Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning
Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning
复制标题
DOI：
10.3390/app11073119
复制
发表时间：
2021-04-01
影响因子：
2.7
通讯作者：
Conde, Olga M.
中科院分区：
文献类型：
--
作者：
Saratxaga, Cristina L.;Bote, Jorge;Conde, Olga M.
特色应用光学相干断层扫描(OCT)图像对结肠息肉的自动诊断，用于开发计算机辅助诊断(CADx)应用程序。(1)背景：临床医生需要新的工具来早期诊断和改进对患者预后至关重要的结肠病变的检测。光学相干断层扫描(OCT)可以对组织进行显微镜检查，并可作为一种光学活组织检查方法，有助于做出现场诊断和治疗决定；(2)方法：获取包含94,000多张图像的小鼠(大鼠)健康、增生性和肿瘤性结肠样本数据库。提出了一种包括数据增强处理策略和深度学习模型的OCT图像自动分类(良性与恶性)的方法，并在该数据集上进行了验证。对单个B超图像和C扫描体积进行对比评估；(3)结果：使用六种不同的数据分割方法对模型进行训练和评估，得到具有统计学意义的结果。考虑到这一点，当通过B超图像进行诊断时，获得了0.9695(+/-0.0141)的敏感性和0.8094(+/-0.1524)的特异性。另一方面，当考虑整个C扫描体积的所有图像时，诊断的灵敏度为0.9821(+/-0.0197)，特异度为0.7865(+/-0.205)；(4)结论：基于深度学习的方法在结肠息肉的自动定性和光学活检范例的未来发展方面具有很大的潜力。
Featured ApplicationAutomatic diagnosis of colon polyps on optical coherence tomography (OCT) images for the development of computer-aided diagnosis (CADx) applications.(1) Background: Clinicians demand new tools for early diagnosis and improved detection of colon lesions that are vital for patient prognosis. Optical coherence tomography (OCT) allows microscopical inspection of tissue and might serve as an optical biopsy method that could lead to in-situ diagnosis and treatment decisions; (2) Methods: A database of murine (rat) healthy, hyperplastic and neoplastic colonic samples with more than 94,000 images was acquired. A methodology that includes a data augmentation processing strategy and a deep learning model for automatic classification (benign vs. malignant) of OCT images is presented and validated over this dataset. Comparative evaluation is performed both over individual B-scan images and C-scan volumes; (3) Results: A model was trained and evaluated with the proposed methodology using six different data splits to present statistically significant results. Considering this, 0.9695 (+/- 0.0141) sensitivity and 0.8094 (+/- 0.1524) specificity were obtained when diagnosis was performed over B-scan images. On the other hand, 0.9821 (+/- 0.0197) sensitivity and 0.7865 (+/- 0.205) specificity were achieved when diagnosis was made considering all the images in the whole C-scan volume; (4) Conclusions: The proposed methodology based on deep learning showed great potential for the automatic characterization of colon polyps and future development of the optical biopsy paradigm.