期刊
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
卷 97, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compmedimag.2022.102052
关键词
Endomicroscopy; Cervical precancer; Multi-task learning; Point-of-care
资金
- National Cancer Institute [R01 CA251911, R01 CA186132, UH2/UH3 CA189910, P30 CA016672]
- NSF [CCF-1911094, IIS-1838177, IIS-1730574]
- ONR [N00014-18-12571, N00014-20-1-2534, N00014-18-1-2047, MURI N00014-20-1-2787]
- AFOSR [FA9550-18-1-0478]
- Vannevar Bush Faculty Fellowship
Cervical cancer is a public health emergency in low- and middle-income countries, where resource limitations hinder effective prevention. This study proposes a deep learning framework that uses a low-cost device called high-resolution endomicroscope (HRME) to diagnose cervical intraepithelial neoplasia grade 2 or more severe. The study shows that the proposed method outperforms other state-of-the-art architectures and achieves comparable performance to expert colposcopy. Incorporating HPV DNA test results as a feature improves the specificity of the diagnosis.
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.
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