Center for Cancer Biology, Vlaams Instituut voor Biotechnologie (VIB), Belgium; Department of Oncology, Katholieke Universiteit (KU) Leuven, Belgium; Department of Biomedical Science and Engineering (BMSE), Institute of Integrated Technology (IIT), Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea.
Department of Biomedical Science and Engineering (BMSE), Institute of Integrated Technology (IIT), Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea.
Comput Methods Programs Biomed. 2023 Oct;240:107718. doi: 10.1016/j.cmpb.2023.107718. Epub 2023 Jul 10.
Cervical cancer affects around 0.5 million women per year, resulting in over 0.3 million fatalities. Therefore, repetitive screening for cervical cancer is of utmost importance. Computer-assisted diagnosis is key for scaling up cervical cancer screening. Current recognition algorithms, however, perform poorly on the whole-slide image (WSI) analysis, fail to generalize for different staining methods and on uneven distribution for subtype imaging, and provide sub-optimal clinical-level interpretations. Herein, we developed CervixFormer-an end-to-end, multi-scale swin transformer-based adversarial ensemble learning framework to assess pre-cancerous and cancer-specific cervical malignant lesions on WSIs.
The proposed framework consists of (1) a self-attention generative adversarial network (SAGAN) for generating synthetic images during patch-level training to address the class imbalanced problems; (2) a multi-scale transformer-based ensemble learning method for cell identification at various stages, including atypical squamous cells (ASC) and atypical squamous cells of undetermined significance (ASCUS), which have not been demonstrated in previous studies; and (3) a fusion model for concatenating ensemble-based results and producing final outcomes.
In the evaluation, the proposed method is first evaluated on a private dataset of 717 annotated samples from six classes, obtaining a high recall and precision of 0.940 and 0.934, respectively, in roughly 1.2 minutes. To further examine the generalizability of CervixFormer, we evaluated it on four independent, publicly available datasets, namely, the CRIC cervix, Mendeley LBC, SIPaKMeD Pap Smear, and Cervix93 Extended Depth of Field image datasets. CervixFormer obtained a fairly better performance on two-, three-, four-, and six-class classification of smear- and cell-level datasets. For clinical interpretation, we used GradCAM to visualize a coarse localization map, highlighting important regions in the WSI. Notably, CervixFormer extracts feature mostly from the cell nucleus and partially from the cytoplasm.
In comparison with the existing state-of-the-art benchmark methods, the CervixFormer outperforms them in terms of recall, accuracy, and computing time.
每年约有 50 万女性受到宫颈癌的影响，导致超过 30 万人死亡。因此，重复性的宫颈癌筛查至关重要。计算机辅助诊断是扩大宫颈癌筛查规模的关键。然而，目前的识别算法在全切片图像（WSI）分析方面表现不佳，无法针对不同的染色方法和亚型成像的不均匀分布进行泛化，并且提供的临床水平解释也不是最佳的。在此，我们开发了 CervixFormer，这是一种基于端到端、多尺度 Swin 变换的对抗式集成学习框架，用于评估 WSI 上的癌前和癌症特异性宫颈恶性病变。
所提出的框架包括：（1）自注意生成对抗网络（SAGAN），用于在斑块级训练过程中生成合成图像，以解决类不平衡问题；（2）一种基于多尺度变换的集成学习方法，用于在不同阶段识别细胞，包括非典型鳞状细胞（ASC）和意义未明的非典型鳞状细胞（ASCUS），这在以前的研究中尚未得到证明；（3）融合模型，用于连接基于集成的结果并生成最终结果。
在评估中，首先在来自六个类别的 717 个注释样本的私有数据集上评估该方法，在大约 1.2 分钟内分别获得了 0.940 和 0.934 的高召回率和精度。为了进一步检查 CervixFormer 的泛化能力，我们在四个独立的公共数据集上评估了它，即 CRIC cervix、Mendeley LBC、SIPaKMeD Pap Smear 和 Cervix93 Extended Depth of Field 图像数据集。CervixFormer 在涂片和细胞级数据集的两、三、四和六类分类中均取得了相当好的性能。对于临床解释，我们使用 GradCAM 生成一个粗略的定位图，突出显示 WSI 中的重要区域。值得注意的是，CervixFormer 主要从细胞核中提取特征，部分从细胞质中提取特征。
与现有的最先进的基准方法相比，CervixFormer 在召回率、准确性和计算时间方面都表现得更好。
