Beyond Lesion-Based Diabetic Retinopathy: A Direct Approach for Referral
Beyond Lesion-Based Diabetic Retinopathy: A Direct Approach for Referral
复制标题
DOI：
10.1109/jbhi.2015.2498104
复制
发表时间：
2017-01-01
影响因子：
7.7
通讯作者：
Rocha, Anderson
中科院分区：
文献类型：
--
作者：
Pires, Ramon;Avila, Sandra;Rocha, Anderson
糖尿病视网膜病变（DR）是成人失明的主要原因，但如果早期发现，可以进行管理。自动化DR筛查有助于指示哪些患者应该转诊给医生。然而，目前的自动筛查技术仍然过于依赖于单个病变的检测。在本研究中，我们绕过病变检测，直接训练分类器进行DR转诊。其他的创新是使用最先进的中级功能的视网膜图像：BossaNova和Fisher矢量。这些特征扩展了经典的视觉词袋，大大提高了复杂分类任务的准确性。所提出的直接转诊技术是有前途的，实现了96.4%的曲线下面积，因此，减少了近40%的分类错误，比目前的最先进的，由病变为基础的技术。
Diabetic retinopathy (DR) is the leading cause of blindness in adults, but can be managed if detected early. Automated DR screening helps by indicating which patients should be referred to the doctor. However, current techniques of automated screening still depend too much on the detection of individual lesions. In this study, we bypass lesion detection, and directly train a classifier for DR referral. Additional novelties are the use of state-of-the-art mid-level features for the retinal images: BossaNova and Fisher Vector. Those features extend the classical Bags of Visual Words and greatly improve the accuracy of complex classification tasks. The proposed technique for direct referral is promising, achieving an area under the curve of 96.4%, thus, reducing the classification error by almost 40% over the current state of the art, held by lesion-based techniques.