Rajendra Acharya U.,Ngee Ann Polytechnic |
Vinitha Sree S.,CA Technologies |
Kulshreshtha S.,CA Technologies |
Molinari F.,Polytechnic University of Turin |
And 6 more authors.
Technology in Cancer Research and Treatment | Year: 2014
Ovarian cancer is the fifth highest cause of cancer in women and the leading cause of death from gynecological cancers. Accurate diagnosis of ovarian cancer from acquired images is dependent on the expertise and experience of ultrasonographers or physicians, and is therefore, associated with inter observer variabilities. Computer Aided Diagnostic (CAD) techniques use a number of different data mining techniques to automatically predict the presence or absence of cancer, and therefore, are more reliable and accurate. A review of published literature in the field of CAD based ovarian cancer detection indicates that many studies use ultrasound images as the base for analysis. The key objective of this work is to propose an effective adjunct CAD technique called GyneScan for ovarian tumor detection in ultrasound images. In our proposed data mining framework, we extract several texture features based on first order statistics, Gray Level Co-occurrence Matrix and run length matrix. The significant features selected using t-test are then used to train and test several supervised learning based classifiers such as Probabilistic Neural Networks (PNN), Support Vector Machine (SVM), Decision Tree (DT), κ-Nearest Neighbor (KNN), and Naïve Bayes (NB). We evaluated the developed framework using 1300 benign and 1300 malignant images. Using 11 significant features in KNN/PNN classifiers, we were able to achieve 100% classification accuracy, sensitivity, specificity, and positive predictive value in detecting ovarian tumor. Even though more validation using larger databases would better establish the robustness of our technique, the preliminary results are promising. This technique could be used as a reliable adjunct method to existing imaging modalities to provide a more confident second opinion on the presence/absence of ovarian tumor. © Adenine Press (2014). Source
Lucatelli P.,University of Rome La Sapienza |
Raz E.,New York University |
Saba L.,Azienda Ospedaliero Universitaria |
Argiolas G.M.,Azienda Ospedaliera Brotzu |
And 8 more authors.
European Radiology | Year: 2016
Objective: To assess the relationship between the degree of leukoaraiosis (LA), carotid intima-media thickness (IMT) and intima-media thickness variability (IMTV). Materials and methods: Sixty-one consecutive patients, who underwent a brain MRI examination and a carotid artery ultrasound, were included in this retrospective study, which conformed with the Declaration of Helsinki. Written informed consent was waived. In each patient, right/left carotid arteries and brain hemispheres were assessed using automated software for IMT, IMTV and LA volume. Results: The mean hemispheric LA volume was 2,224 mm3 (SD 2,702 mm3) and there was no statistically significant difference in LA volume between the right and left hemispheres (p value = 0.628). The mean IMT and IMTV values were 0.866 mm (SD 0.170) and 0.143 mm (SD 0.100), respectively, without significant differences between the right and left sides (p values 0.733 and 0.098, respectively). The correlation coefficient between IMTV and LA volume was 0.41 (p value = 0.0001), and 0.246 (p value = 0.074) between IMT and LA volume. Conclusions: IMTV significantly correlates with LA volume. Further studies are warranted to verify whether this parameter can be used clinically as a marker of cerebrovascular risk. Key Points: • Intima-media thickness variability (IMTV) significantly correlates with leukoaraiosis volume.• IMTV could be used as a marker for cerebrovascular risk.• IMTV seems to be a better predictor of weighted mean difference than IMT. © 2016 European Society of Radiology Source
Saba L.,University of Cagliari |
Ikeda N.,Toho University |
Deidda M.,University of Cagliari |
Araki T.,Toho University |
And 10 more authors.
Diabetes Research and Clinical Practice | Year: 2013
Aims: The purpose of this study was to evaluate whether carotid IMT (cIMT) identified using automated software is associated with HbA1c in Japanese patients with coronary artery disease. Methods: 370 consecutive patients (males 218; median age 69 years. ±. 11) who underwent carotid-US and first coronary angiography were prospectively analyzed. After ultrasonographic examinations were performed, the plaque score (PS) was calculated and automated IMT analysis was obtained with a dedicated algorithm. Pearson correlation analysis was performed to calculate the association between automated IMT, PS and HbA1c. Results: The mean value of cIMT was 1.00. ±. 0.47. mm for the right carotid and 1.04. ±. 0.49. mm for the left carotid; the average bilateral value was 1.02. ±. 0.43. mm. No significant difference of cIMT was detected between men and women. We found a direct correlation between cIMT values and HbA1c (p= 0.0007) whereas the plaque score did not correlate with the HbA1c values (p>. 0.05). Conclusion: The results of our study confirm that automated cIMT values and levels of HbA1c in Japanese patients with coronary artery disease are correlated whereas the plaque score does not show a statistically significant correlation. © 2013 Elsevier Ireland Ltd. Source
Saba L.,Azienda Ospedaliero Universitaria |
Argiolas G.M.,Azienda Ospedaliero Brotzu A.O.B. |
Raz E.,New York University |
Raz E.,University of Rome La Sapienza |
And 8 more authors.
European Journal of Radiology | Year: 2014
Purpose The purpose of this work was to evaluate if the use of color maps, instead of conventional grayscale images, would improve the observer's diagnostic confidence in the non-contrast CT evaluation of internal carotid artery dissection (ICAD).Materials and methods One hundred patients (61 men, 39 women; mean age, 51 years; range, 25-78 years), 40 with and 60 without ICAD, underwent non-contrast CT and were included in this the retrospective study. In this study, three groups of patients were considered: patients with MR confirmation of ICAD, n = 40; patients with MR confirmation of ICAD absence, n = 20; patients who underwent CT of the carotid arteries because of atherosclerotic disease, n = 40. Four blinded observers with different levels of expertise (expert, intermediate A, intermediate B and trainee) analyzed the non-contrast CT datasets using a cross model (one case grayscale and the following case using the color scale). The presence of ICAD was scored on a 5-point scale in order to assess the observer's diagnostic confidence. After 3 months the four observers evaluated the same datasets by using the same cross-model for the alternate readings (one case color scale and the following case using the grayscale). Statistical analysis included receiver operating characteristics (ROC) curve analysis, the Cohen weighted test and sensitivity, specificity, PPV, NPV, accuracy, LR+ and LR-.Results The ROC curve analysis showed that, for all observers, the use of color scale resulted in an improved diagnostic confidence with AUC values increasing from 0.896 to 0.936, 0.823 to 0.849, 0.84 to 0.909 and 0.749 to 0.861 for expert, intermediate A, intermediate B and trainee observers, respectively. The increase in diagnostic confidence (between the AUC areas) was statistically significant (p = 0.036) for the trainee. Accuracy as well as sensitivity, specificity, PPV, NPV, LR+ and LR- were improved using the color scale.Conclusion Our study suggests that the use of a color scale instead the conventional grayscale improves the diagnostic confidence, accuracy and inter-observer agreement of the readers, in particular of junior ones, in the diagnosis of ICAD on non-contrast CT. © 2014 Elsevier Ireland Ltd. All rights reserved. Source
Noor N.M.,University of Technology Malaysia |
Than J.C.M.,UniversitiTeknologi Malaysia |
Rijal O.M.,University of Malaya |
Kassim R.M.,Kuala Lumpur Hospital |
And 7 more authors.
Journal of Medical Systems | Year: 2015
Interstitial Lung Disease (ILD) encompasses a wide array of diseases that share some common radiologic characteristics. When diagnosing such diseases, radiologists can be affected by heavy workload and fatigue thus decreasing diagnostic accuracy. Automatic segmentation is the first step in implementing a Computer Aided Diagnosis (CAD) that will help radiologists to improve diagnostic accuracy thereby reducing manual interpretation. Automatic segmentation proposed uses an initial thresholding and morphology based segmentation coupled with feedback that detects large deviations with a corrective segmentation. This feedback is analogous to a control system which allows detection of abnormal or severe lung disease and provides a feedback to an online segmentation improving the overall performance of the system. This feedback system encompasses a texture paradigm. In this study we studied 48 males and 48 female patients consisting of 15 normal and 81 abnormal patients. A senior radiologist chose the five levels needed for ILD diagnosis. The results of segmentation were displayed by showing the comparison of the automated and ground truth boundaries (courtesy of ImgTracer™ 1.0, AtheroPoint™ LLC, Roseville, CA, USA). The left lung’s performance of segmentation was 96.52 % for Jaccard Index and 98.21 % for Dice Similarity, 0.61 mm for Polyline Distance Metric (PDM), −1.15 % for Relative Area Error and 4.09 % Area Overlap Error. The right lung’s performance of segmentation was 97.24 % for Jaccard Index, 98.58 % for Dice Similarity, 0.61 mm for PDM, −0.03 % for Relative Area Error and 3.53 % for Area Overlap Error. The segmentation overall has an overall similarity of 98.4 %. The segmentation proposed is an accurate and fully automated system. © 2015, Springer Science+Business Media New York. Source