ACNet: Enhancing Occlusion Awareness and Multi-Scale feature Capture for Cervical Cell Segmentation

Cell segmentation is critical for early cervical cancer screening, yet it faces challenges inherent in cervical cell images, such as cell occlusion and scale diversity. In this paper we proposed an innovative cell image segmentation framework called ACNet. This framework employs an Easy-to-Difficult Indirect Decoupling Strategy (EDS), combined with a Feature Refinement Module (FRM), to improve the model’s perception of occluded instances and invisible regions. Additionally, we designed a Squeeze-and-Excitation Module (SEM) and a Point Supervision Module (PSM) to improve the model’s ability to capture features of larger occluded cells and smaller cells in low-contrast images, respectively. We verified our method using two occlusion cytology image segmentation datasets, and compared it with state of the art segmentation methods. ACNet achieved superior segmentation results on cervical cell images with cell occlusion and scale diversity. This study provides an important driving force for early screening for cervical cancer.