期刊
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
卷 27, 期 8, 页码 4086-4097出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2023.3276919
关键词
Feature extraction; Lesions; Image segmentation; Detectors; Proposals; Object detection; Cervical cancer; Cervical cytology screening; contextual relationships; object detection; whole slide image
To improve the performance of cervical abnormal cell detection, we propose a method that utilizes contextual relationships. By exploring the relationships between cells and cell-to-global images, the features of each region of interest are enhanced. Our experiments on a large dataset validate the effectiveness of the proposed method by achieving better average precision (AP) than baseline methods.
Cervical abnormal cell detection is a challenging task as the morphological discrepancies between abnormal and normal cells are usually subtle. To determine whether a cervical cell is normal or abnormal, cytopathologists always take surrounding cells as references to identify its abnormality. To mimic these behaviors, we propose to explore contextual relationships to boost the performance of cervical abnormal cell detection. Specifically, both contextual relationships between cells and cell-to-global images are exploited to enhance features of each region of interest (RoI) proposal. Accordingly, two modules, dubbed as RoI-relationship attention module (RRAM) and global RoI attention module (GRAM), are developed and their combination strategies are also investigated. We establish a strong baseline by using Double-Head Faster R-CNN with a feature pyramid network (FPN) and integrate our RRAM and GRAM into it to validate the effectiveness of the proposed modules. Experiments conducted on a large cervical cell detection dataset reveal that the introduction of RRAM and GRAM both achieves better average precision (AP) than the baseline methods. Moreover, when cascading RRAM and GRAM, our method outperforms the state-of-the-art (SOTA) methods. Furthermore, we show that the proposed feature-enhancing scheme can facilitate image- and smear-level classification.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据