Fusion of local and global features for classification of abnormality in mammograms

Phadke, Anuradha C.; Rege, Priti P.

doi:10.1007/s12046-016-0482-y

Cited by 32 publications

(8 citation statements)

References 14 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameters of SVM, such as gamma and soft margin constant, are optimized by iteratively conducting cross-validation within the training data. In cases where the datasets are not linearly separable in the original finitedimensional space, the data can be re-mapped into a sufficiently higher-dimensional space using a defined kernel function, kðx; yÞ, which presumably ensures an easier separation of the datasets [35]. The hyperplane defined in the higher-dimensional space can be viewed as a non-linear separating hyperplane in the original finite-dimensional space.…”

Section: Classification Of Eeg Signals With Svmmentioning

confidence: 99%

Objective identification of pain due to uterine contraction during the first stage of labour using continuous EEG signals and SVM

et al. 2019

View full text Add to dashboard Cite

This study aimed to assess the utility of electroencephalography (EEG) as an objective marker of pain during the first stage of labour. EEG and cardiotocography (CTG) data were obtained from 10 parturient women during their first stage of labour. The study subjects reported the extent of their pain experienced due to uterine contractions, which were recorded by the CTG tracing. Simultaneous 16-channel EEG traces were obtained for spectral analysis and a subsequent machine learning classification using Support Vector Machine (SVM) aiming to predict the pain experienced in relation to uterine contractions. It was found that pain due to uterine contraction correlated positively with relative delta and beta band activities and negatively with relative theta and alpha band activities of the EEG signals. SVM using the spectral activities, statistical and non-linear features of the EEG classified the state of pain with 83% accuracy using a classification model generalizable across subjects. Furthermore, dimension reduction using Principal Component Analysis (PCA) successfully reduced the number of features used in the classification while achieving a maximum classification accuracy of 84%. Continuous EEG affords the means to assess objectively maternal pain experienced during the active contraction phase of the first stage of labour. Monitoring of the pain experience using EEG signals may complement the clinical decision-making process behind administration of epidural anaesthesia during labour. We envision future studies to investigate EEG markers of pain in other clinical states, aiming to generalize the use of EEG as an objective method of pain assessment.

show abstract

Section: Classification Of Eeg Signals With Svmmentioning

confidence: 99%

Objective identification of pain due to uterine contraction during the first stage of labour using continuous EEG signals and SVM

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In the feature extraction step, some statistical features were extracted and Finally, the proposed CAD system has been compared with other papers in the field that have the same conditions to prove the efficiency of the proposed method as shown in Table 11. Regarding the MIAS dataset, it was clear that the results have shown that the proposed CAD system recorded the highest accuracy and AUC compared to El-Toukhy et al [47], Beura et al [15], Pawar and Talbar [16], Phadke and Rege [48], and Mohanty et. al.…”

Section: Discussionmentioning

confidence: 90%

Breast Cancer Diagnosis Using an Efficient CAD System Based on Multiple Classifiers

2019

View full text Add to dashboard Cite

Breast cancer is one of the major health issues across the world. In this study, a new computer-aided detection (CAD) system is introduced. First, the mammogram images were enhanced to increase the contrast. Second, the pectoral muscle was eliminated and the breast was suppressed from the mammogram. Afterward, some statistical features were extracted. Next, k-nearest neighbor (k-NN) and decision trees classifiers were used to classify the normal and abnormal lesions. Moreover, multiple classifier systems (MCS) was constructed as it usually improves the classification results. The MCS has two structures, cascaded and parallel structures. Finally, two wrapper feature selection (FS) approaches were applied to identify those features, which influence classification accuracy. The two data sets (1) the mammographic image analysis society digital mammogram database (MIAS) and (2) the digital mammography dream challenge were combined together to test the CAD system proposed. The highest accuracy achieved with the proposed CAD system before FS was 99.7% using the Adaboosting of the J48 decision tree classifiers. The highest accuracy after FS was 100 %, which was achieved with k‐NN classifier. Moreover, the area under the curve (AUC) of the receiver operating characteristic (ROC) curve was equal to 1.0. The results showed that the proposed CAD system was able to accurately classify normal and abnormal lesions in mammogram samples.

show abstract

“…The classification performance of the introduced system is further assessed in comparison to a number of state-of-the-art breast cancer detection systems as reported in Table 4. The early studies [72][73][74][75][76][77][78] focused mostly on identifying the textural features of breast tissues and applying traditional machine learning algorithms for classification purpose. The outcomes of those methods were not appropriated for the accurate classification of breast lesions since they lack high accuracy and sensitivity.…”

Section: Comparing the Performance And Conclusionmentioning

confidence: 99%

A Hybrid Deep Transfer Learning of CNN-Based LR-PCA for Breast Lesion Diagnosis via Medical Breast Mammograms

Alhussan

Ghoneim

Atteia

et al. 2022

Sensors

View full text Add to dashboard Cite

One of the most promising research areas in the healthcare industry and the scientific community is focusing on the AI-based applications for real medical challenges such as the building of computer-aided diagnosis (CAD) systems for breast cancer. Transfer learning is one of the recent emerging AI-based techniques that allow rapid learning progress and improve medical imaging diagnosis performance. Although deep learning classification for breast cancer has been widely covered, certain obstacles still remain to investigate the independency among the extracted high-level deep features. This work tackles two challenges that still exist when designing effective CAD systems for breast lesion classification from mammograms. The first challenge is to enrich the input information of the deep learning models by generating pseudo-colored images instead of only using the input original grayscale images. To achieve this goal two different image preprocessing techniques are parallel used: contrast-limited adaptive histogram equalization (CLAHE) and Pixel-wise intensity adjustment. The original image is preserved in the first channel, while the other two channels receive the processed images, respectively. The generated three-channel pseudo-colored images are fed directly into the input layer of the backbone CNNs to generate more powerful high-level deep features. The second challenge is to overcome the multicollinearity problem that occurs among the high correlated deep features generated from deep learning models. A new hybrid processing technique based on Logistic Regression (LR) as well as Principal Components Analysis (PCA) is presented and called LR-PCA. Such a process helps to select the significant principal components (PCs) to further use them for the classification purpose. The proposed CAD system has been examined using two different public benchmark datasets which are INbreast and mini-MAIS. The proposed CAD system could achieve the highest performance accuracies of 98.60% and 98.80% using INbreast and mini-MAIS datasets, respectively. Such a CAD system seems to be useful and reliable for breast cancer diagnosis.

show abstract

Fusion of local and global features for classification of abnormality in mammograms

Cited by 32 publications

References 14 publications

Objective identification of pain due to uterine contraction during the first stage of labour using continuous EEG signals and SVM

Objective identification of pain due to uterine contraction during the first stage of labour using continuous EEG signals and SVM

Breast Cancer Diagnosis Using an Efficient CAD System Based on Multiple Classifiers

A Hybrid Deep Transfer Learning of CNN-Based LR-PCA for Breast Lesion Diagnosis via Medical Breast Mammograms

Contact Info

Product

Resources

About