Microcalcification detection using fuzzy logic and scale space approaches

Cheng, Heng-Da; Wang, Jingli; Shi, Xiangjun

doi:10.1016/s0031-3203(03)00230-9

Cited by 69 publications

(42 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cheng et al (25) use a three-layer, feed-forward, error BP-ANN in order to classify the detected clusters of microcalcifications using as inputs the mean and the standard deviation and achieves an accuracy >97% TP rate with the FP rate of three clusters per image. The mammographic database they use is the Nijmegen database.…”

Section: Multiscale Texture Features Extraction -Wavelet Based Methodmentioning

confidence: 99%

Classification algorithms for microcalcifications in mammograms (Review)

Sakka

Prentza²,

Koutsouris³

2006

Oncol Rep

View full text Add to dashboard Cite

Abstract. Early detection is the key to improve breast cancer prognosis. The only proven effective method of breast cancer early detection is mammography. An early sign of 30-50% of breast cancer is the appearance of clusters of fine, granular microcalcifications and 60-80% of breast carcinomas reveal microcalcification clusters upon histological examination. The high correlation between the appearance of the microcalcification clusters and diseases, proves that computer aided diagnosis (CAD) systems for automated classification of microcalcification clusters will be very useful and helpful for breast cancer control. The fuzzy nature of microcalcification, the low contrast and the low ability of distinguishing them from their surroundings make automated characterization of them extremely difficult. In this study, we give an overview of the currently available literature on characterization of malignant and benign microcalcifications. We compare and evaluate some of the classification algorithms on microcalcifications in mammograms used in various CAD systems, which are separated into categories according to the method in use. Neural networks are used in applications where only a few decisions are required concerning an amount of data. The K-nearest neighbour classifier distinguishes unknown patterns based on the similarity to known samples and the decision tree approach is much simpler than neural networks and does not need extensive knowledge of the probability distribution of the features.

show abstract

Section: Multiscale Texture Features Extraction -Wavelet Based Methodmentioning

confidence: 99%

Classification algorithms for microcalcifications in mammograms (Review)

Sakka

Prentza²,

Koutsouris³

2006

Oncol Rep

View full text Add to dashboard Cite

show abstract

“…The texture discriminatory power of wavelet transform leads to significant improvement in computer assisted diagnosis in digitized mammograms. Fuzzy and scale space based approaches for detection of micro-calcification have been proposed by Cheng et al (2004). Based on fuzzy entropy the image is fuzzified and further the image is enhanced and classified using scale space and Gaussian filter.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Detection and Classification of Microcalcification in Compressed Mammogram Image

Joseph

Baskaran²,

Muthukrishnan

2015

Image Anal Stereol

View full text Add to dashboard Cite

The main contribution of this article is introducing an intelligent classifier to distinguish between benign and malignant areas of micro-calcification in companded mammogram image which is not proved or addressed elsewhere. This method does not require any manual processing technique for classification, thus it can be assimilated for identifying benign and malignant areas in intelligent way. Moreover it gives good classification responses for compressed mammogram image. The goal of the proposed method is twofold: one is to preserve the details in Region of Interest (ROI) at low bit rate without affecting the diagnostic related information and second is to classify and segment the micro-calcification area in reconstructed mammogram image with high accuracy. The prime contribution of this work is that details of ROI and Non-ROI regions extracted using multi-wavelet transform are coded at variable bit rate using proposed Region Based Set Partitioning in Hierarchical Trees (RBSPIHT) before storing or transmitting the image. Image reconstructed during retrieval or at the receiving end is preprocessed to remove the channel noise and to enhance the diagnostic contrast information. Then the preprocessed image is classified as normal or abnormal (benign or malignant) using Probabilistic neural network. Segmentation of cancerous region is done using Fuzzy C-means Clustering (FCC) algorithm and the cancerous area is computed. The experimental result shows that the proposed model performance is good at achieving high sensitivity of 97.27%, specificity of 94.38% at an average compression rate and Peak Signal to Noise Ratio (PSNR) of 0.5bpp and 58dB respectively.

show abstract

“…Among them, focusing on image segmentation and specification of regions of interest (ROI), several methods have been proposed, such as classical image filter and local threshold [3,4], and techniques based on mathematical morphology [5], fractal models [6], optimal filters [7], wavelet analysis and multi-scale analysis [3]. Various classification approaches have also been presented to characterize MCs, such as rule-based systems [8], fuzzy logic systems [9,10], statistical methods based on Markov random fields(MRF) [11], and support vector machines [12]. In the past decade, most of the work reported in the literatures has employed neural networks in MCs characterization [5,13,14].…”

Section: Introductionmentioning

confidence: 99%