Multi-task network for automated analysis of high-resolution endomicroscopy images to detect cervical precancer and cancer.
Multi-task network for automated analysis of high-resolution endomicroscopy images to detect cervical precancer and cancer.
复制标题
DOI：
10.1016/j.compmedimag.2022.102052
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
宫颈癌是低收入和中等收入国家的一种公共卫生紧急情况，在这些国家，资源限制阻碍了标准护理预防战略。高分辨率显微内镜（HRME）是一种低成本的床旁设备，医护人员可以使用它对宫颈病变的细胞核形态进行成像。在这里，我们提出了一个深度学习框架，用于从HRME图像中诊断2级或更严重的宫颈上皮内瘤变。所提出的多任务卷积神经网络使用核分割来学习诊断相关的表示。核分割通过代理标签进行训练，以避免对昂贵的手动注释核掩模的需要。来自1600多名患者的图像数据集被用于训练、验证和测试我们的算法; 20%的患者的数据被保留用于测试。使用来自508名患者的图像的外部评估集来进一步验证我们的发现。所提出的方法始终优于其他最先进的架构，实现了0.87的受试者工作特征曲线（AUC-ROC）下每个患者面积的测试。性能与专家阴道镜检查相当，检测灵敏度和特异性分别为0.94（p=0.3）和0.58（p=1.0）。人乳头瘤病毒（HPV）感染的患者患宫颈癌的风险更高。因此，我们试图将HPV DNA检测结果作为一个特征来告知预测。我们发现，纳入患者HPV状态将检测特异性提高到0.71，灵敏度为0.94。
Cervical cancer is a public health emergency in low- and middle-income countries where resource limitations hamper standard-of-care prevention strategies. The high-resolution endomicroscope (HRME) is a low-cost, point-of-care device with which care providers can image the nuclear morphology of cervical lesions. Here, we propose a deep learning framework to diagnose cervical intraepithelial neoplasia grade 2 or more severe from HRME images. The proposed multi-task convolutional neural network uses nuclear segmentation to learn a diagnostically relevant representation. Nuclear segmentation was trained via proxy labels to circumvent the need for expensive, manually annotated nuclear masks. A dataset of images from over 1600 patients was used to train, validate, and test our algorithm; data from 20% of patients were reserved for testing. An external evaluation set with images from 508 patients was used to further validate our findings. The proposed method consistently outperformed other state-of-the art architectures achieving a test per patient area under the receiver operating characteristic curve (AUC-ROC) of 0.87. Performance was comparable to expert colposcopy with a test sensitivity and specificity of 0.94 (p=0.3) and 0.58 (p=1.0), respectively. Patients with recurrent human papillomavirus (HPV) infections are at a higher risk of developing cervical cancer. Thus, we sought to incorporate HPV DNA test results as a feature to inform prediction. We found that incorporating patient HPV status improved test specificity to 0.71 at a sensitivity of 0.94.
登录
查看更多内容
影响因子：
6.4
作者：
Hunt B;Fregnani JHTG;Brenes D;Schwarz RA;Salcedo MP;Possati-Resende JC;Antoniazzi M;de Oliveira Fonseca B;Santana IVV;de Macêdo Matsushita G;Castle PE;Schmeler KM;Richards-Kortum R
通讯作者：
Richards-Kortum R
影响因子：
25
作者：
Dworkin, Jordan D.;Linn, Kristin A.;Bassett, Danielle S.
通讯作者：
Bassett, Danielle S.
影响因子：
34.3
作者：
Arbyn, Marc;Weiderpass, Elisabete;Bray, Freddie
通讯作者：
Bray, Freddie
影响因子：
3.3
作者：
Hunt, Brady;Tavares Guerreiro Fregnani, Jose Humberto;Richards-Kortum, Rebecca
通讯作者：
Richards-Kortum, Rebecca
DOI：
10.1016/0020-7292(91)90176-6
发表时间：
1991-09-01
影响因子：
3.8
作者：
OLATUNBOSUM, OA;OKONOFUA, FE;AYANGADE, SO
通讯作者：
AYANGADE, SO