METHODS: The dataset used in this study has been acquired by the Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. The dataset consists of 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with resolution of 1024 px × 512 px, resulting in more than 3800 images being processed. All SD-OCT volumes are read and assessed by trained graders and identified as normal or DME cases based on evaluation of retinal thickening, hard exudates, intraretinal cystoid space formation, and subretinal fluid. Within the DME sub-set, a large number of lesions has been selected to create a rather complete and diverse DME dataset. This paper presents an automatic classification framework for SD-OCT volumes in order to identify DME versus normal volumes. In this regard, a generic pipeline including pre-processing, feature detection, feature representation, and classification was investigated. More precisely, extraction of histogram of oriented gradients and local binary pattern (LBP) features within a multiresolution approach is used as well as principal component analysis (PCA) and bag of words (BoW) representations.
RESULTS AND CONCLUSION: Besides comparing individual and combined features, different representation approaches and different classifiers are evaluated. The best results are obtained for LBP[Formula: see text] vectors while represented and classified using PCA and a linear-support vector machine (SVM), leading to a sensitivity(SE) and specificity (SP) of 87.5 and 87.5%, respectively.
METHODS: A 3D-printed cardiac insert and Catphan 500 phantoms were scanned using CCTA protocols at 120 and 100 kVp tube voltages. All CT acquisitions were reconstructed using filtered back projection (FBP) and Adaptive Statistical Iterative Reconstruction (ASIR) algorithm at 40% and 60% strengths. Image quality characteristics such as image noise, signal-noise ratio (SNR), contrast-noise ratio (CNR), high spatial resolution, and low contrast resolution were analyzed.
RESULTS: There was no significant difference (P > 0.05) between 120 and 100 kVp measures for image noise for FBP vs ASIR 60% (16.6 ± 3.8 vs 16.7 ± 4.8), SNR of ASIR 40% vs ASIR 60% (27.3 ± 5.4 vs 26.4 ± 4.8), and CNR of FBP vs ASIR 40% (31.3 ± 3.9 vs 30.1 ± 4.3), respectively. Based on the Modulation Transfer Function (MTF) analysis, there was a minimal change of image quality for each tube voltage but increases when higher strengths of ASIR were used. The best measure of low contrast detectability was observed at ASIR 60% at 120 kVp.
CONCLUSIONS: Changing the IR strength has yielded different image quality noise characteristics. In this study, the use of 100 kVp and ASIR 60% yielded comparable image quality noise characteristics to the standard CCTA protocols using 120 kVp of ASIR 40%. A combination of 3D-printed and Catphan® 500 phantoms could be used to perform CT dose optimization protocols.