An efficient multi-level pre-processing algorithm for the enhancement of dermoscopy images in melanoma detection

In this paper, a multi-level algorithm for pre-processing of dermoscopy images is proposed, which helps in improving the quality of the raw images, making it suitable for skin lesion detection. This multi-level pre-processing method has a positive impact on automated skin lesion segmentation using Regularized Extreme Learning Machine. Raw images are subjected to de-noising, illumination correction, contrast enhancement, sharpening, reflection removal, and virtual shaving before the skin lesion segmentation. The Non-Local Means (NLM) filter with lowest Blind Reference less Image Spatial Quality Evaluator (BRISQUE) score exhibits better de-noising of dermoscopy images. To suppress uneven illumination, gamma correction is subjected to the denoised image. The Robust Image Contrast Enhancement (RICE) algorithm is used for contrast enhancement, and produces enhanced images with better structural preservation and negligible loss of information. Unsharp masking for sharpening exhibits low BRISQUE scores for better sharpening of fine details in an image. Output images produced by the phase congruency-based method in virtual shaving show high similarity with ground truth images as the hair is removed completely from the input images. Obtained scores at each stage of pre-processing framework show that the performance is superior compared to all the existing methods, both qualitatively and quantitatively, in terms of uniform contrast, preservation of information content, removal of undesired information, and elimination of artifacts in melanoma images. The output of the proposed system is assessed qualitatively and quantitatively with and without pre-processing of dermoscopy images. From the overall evaluation results, it is found that the segmentation of skin lesion is more efficient using Regularized Extreme Learning Machine if the multi-level pre-processing steps are used in proper sequence.

Hybrid multi-kernel SVM algorithm for detection of microaneurysm in color fundus images

Diabetic retinopathy (DR) is a chronic disease that may cause vision loss in diabetic patients. Microaneurysms which are characterized by small red spots on the retina due to fluid or blood leakage from the weak capillary wall often occur during the early stage of DR, making screening at this stage is essential. In this paper, an automatic screening system for early detection of DR in retinal images is developed using a combined shape and texture features. Due to minimum number of hand-crafted features, the computational burden is much reduced. The proposed hybrid multi-kernel support vector machine classifier is constructed by learning a kernel model formed as a combination of the base kernels. This approach outperforms the recent deep learning techniques in terms of the evaluation metrics. The efficiency of the proposed scheme is experimentally validated on three public datasets - Retinopathy Online Challenge, DIARETdB1, MESSIDOR, and AGAR300 (developed for this study). Studies reveal that the proposed model produced the best results of 0.503 in ROC dataset, 0.481 in DIARETdB1, and 0.464 in the MESSIDOR dataset in terms of FROC score. The AGAR300 database outperforms the existing MA detection algorithm in terms of FROC, AUC, F1 score, precision, sensitivity, and specificity which guarantees the robustness of this system.

Cardiovascular Risk Prediction using JBS3 Tool: A Kerala based Study

Background:

Accuracy of Joint British Society calculator3 (JBS3) cardiovascular (CV) risk assessment tool may vary across the Indian states, which is not verified in south Indian, Kerala based population.

Objectives:

To evaluate the traditional risk factors (TRFs) based CV risk estimation done in Kerala based population.

Methods:

This cross-sectional study uses details of 977 subjects aged between 30 and 80 years, recorded from the medical archives of clinical locations at Ernakulum district, in Kerala. The risk categories used are Low (<7.5%), Intermediate (≥7.5% and <20%), and High (≥20%) 10-year risk classifications. The lifetime classifications are Low lifetime (≤39%) and High lifetime (≥40%) are used. The study evaluated using statistical analysis; the Chi-square test was used for dependent and categorical CV risk variable comparisons. A multivariate ordinal logistic regression analysis for the 10-year risk and odds logistic regression analysis for the lifetime risk model identified the significant risk variables.

Results:

The mean age of the study population is 52.56±11.43 years. With 39.1% in low, 25.0% in intermediate, and 35.9% has high 10-year risk. Low lifetime risk with 41.1%, the high lifetime risk has 58.9% subjects. The intermediate 10-year risk category shows the highest reclassifications to High lifetime risk. The Hosmer-Lemeshow goodness-of-fit statistics indicates a good model fit.

Conclusion:

Timely interventions using risk predictions can aid in appropriate therapeutic and lifestyle modifications useful for primary prevention. Precaution to avoid short-term incidences and reclassifications to a high lifetime risk can reduce the CVD related mortality rates.

Relative Estimate of Revised Cardiovascular Risk Combining Traditional and Non-traditional Image-based CV Markers: A Kerala Based Study

BACKGROUND

Non-traditional image markers can improve the traditional cardiovascular risk estimation, is untested in Kerala based participants.

OBJECTIVE

To identify the relationship between the 'Modified CV risk' categories with traditional and non-traditional image-based risk markers. The correlation and improvement in reclassification, achieved by pooling atherosclerotic non-traditional markers with Intermediate (≥7.5% and <20%) and High (≥20%) 10-year participants is evaluated.

METHODS

The cross-sectional study with 594 participants has the ultrasound measurements recorded from the medical archives of clinical locations at Ernakulum district, Kerala. With carotid Intima-Media Thickness (cIMT) measurement, the Plaque (cP) complexity was computed using selected plaque characteristics to compute the carotid Total Plaque Risk Score (cTPRS) for superior risk tagging. Statistical analysis was done using RStudio, the classification accuracy was verified using the decision tree algorithm.

RESULTS

The mean age of the participants was (58.14±10.05) years. The mean cIMT was (0.956±0.302) mm, with 65.6% plaque incidence. With 94.90% variability around its mean, the Multinomial Logistic Regression model identifies cIMT and cTPRS, age, diabetics, Familial Hypercholesterolemia (FH), Hypertension treatment, the presence of Rheumatoid Arthritis (RA), Chronic Kidney Disease (CKD) as significant (p<0.05). cIMT and cP were found significant for 'Intermediate High', 'High' and 'Very High' 'Modified CV risk' categories. However, age, diabetes, gender and use of hypertension treatment are significant for the 'Intermediate' 'Modified CV risk' category. The overall performance of the MLR model was 80.5%. The classification accuracy verified using the decision tree algorithm has 78.7% accuracy.

CONCLUSION

The use of atherosclerotic markers shows a significant correlation suitable for a nextlevel reclassification of the traditional CV risk.