Search

Endometrial cancer screening is crucial for clinical treatment. Currently, cytopathologists analyze cytopathology images is considered a popular screening method, but manual diagnosis is time-consuming and laborious. Deep learning can provide objective guidance efficiency. But endometrial cytopathology images often come from different medical centers with different staining styles. It decreases the generalization ability of deep learning models in cytopathology images analysis, leading to poor performance. This study presents a robust automated screening framework for endometrial cancer that can be applied to cytopathology images with different staining styles, and provide an objective diagnostic reference for cytopathologists, thus contributing to clinical treatment. We collected and built the XJTU-EC dataset, the first cytopathology dataset that includes segmentation and classification labels. And we propose an efficient two-stage framework for adapting different staining style images, and screening endometrial cancer at the cellular level. Specifically, in the first stage, a novel CM-UNet is utilized to segment cell clumps, with a channel attention (CA) module and a multi-level semantic supervision (MSS) module. It can ignore staining variance and focus on extracting semantic information for segmentation. In the second stage, we propose a robust and effective classification algorithm based on contrastive learning, ECRNet. By momentum-based updating and adding labeled memory banks, it can reduce most of the false negative results. On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. Our method robustly predicts endometrial cancer on cytopathologic images with different staining styles, which will further advance research in endometrial cancer screening and provide early diagnosis for patients. The code will be available on GitHub. [ABSTRACT FROM AUTHOR]

Background: In the study, we aimed to evaluate the ability of micro‐histology combined with cytology to improve the quality of slides and diagnose endometrial lesions. Methods: Endometrial specimens were collected from Li Brushes. Every specimen was prepared for micro‐histological and cytological slides, using cell block (CB) and liquid‐based cytology (LBC) technologies. Semi‐quantitative scoring system was used to evaluate the qualities of slides. CB slides were assessed by 5‐category scoring system. Diagnostic accuracy was calculated in LBC, CB, and LBC + CB groups based on the histological gold standard. Endometrial atypical hyperplasia, and endometrial cancer were considered positive, whereas others were considered negative. Results: A total of 167 patients were enrolled. CB slides were inferior to LBC slides only in cellularity (p < 0.001), but superior in the other six parameters (all p < 0.001). The satisfaction rate of micro‐histology accounted for 92.3%. The accuracy index in the CB group was higher than in the LBC group in terms of sensitivity (85.5% vs. 82.7%) and specificity (98.9% vs. 95.7%). The sensitivity and specificity in the LBC + CB group were increased to 94.2% and 99.0%, respectively. Conclusions: The quality of micro‐histological slides was higher than that of cytological slides. By combining micro‐histology with cytology, higher accuracy was achieved for endometrial lesions diagnosis. [ABSTRACT FROM AUTHOR]