Breast cancer detection without removal pectoral muscle by extraction turn counts feature
TL;DR: The aim of this study was to extract the feature without removing pectoral muscle in preprocessing stage using a new and efficient method and the results of support vector machine classifier showed accuracy.
Abstract: During late decade breast cancer is recognized as major cause of death among women and the number of breast cancer patients is increasing. There is more evidence that women in 15–54 years old are died by breast cancer. Breast cancer cannot be prevented because its major factors have not been identified. Therefore earlier diagnosis can increase the possibility of improvement. The aim of this study was to extract the feature without removing pectoral muscle in preprocessing stage using a new and efficient method. Database of MIAS mammography images was used to classify normal/ abnormal individuals and benign/ malignant cancer patients and the results of support vector machine classifier showed accuracy of 95.80 and 86.50 respectively.
Citations
More filters
01 Nov 2018
TL;DR: A combination of Gray-level co-occurrence matrix (GLCM) and Support Vector Machine (SVM) is used to classify benign-malignant patient based on mammography image to find the optimal GLCM angle for breast cancer classification cases using mammogram data.
Abstract: Breast cancer is the most common cancer in women. Breast cancer is also the deadliest cancer in women. In 2012, there were 19,750 breast cancer patients in Indonesia dead. There is no sure way to prevent breast cancer. However, the recovery rates and survival rates can be improved by early detection through routine examination. Using X-ray radiation, breast tissue can be obtained. This image is called mammogram. In this paper, a combination of Gray-level co-occurrence matrix (GLCM) and Support Vector Machine (SVM) is used to classify benign-malignant patient based on mammography image. This paper aims to find the optimal GLCM angle for breast cancer classification cases using mammogram data. Mammogram images used in this paper provided by Curated Breast Imaging Subset of Digital Database Screening Mammography (CBIS-DDSM) dataset. From experimental result, obtained accuracy 63.03% and specificity 89.01%.
22 citations
Cites methods from "Breast cancer detection without rem..."
...In the case of breast cancer, the most efficient method for detecting cases of cancer in the early stage is to use mammography [4]....
[...]
01 Oct 2019
TL;DR: A system using different classification method like Support Vector Machine, Naive Bayes, Decision tree and MLP (Multi-Layer Perceptron) for early detection of cancer and a comparative study between both datasets is proposed.
Abstract: Breast cancer is a very aggressive type of cancer with a very low median survival. Today the deaths of women in the age group 15-55 are increasing because of malignant cells are increasing in breast. For the death of women it is the main cause. So, the possibility of improvement is only the early diagnosis of patients. Machine Learning (ML) techniques can assist the physicians by expanding tools for detection at initial stage and analysis of breast cancer thus increasing the probability of patient’s survival [1]. At present, mammography is the best imaging strategy utilized by radiologist for screening breast tumours. In this paper, author proposes a system using different classification method like Support Vector Machine (SVM), Naive Bayes, Decision tree and MLP (Multi-Layer Perceptron) for early detection of cancer. Propose system extracts the texture based features and shape based features using LBP, GLCM, Otsu, Compactness, Fourier Transform. The main focus of the presented work is on application of MLP for breast cancer classification. In addition medical images data has been used to improve accuracy. Proposed system will do the comparative study between both datasets by extracting the feature with and without removing pectoral muscles.
1 citations
Cites background from "Breast cancer detection without rem..."
...Limitations of this paper are it requires large number of cases [2]....
[...]
TL;DR: In this article , a fusion model of CNN + RNN is proposed for the detection of oral cancer with the fusion model outperforms the state-of-the-art techniques with 82% accuracy.
Abstract: In recent days, oral cancer cases are significantly increasing due to increase in tobacco consumption, along with the combination of consumption of alcohol, poor oral hygiene, and human papilloma virus (HPV) infection. Early detection of this kind of cancers is preventive, or else, it may leads to premature deaths. 50% of cases are detected in advanced stages. For the above reasons, it is important to develop the new model to detect the oral cavity cancer in early stage from the digital data and image processing techniques. The research in detection of oral cancer is highly active from the twentieth century. In this paper, the detection of oral cancer with the fusion model of CNN + RNN is proposed. The proposed model outperforms the state-of-art techniques in detection of oral cancer with 82% of accuracy. The obtained result is analyzed with systematic approach, and assured diagnosis is ensured the diagnosis of the oral cancer we attempt to near future. The intention of the proposed method is to improve the detection accuracy in the early diagnosis of oral cavity cancers.
References
More filters
TL;DR: Computer-aided classification of benign and malignant masses on mammograms is attempted in this study by computing gradient-based and texture-based features based on posterior probabilities computed from Mahalanobis distances.
Abstract: Computer-aided classification of benign and malignant masses on mammograms is attempted in this study by computing gradient-based and texture-based features. Features computed based on gray-level co-occurrence matrices (GCMs) are used to evaluate the effectiveness of textural information possessed by mass regions in comparison with the textural information present in mass margins. A method involving polygonal modeling of boundaries is proposed for the extraction of a ribbon of pixels across mass margins. Two gradient-based features are developed to estimate the sharpness of mass boundaries in the ribbons of pixels extracted from their margins. A total of 54 images (28 benign and 26 malignant) containing 39 images from the Mammographic Image Analysis Society (MIAS) database and 15 images from a local database are analyzed. The best benign versus malignant classification of 82.1%, with an area (A/sub z/) of 0.85 under the receiver operating characteristics (ROC) curve, was obtained with the images from the MIAS database by using GCM-based texture features computed from mass margins. The classification method used is based on posterior probabilities computed from Mahalanobis distances. The corresponding accuracy using jack-knife classification was observed to be 74.4%, with A/sub x/=0.67. Gradient-based features achieved A/sub x/=0.6 on the MIAS database and A/sub z/=0.76 on the combined database. The corresponding values obtained using jack-knife classification were observed to be 0.52 and 0.73 for the MIAS and combined databases, respectively.
281 citations
"Breast cancer detection without rem..." refers background in this paper
...abnormal individuals and benign and malignant cancers [11]....
[...]
01 Mar 2001
TL;DR: An easy-to-use intelligent system that gives the user options to diagnose, detect, enlarge, zoom and measure distances of areas in digital mammograms and finds that a combination of three features is the best combination to distinguish a benign microcalcification pattern from one that is malignant.
Abstract: An intelligent computer-aided diagnosis system can be very helpful for radiologist in detecting and diagnosing microcalcification patterns earlier and faster than typical screening programs. In this paper, we present a system based on fuzzy-neural and feature extraction techniques for detecting and diagnosing microcalcifications' patterns in digital mammograms. We have investigated and analyzed a number of feature extraction techniques and found that a combination of three features (such as entropy, standard deviation and number of pixels) is the best combination to distinguish a benign microcalcification pattern from one that is malignant. A fuzzy technique in conjunction with three features was used to detect a microcalcification pattern and a neural network was used to classify it into benign/malignant. The system was developed on a Microsoft Windows platform. It is an easy-to-use intelligent system that gives the user options to diagnose, detect, enlarge, zoom and measure distances of areas in digital mammograms.
219 citations
"Breast cancer detection without rem..." refers methods in this paper
...Verma et al introduced the combination of entropy, standard deviation and number of pixel as the best option to diagnose benign and malignant micro classifications by analyzing extraction techniques [5]....
[...]
TL;DR: A new method is proposed for the identification of the pectoral muscle in MLO mammograms based upon a multiresolution technique using Gabor wavelets, which overcomes the limitation of the straight-line representation considered in the initial investigation using the Hough transform.
Abstract: The pectoral muscle represents a predominant density region in most medio-lateral oblique (MLO) views of mammograms; its inclusion can affect the results of intensity-based image processing methods or bias procedures in the detection of breast cancer. Local analysis of the pectoral muscle may be used to identify the presence of abnormal axillary lymph nodes, which may be the only manifestation of occult breast carcinoma. We propose a new method for the identification of the pectoral muscle in MLO mammograms based upon a multiresolution technique using Gabor wavelets. This new method overcomes the limitation of the straight-line representation considered in our initial investigation using the Hough transform. The method starts by convolving a group of Gabor filters, specially designed for enhancing the pectoral muscle edge, with the region of interest containing the pectoral muscle. After computing the magnitude and phase images using a vector-summation procedure, the magnitude value of each pixel is propagated in the direction of the phase. The resulting image is then used to detect the relevant edges. Finally, a post-processing stage is used to find the true pectoral muscle edge. The method was applied to 84 MLO mammograms from the Mini-MIAS (Mammographic Image Analysis Society, London, U.K.) database. Evaluation of the pectoral muscle edge detected in the mammograms was performed based upon the percentage of false-positive (FP) and false-negative (FN) pixels determined by comparison between the numbers of pixels enclosed in the regions delimited by the edges identified by a radiologist and by the proposed method. The average FP and FN rates were, respectively, 0.58% and 5.77%. Furthermore, the results of the Gabor-filter-based method indicated low Hausdorff distances with respect to the hand-drawn pectoral muscle edges, with the mean and standard deviation being 3.84/spl plusmn/1.73 mm over 84 images.
213 citations
"Breast cancer detection without rem..." refers methods in this paper
...[9] proposed an algorithm for automatic segmentation of the pectoral muscle in mammograms....
[...]
TL;DR: A novel algorithm for image denoising and enhancement based on dyadic wavelet processing is proposed, which seems to meaningfully improve the diagnosis in the early breast cancer detection with respect to other approaches.
Abstract: Mammography is the most effective method for the early detection of breast diseases. However, the typical diagnostic signs such as microcalcifications and masses are difficult to detect because mammograms are low-contrast and noisy images. In this paper, a novel algorithm for image denoising and enhancement based on dyadic wavelet processing is proposed. The denoising phase is based on a local iterative noise variance estimation. Moreover, in the case of microcalcifications, we propose an adaptive tuning of enhancement degree at different wavelet scales, whereas in the case of mass detection, we developed a new segmentation method combining dyadic wavelet information with mathematical morphology. The innovative approach consists of using the same algorithmic core for processing images to detect both microcalcifications and masses. The proposed algorithm has been tested on a large number of clinical images, comparing the results with those obtained by several other algorithms proposed in the literature through both analytical indexes and the opinions of radiologists. Through preliminary tests, the method seems to meaningfully improve the diagnosis in the early breast cancer detection with respect to other approaches.
203 citations
"Breast cancer detection without rem..." refers methods in this paper
...proposed a new algorithm to diagnose cancer tissue by 2-D wavelet transform [2]....
[...]