on an in-house dataset and a public dataset to evaluate the proposed method. Extensive experiments have demonstrated the effectiveness of the proposed method and its advantages to the present histopathology retrieval methods. The code is available at https://github.com/hudingyi/FGCR.

Clinical significance of expression level of ZNF471 in gastric cancer.

BACKGROUND: As a tumor suppressor gene, zinc finger protein 471 (ZNF471) has an essential role in tumor occurrence and development. Due to promoter hypermethylation, it can be underexpressed or silenced in gastric cancer (GC) cell lines. In this study, we investigated relationships between clinical characteristics and ZNF471 expression levels in tissues of patients with GC. METHODS: We used immunohistochemistry (IHC) to detect ZNF471 expression in paraffin tissue specimens, and quantitative real-time PCR (qRT-PCR) and western blot (WB) analysis to measure expression levels of ZNF471 in fresh tissue specimens. We analyzed relationships between ZNF471 expression levels and characteristics, such as tumor size, gender, age, TNM stage, and lymph node metastasis. RESULTS: Immunohistochemistry revealed the expression of ZNF471 protein from paraffin blocks of GC tissues was significantly lower than that of adjacent tissues. Expression levels of ZNF471 mRNA and protein in fresh GC tissues were markedly lower than those in adjacent tissues and in normal gastric mucosal tissues from healthy subjects. ZNF471 expression was significantly correlated with tumor size, lymph node metastasis, and TNM stage (all P<0.05). There were no significant associations with gender, age, distant metastasis, or pathologic type. Expression of ZNF471 mRNA and protein was not significantly different between adjacent tissues of patients with GC and normal gastric mucosal tissue from healthy subjects. CONCLUSION: ZNF471 functions as a tumor suppressor during the pathogenesis of GC. Thus, it is a promising biomarker for diagnosis and therapy of GC.

Kernel Attention Transformer for Histopathology Whole Slide Image Analysis and Assistant Cancer Diagnosis.

Transformer has been widely used in histopathology whole slide image analysis. However, the design of token-wise self-attention and positional embedding strategy in the common Transformer limits its effectiveness and efficiency when applied to gigapixel histopathology images. In this paper, we propose a novel kernel attention Transformer (KAT) for histopathology WSI analysis and assistant cancer diagnosis. The information transmission in KAT is achieved by cross-attention between the patch features and a set of kernels related to the spatial relationship of the patches on the whole slide images. Compared to the common Transformer structure, KAT can extract the hierarchical context information of the local regions of the WSI and provide diversified diagnosis information. Meanwhile, the kernel-based cross-attention paradigm significantly reduces the computational amount. The proposed method was evaluated on three large-scale datasets and was compared with 8 state-of-the-art methods. The experimental results have demonstrated the proposed KAT is effective and efficient in the task of histopathology WSI analysis and is superior to the state-of-the-art methods.

Evaluation of Liquid Biopsy in Patients with HER2-Positive Breast Cancer.

Breast cancer is one of the common malignant tumors, and liquid biopsy has become a hot spot for clinical testing. To clarify the detection effect of liquid biopsy in breast cancer, we collected peripheral blood of HER2-positive (human epidermal growth factor receptor 2-positive) patients. Circulating tumor cells (CTCs) were isolated and analyzed. HER2 expression on CTCs was detected. The results showed that in the 198 HER2-positive samples, the CTC detection rate was 79.8% (158/198), and the mean number of CTCs was 21, ranging from 1 to 63/7.5 mL peripheral blood. Only 41.1% (65/158) of patients had histology and CTC HER2 status consistent with the remaining 58.9% (93/158) of patients, although their histological HER2 was positive, and CTC HER2 was negative. Our study confirmed the value of CTC HER2 real-time status testing in HER2-positive breast cancer patients. The inconsistency in HER2 status between CTCs and histology may be related to the time interval between CTCs and histological HER2 detection, suggesting that real-time HER2 detection is necessary for histological HER2-positive patients.

Diagnostic Regions Attention Network (DRA-Net) for Histopathology WSI Recommendation and Retrieval.

The development of whole slide imaging techniques and online digital pathology platforms have accelerated the popularization of telepathology for remote tumor diagnoses. During a diagnosis, the behavior information of the pathologist can be recorded by the platform and then archived with the digital case. The browsing path of the pathologist on the WSI is one of the valuable information in the digital database because the image content within the path is expected to be highly correlated with the diagnosis report of the pathologist. In this article, we proposed a novel approach for computer-assisted cancer diagnosis named session-based histopathology image recommendation (SHIR) based on the browsing paths on WSIs. To achieve the SHIR, we developed a novel diagnostic regions attention network (DRA-Net) to learn the pathology knowledge from the image content associated with the browsing paths. The DRA-Net does not rely on the pixel-level or region-level annotations of pathologists. All the data for training can be automatically collected by the digital pathology platform without interrupting the pathologists' diagnoses. The proposed approaches were evaluated on a gastric dataset containing 983 cases within 5 categories of gastric lesions. The quantitative and qualitative assessments on the dataset have demonstrated the proposed SHIR framework with the novel DRA-Net is effective in recommending diagnostically relevant cases for auxiliary diagnosis. The MRR and MAP for the recommendation are respectively 0.816 and 0.836 on the gastric dataset. The source code of the DRA-Net is available at https://github.com/zhengyushan/dpathnet.

Purification and characterization of anti-clotting protein component (ACPF-7221) from venom of Agkistrodon acutus.

BACKGROUND: Snake venom contains a number of components with different pharmacological and biological activities, especially in cancer therapy, and has increasingly become a research focus. This study was designed to isolate and purify a novel anti-clotting protein component from the venom of Agkistrodon acutus, and to explore its physico-chemical properties and biological activity. METHODS: The venom of Agkistrodon was isolated and purified by ion-exchange chromatography on diethylaminoethyl (DEAE)-Sepharose Fast Flow, molecular sieve filtration through Sephadex G75, SP-Sepharose Fast Flow and molecular sieve filtration through Sephadex G50. We detected the activated partial thromboplastin time (APTT) of the eluant to select the anti-clotting protein component of interest. The molecular weight was determined by sodium dodecyl sulfate-polyacrylamid gel electrphoresis (SDS-PAGE) and liquid chromatography. Its protein content was detected by bicinchoninic acid (BCA). RESULTS: SDS-PAGE vertical gel electrophoresis showed that the anticoagulant factor is a tripolymer composed of three proteins whose molecular weights are 25 KDa, 30 KDa and 50 KDa. The factor contains about 65% percent protein. CONCLUSIONS: A novel anti-clotting protein component was purified by ion-exchange chromatography and molecular sieve filtration from the venom of Agkistrodon acutus and was found to be composed of three kinds of proteins.