Qian Huang

An efficient Fusion-Purification Network for Cervical pap-smear image classification

In cervical cell diagnostics, autonomous screening technology constitutes the foundation of automated diagnostic systems. Currently, numerous deep learning-based classification techniques have been successfully implemented in the analysis of cervical cell images, yielding favorable outcomes. Nevertheless, efficient discrimination of cervical cells continues to be challenging due to large intra-class and small inter-class variations. The key to dealing with this problem is to capture localized informative differences from cervical cell images and to represent discriminative features efficiently. Existing methods neglect the importance of global morphological information, resulting in inadequate feature representation capability. To address this limitation, we propose a novel cervical cell classification model that focuses on purified fusion information. Specifically, we first integrate the detailed texture information and morphological structure features, named cervical pathology information fusion. Second, in order to enhance the discrimination of cervical cell features and address the data redundancy and bias inherent after fusion, we design a cervical purification bottleneck module. This model strikes a balance between leveraging purified features and facilitating high-efficiency discrimination. Furthermore, we intend to unveil a more intricate cervical cell dataset: Cervical Cytopathology Image Dataset (CCID). Extensive experiments on two real-world datasets show that our proposed model outperforms state-of-the-art cervical cell classification models. The results show that our method can well help pathologists to accurately evaluate cervical smears.

Circulating Tumor Cells Counting Act as a Potential Prognostic Factor in Cervical Cancer

Background: Circulating tumor cells (CTCs) hold huge potential for both clinical applications and basic research into the management of cancer, but the relationship between CTC count and cervical cancer prognosis remains unclear. Therefore, research on this topic is urgently required. Objective: This study investigated whether CTCs were detectable in patients with cervical cancer and whether CTC count was an indicator of prognosis. Methods: We enrolled 107 patients with pathologically confirmed cervical cancer. CTCs were detected after radiotherapy or concurrent cisplatin-containing chemotherapy in all patients. We evaluated all medical records and imaging data as well as follow-up information to calculate progression-free survival (PFS). PFS was defined as the time until first diagnosis of tumor progression or death. We also analyzed the relationship between CTC count and patient age, disease stage, histological differentiation, tumor size, and pathological type. Results: CTCs were identified in 86 of 107 patients (80%), and the CTC count ranged from 0 to 27 cells in 3.2 mL blood. The median progression-free survival (PFS) was 43.1 months. Patients in which CTCs were detected had a significantly shorter PFS than CTC-negative patients (P = 0.018). Multivariate analysis indicated that CTC count was an independent negative prognostic factor for survival. However, no correlation was observed between CTC count and patient age, disease stage, histological differentiation, tumor size, and pathological type. Conclusion: CTC count is an independent negative prognostic factor for cervical cancer.