Advancing Bag-of-Visual-Words Representations for Lesion Classification in Retinal Images

Autor(es)

Pires, Ramon ^[1] ; Jelinek, Herbert F. ^{[2, 3]} ; Wainer, Jacques ^[1] ; Valle, Eduardo ^[4] ; Rocha, Anderson ^[1]

Afiliação do(s) autor(es)

^[1] Univ Campinas UNICAMP, Inst Comp, Sao Paulo - Brazil

^[2] Khalifa Univ, Dept Biomed Engn, Abu Dhabi - U Arab Emirates

^[3] Macquarie Univ, Australian Sch Adv Med, N Ryde, NSW - Australia

^[4] Univ Campinas UNICAMP, Sch Elect & Comp Engn, Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: PLoS One; v. 9, n. 6 JUN 2 2014.
• Citações Web of Science: 26

Resumo

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 +/- 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors. (AU)

• Processo FAPESP: 11/15349-3 - Técnicas de Fusão de Classificadores para um Sistema Automático de Triagem de Retinopatia Diabética
• Beneficiário: José Ramon Trindade Pires
• Modalidade de apoio: Bolsas no Brasil - Mestrado
• Processo FAPESP: 10/05647-4 - Computação forense e criminalística de documentos: coleta, organização, classificação e análise de evidências
• Beneficiário: Anderson de Rezende Rocha
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores