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) proposals. 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 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 also show the proposed feature enhancing scheme can facilitate both image-level and smear-level classification. The code and trained models are publicly available at https://github.com/CVIU-CSU/CR4CACD.
翻译:异常细胞异常检测是一项艰巨的任务,因为异常和正常细胞之间的形态差异通常是微妙的。为了确定子宫颈细胞是正常还是异常,细胞病理学家总是将周围细胞作为参照点,以确定其异常性。为了模仿这些行为,我们提议探索背景关系,以提高宫颈异常细胞检测的性能。具体地说,利用细胞之间和细胞到全球图像之间的背景关系,以加强每个感兴趣的区域(RoI)建议的特点。因此,正在开发两个模块,称为RoI-关系关注模块和全球RoI关注模块(GRAM),并调查其组合战略。我们通过使用双头快速R-CNN和功能金字塔网络(FPN)来建立强有力的基线,并将我们的RRAM和GRAM纳入其中,以验证拟议模块的有效性。在大型宫颈细胞检测数据集上进行的实验表明,RRAM和GRAM两者的采用均比基线方法(AP)。此外,当我们进行REM和GRAM-C4的C-C-CRRAM-C-C-C-C-SLALA-SLSLA-SLA-SLAD-SLAD-SLAD-S-SUD-SLV-I-I-SLV-SLV-SLO-S-SLAD-SLAF-S-SLV-S-S-S-S-S-SLAF-S-S-S-S-S-S-S-S-S-S-S-S-S-S-I-SLV-SLFLV-SD-SD-IF-S-S-S-SD-C-S-SLF-S-S-S-S-S-S-S-I-I-SD-SD-I-I-I-I-SD-SD-SD-LV-SLFAFAD-SD-SD-SD-SD-I-I-SLM-SLM-I-SL-SL-SLM-SL-SI-S-SLM-SI-I-I-I-I-I-I-I-I-SL-