Description:
Mammography is a proven way of detecting breast cancer at an early stage. Various feature extraction techniques such as histograms, co-occurrence matrix, local binary patterns, Gabor filters, wavelet transforms are used for analysing mammograms. The novel pixel N-gram feature extraction technique has been inspired from the character N-gram concept of text retrieval. In this paper, we have compared the novel N-gram feature extraction technique with the co-occurrence matrix feature extraction technique. The experiments were conducted on the benchmark miniMIAS mammography database. Classification of mammograms into normal and abnormal category using N-gram features showed promising results with greater classification accuracy, sensitivity and specificity compared to classification using co-occurrence matrix features. Moreover, N-gram features computation are found to be considerably faster than co-occurrence matrix feature computation
Description:
The extraction of Bag of Visual Words (BoVW) features from retinal images for automated classification has been shown to be effective but computationally expensive. Histogram and co-variance matrix features do not generally result in models that have the same predictive accuracy as BoVW and are still computationally expensive. The discovery of features that result in accurate image classification on computationally constrained devices such as smartphones would enable new and promising applications for image classification. For example, smartphone retinal cameras can conceivably make diabetic retinopathy widely available and potentially reduce undiagnosed retinopathy if it could be achieved with computationally simple classification algorithms. A novel image feature extraction technique inspired by N-grams in text mining, called 'Pixel N-grams' is described that can serve this purpose. Results on mammogram and texture classification have shown high accuracy despite the reduced computational complexity. However retinal scan classification results using Pixel N-grams lag behind BoVW approaches. An explanation for the relative poor performance of Pixel N-grams with diabetic retinopathy that draws on concepts associated with the No Free Lunch theorem are presented.
Description:
Texture image classification is very useful in many domains. It has been tried using statistical, spectral and structural approaches. A novel Pixel N-grams technique has emerged for image feature extraction recently. The aim of this paper is to analyse the efficacy of Pixel N-grams technique for texture image classification in comparison with the traditional techniques namely Intensity histogram, Haralick’s features based on co-occurrence matrix and state-of-the-art Bag-of-Visual-Words (BoVW). The experiments were carried out on the benchmark UIUC texture dataset using SVM classifier. The classification performance was compared using Fscore, Recall and Precision. The classification results using Pixel N-gram were significantly better than that using Intensity histogram and Haralick features whereas, they were comparable with the BoVW approach.
Description:
In healthcare systems, medical devices help physicians and specialists in diagnosis, prognosis, and therapeutics. As research shows, validation of medical devices is significantly optimized by accurate signal processing. Biomedical Signal and Image Processing in Patient Care is a pivotal reference source for progressive research on the latest development of applications and tools for healthcare systems. Featuring extensive coverage on a broad range of topics and perspectives such as telemedicine, human machine interfaces, and multimodal data fusion, this publication is ideally designed for academicians, researchers, students, and practitioners seeking current scholarly research on real-life technological inventions. In healthcare systems, medical devices help physicians and specialists in diagnosis, prognosis, and therapeutics. As research shows, validation of medical devices is significantly optimized by accurate signal processing. Biomedical Signal and Image Processing in Patient Care is a pivotal reference source for progressive research on the latest development of applications and tools for healthcare systems. Featuring extensive coverage on a broad range of topics and perspectives such as telemedicine, human machine interfaces, and multimodal data fusion, this publication is ideally designed for academicians, researchers, students, and practitioners seeking current scholarly research on real-life technological inventions.
Description:
X-ray screening for breast cancer is an important public health initiative in the management of a leading cause of death for women. However, screening is expensive if mammograms are required to be manually assessed by radiologists. Moreover, manual screening is subject to perception and interpretation errors. Computer aided detection/diagnosis (CAD) systems can help radiologists as computer algorithms are good at performing image analysis consistently and repetitively. However, image features that enhance CAD classification accuracies are necessary for CAD systems to be deployed. Many CAD systems have been developed but the specificity and sensitivity is not high; in part because of challenges inherent in identifying effective features to be initially extracted from raw images. Existing feature extraction techniques can be grouped under three main approaches; statistical, spectral and structural. Statistical and spectral techniques provide global image features but often fail to distinguish between local pattern variations within an image. On the other hand, structural approach have given rise to the Bag-of-Visual-Words (BoVW) model, which captures local variations in an image, but typically do not consider spatial relationships between the visual “words”. Moreover, statistical features and features based on BoVW models are computationally very expensive. Similarly, structural feature computation methods other than BoVW are also computationally expensive and strongly dependent upon algorithms that can segment an image to localize a region of interest likely to contain the tumour. Thus, classification algorithms using structural features require high resource computers. In order for a radiologist to classify the lesions on low resource computers such as Ipads, Tablets, and Mobile phones, in a remote location, it is necessary to develop computationally inexpensive classification algorithms. Therefore, the overarching aim of this research is to discover a feature extraction/image representation model which can be used to classify mammographic lesions with high accuracy, sensitivity and specificity along with low computational cost. For this purpose a novel feature extraction technique called ‘Pixel N-grams’ is proposed. The Pixel N-grams approach is inspired from the character N-gram concept in text categorization. Here, N number of consecutive pixel intensities are considered in a particular direction. The image is then represented with the help of histogram of occurrences of the Pixel N-grams in an image. Shape and texture of mammographic lesions play an important role in determining the malignancy of the lesion. It was hypothesized that the Pixel N-grams would be able to distinguish between various textures and shapes. Experiments carried out on benchmark texture databases and binary basic shapes database have demonstrated that the hypothesis was correct. Moreover, the Pixel N-grams were able to distinguish between various shapes irrespective of size and location of shape in an image. The efficacy of the Pixel N-gram technique was tested on mammographic database of primary digital mammograms sourced from a radiological facility in Australia (LakeImaging Pty Ltd) and secondary digital mammograms (benchmark miniMIAS database). A senior radiologist from LakeImaging provided real time de-identified high resolution mammogram images with annotated regions of interests (which were used as groundtruth), and valuable radiological diagnostic knowledge. Two types of classifications were observed on these two datasets. Normal/abnormal classification useful for automated screening and circumscribed/speculation/normal classification useful for automated diagnosis of breast cancer. The classification results on both the mammography datasets using Pixel N-grams were promising. Classification performance (Fscore, sensitivity and specificity) using Pixel N-gram technique was observed to be significantly better than the existing techniques such as intensity histogram, co-occurrence matrix based features and comparable with the BoVW features. Further, Pixel N-gram features are found to be computationally less complex than the co-occurrence matrix based features as well as BoVW features paving the way for mammogram classification on low resource computers. Although, the Pixel N-gram technique was designed for mammographic classification, it could be applied to other image classification applications such as diabetic retinopathy, histopathological image classification, lung tumour detection using CT images, brain tumour detection using MRI images, wound image classification and tooth decay classification using dentistry x-ray images. Further, texture and shape classification is also useful for classification of real world images outside the medical domain. Therefore, the pixel N-gram technique could be extended for applications such as classification of satellite imagery and other object detection tasks.
Description:
X-ray screening for breast cancer is an important public health initiative in the management of a leading cause of death for women. However, screening is expensive if mammograms are required to be manually assessed by radiologists. Moreover, manual screening is subject to perception and interpretation errors. Computer aided detection/diagnosis (CAD) systems can help radiologists as computer algorithms are good at performing image analysis consistently and repetitively. However, image features that enhance CAD classification accuracies are necessary for CAD systems to be deployed. Many CAD systems have been developed but the specificity and sensitivity is not high; in part because of challenges inherent in identifying effective features to be initially extracted from raw images. Existing feature extraction techniques can be grouped under three main approaches; statistical, spectral and structural. Statistical and spectral techniques provide global image features but often fail to distinguish between local pattern variations within an image. On the other hand, structural approach have given rise to the Bag-of-Visual-Words (BoVW) model, which captures local variations in an image, but typically do not consider spatial relationships between the visual “words”. Moreover, statistical features and features based on BoVW models are computationally very expensive. Similarly, structural feature computation methods other than BoVW are also computationally expensive and strongly dependent upon algorithms that can segment an image to localize a region of interest likely to contain the tumour. Thus, classification algorithms using structural features require high resource computers. In order for a radiologist to classify the lesions on low resource computers such as Ipads, Tablets, and Mobile phones, in a remote location, it is necessary to develop computationally inexpensive classification algorithms. Therefore, the overarching aim of this research is to discover a feature extraction/image representation model which can be used to classify mammographic lesions with high accuracy, sensitivity and specificity along with low computational cost. For this purpose a novel feature extraction technique called ‘Pixel N-grams’ is proposed. The Pixel N-grams approach is inspired from the character N-gram concept in text categorization. Here, N number of consecutive pixel intensities are considered in a particular direction. The image is then represented with the help of histogram of occurrences of the Pixel N-grams in an image. Shape and texture of mammographic lesions play an important role in determining the malignancy of the lesion. It was hypothesized that the Pixel N-grams would be able to distinguish between various textures and shapes. Experiments carried out on benchmark texture databases and binary basic shapes database have demonstrated that the hypothesis was correct. Moreover, the Pixel N-grams were able to distinguish between various shapes irrespective of size and location of shape in an image. The efficacy of the Pixel N-gram technique was tested on mammographic database of primary digital mammograms sourced from a radiological facility in Australia (LakeImaging Pty Ltd) and secondary digital mammograms (benchmark miniMIAS database). A senior radiologist from LakeImaging provided real time de-identified high resolution mammogram images with annotated regions of interests (which were used as groundtruth), and valuable radiological diagnostic knowledge. Two types of classifications were observed on these two datasets. Normal/abnormal classification useful for automated screening and circumscribed/speculation/normal classification useful for automated diagnosis of breast cancer. The classification results on both the mammography datasets using Pixel N-grams were promising. Classification performance (Fscore, sensitivity and specificity) using Pixel N-gram technique was observed to be significantly better than the existing techniques such as intensity histogram, co-occurrence matrix based features and comparable with the BoVW features. Further, Pixel N-gram features are found to be computationally less complex than the co-occurrence matrix based features as well as BoVW features paving the way for mammogram classification on low resource computers. Although, the Pixel N-gram technique was designed for mammographic classification, it could be applied to other image classification applications such as diabetic retinopathy, histopathological image classification, lung tumour detection using CT images, brain tumour detection using MRI images, wound image classification and tooth decay classification using dentistry x-ray images. Further, texture and shape classification is also useful for classification of real world images outside the medical domain. Therefore, the pixel N-gram technique could be extended for applications such as classification of satellite imagery and other object detection tasks.
Description:
Automated classification algorithms have been applied to breast cancer diagnosis in order to improve the diagnostic accuracy and turnover time. However, classification accuracy, sensitivity and specificity could still be improved further. Moreover, reducing computational cost is another challenge as the number of images to be analyzed is typically large. In this paper, a novel Pixel N-gram approach inspired from character N-grams in the text retrieval context has been applied for mammographic lesion classification. The experiments on real world database demonstrate that the Pixel N-grams outperform the existing histogram as well as Haralick features with respect to classification accuracy as well as sensitivity. Effect of varying N and using various classifiers is also analyzed in this paper. Results show that optimum value of N is equal to 3 and MLP classifier performs better than SVM and KNN classifier using 3-gram features.
Description:
Various statistical methods such as co-occurrence matrix, local binary patterns and spectral approaches such as Gabor filters have been used for generating global features for image classification. However, global image features fail to distinguish between local variations within an image. Bag-of-visual-words (BoVW) model do capture local variations in an image, but typically do not consider spatial relationships between the visual words. Here, a novel image representation ‘Pixel N-grams’, inspired from the character N-gram concept in text retrieval has been applied for texture classification purpose. Texture is an important property for image classification. Experiments on the benchmark texture database (UIUC) demonstrates that the overall classification accuracy resulting from Pixel N-gram approach (89.5%) is comparable with that achieved using BoVW approach (84.4%) with the added advantage of simplicity and reduced computational cost.
Description:
Diagnostic radiology struggles to maintain high interpretation accuracy. Retrieval of past similar cases would help the inexperienced radiologist in the interpretation process. Character n-gram model has been effective in text retrieval context in languages such as Chinese where there are no clear word boundaries. We propose the use of visual character n-gram model for representation of image for classification and retrieval purposes. Regions of interests in mammographic images are represented with the character n-gram features. These features are then used as input to back-propagation neural network for classification of regions into normal and abnormal categories. Experiments on miniMIAS database show that character n-gram features are useful in classifying the regions into normal and abnormal categories. Promising classification accuracies are observed (83.33%) for fatty background tissue warranting further investigation. We argue that Classifying regions of interests would reduce the number of comparisons necessary for finding similar images from the database and hence would reduce the time required for retrieval of past similar cases.
Description:
Diagnostic radiology struggles to maintain high interpretation accuracy. Retrieval of past similar cases would help the inexperienced radiologist in the interpretation process. Character n-gram model has been effective in text retrieval context in languages such as Chinese where there are no clear word boundaries. We propose the use of visual character n-gram model for representation of image for classification and retrieval purposes. Regions of interests in mammographic images are represented with the character n-gram features. These features are then used as input to back-propagation neural network for classification of regions into normal and abnormal categories. Experiments on miniMIAS database show that character n-gram features are useful in classifying the regions into normal and abnormal categories. Promising classification accuracies are observed (83.33%) for fatty background tissue warranting further investigation. We argue that Classifying regions of interests would reduce the number of comparisons necessary for finding similar images from the database and hence would reduce the time required for retrieval of past similar cases.