Guo Peng, Xue Zhiyun, Jeronimo Jose, Gage Julia C, Desai Kanan T, Befano Brian, García Francisco, Long L Rodney, Schiffman Mark, Antani Sameer
Communications Engineering Branch, Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA.
Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, Rockville, MD 20850, USA.
J Clin Med. 2021 Mar 1;10(5):953. doi: 10.3390/jcm10050953.
Uterine cervical cancer is a leading cause of women's mortality worldwide. Cervical tissue ablation is an effective surgical excision of high grade lesions that are determined to be precancerous. Our prior work on the Automated Visual Examination (AVE) method demonstrated a highly effective technique to analyze digital images of the cervix for identifying precancer. Next step would be to determine if she is treatable using ablation. However, not all women are eligible for the therapy due to cervical characteristics. We present a machine learning algorithm that uses a deep learning object detection architecture to determine if a cervix is eligible for ablative treatment based on visual characteristics presented in the image. The algorithm builds on the well-known RetinaNet architecture to derive a simpler and novel architecture in which the last convolutional layer is constructed by upsampling and concatenating specific RetinaNet pretrained layers, followed by an output module consisting of a Global Average Pooling (GAP) layer and a fully connected layer. To explain the recommendation of the deep learning algorithm and determine if it is consistent with lesion presentation on the cervical anatomy, we visualize classification results using two techniques: our (i) Class-selective Relevance Map (CRM), which has been reported earlier, and (ii) Class Activation Map (CAM). The class prediction heatmaps are evaluated by a gynecologic oncologist with more than 20 years of experience. Based on our observation and the expert's opinion, the customized architecture not only outperforms the baseline RetinaNet network in treatability classification, but also provides insights about the features and regions considered significant by the network toward explaining reasons for treatment recommendation. Furthermore, by investigating the heatmaps on Gaussian-blurred images that serve as surrogates for out-of-focus cervical pictures we demonstrate the effect of image quality degradation on cervical treatability classification and underscoring the need for using images with good visual quality.
子宫颈癌是全球女性死亡的主要原因。宫颈组织消融是一种有效的手术切除方法，用于切除被确定为癌前病变的高级别病变。我们之前关于自动视觉检查（AVE）方法的研究展示了一种高效技术，可分析子宫颈的数字图像以识别癌前病变。下一步是确定她是否适合使用消融治疗。然而，由于宫颈特征，并非所有女性都适合这种治疗。我们提出了一种机器学习算法，该算法使用深度学习目标检测架构，根据图像中呈现的视觉特征来确定子宫颈是否适合进行消融治疗。该算法基于著名的RetinaNet架构构建，以派生一种更简单新颖的架构，其中最后一个卷积层通过对特定的RetinaNet预训练层进行上采样和拼接来构建，随后是一个由全局平均池化（GAP）层和一个全连接层组成的输出模块。为了解释深度学习算法的建议并确定其是否与宫颈解剖结构上的病变表现一致，我们使用两种技术可视化分类结果：（i）我们之前报道过的类选择性相关映射（CRM），以及（ii）类激活映射（CAM）。类预测热图由一位拥有20多年经验的妇科肿瘤学家进行评估。基于我们的观察和专家意见，定制架构不仅在可治疗性分类方面优于基线RetinaNet网络，还提供了有关网络认为重要的特征和区域的见解，以解释治疗建议的原因。此外，通过研究高斯模糊图像上的热图（这些图像可作为失焦宫颈图片的替代），我们展示了图像质量下降对宫颈可治疗性分类的影响，并强调了使用具有良好视觉质量图像的必要性。
