Establishment of a cholangiocarcinoma risk evaluation model based on mucin expression levels.

BACKGROUND: Cholangiocarcinoma (CCA) is a highly malignant cancer, characterized by frequent mucin overexpression. MUC1 has been identified as a critical oncogene in the progression of CCA. However, the comprehensive understanding of how the mucin family influences CCA progression and prognosis is still incomplete. AIM: To investigate the functions of mucins on the progression of CCA and to establish a risk evaluation formula for stratifying CCA patients. METHODS: Single-cell RNA sequencing data from 14 CCA samples were employed for elucidating the roles of mucins, complemented by bioinformatic analyses. Subsequent validations were conducted through spatial transcriptomics and immunohistochemistry. The construction of a risk evaluation model utilized the least absolute shrinkage and selection operator regression algorithm, which was further confirmed by independent cohorts and diverse data types. RESULTS: CCA tumor cells with elevated levels of MUC1 and MUC4 showed activated nucleotide metabolic pathways and increased invasiveness. MUC5AC-high cells were found to promote CCA progression through WNT signaling. MUC5B-high cells exhibited robust cellular oxidation activities, leading to resistance against antitumoral treatments. MUC13-high cells were observed to secret chemokines, recruiting and transforming macrophages into the M2-polarized state, thereby suppressing antitumor immunity. MUC16-high cells were found to promote tumor progression through interleukin-1/nuclear factor kappa-light-chain-enhancer of activated B cells signaling upon interaction with neutrophils. Utilizing the expression levels of these mucins, a risk factor evaluation formula for CCA was developed and validated across multiple cohorts. CCA samples with higher risk factors exhibited stronger metastatic potential, chemotherapy resistance, and poorer prognosis. CONCLUSION: Our study elucidates the functional mechanisms through which mucins contribute to CCA development, and provides tools for risk stratification in CCA.

SPINK1 Overexpression Correlates with Hepatocellular Carcinoma Treatment Resistance Revealed by Single Cell RNA-Sequencing and Spatial Transcriptomics.

Low efficacy of treatments and chemoresistance are challenges in addressing refractory hepatocellular carcinoma (HCC). SPINK1, an oncogenic protein, is frequently overexpressed in many HCC cases. However, the impact of SPINK1 on HCC treatment resistance remains poorly understood. Here, we elucidate the functions of SPINK1 on HCC therapy resistance. Analysis of SPINK1 protein level reveals a correlation between elevated SPINK1 expression and unfavorable prognosis. Furthermore, intercellular variations in SPINK1 expression levels are observed. Subsequent examination of single cell RNA-sequencing data from two HCC cohorts further suggest that SPINK1-high cells exhibit heightened activity in drug metabolic pathways compared to SPINK1-low HCC cells. High SPINK1 expression is associated with reduced sensitivities to both chemotherapy drugs and targeted therapies. Moreover, spatial transcriptomics data indicate that elevated SPINK1 expression correlates with non-responsive phenotype during treatment with targeted therapy and immune checkpoint inhibitors. This is attributed to increased levels of drug metabolic regulators, especially CES2 and CYP3A5, in SPINK1-high cells. Experimental evidence further demonstrates that SPINK1 overexpression induces the expression of CES2 and CYP3A5, consequently promoting chemoresistance to sorafenib and oxaliplatin. In summary, our study unveils the predictive role of SPINK1 on HCC treatment resistance, identifying it as a potential therapeutic target for refractory HCC.

Predicting the status of lymphovascular space invasion using quantitative parameters from synthetic MRI in cervical squamous cell carcinoma without lymphatic metastasis.

Purpose: To investigate the value of quantitative longitudinal relaxation time (T1), transverse relaxation time (T2), and proton density (PD) maps derived from synthetic magnetic resonance imaging (MRI) for evaluating the status of lymphovascular space invasion (LVSI) in cervical squamous cell carcinoma (CSCC) without lymph node metastasis (LNM). Material and methods: Patients with suspected cervical cancer who visited our hospital from May 2020 to March 2023 were collected. All patients underwent preoperative MRI, including routine sequences and synthetic MRI. Patients with pathologically confirmed CSCC without lymphatic metastasis were included in this study. The subjects were divided into negative- and positive-LVSI groups based on the status of LVSI. Quantitative parameters of T1, T2, and PD values derived from synthetic MRI were compared between the two groups using independent samples t-test. Receiver operating characteristic curves were used to determine the diagnostic efficacy of the parameters. Results: 59 patients were enrolled in this study and were classified as positive (n = 32) and negative LVSI groups (n = 27). T1 and T2 values showed significant differences in differentiating negative-LVSI from positive-LVSI CSCC (1307.39 ± 122.02 vs. 1193.03 ± 107.86, P<0.0001; 88.42 ± 7.24 vs. 80.99 ± 5.50, P<0.0001, respectively). The area under the curve (AUC) for T1, T2 values and a combination of T1 and T2 values were 0.756, 0.799, 0.834 respectively, and there is no statistically significant difference in the diagnostic efficacy between individual and combined diagnosis of each parameter. Conclusions: Quantitative parameters derived from synthetic MRI can be used to evaluate the LVSI status in patients with CSCC without LNM.

Prognostic Value of Tumor Size in Colon Cancer-Smaller is Better?

BACKGROUND: The prognostic value of tumor size in colon cancer remains controversial. This study aimed to reveal the correlation between tumor size and prognosis of colon cancer. METHODS: A total of 491 patients with colon cancer were included in this study. The correlation of tumor size with prognosis, mismatch repair status, and other clinicopathological characteristics as well as tumor microenvironment was analyzed. RESULTS: For stage IIA microsatellite stable (MSS) colon cancer, tumors sized <3.5 cm and ≥5 cm were associated with a poorer disease free survival (DFS) compared with tumors sized between 3.5 and 5 cm (P = .002). Small tumor size (HR = 5.098, P = .001) and large tumor size (HR = 2.749, P = .029) were found to be independent prognostic factors for stage IIA MSS colon cancer. Moreover, high expression of transgelin (TAGLN), a marker of cancer-associated fibroblasts (CAFs), was found to be an independent prognostic factor for poorer DFS (HR = 9.651, P = .009), which was also associated with smaller tumor size (P = .027). CONCLUSION: Small (<3.5 cm) and large (≥5 cm) tumor sizes are associated with decreased DFS in stage IIA MSS colon cancer. Enrichment of TAGLN+ CAFs is associated with decreased DFS and small tumor size.

Integrative single-cell multiomics analyses dissect molecular signatures of intratumoral heterogeneities and differentiation states of human gastric cancer.

Human gastric cancer is a highly lethal disease, but the underlying multiomic molecular signatures remain largely unclear. Here, we performed multi-regional sampling, parallel single-cell multiomics sequencing and integrated analyses of human gastric cancer. We identified common transcriptomic alterations of gastric cancer cells, such as aberrant down-regulation of genes associated with normal stomach function and up-regulation of KRT7, PI3, S100A4, etc. Surprisingly, aberrant and prevalent up-regulation of genes highly expressed in normal colorectal epithelial cells were also identified in cancer cells, which may be partially regulated by promoter chromatin accessibility and DNA methylation levels. We revealed the single-cell DNA methylome landscape of gastric cancer, and identified candidate DNA methylation biomarkers, such as hypermethylated promoters of TMEM240 and HAGLROS, and hypomethylated promoters of TRPM2-AS and HRH1. Additionally, the relationships between genetic lineages, DNA methylation and transcriptomic clusters were systematically revealed at single-cell level. We showed that DNA methylation heterogeneities were mainly among different genetic lineages of cancer cells. Moreover, we found that DNA methylation levels of cancer cells with poorer differentiation states tend to be higher than those of cancer cells with better differentiation states in the primary tumor within the same patient, although still lower than in normal gastric epithelial cells. Cancer cells with poorer differentiation states also prevalently down-regulated MUC1 expression and immune-related pathways, and had poor infiltration of CD8+ T cells. Our study dissected the molecular signatures of intratumoral heterogeneities and differentiation states of human gastric cancer using integrative single-cell multiomics analyses.

A Deep Learning-Based System Trained for Gastrointestinal Stromal Tumor Screening Can Identify Multiple Types of Soft Tissue Tumors.

The accuracy and timeliness of the pathologic diagnosis of soft tissue tumors (STTs) critically affect treatment decision and patient prognosis. Thus, it is crucial to make a preliminary judgement on whether the tumor is benign or malignant with hematoxylin and eosin-stained images. A deep learning-based system, Soft Tissue Tumor Box (STT-BOX), is presented herein, with only hematoxylin and eosin images for malignant STT identification from benign STTs with histopathologic similarity. STT-BOX assumed gastrointestinal stromal tumor as a baseline for malignant STT evaluation, and distinguished gastrointestinal stromal tumor from leiomyoma and schwannoma with 100% area under the curve in patients from three hospitals, which achieved higher accuracy than the interpretation of experienced pathologists. Particularly, this system performed well on six common types of malignant STTs from The Cancer Genome Atlas data set, accurately highlighting the malignant mass lesion. STT-BOX was able to distinguish ovarian malignant sex-cord stromal tumors without any fine-tuning. This study included mesenchymal tumors that originated from the digestive system, bone and soft tissues, and reproductive system, where the high accuracy of migration verification may reveal the morphologic similarity of the nine types of malignant tumors. Further evaluation in a pan-STT setting would be potential and prospective, obviating the overuse of immunohistochemistry and molecular tests, and providing a practical basis for clinical treatment selection in a timely manner.

Relationships of tumor differentiation and immune infiltration in gastric cancers revealed by single-cell RNA-seq analyses.

Gastric cancers are highly heterogeneous malignant tumors. To reveal the relationship between differentiation status of cancer cells and tumor immune microenvironments in gastric cancer, single-cell RNA-sequencing was performed on normal mucosa tissue, differentiated gastric cancer (DGC) tissue, poorly differentiated gastric cancer (PDGC) tissue and neuroendocrine carcinoma (NEC) tissue sampled from surgically resected gastric cancer specimens. We identified the signature genes for both DGC and PDGC, and found that signature genes of PDGC strongly enriched in the epithelial-mesenchymal transition (EMT) program. Furthermore, we found that DGC tends to be immune-rich type whereas PDGC tends to be immune-poor type defined according to the density of tumor-infiltrating CD8+ T cells. Additionally, interferon alpha and gamma responding genes were specifically expressed in the immune-rich malignant cells compared with immune-poor malignant cells. Through analyzing the mixed adenoneuroendocrine carcinoma, we identified intermediate state malignant cells during the trans-differentiation process from DGC to NEC, which showed double-negative expressions of both DGC marker genes and NEC marker genes. Interferon-related pathways were gradually downregulated along the DGC to NEC trans-differentiation path, which was accompanied by reduced CD8+ cytotoxic T-cell infiltration. In summary, molecular features of both malignant cells and immune microenvironment cells of DGC, PDGC and NEC were systematically revealed, which may partially explain the strong tumor heterogeneities of gastric cancer. Especially along the DGC to NEC trans-differentiation path, immune-evasion was gradually enhanced with the decreasing activities of interferon pathway responses in malignant cells.

Mitochondrial genome of Leocrates chinensis Kinberg, 1866 (Annelida: Hesionidae).

We report the complete mitochondrial genome of Leocrates chinensis Kinberg, 1866 - the type species of the genus. It is 15061 bp long, and contains 13 protein-coding genes (PCGs), 22 tRNA genes (tRNAs), and 2 rRNA genes (rRNAs), and 1 putative control region. Phylogenetic analysis indicated that L. chinensis was placed as sister to Sirsoe methanicola (BS = 100) of the same family Hesionidae.

Knowledge mapping of population health: A bibliometric analysis.

In recent years, population health has aroused great interest, especially after the outbreak of Covid-19. The related research increases substantially year by year. There are many kinds of research about population health, but few scholars use the bibliometric method to discuss them. Motivated by keeping abreast of emerging trends and critical turns in population health, this study adopts the bibliometric method to analyze the development history and status quo of population health, providing a summary description for it. This study adopts CiteSpace to conduct a bibliometric analysis of publications related to population health in Web of Science from 1971 to 2021. The most productive countries, authors, institutions, and research direction changes are analyzed. The research results show that: First, the number of publications and citations related to population health increases for years, especially in Canada, the United States, the United Kingdom, and Australia. Second, the number of publications by different countries or institutions in population health varies greatly, and they cooperate closely. Third, the co-occurrence of disciplines and keywords in population health is displayed. Finally, this study reveals the primary research force, the major themes, significant milestones, landmarks, and the evolution of the hot fronts. In all, the comprehensive analysis of this study would provide some enlightenment for future research.

Diffusion-weighted imaging-based radiomics in epithelial ovarian tumors: Assessment of histologic subtype.

Background: Epithelial ovarian tumors (EOTs) are a group of heterogeneous neoplasms. It is importance to preoperatively differentiate the histologic subtypes of EOTs. Our study aims to investigate the potential of radiomics signatures based on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) maps for categorizing EOTs. Methods: This retrospectively enrolled 146 EOTs patients [34 with borderline EOT(BEOT), 30 with type I and 82 with type II epithelial ovarian cancer (EOC)]. A total of 390 radiomics features were extracted from DWI and ADC maps. Subsequently, the LASSO algorithm was used to reduce the feature dimensions. A radiomics signature was established using multivariable logistic regression method with 3-fold cross-validation and repeated 50 times. Patients with bilateral lesions were included in the validation cohort and a heuristic selection method was established to select the tumor with maximum probability for final consideration. A nomogram incorporating the radiomics signature and clinical characteristics was also developed. Receiver operator characteristic, decision curve analysis (DCA), and net reclassification index (NRI) were applied to compare the diagnostic performance and clinical net benefit of predictive model. Results: For distinguishing BEOT from EOC, the radiomics signature and nomogram showed more favorable discrimination than the clinical model (0.915 vs. 0.852 and 0.954 vs. 0.852, respectively) in the training cohort. In classifying early-stage type I and type II EOC, the radiomics signature exhibited superior diagnostic performance over the clinical model (AUC 0.905 vs. 0.735). The diagnostic efficacy of the nomogram was the same as that of the radiomics model with NRI value of -0.1591 (P = 0.7268). DCA also showed that the radiomics model and combined model had higher net benefits than the clinical model. Conclusion: Radiomics analysis based on DWI, and ADC maps serve as an effective quantitative approach to categorize EOTs.

Preoperative Multiparametric Quantitative Magnetic Resonance Imaging Correlates with Prognosis and Recurrence Patterns in Pancreatic Ductal Adenocarcinoma.

Magnetic resonance imaging (MRI) has been shown to be associated with prognosis in some tumors; however, the correlation in pancreatic ductal adenocarcinoma (PDAC) remains inconclusive. In this retrospective study, we ultimately included 136 patients and analyzed quantitative MRI parameters that are associated with prognosis and recurrence patterns in PDAC using survival analysis and competing risks models; all the patients have been operated on with histopathology and immunohistochemical staining for further evaluation. In intravoxel incoherent motion diffusion-weighted imaging (DWI), we found that pure-diffusion coefficient D value was an independent risk factor for overall survival (OS) (HR: 1.696, 95% CI: 1.003-2.869, p = 0.049) and recurrence-free survival (RFS) (HR: 2.066, 95% CI: 1.252-3.409, p = 0.005). A low D value (≤1.08 × 10-3 mm2/s) was significantly associated with a higher risk of local recurrence (SHR: 5.905, 95% CI: 2.107-16.458, p = 0.001). Subgroup analysis revealed that patients with high D and f values had significantly better outcomes with adjuvant chemotherapy. Distant recurrence patients in the high-D value group who received chemotherapy may significantly improve their OS and RFS. It was found that preoperative multiparametric quantitative MRI correlates with prognosis and recurrence patterns in PDAC. Diffusion coefficient D value can be used as a noninvasive biomarker for predicting prognosis and recurrence patterns in PDAC.

RPA1 controls chromatin architecture and maintains lipid metabolic homeostasis.

Non-alcoholic fatty liver disease (NAFLD) is the most common liver disease, with a prevalence of 25% worldwide. However, the underlying molecular mechanism involved in the development and progression of the NAFLD spectrum remains unclear. Single-stranded DNA-binding protein replication protein A1 (RPA1) participates in DNA replication, recombination, and damage repair. Here, we show that Rpa1+/- mice develop fatty liver disease during aging and in response to a high-fat diet. Liver-specific deletion of Rpa1 results in downregulation of genes related to fatty acid oxidation and impaired fatty acid oxidation, which leads to hepatic steatosis and hepatocellular carcinoma. Mechanistically, RPA1 binds gene regulatory regions, chromatin-remodeling factors, and HNF4A and remodels chromatin architecture, through which RPA1 promotes HNF4A transcriptional activity and fatty acid ß oxidation. Collectively, our data demonstrate that RPA1 is an important regulator of NAFLD through controlling chromatin accessibility.

Digital Industry Financial Risk Early Warning System Based on Improved K-Means Clustering Algorithm.

Corporate financial risks not only endanger the financial stability of digital industry but also cause huge losses to the macro-economy and social wealth. In order to detect and warn digital industry financial risks in time, this paper proposes an early warning system of digital industry financial risks based on improved K-means clustering algorithm. Aiming to speed up the K-means calculation and find the optimal clustering subspace, a specific transformation matrix is used to project the data. The feature space is divided into clustering space and noise space. The former contains all spatial structure information; the latter does not contain any information. Each iteration of K-means is carried out in the clustering space, and the effect of dimensionality screening is achieved in the iteration process. At the same time, the retained dimensions are fed back to the next iteration. The dimensional information of the cluster space is discovered automatically, so no additional parameters are introduced. Experimental results show that the accuracy of the proposed algorithm is higher than other algorithms in financial risk detection.

The Prognostic Significance and Gene Expression Characteristics of Gastric Signet-Ring Cell Carcinoma: A Study Based on the SEER and TCGA Databases.

Purpose: This study is based on the Surveillance, Epidemiology, and End Results (SEER) program to explore the prognostic differences between signet-ring cell carcinoma (SRC) and intestinal-type gastric carcinoma (ITGC). This study is also based on gene sequencing data from The Cancer Genome Atlas (TCGA) to identify unique genetic contributions to the prognostic differences between the two subtypes of gastric cancer. Patients and Methods: The clinical data were based on the SEER database from 2004 to 2015. Kaplan-Meier (KM) curves were used to compare 5-year overall survival (OS), and Cox regression was used for univariate and multivariate analyses. Gene expression profiles were obtained from TCGA database, and differentially expressed genes (DEGs) were screened. Functional enrichment analysis, protein interaction and survival analysis will be further carried out. Genes of interest were verified by the Human Protein Atlas, immunohistochemistry, and encyclopedia of Cancer Cell Lines (CCLE). The relationship between genes of interest and immune cell infiltration was also analyzed by Tumor Immune Estimation Resource (TIMER). Results: Compared with ITGC patients, SRC patients were more likely to be female, tended to be younger, and have a greater tumor distribution in the middle and lower stomach (p < 0.01). SRCs showed a significantly better prognosis than ITGCs (p < 0.01) in early gastric cancer (EGC), while the prognosis of SRCs was significantly worse than ITGCs (p < 0.05) in advanced gastric cancer (AGC). A total of 256 DEGs were screened in SRCs compared to ITGCs, and the enrichment analysis and protein interactions revealed that differential genes were mainly related to extracellular matrix organization. Thrombospondin1 (THBS1) and serpin peptidase inhibitor, clade E, member 1 (SERPINE1) are significantly differentially expressed between SRC and ITGC, which has been preliminarily verified by immunohistochemistry and open-source databases. THBS1 and SERPINE1 are also associated with multiple immune cell infiltrates in gastric cancer. Conclusions: There were significant differences in the clinicopathological features and prognosis between SRC and ITGC. These results suggest that SRC and ITGC may be two distinct types of tumors with different pathogeneses. We found many codifferentially expressed genes and important pathways between SRC and ITGC. THBS1 and SERPINE1 were significantly differentially expressed in the two types of gastric cancer, and may have potentially important functions.

Lung cancer scRNA-seq and lipidomics reveal aberrant lipid metabolism for early-stage diagnosis.

Lung cancer is the leading cause of cancer mortality, and early detection is key to improving survival. However, there are no reliable blood-based tests currently available for early-stage lung cancer diagnosis. Here, we performed single-cell RNA sequencing of different early-stage lung cancers and found that lipid metabolism was broadly dysregulated in different cell types, with glycerophospholipid metabolism as the most altered lipid metabolism-related pathway. Untargeted lipidomics was carried out in an exploratory cohort of 311 participants. Through support vector machine algorithm-based and mass spectrum-based feature selection, we identified nine lipids (lysophosphatidylcholines 16:0, 18:0, and 20:4; phosphatidylcholines 16:0-18:1, 16:0-18:2, 18:0-18:1, 18:0-18:2, and 16:0-22:6; and triglycerides 16:0-18:1-18:1) as the features most important for early-stage cancer detection. Using these nine features, we developed a liquid chromatography-mass spectrometry (MS)-based targeted assay using multiple reaction monitoring. This target assay achieved 100.00% specificity on an independent validation cohort. In a hospital-based lung cancer screening cohort of 1036 participants examined by low-dose computed tomography and a prospective clinical cohort containing 109 participants, the assay reached more than 90.00% sensitivity and 92.00% specificity. Accordingly, matrix-assisted laser desorption/ionization MS imaging confirmed that the selected lipids were differentially expressed in early-stage lung cancer tissues in situ. This method, designated as Lung Cancer Artificial Intelligence Detector, may be useful for early detection of lung cancer or large-scale screening of high-risk populations for cancer prevention.

PathNarratives: Data annotation for pathological human-AI collaborative diagnosis.

Pathology is the gold standard of clinical diagnosis. Artificial intelligence (AI) in pathology becomes a new trend, but it is still not widely used due to the lack of necessary explanations for pathologists to understand the rationale. Clinic-compliant explanations besides the diagnostic decision of pathological images are essential for AI model training to provide diagnostic suggestions assisting pathologists practice. In this study, we propose a new annotation form, PathNarratives, that includes a hierarchical decision-to-reason data structure, a narrative annotation process, and a multimodal interactive annotation tool. Following PathNarratives, we recruited 8 pathologist annotators to build a colorectal pathological dataset, CR-PathNarratives, containing 174 whole-slide images (WSIs). We further experiment on the dataset with classification and captioning tasks to explore the clinical scenarios of human-AI-collaborative pathological diagnosis. The classification tasks show that fine-grain prediction enhances the overall classification accuracy from 79.56 to 85.26%. In Human-AI collaboration experience, the trust and confidence scores from 8 pathologists raised from 3.88 to 4.63 with providing more details. Results show that the classification and captioning tasks achieve better results with reason labels, provide explainable clues for doctors to understand and make the final decision and thus can support a better experience of human-AI collaboration in pathological diagnosis. In the future, we plan to optimize the tools for the annotation process, and expand the datasets with more WSIs and covering more pathological domains.

Metabolic detection and systems analyses of pancreatic ductal adenocarcinoma through machine learning, lipidomics, and multi-omics.

Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers, characterized by rapid progression, metastasis, and difficulty in diagnosis. However, there are no effective liquid-based testing methods available for PDAC detection. Here we introduce a minimally invasive approach that uses machine learning (ML) and lipidomics to detect PDAC. Through greedy algorithm and mass spectrum feature selection, we optimized 17 characteristic metabolites as detection features and developed a liquid chromatography-mass spectrometry-based targeted assay. In this study, 1033 patients with PDAC at various stages were examined. This approach has achieved 86.74% accuracy with an area under curve (AUC) of 0.9351 in the large external validation cohort and 85.00% accuracy with 0.9389 AUC in the prospective clinical cohort. Accordingly, single-cell sequencing, proteomics, and mass spectrometry imaging were applied and revealed notable alterations of selected lipids in PDAC tissues. We propose that the ML-aided lipidomics approach be used for early detection of PDAC.

A Cervical Histopathology Dataset for Computer Aided Diagnosis of Precancerous Lesions.

Cervical cancer, as one of the most frequently diagnosed cancers worldwide, is curable when detected early. Histopathology images play an important role in precision medicine of the cervical lesions. However, few computer aided algorithms have been explored on cervical histopathology images due to the lack of public datasets. In this article, we release a new cervical histopathology image dataset for automated precancerous diagnosis. Specifically, 100 slides from 71 patients are annotated by three independent pathologists. To show the difficulty of the task, benchmarks are obtained through both fully and weakly supervised learning. Extensive experiments based on typical classification and semantic segmentation networks are carried out to provide strong baselines. In particular, a strategy of assembling classification, segmentation, and pseudo-labeling is proposed to further improve the performance. The Dice coefficient reaches 0.7833, indicating the feasibility of computer aided diagnosis and the effectiveness of our weakly supervised ensemble algorithm. The dataset and evaluation codes are publicly available. To the best of our knowledge, it is the first public cervical histopathology dataset for automated precancerous segmentation. We believe that this work will attract researchers to explore novel algorithms on cervical automated diagnosis, thereby assisting doctors and patients clinically.

Triple Up-Sampling Segmentation Network With Distribution Consistency Loss for Pathological Diagnosis of Cervical Precancerous Lesions.

OBJECTIVE: Cervical cancer, as one of the most frequently diagnosed cancers in women, is curable when detected early. However, automated algorithms for cervical pathology precancerous diagnosis are limited. METHODS: In this paper, instead of popular patch-wise classification, an end-to-end patch-wise segmentation algorithm is proposed to focus on the spatial structure changes of pathological tissues. Specifically, a triple up-sampling segmentation network (TriUpSegNet) is constructed to aggregate spatial information. Second, a distribution consistency loss (DC-loss) is designed to constrain the model to fit the inter-class relationship of the cervix. Third, the Gauss-like weighted post-processing is employed to reduce patch stitching deviation and noise. RESULTS: The algorithm is evaluated on three challenging and public datasets: 1) MTCHI for cervical precancerous diagnosis, 2) DigestPath for colon cancer, and 3) PAIP for liver cancer. The Dice coefficient is 0.7413 on the MTCHI dataset, which is significantly higher than the published state-of-the-art results. CONCLUSION: Experiments on the public dataset MTCHI indicate the superiority of the proposed algorithm on cervical pathology precancerous diagnosis. In addition, the experiments on two other pathological datasets, i.e., DigestPath and PAIP, demonstrate the effectiveness and generalization ability of the TriUpSegNet and weighted post-processing on colon and liver cancers. SIGNIFICANCE: The end-to-end TriUpSegNet with DC-loss and weighted post-processing leads to improved segmentation in pathology of various cancers.