Microaneurysms detection in color fundus images using machine learning based on directional local contrast.

BACKGROUND: As one of the major complications of diabetes, diabetic retinopathy (DR) is a leading cause of visual impairment and blindness due to delayed diagnosis and intervention. Microaneurysms appear as the earliest symptom of DR. Accurate and reliable detection of microaneurysms in color fundus images has great importance for DR screening. METHODS: A microaneurysms' detection method using machine learning based on directional local contrast (DLC) is proposed for the early diagnosis of DR. First, blood vessels were enhanced and segmented using improved enhancement function based on analyzing eigenvalues of Hessian matrix. Next, with blood vessels excluded, microaneurysm candidate regions were obtained using shape characteristics and connected components analysis. After image segmented to patches, the features of each microaneurysm candidate patch were extracted, and each candidate patch was classified into microaneurysm or non-microaneurysm. The main contributions of our study are (1) making use of directional local contrast in microaneurysms' detection for the first time, which does make sense for better microaneurysms' classification. (2) Applying three different machine learning techniques for classification and comparing their performance for microaneurysms' detection. The proposed algorithm was trained and tested on e-ophtha MA database, and further tested on another independent DIARETDB1 database. Results of microaneurysms' detection on the two databases were evaluated on lesion level and compared with existing algorithms. RESULTS: The proposed method has achieved better performance compared with existing algorithms on accuracy and computation time. On e-ophtha MA and DIARETDB1 databases, the area under curve (AUC) of receiver operating characteristic (ROC) curve was 0.87 and 0.86, respectively. The free-response ROC (FROC) score on the two databases was 0.374 and 0.210, respectively. The computation time per image with resolution of 2544×1969, 1400×960 and 1500×1152 is 29 s, 3 s and 2.6 s, respectively. CONCLUSIONS: The proposed method using machine learning based on directional local contrast of image patches can effectively detect microaneurysms in color fundus images and provide an effective scientific basis for early clinical DR diagnosis.

Protective Effects of Tirofiban on Myocardial Ischemia-Reperfusion Injury in Rabbits.

We aimed to explore the different protective effects of tirofiban on myocardial ischemia-reperfusion (IR) injury in New Zealand white rabbits by comparing the results from different administration methods. Fifty New Zealand white rabbits were randomly divided into a sham group (group A, n = 10) and four IR groups (group B, IR group with injection of physiological saline; group C, tirofiban administered through marginal ear vein after reperfusion; group D, tirofiban injected through coronary ostia before reperfusion; group E, tirofiban injected through coronary artery after blood flow restoration; all n = 10). Myocardial IR injury models were prepared in IR groups. An automatic biochemical analyzer (HITACHI 7020, Japan) was applied for testing serum creatine kinase-MB levels. The myeloperoxidase activity, malondialdehyde levels, nitric oxide synthase activity, and nitric oxide (NO) volume were detected 180 minutes after reperfusion. The myocardial apoptosis was identified using the terminal deoxynucleotidyl transferase-mediated dUTP-biotin nick end labeling technique, and the protein expressions of B-cell lymphoma-2, Bcl-2 associated X, and aquaporin-1 were measured through Western blot. The highest and lowest ST-segment resolution among the IR groups was observed in groups E and B, respectively. The creatine kinase-MB levels at 60, 120, and 180 minutes in group E was greatly decreased than in groups B, C, and D. Compared with the sham group, the IR groups demonstrated evidently elevated myeloperoxidase activity, malondialdehyde levels, inducible NOS activity, NO volume, myocardial apoptotic index, and aquaporin-1 expressions; among the IR groups, these indicators were increased and decreased most in groups B and E, respectively. The B-cell lymphoma-2/Bcl-2 associated X ratio in the IR groups were evidently higher than the sham group, with the highest and lowest rate in groups E and B, respectively. Tirofiban injection through coronary artery after blood flow restoration has a better protective effect against myocardial IR injury than tirofiban administration through coronary ostia before reperfusion and tirofiban injection through the auricular vein after reperfusion.

Automatic Detection of Hard Exudates in Color Retinal Images Using Dynamic Threshold and SVM Classification: Algorithm Development and Evaluation.

Diabetic retinopathy (DR) is one of the most common causes of visual impairment. Automatic detection of hard exudates (HE) from retinal photographs is an important step for detection of DR. However, most of existing algorithms for HE detection are complex and inefficient. We have developed and evaluated an automatic retinal image processing algorithm for HE detection using dynamic threshold and fuzzy C-means clustering (FCM) followed by support vector machine (SVM) for classification. The proposed algorithm consisted of four main stages: (i) imaging preprocessing; (ii) localization of optic disc (OD); (iii) determination of candidate HE using dynamic threshold in combination with global threshold based on FCM; and (iv) extraction of eight texture features from the candidate HE region, which were then fed into an SVM classifier for automatic HE classification. The proposed algorithm was trained and cross-validated (10 fold) on a publicly available e-ophtha EX database (47 images) on pixel-level, achieving the overall average sensitivity, PPV, and F-score of 76.5%, 82.7%, and 76.7%. It was tested on another independent DIARETDB1 database (89 images) with the overall average sensitivity, specificity, and accuracy of 97.5%, 97.8%, and 97.7%, respectively. In summary, the satisfactory evaluation results on both retinal imaging databases demonstrated the effectiveness of our proposed algorithm for automatic HE detection, by using dynamic threshold and FCM followed by an SVM for classification.

Platelet activation through the efficacy of aspirin in congenital heart disease patients undergoing transcatheter closure of atrial septal defects or ventricular septal defects.

OBJECTIVES: The aim of this study is to compare preoperative and postoperative conditions of GMP-140 concentration, the aggregation and activation of platelets in congenital heart disease patients undergoing transcatheter closure of atrial septal defects (ASDs) or ventricular septal defects (VSDs), and the appropriate dose of aspirin of patients after transcatheter closure. MATERIALS AND METHODS: Thirty-two consecutive patients with ASD (n=16) and VSD (n=16), as shown on transthoracic echocardiography and right heart catheter examination, were treated with a percutaneous catheter occlusion. The patients comprised 13 males and 19 females with a mean age of 25.6±9.15. Patients were randomly assigned into two groups within half an hour after ASD or VSD occlusion. Group A cases were treated with 3 mg/kg/day enteric-coated aspirin tablets for 6 months, while patients in group B received 5 mg/kg/day enteric-coated aspirin tablets for 6 months. RESULTS: The rates of platelet aggregation (PAG) in the immediate postoperative ASD/VSD occlusion were significantly higher than those in the preoperative ASD/VSD occlusion (adenosine diphosphate [ADP]-induced PAG: 64.98%±7.65% vs. 86.33%±6.54%, p<0.05; arachidonic acid [AA]-induced PAG: 62.92%±9.11% vs. 86.96%±6.90%, p<0.05, respectively). After treatment with aspirin, the GMP-140 levels presented a clearly defined downward trend in the immediate postoperative period (3 mg/kg/day aspirin: 18.30±3.42 vs. 13.37±1.80, p<0.05; 5 mg/kg/day aspirin: 18.30±3.42 vs. 13.41±1.60, p<0.05), but no obvious difference was observed considering the GMP-140 levels in the 4 days after occlusion (all p>0.05). CONCLUSION: Our study showed that the GMP-140 serum level and PAG were increased after ASD and VSD occlusion, and patients may have a trend of decreased GMP-140 serum levels after the ASD or VSD occlusion surgeries after the treatment with aspirin. Daily oral administration of 3 and 5 mg/kg/day aspirin can induce a significant decrease in PAG of patients after VSD/ASD occlusion.