2014 · 20 citations · 23 references
Veterinary MedicineOphthalmologyRadiologyDiagnostic ImagingUltrasonographyUltrasoundCataract AssessmentCataract EvaluationCataract SurgeryOcular UltrasonographyOphthalmic ImagingSupport Vector MachinesCataract ClassificationCataract DiagnosisCataract ImagingImmersionMulticlass ClassificationMulticlass Support Vector MachinesSupport Vector Machine Classification
In the present work, ultrasound A-scan signals were acquired from healthy and cataractous porcine lenses. B-mode images were reconstructed from the collected signals. The parametric Nakagami images were subsequently constructed from the B-mode images. Acoustical and spectral parameters were obtained from the central region of the lens. Image textural parameters were extracted from the B-scan and Nakagami images. Ninety-seven parameters were extracted from a total of 75 healthy and 135 cataractous lenses. Lenses with cataract were split in two groups: incipient and advanced cataract, corresponding to a 60 and 120 minutes of immersion time in a cataract induction solution, respectively. The obtained parameters were subjected to feature selection with Principal Component Analysis (PCA) and used for classification through a multiclass Support Vector Machine (SVM). This paper shows that multiclass SVM can perform effectively the classification of the cataract severity, with an overall performance of 89%, classifying correctly 93% of the features.
23
Norden E. Huang, Steven Long, Man‐Li C. Wu et al. · Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences · 1998 · 23.3K citations · Full text
Computing, Computational Engineering, Biomedical Signal Processing +16
A support vector machine approach for detection of microcalcifications
I. El-Naqa, Yongyi Yang, M.N. Wernick et al. · IEEE Transactions on Medical Imaging · 2002 · 574 citations