AIMS: The objective of this study was to compare the image quality for DSPM and FFDM using a grading scale based on previously published articles.
MATERIALS AND METHODS: This comparative diagnostic study was done for 5-month duration at the Breast Clinic. The system used was the Lorad Selenia FFDM system and the Mammomat 3000 Nova DSPM system. The craniocaudal and mediolateral oblique projections were done on both breast on 58 asymptomatic women using both DSPM and FFDM. The mammograms were evaluated for eight criteria of image quality: Tissue coverage, compression, exposure, contrast, resolution, noise, artifact, and sharpness by two independent radiologists.
STATISTICAL ANALYSIS: Wilcoxon Signed Rank Test and Weighted Kappa.
RESULTS: FFDM was rated significantly better (P < 0.05) for five aspects: Tissue coverage, compression, contrast, exposure, and resolution and equal to DSPM for sharpness, noise, and artifact.
CONCLUSION: FFDM was superior in five aspects and equal to DSPM for three aspects of image quality.
METHODS: From February 2014 to January 2015, 214 patients underwent DM and DBT, acquired with a Siemens Mammomat Inspiration unit. 2 expert readers independently reviewed the studies in 2 steps: DM and DM+DBT, according to BI-RADS rate. Patients with BI-RADS 0, 3, 4, and 5 were recalled for work-up. Inter-reader agreement for BI-RADS rate and work-up rate were evaluated using Cohen's kappa.
RESULTS: Inter-reader agreement (κ value) for BI-RADS classification was 0.58 for DM and 0.8 for DM+DBT. DM+DBT increased the number of BI-RADS 1, 2, 4, 5 and reduced the number of BI-RADS 0 and 3 for both readers compared to DM alone. Regarding work-up rate agreement, κ was poor for DM and substantial (0.7) for DM+DBT. DM+DBT also reduced the work-up rate for both Reader 1 and Reader 2.
CONCLUSION: DM+DBT increased the number of negative and benign cases (BI-RADS 1 and 2) and suspicious and malignant cases (BI-RADS 4 and 5), while it reduced the number of BI-RADS 0 and 3. DM+DBT also improved inter-reader agreement and reduced the overall recall for additional imaging or short-interval follow-up.
METHODS: The pterygium screening system was tested on two normal eye databases (UBIRIS and MILES) and two pterygium databases (Australia Pterygium and Brazil Pterygium). This system comprises four modules: (i) a preprocessing module to enhance the pterygium tissue using HSV-Sigmoid; (ii) a segmentation module to differentiate the corneal region and the pterygium tissue; (iii) a feature extraction module to extract corneal features using circularity ratio, Haralick's circularity, eccentricity, and solidity; and (iv) a classification module to identify the presence or absence of pterygium. System performance was evaluated using support vector machine (SVM) and artificial neural network.
RESULTS: The three-step frame differencing technique was introduced in the corneal segmentation module. The output image successfully covered the region of interest with an average accuracy of 0.9127. The performance of the proposed system using SVM provided the most promising results of 88.7%, 88.3%, and 95.6% for sensitivity, specificity, and area under the curve, respectively.
CONCLUSION: A basic platform for computer-aided pterygium screening was successfully developed using the proposed modules. The proposed system can classify pterygium and non-pterygium cases reasonably well. In our future work, a standard grading system will be developed to identify the severity of pterygium cases. This system is expected to increase the awareness of communities in rural areas on pterygium.