Computer-aided Prostate Cancer Detection using Texture Features and Clinical Features in Ultrasound Image

Han, Seok Min; Lee, Hak Jong; Choi, Jin Young

doi:10.1007/s10278-008-9106-3

Cited by 54 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the first stage, to detect the texture features of a calcification point and conduct feature selection by SFS, the SVM performed better than the generalized regression neural network [GRNN] in classifying benign versus malignant calcifications. Han's team 14 proposed an ultrasonic image detection system to effectively improve the rate of cancer diagnosis by integrating texture and clinical features with SVM classifiers. In contrast, Horng 15 used ultrasonic images of the supraspinatus muscle and 4 different methods of texture analysis to capture the different features; 5 different multi-class support vector machines (MCSVMs) were applied to detect supraspinatus muscle injuries and were reported to achieve 90% of the classification results.…”

Section: Discussionmentioning

confidence: 99%

Combined Image Enhancement, Feature Extraction, and Classification Protocol to Improve Detection and Diagnosis of Rotator-cuff Tears on MR Imaging

Lin

Wang

et al. 2014

MRMS

View full text Add to dashboard Cite

Purpose: The diagnosis of most rotator cuff tears (RCTs) relies upon magnetic resonance (MR) imaging, but direct capture of MR images without enhanced image processing leads to poor image contrast and potential misdiagnosis. Therefore, we developed a 2-stage model for the detection and diagnosis of injury of the supraspinatus tendon.Methods: The first stage used coupled weighted histogram separation (WHS) to improve image enhancement, and the second stage extracted suspicious texture, features of both spatial and spectral domains, and sequential floating forward selection (SFFS) selected features conducive to classification of RCTs. We then tested injuries of the supraspinatus tendon using the classifier.Results: The extraction of features by SFFS can increase detection of supraspinatus injury by reducing the input vector by 57.78% from the enhanced input images. The receiver operating characteristic (ROC) curve indicated an azimuth (Az) value of 84.38% when SFFS selected 76 features to construct a support vector machine (SVM) classifier from the enhanced images, compared with 56.94% when all 180 features from the raw input images were used for the construction.Conclusions: The performance of the classifier constructed by SFFS-selected features is superior to that using all features. These findings can serve as references to improve diagnosis and treatment of supraspinatus injuries.

show abstract

Section: Discussionmentioning

confidence: 99%

Combined Image Enhancement, Feature Extraction, and Classification Protocol to Improve Detection and Diagnosis of Rotator-cuff Tears on MR Imaging

Lin

Wang

et al. 2014

MRMS

View full text Add to dashboard Cite

show abstract

“…Fu et al applied the general regression neural network (GRNN) and SVM to discriminate suspected micro classifications. Experimental results showed that SVM out performs GRNN [19]. Li et al used hair and clothing rather using the whole face.…”

Section: Introductionmentioning

confidence: 95%

Gender recognition improvement: A new approach for extracting and selecting features

Maleki

Moghaddam

Moattar

2014

2014 International Congress on Technology, Communication and Knowledge (ICTCK)

View full text Add to dashboard Cite

Human face based gender recognition is a challenging issue in image processing and machine vision domain. In this paper we proposed an approach for gender recognition using combination of statistical features and Local Binary Pattern (LBP). The optimal block size and statistical features set are determined by sequential forward floating selection (SFFS) algorithm for gender recognition improvement. The assessment and comparison with other methods have been carried out using Iranian facial image dataset. The proposed approach can carry out the classification more accurately. The rates of true classification using Support Vector Machine (SVM) and Multi Layer Perceptron (MLP) classifiers are 99.41% and 99.31 respectively.

show abstract

“…Ultrasound imaging techniques are widely used in medical diagnosis [10], [11]. Its non-invasive nature, low cost, portability, and real-time image formation make it attractive, however, one of its limitations is the relatively poor image quality affected by speckle noise.…”

Section: A Pre-processing Phasementioning

confidence: 99%

“…Different types of diagnostics, such as digital rectal examination (DRE) and prostatespecific antigen (PSA), can be used to detect prostate cancer at an early stage. However, DRE may miss small tumors, while PSA values are dependent on several factors that are not caused only by prostate cancer [11], [10]. Therefore, diagnosis often also relies on imaging methods for accurate localisation and staging of the disease [10].…”

Section: Introductionmentioning

confidence: 99%

Intelligent analysis of prostate ultrasound images

Hassanien

Al-Qaheri

Schaefer

et al. 2009

2009 World Congress on Nature &Amp; Biologically Inspired Computing (NaBIC)

View full text Add to dashboard Cite

In this paper, we present an intelligent approach to analysing prostrate ultrasound images in order to diagnose prostate cancer. Algorithms based on fuzzy image processing are applied first to enhance the contrast of the original image, to extract the region of interest and to enhance the edges surrounding that region. Then, we extract features characterising the underlying texture of the regions of interest based wavelet domain features. Finally, a rough neural network, where a neural network and rough set theory are integrated into a hybrid system, is designed for discrimination of different regions of interest to test whether they represent malignant or benign cases. The neural network is built from rough neurons, each of which can be viewed as a pair of subneurons, corresponding to the lower and upper bound concepts of rough set theory. Experimental results show that the overall classification accuracy of our approach is high.Keywords-Prostate cancer, ultrasound imaging, fuzzy logic, neural networks, wavelets, rough set theory, intelligent hybrid approach. 978-1-4244-5612-3/09/$26.00 c 2009 IEEE

show abstract

Computer-aided Prostate Cancer Detection using Texture Features and Clinical Features in Ultrasound Image

Cited by 54 publications

References 12 publications

Combined Image Enhancement, Feature Extraction, and Classification Protocol to Improve Detection and Diagnosis of Rotator-cuff Tears on MR Imaging

Combined Image Enhancement, Feature Extraction, and Classification Protocol to Improve Detection and Diagnosis of Rotator-cuff Tears on MR Imaging

Gender recognition improvement: A new approach for extracting and selecting features

Intelligent analysis of prostate ultrasound images

Contact Info

Product

Resources

About