Characterization of mammographic masses based on level set segmentation with new image features and patient information

Diagnosis of Breast Cancer Using Radiomics Models Built Based on Dynamic Contrast Enhanced MRI Combined With Mammography

Objective

To build radiomics models using features extracted from DCE-MRI and mammography for diagnosis of breast cancer.

Materials and Methods

266 patients receiving MRI and mammography, who had well-enhanced lesions on MRI and histologically confirmed diagnosis were analyzed. Training dataset had 146 malignant and 56 benign, and testing dataset had 48 malignant and 18 benign lesions. Fuzzy-C-means clustering algorithm was used to segment the enhanced lesion on subtraction MRI maps. Two radiologists manually outlined the corresponding lesion on mammography by consensus, with the guidance of MRI maximum intensity projection. Features were extracted using PyRadiomics from three DCE-MRI parametric maps, and from the lesion and a 2-cm bandshell margin on mammography. The support vector machine (SVM) was applied for feature selection and model building, using 5 datasets: DCE-MRI, mammography lesion-ROI, mammography margin-ROI, mammography lesion+margin, and all combined.

Results

In the training dataset evaluated using 10-fold cross-validation, the diagnostic accuracy of the individual model was 83.2% for DCE-MRI, 75.7% for mammography lesion, 64.4% for mammography margin, and 77.2% for lesion+margin. When all features were combined, the accuracy was improved to 89.6%. By adding mammography features to MRI, the specificity was significantly improved from 69.6% (39/56) to 82.1% (46/56), p<0.01. When the developed models were applied to the independent testing dataset, the accuracy was 78.8% for DCE-MRI and 83.3% for combined MRI+Mammography.

Conclusion

The radiomics model built from the combined MRI and mammography has the potential to provide a machine learning-based diagnostic tool and decrease the false positive diagnosis of contrast-enhanced benign lesions on MRI.

AUNet: attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms

Mammography is one of the most commonly applied tools for early breast cancer screening. Automatic segmentation of breast masses in mammograms is essential but challenging due to the low signal-to-noise ratio and the wide variety of mass shapes and sizes. Existing methods deal with these challenges mainly by extracting mass-centered image patches manually or automatically. However, manual patch extraction is time-consuming and automatic patch extraction brings errors that could not be compensated in the following segmentation step. In this study, we propose a novel attention-guided dense-upsampling network (AUNet) for accurate breast mass segmentation in whole mammograms directly. In AUNet, we employ an asymmetrical encoder-decoder structure and propose an effective upsampling block, attention-guided dense-upsampling block (AU block). Especially, the AU block is designed to have three merits. Firstly, it compensates the information loss of bilinear upsampling by dense upsampling. Secondly, it designs a more effective method to fuse high- and low-level features. Thirdly, it includes a channel-attention function to highlight rich-information channels. We evaluated the proposed method on two publicly available datasets, CBIS-DDSM and INbreast. Compared to three state-of-the-art fully convolutional networks, AUNet achieved the best performances with an average Dice similarity coefficient of 81.8% for CBIS-DDSM and 79.1% for INbreast.

A Semi-Supervised Method for Tumor Segmentation in Mammogram Images

Background:

Breast cancer is one of the most common cancers in women. Mammogram images have an important role in the treatment of various states of this cancer. In recent years, machine learning methods have been widely used for tumor segmentation in mammogram images. Pixel-based segmentation methods have been presented using both supervised and unsupervised learning approaches. Supervised learning methods are usually fast and accurate, but they usually use a large number of labeled data. Besides, providing these samples is very hard and usually expensive. Unsupervised learning methods do not require the labels of the training data for decision making and they completely ignore the prior knowledge that may lead to a low performance. Semi-supervised learning methods which use a small number of labeled data solve the problem of providing the high number of samples in supervised methods, while they usually result in a higher accuracy in comparison to the unsupervised methods.

Methods:

In this study, we used a semisupervised method for tumor segmentation in which the pixel information is used for the classification. The static and gray level run length matrix features for each pixel are considered as the features, and Fisher discriminant analysis (FDA) is used for feature reduction. A cotraining algorithm based on support vector machine and Bayes classifiers is proposed for tumor segmentation on MIAS data set.

Results and Conclusion:

The results show that the proposed method outperforms both supervised methods.

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

To predict lung nodule malignancy with a high sensitivity and specificity for low dose CT (LDCT) lung cancer screening, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine HF, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM). We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 HF were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the HF and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the HF that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of HF. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models.

Analysis of the Cluster Prominence Feature for Detecting Calcifications in Mammograms

In mammograms, a calcification is represented as small but brilliant white region of the digital image. Earlier detection of malignant calcifications in patients provides high expectation of surviving to this disease. Nevertheless, white regions are difficult to see by visual inspection because a mammogram is a gray-scale image of the breast. To help radiologists in detecting abnormal calcification, computer-inspection methods of mammograms have been proposed; however, it remains an open important issue. In this context, we propose a strategy for detecting calcifications in mammograms based on the analysis of the cluster prominence (cp) feature histogram. The highest frequencies of the cp histogram describe the calcifications on the mammography. Therefore, we obtain a function that models the behaviour of the cp histogram using the Vandermonde interpolation twice. The first interpolation yields a global representation, and the second models the highest frequencies of the histogram. A weak classifier is used for obtaining a final classification of the mammography, that is, with or without calcifications. Experimental results are compared with real DICOM images and their corresponding diagnosis provided by expert radiologists, showing that the cp feature is highly discriminative.

Mammographic mass segmentation using fuzzy contours

BACKGROUND AND OBJECTIVE

Accurate mass segmentation in mammographic images is a critical requirement for computer-aided diagnosis systems since it allows accurate feature extraction and thus improves classification precision.

METHODS

In this paper, a novel automatic breast mass segmentation approach is presented. This approach consists of mainly three stages: contour initialization applied to a given region of interest; construction of fuzzy contours and estimation of fuzzy membership maps of different classes in the considered image; integration of these maps in the Chan-Vese model to get a fuzzy-energy based model that is used for final delineation of mass.

RESULTS

The proposed approach is evaluated using mass regions of interest extracted from the mini-MIAS database. The experimental results show that the proposed method achieves an average true positive rate of 91.12% with a precision of 88.08%.

CONCLUSIONS

The achieved results show high accuracy in breast mass segmentation when compared to manually annotated ground truth and to other methods from the literature.

3D Shape-Weighted Level Set Method for Breast MRI 3D Tumor Segmentation

Three-dimensional (3D) medical image segmentation is used to segment the target (a lesion or an organ) in 3D medical images. Through this process, 3D target information is obtained; hence, this technology is an important auxiliary tool for medical diagnosis. Although some methods have proved to be successful for two-dimensional (2D) image segmentation, their direct use in the 3D case has been unsatisfactory. To obtain more precise tumor segmentation results from 3D MR images, in this paper, we propose a method known as the 3D shape-weighted level set method (3D-SLSM). The proposed method first converts the LSM, which is superior with respect to 2D image segmentation, into a 3D algorithm that is suitable for overall calculations in 3D image models, and which improves the efficiency and accuracy of calculations. A 3D shape-weighted value is then added for each 3D-SLSM iterative process according to the changes in volume. Besides increasing the convergence rate and eliminating background noise, this shape-weighted value also brings the segmented contour closer to the actual tumor margins. To perform a quantitative analysis of 3D-SLSM and to examine its feasibility in clinical applications, we have divided our experiments into computer-simulated sequence images and actual breast MRI cases. Subsequently, we simultaneously compared various existing 3D segmentation methods. The experimental results demonstrated that 3D-SLSM exhibited precise segmentation results for both types of experimental images. In addition, 3D-SLSM showed better results for quantitative data compared with existing 3D segmentation methods.

Mesh-free based variational level set evolution for breast region segmentation and abnormality detection using mammograms

Automatic segmentation of abnormal region is a crucial task in computer-aided detection system using mammograms. In this work, an automatic abnormality detection algorithm using mammographic images is proposed. In the preprocessing step, partial differential equation-based variational level set method is used for breast region extraction. The evolution of the level set method is done by applying mesh-free-based radial basis function (RBF). The limitation of mesh-based approach is removed by using mesh-free-based RBF method. The evolution of variational level set function is also done by mesh-based finite difference method for comparison purpose. Unsharp masking and median filtering is used for mammogram enhancement. Suspicious abnormal regions are segmented by applying fuzzy c-means clustering. Texture features are extracted from the segmented suspicious regions by computing local binary pattern and dominated rotated local binary pattern (DRLBP). Finally, suspicious regions are classified as normal or abnormal regions by means of support vector machine with linear, multilayer perceptron, radial basis, and polynomial kernel function. The algorithm is validated on 322 sample mammograms of mammographic image analysis society (MIAS) and 500 mammograms from digital database for screening mammography (DDSM) datasets. Proficiency of the algorithm is quantified by using sensitivity, specificity, and accuracy. The highest sensitivity, specificity, and accuracy of 93.96%, 95.01%, and 94.48%, respectively, are obtained on MIAS dataset using DRLBP feature with RBF kernel function. Whereas, the highest 92.31% sensitivity, 98.45% specificity, and 96.21% accuracy are achieved on DDSM dataset using DRLBP feature with RBF kernel function.

Automated Analysis of Unregistered Multi-View Mammograms With Deep Learning

We describe an automated methodology for the analysis of unregistered cranio-caudal (CC) and medio-lateral oblique (MLO) mammography views in order to estimate the patient's risk of developing breast cancer. The main innovation behind this methodology lies in the use of deep learning models for the problem of jointly classifying unregistered mammogram views and respective segmentation maps of breast lesions (i.e., masses and micro-calcifications). This is a holistic methodology that can classify a whole mammographic exam, containing the CC and MLO views and the segmentation maps, as opposed to the classification of individual lesions, which is the dominant approach in the field. We also demonstrate that the proposed system is capable of using the segmentation maps generated by automated mass and micro-calcification detection systems, and still producing accurate results. The semi-automated approach (using manually defined mass and micro-calcification segmentation maps) is tested on two publicly available data sets (INbreast and DDSM), and results show that the volume under ROC surface (VUS) for a 3-class problem (normal tissue, benign, and malignant) is over 0.9, the area under ROC curve (AUC) for the 2-class "benign versus malignant" problem is over 0.9, and for the 2-class breast screening problem (malignancy versus normal/benign) is also over 0.9. For the fully automated approach, the VUS results on INbreast is over 0.7, and the AUC for the 2-class "benign versus malignant" problem is over 0.78, and the AUC for the 2-class breast screening is 0.86.

Overview of deep learning in medical imaging

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. "Deep learning", or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

A deep learning approach for the analysis of masses in mammograms with minimal user intervention

We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal-to-noise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down into three stages: mass detection, mass segmentation, and mass classification. For the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimisation. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose the use of a deep learning classifier, which is pre-trained with a regression to hand-crafted feature values and fine-tuned based on the annotations of the breast mass classification dataset. We test our proposed system on the publicly available INbreast dataset and compare the results with the current state-of-the-art methodologies. This evaluation shows that our system detects 90% of masses at 1 false positive per image, has a segmentation accuracy of around 0.85 (Dice index) on the correctly detected masses, and overall classifies masses as malignant or benign with sensitivity (Se) of 0.98 and specificity (Sp) of 0.7.

Reducing false positives of microcalcification detection systems by removal of breast arterial calcifications

PURPOSE

In the past decades, computer-aided detection (CADe) systems have been developed to aid screening radiologists in the detection of malignant microcalcifications. These systems are useful to avoid perceptual oversights and can increase the radiologists' detection rate. However, due to the high number of false positives marked by these CADe systems, they are not yet suitable as an independent reader. Breast arterial calcifications (BACs) are one of the most frequent false positives marked by CADe systems. In this study, a method is proposed for the elimination of BACs as positive findings. Removal of these false positives will increase the performance of the CADe system in finding malignant microcalcifications.

METHODS

A multistage method is proposed for the removal of BAC findings. The first stage consists of a microcalcification candidate selection, segmentation and grouping of the microcalcifications, and classification to remove obvious false positives. In the second stage, a case-based selection is applied where cases are selected which contain BACs. In the final stage, BACs are removed from the selected cases. The BACs removal stage consists of a GentleBoost classifier trained on microcalcification features describing their shape, topology, and texture. Additionally, novel features are introduced to discriminate BACs from other positive findings.

RESULTS

The CADe system was evaluated with and without BACs removal. Here, both systems were applied on a validation set containing 1088 cases of which 95 cases contained malignant microcalcifications. After bootstrapping, free-response receiver operating characteristics and receiver operating characteristics analyses were carried out. Performance between the two systems was compared at 0.98 and 0.95 specificity. At a specificity of 0.98, the sensitivity increased from 37% to 52% and the sensitivity increased from 62% up to 76% at a specificity of 0.95. Partial areas under the curve in the specificity range of 0.8-1.0 were significantly different between the system without BACs removal and the system with BACs removal, 0.129 ± 0.009 versus 0.144 ± 0.008 (p<0.05), respectively. Additionally, the sensitivity at one false positive per 50 cases and one false positive per 25 cases increased as well, 37% versus 51% (p<0.05) and 58% versus 67% (p<0.05) sensitivity, respectively. Additionally, the CADe system with BACs removal reduces the number of false positives per case by 29% on average. The same sensitivity at one false positive per 50 cases in the CADe system without BACs removal can be achieved at one false positive per 80 cases in the CADe system with BACs removal.

CONCLUSIONS

By using dedicated algorithms to detect and remove breast arterial calcifications, the performance of CADe systems can be improved, in particular, at false positive rates representative for operating points used in screening.

Computer-aided diagnosis: detection and localization of prostate cancer within the peripheral zone

We propose a methodology for prostate cancer detection and localization within the peripheral zone based on combining multiple segmentation techniques. We extract four image features using Gaussian and median filters. Subsequently, we use each image feature separately to generate binary segmentations. Finally, we take the intersection of all four binary segmentations, incorporating a model of the peripheral zone, and perform erosion to remove small false-positive regions. The initial evaluation of this method is based on 275 MRI images from 37 patients, and 86% of the slices were classified correctly with 87% and 86% sensitivity and specificity achieved, respectively. This paper makes two contributions: firstly, a novel computer-aided diagnosis approach, which is based on combining multiple segmentation techniques using only a small number of simple image features, and secondly, the development of the proposed method and its application in prostate cancer detection and localization using a single MRI modality with the results comparable with the state-of-the-art multimodality and advanced computer vision methods in the literature. Copyright © 2015 John Wiley & Sons, Ltd.

Dependence of Shape-Based Descriptors and Mass Segmentation Areas on Initial Contour Placement Using the Chan-Vese Method on Digital Mammograms

Variation in signal intensity within mass lesions and missing boundary information are intensity inhomogeneities inherent in digital mammograms. These inhomogeneities render the performance of a deformable contour susceptible to the location of its initial position and may lead to poor segmentation results for these images. We investigate the dependence of shape-based descriptors and mass segmentation areas on initial contour placement with the Chan-Vese segmentation method and compare these results to the active contours with selective local or global segmentation model. For each mass lesion, final contours were obtained by propagation of a proposed initial level set contour and by propagation of a manually drawn contour enclosing the region of interest. Differences in shape-based descriptors were quantified using absolute percentage differences, Euclidean distances, and Bland-Altman analysis. Segmented areas were evaluated with the area overlap measure. Differences were dependent upon the characteristics of the mass margins. Boundary moments presented large percentage differences. Pearson correlation analysis showed statistically significant correlations between shape-based descriptors from both initial locations. In conclusion, boundary moments of digital mass lesions are sensitive to the placement of initial level set contours while shape-based descriptors such as Fourier descriptors, shape convexity, and shape rectangularity exhibit a certain degree of robustness to changes in the location of the initial level set contours for both segmentation algorithms.

Mammogram segmentation using maximal cell strength updation in cellular automata

Breast cancer is the most frequently diagnosed type of cancer among women. Mammogram is one of the most effective tools for early detection of the breast cancer. Various computer-aided systems have been introduced to detect the breast cancer from mammogram images. In a computer-aided diagnosis system, detection and segmentation of breast masses from the background tissues is an important issue. In this paper, an automatic segmentation method is proposed to identify and segment the suspicious mass regions of mammogram using a modified transition rule named maximal cell strength updation in cellular automata (CA). In coarse-level segmentation, the proposed method performs an adaptive global thresholding based on the histogram peak analysis to obtain the rough region of interest. An automatic seed point selection is proposed using gray-level co-occurrence matrix-based sum average feature in the coarse segmented image. Finally, the method utilizes CA with the identified initial seed point and the modified transition rule to segment the mass region. The proposed approach is evaluated over the dataset of 70 mammograms with mass from mini-MIAS database. Experimental results show that the proposed approach yields promising results to segment the mass region in the mammograms with the sensitivity of 92.25% and accuracy of 93.48%.

Application of artificial neural networks in computer-aided diagnosis

Computer-aided diagnosis is a diagnostic procedure in which a radiologist uses the outputs of computer analysis of medical images as a second opinion in the interpretation of medical images, either to help with lesion detection or to help determine if the lesion is benign or malignant. Artificial neural networks (ANNs) are usually employed to formulate the statistical models for computer analysis. Receiver operating characteristic curves are used to evaluate the performance of the ANN alone, as well as the diagnostic performance of radiologists who take into account the ANN output as a second opinion. In this chapter, we use mammograms to illustrate how an ANN model is trained, tested, and evaluated, and how a radiologist should use the ANN output as a second opinion in CAD.

Improving the Mann-Whitney statistical test for feature selection: an approach in breast cancer diagnosis on mammography

OBJECTIVE

This work addresses the theoretical description and experimental evaluation of a new feature selection method (named uFilter). The uFilter improves the Mann-Whitney U-test for reducing dimensionality and ranking features in binary classification problems. Also, it presented a practical uFilter application on breast cancer computer-aided diagnosis (CADx).

MATERIALS AND METHODS

A total of 720 datasets (ranked subsets of features) were formed by the application of the chi-square (CHI2) discretization, information-gain (IG), one-rule (1Rule), Relief, uFilter and its theoretical basis method (named U-test). Each produced dataset was used for training feed-forward backpropagation neural network, support vector machine, linear discriminant analysis and naive Bayes machine learning algorithms to produce classification scores for further statistical comparisons.

RESULTS

A head-to-head comparison based on the mean of area under receiver operating characteristics curve scores against the U-test method showed that the uFilter method significantly outperformed the U-test method for almost all classification schemes (p<0.05); it was superior in 50%; tied in a 37.5% and lost in a 12.5% of the 24 comparative scenarios. Also, the performance of the uFilter method, when compared with CHI2 discretization, IG, 1Rule and Relief methods, was superior or at least statistically similar on the explored datasets while requiring less number of features.

CONCLUSIONS

The experimental results indicated that uFilter method statistically outperformed the U-test method and it demonstrated similar, but not superior, performance than traditional feature selection methods (CHI2 discretization, IG, 1Rule and Relief). The uFilter method revealed competitive and appealing cost-effectiveness results on selecting relevant features, as a support tool for breast cancer CADx methods especially in unbalanced datasets contexts. Finally, the redundancy analysis as a complementary step to the uFilter method provided us an effective way for finding optimal subsets of features without decreasing the classification performances.

Reduction of false-positive recalls using a computerized mammographic image feature analysis scheme

The high false-positive recall rate is one of the major dilemmas that significantly reduce the efficacy of screening mammography, which harms a large fraction of women and increases healthcare cost. This study aims to investigate the feasibility of helping reduce false-positive recalls by developing a new computer-aided diagnosis (CAD) scheme based on the analysis of global mammographic texture and density features computed from four-view images. Our database includes full-field digital mammography (FFDM) images acquired from 1052 recalled women (669 positive for cancer and 383 benign). Each case has four images: two craniocaudal (CC) and two mediolateral oblique (MLO) views. Our CAD scheme first computed global texture features related to the mammographic density distribution on the segmented breast regions of four images. Second, the computed features were given to two artificial neural network (ANN) classifiers that were separately trained and tested in a ten-fold cross-validation scheme on CC and MLO view images, respectively. Finally, two ANN classification scores were combined using a new adaptive scoring fusion method that automatically determined the optimal weights to assign to both views. CAD performance was tested using the area under a receiver operating characteristic curve (AUC). The AUC = 0.793  ±  0.026 was obtained for this four-view CAD scheme, which was significantly higher at the 5% significance level than the AUCs achieved when using only CC (p = 0.025) or MLO (p = 0.0004) view images, respectively. This study demonstrates that a quantitative assessment of global mammographic image texture and density features could provide useful and/or supplementary information to classify between malignant and benign cases among the recalled cases, which may eventually help reduce the false-positive recall rate in screening mammography.

Mammographic images segmentation based on chaotic map clustering algorithm

BACKGROUND

This work investigates the applicability of a novel clustering approach to the segmentation of mammographic digital images. The chaotic map clustering algorithm is used to group together similar subsets of image pixels resulting in a medically meaningful partition of the mammography.

METHODS

The image is divided into pixels subsets characterized by a set of conveniently chosen features and each of the corresponding points in the feature space is associated to a map. A mutual coupling strength between the maps depending on the associated distance between feature space points is subsequently introduced. On the system of maps, the simulated evolution through chaotic dynamics leads to its natural partitioning, which corresponds to a particular segmentation scheme of the initial mammographic image.

RESULTS

The system provides a high recognition rate for small mass lesions (about 94% correctly segmented inside the breast) and the reproduction of the shape of regions with denser micro-calcifications in about 2/3 of the cases, while being less effective on identification of larger mass lesions.

CONCLUSIONS

We can summarize our analysis by asserting that due to the particularities of the mammographic images, the chaotic map clustering algorithm should not be used as the sole method of segmentation. It is rather the joint use of this method along with other segmentation techniques that could be successfully used for increasing the segmentation performance and for providing extra information for the subsequent analysis stages such as the classification of the segmented ROI.

Optimization of breast mass classification using sequential forward floating selection (SFFS) and a support vector machine (SVM) model

PURPOSE

Improving radiologists' performance in classification between malignant and benign breast lesions is important to increase cancer detection sensitivity and reduce false-positive recalls. For this purpose, developing computer-aided diagnosis schemes has been attracting research interest in recent years. In this study, we investigated a new feature selection method for the task of breast mass classification.

METHODS

We initially computed 181 image features based on mass shape, spiculation, contrast, presence of fat or calcifications, texture, isodensity, and other morphological features. From this large image feature pool, we used a sequential forward floating selection (SFFS)-based feature selection method to select relevant features and analyzed their performance using a support vector machine (SVM) model trained for the classification task. On a database of 600 benign and 600 malignant mass regions of interest, we performed the study using a tenfold cross-validation method. Feature selection and optimization of the SVM parameters were conducted on the training subsets only.

RESULTS

The area under the receiver operating characteristic curve [Formula: see text] was obtained for the classification task. The results also showed that the most frequently selected features by the SFFS-based algorithm in tenfold iterations were those related to mass shape, isodensity, and presence of fat, which are consistent with the image features frequently used by radiologists in the clinical environment for mass classification. The study also indicated that accurately computing mass spiculation features from the projection mammograms was difficult, and failed to perform well for the mass classification task due to tissue overlap within the benign mass regions.

CONCLUSION

In conclusion, this comprehensive feature analysis study provided new and valuable information for optimizing computerized mass classification schemes that may have potential to be useful as a "second reader" in future clinical practice.

Quantitative measures confirm the inverse relationship between lesion spiculation and detection of breast masses

OBJECTIVE

To identify specific mammographic appearances that reduce the mammographic detection of breast cancer.

MATERIALS AND METHODS

This study received institutional board review approval and all readers gave informed consent. A set of 60 mammograms each consisting of craniocaudal and mediolateral oblique projections were presented to 129 mammogram Breastscreen readers. The images consisted of 20 positive cases with single and multicentric masses in 16 and 4 cases, respectively (resulting in a total of 24 cancers), and readers were asked to identify and locate the lesions. Each lesion was then ranked according to a detectability rating (ie, the number of observers who correctly located the lesion divided by the total number of observers), and this was correlated with breast density, lesion size, and various descriptors of lesion shape and texture.

RESULTS

Negative and positive correlations between lesion detection and density (r = -0.64, P = .007) and size (r = 0.65, P = .005), respectively, were demonstrated. In terms of lesion size and shape, there were significant correlations between the probability of detection and area (r = 0.43, P = .04), perimeter (r = 0.66, P = .0004), lesion elongation (r = 0.49, P = .02), and lesion nonspiculation (r = 0.78, P < .0001).

CONCLUSIONS

The results of this study have identified specific lesion characteristics associated with shape that may contribute to reduced cancer detection. Mammographic sensitivity may be adversely affected without appropriate attention to spiculation.

Pixel-based machine learning in medical imaging

Machine learning (ML) plays an important role in the medical imaging field, including medical image analysis and computer-aided diagnosis, because objects such as lesions and organs may not be represented accurately by a simple equation; thus, medical pattern recognition essentially require “learning from examples.” One of the most popular uses of ML is classification of objects such as lesions into certain classes (e.g., abnormal or normal, or lesions or nonlesions) based on input features (e.g., contrast and circularity) obtained from segmented object candidates. Recently, pixel/voxel-based ML (PML) emerged in medical image processing/analysis, which use pixel/voxel values in images directly instead of features calculated from segmented objects as input information; thus, feature calculation or segmentation is not required. Because the PML can avoid errors caused by inaccurate feature calculation and segmentation which often occur for subtle or complex objects, the performance of the PML can potentially be higher for such objects than that of common classifiers (i.e., feature-based MLs). In this paper, PMLs are surveyed to make clear (a) classes of PMLs, (b) similarities and differences within (among) different PMLs and those between PMLs and feature-based MLs, (c) advantages and limitations of PMLs, and (d) their applications in medical imaging.

Marker-controlled watershed for lesion segmentation in mammograms

Lesion segmentation, which is a critical step in computer-aided diagnosis system, is a challenging task as lesion boundaries are usually obscured, irregular, and low contrast. In this paper, an accurate and robust algorithm for the automatic segmentation of breast lesions in mammograms is proposed. The traditional watershed transformation is applied to the smoothed (by the morphological reconstruction) morphological gradient image to obtain the lesion boundary in the belt between the internal and external markers. To automatically determine the internal and external markers, the rough region of the lesion is identified by a template matching and a thresholding method. Then, the internal marker is determined by performing a distance transform and the external marker by morphological dilation. The proposed algorithm is quantitatively compared to the dynamic programming boundary tracing method and the plane fitting and dynamic programming method on a set of 363 lesions (size range, 5-42 mm in diameter; mean, 15 mm), using the area overlap metric (AOM), Hausdorff distance (HD), and average minimum Euclidean distance (AMED). The mean ± SD of the values of AOM, HD, and AMED for our method were respectively 0.72 ± 0.13, 5.69 ± 2.85 mm, and 1.76 ± 1.04 mm, which is a better performance than two other proposed segmentation methods. The results also confirm the potential of the proposed algorithm to allow reliable segmentation and quantification of breast lesion in mammograms.

Mass segmentation using a combined method for cancer detection

Background

Breast cancer is one of the leading causes of cancer death for women all over the world and mammography is thought of as one of the main tools for early detection of breast cancer. In order to detect the breast cancer, computer aided technology has been introduced. In computer aided cancer detection, the detection and segmentation of mass are very important. The shape of mass can be used as one of the factors to determine whether the mass is malignant or benign. However, many of the current methods are semi-automatic. In this paper, we investigate fully automatic segmentation method.

Results

In this paper, a new mass segmentation algorithm is proposed. In the proposed algorithm, a fully automatic marker-controlled watershed transform is proposed to segment the mass region roughly, and then a level set is used to refine the segmentation. For over-segmentation caused by watershed, we also investigated different noise reduction technologies. Images from DDSM were used in the experiments and the results show that the new algorithm can improve the accuracy of mass segmentation.

Conclusions

The new algorithm combines the advantages of both methods. The combination of the watershed based segmentation and level set method can improve the efficiency of the segmentation. Besides, the introduction of noise reduction technologies can reduce over-segmentation.

Fissures segmentation using surface features: content-based retrieval for mammographic mass using ensemble classifier

RATIONALE AND OBJECTIVES

Accurate classification is critical in mammography computer-aided diagnosis using content-based image retrieval approaches (CBIR CAD). The objectives of this study were to: 1) develop an accurate ensemble classifier based on domain knowledge and a robust feature selection method for CBIR CAD; 2) propose three new features; and 3) assess the performance of the proposed method and new features by using a relatively large imaging data set.

MATERIALS AND METHODS

The data set used in this study consisted of 2114 regions of interest (ROI) extracted from a publicly available image database. The proposed ensemble classifier method we called E-DGA-KNN included four steps. In the first step, 804 ROIs depict masses were divided into five classes according to their boundary types. Then, each class of ROI with an equal number of negative ROIs were put together to create a sub-database. Second, a dual-stage genetic algorithm, which was called DGA, was applied on those five sub-databases for feature selection and weights determination respectively. In the third step, five base K-nearest neighbor (KNN) classifiers were created by using the results of the second step on 2114 ROIs, and five detection scores for a given queried ROI were obtained. Finally, these classifiers are combined to yield a final classification. The performances of the proposed methods were evaluated by using receiver operating characteristic (ROC) analysis. A comparison with eight different methods on the data set was provided which include the stepwise linear discriminative analysis algorithm (SLDA) and particle swarm optimization (PSO) algorithm with KNN classifier.

RESULTS

When four hybrid feature selection methods were applied with single KNN classifier (ie, DGA-KNN, SLDA-WGA-KNN, SLDA-PSO-KNN, GA-PSO-KNN) and the proposed E-DGA-KNN method to the data set, the computed areas under the ROC curve (Az) were 0.8782 ± 0.0080, 0.8675 ± 0.0081, 0.8623 ± 0.0083, 0.8725 ± 0.0079, and 0.8927 ± 0.0073, respectively. If all features and single KNN classifier were used, the Az value was 0.8478 ± 0.0088. Az values were 0.8592 ± 0.0083 and 0.8632 ± 0.0081 when SLDA or GA algorithm used alone.

CONCLUSIONS

In this study, an ensemble classifier based on domain knowledge and a dual-stage feature selection method was proposed. Evaluation results indicated that the proposed method achieved largest value of ROC compared to other algorithms. The proposed method shows better performance and has the potential to improve the performance of CBIR CAD in interpreting and analyzing mammograms.

A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images

Breast cancer is a major public health problem for women in the Iran and many other parts of the world. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a pivotal role in breast cancer care, including detection, diagnosis, and treatment monitoring. But segmentation of these images which is seriously affected by intensity inhomogeneities created by radio-frequency coils is a challenging task. Markov Random Field (MRF) is used widely in medical image segmentation especially in MR images. It is because this method can model intensity inhomogeneities occurring in these images. But this method has two critical weaknesses: Computational complexity and sensitivity of the results to the models parameters. To overcome these problems, in this paper, we present Improved-Markov Random Field (I-MRF) method for breast lesion segmentation in MR images. Unlike the conventional MRF, in the proposed approach, we don't use the Iterative Conditional Mode (ICM) method or Simulated Annealing (SA) for class membership estimation of each pixel (lesion and non-lesion). The prior distribution of the class membership is modeled as a ratio of two conditional probability distributions in a neighborhood which is defined for each pixel: probability distribution of similar pixels and non-similar ones. Since our proposed approach don't use an iterative method for maximizing the posterior probability, above mentioned problems are solved. Experimental results show that performance of segmentation in this approach is higher than conventional MRF in terms of accuracy, precision, and Computational complexity.

IMPST: A New Interactive Self-Training Approach to Segmentation Suspicious Lesions in Breast MRI

Breast lesion segmentation in magnetic resonance (MR) images is one of the most important parts of clinical diagnostic tools. Pixel classification methods have been frequently used in image segmentation with two supervised and unsupervised approaches up to now. Supervised segmentation methods lead to high accuracy, but they need a large amount of labeled data, which is hard, expensive, and slow to be obtained. On the other hand, unsupervised segmentation methods need no prior knowledge and lead to low performance. However, semi-supervised learning which uses not only a few labeled data, but also a large amount of unlabeled data promises higher accuracy with less effort. In this paper, we propose a new interactive semi-supervised approach to segmentation of suspicious lesions in breast MRI. Using a suitable classifier in this approach has an important role in its performance; in this paper, we present a semi-supervised algorithm improved self-training (IMPST) which is an improved version of self-training method and increase segmentation accuracy. Experimental results show that performance of segmentation in this approach is higher than supervised and unsupervised methods such as K nearest neighbors, Bayesian, Support Vector Machine, and Fuzzy c-Means.

Multilevel learning-based segmentation of ill-defined and spiculated masses in mammograms

PURPOSE

A learning-based approach integrating the use of pixel-level statistical modeling and spiculation detection is presented for the segmentation of mammographic masses with ill-defined margins and spiculations.

METHODS

The algorithm involves a multiphase pixel-level classification, using a comprehensive group of features computed from regional intensity, shape, and textures, to generate a mass-conditional probability map (PM). Then, the mass candidate, along with the background clutters consisting of breast fibroglandular and other nonmass tissues, is extracted from the PM by integrating the prior knowledge of shape and location of masses. A multiscale steerable ridge detection algorithm is employed to detect spiculations. Finally, all the object-level findings, including mass candidate, detected spiculations, and clutters, along with the PM, are integrated by graph cuts to generate the final segmentation mask.

RESULTS

The method was tested on 54 masses (51 malignant and 3 benign), all with ill-defined margins and irregular shape or spiculations. The ground truth delineations were provided by five experienced radiologists. Area overlapping ratio of 0.689 (+/- 0.160) and 0.540 (+/- 0.164) were obtained for segmenting entire mass and margin portion only, respectively. Williams index of area and contour based measurements indicated that the segmentation results of the algorithm agreed well with the radiologists' delineation.

CONCLUSIONS

The proposed approach could closely delineate the mass body. Most importantly, it is capable of including mass margin and its spicule extensions which are considered as key features for breast lesion analyses.

Computer-aided classification of breast masses: performance and interobserver variability of expert radiologists versus residents

PURPOSE

To evaluate the interobserver variability in descriptions of breast masses by dedicated breast imagers and radiology residents and determine how any differences in lesion description affect the performance of a computer-aided diagnosis (CAD) computer classification system.

MATERIALS AND METHODS

Institutional review board approval was obtained for this HIPAA-compliant study, and the requirement to obtain informed consent was waived. Images of 50 breast lesions were individually interpreted by seven dedicated breast imagers and 10 radiology residents, yielding 850 lesion interpretations. Lesions were described with use of 11 descriptors from the Breast Imaging Reporting and Data System, and interobserver variability was calculated with the Cohen κ statistic. Those 11 features were selected, along with patient age, and merged together by a linear discriminant analysis (LDA) classification model trained by using 1005 previously existing cases. Variability in the recommendations of the computer model for different observers was also calculated with the Cohen κ statistic.

RESULTS

A significant difference was observed for six lesion features, and radiology residents had greater interobserver variability in their selection of five of the six features than did dedicated breast imagers. The LDA model accurately classified lesions for both sets of observers (area under the receiver operating characteristic curve = 0.94 for residents and 0.96 for dedicated imagers). Sensitivity was maintained at 100% for residents and improved from 98% to 100% for dedicated breast imagers. For residents, the computer model could potentially improve the specificity from 20% to 40% (P < .01) and the κ value from 0.09 to 0.53 (P < .001). For dedicated breast imagers, the computer model could increase the specificity from 34% to 43% (P = .16) and the κ value from 0.21 to 0.61 (P < .001).

CONCLUSION

Among findings showing a significant difference, there was greater interobserver variability in lesion descriptions among residents; however, an LDA model using data from either dedicated breast imagers or residents yielded a consistently high performance in the differentiation of benign from malignant breast lesions, demonstrating potential for improving specificity and decreasing interobserver variability in biopsy recommendations.

Snakules: a model-based active contour algorithm for the annotation of spicules on mammography

We have developed a novel, model-based active contour algorithm, termed "snakules", for the annotation of spicules on mammography. At each suspect spiculated mass location that has been identified by either a radiologist or a computer-aided detection (CADe) algorithm, we deploy snakules that are converging open-ended active contours also known as snakes. The set of convergent snakules have the ability to deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Starting from a natural set of automatically detected candidate points, snakules are deployed in the region around a suspect spiculated mass location. Statistics of prior physical measurements of spiculated masses on mammography are used in the process of detecting the set of candidate points. Observer studies with experienced radiologists to evaluate the performance of snakules demonstrate the potential of the algorithm as an image analysis technique to improve the specificity of CADe algorithms and as a CADe prompting tool.

Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy c-means clustering and level set segmentation

The goal of this study was to develop an automated method to segment breast masses on dynamic contrast-enhanced (DCE) magnetic resonance (MR) scans and to evaluate its potential for estimating tumor volume on pre- and postchemotherapy images and tumor change in response to treatment. A radiologist experienced in interpreting breast MR scans defined a cuboid volume of interest (VOI) enclosing the mass in the MR volume at one time point within the sequence of DCE-MR scans. The corresponding VOIs over the entire time sequence were then automatically extracted. A new 3D VOI representing the local pharmacokinetic activities in the VOI was generated from the 4D VOI sequence by summarizing the temporal intensity enhancement curve of each voxel with its standard deviation. The method then used the fuzzy c-means (FCM) clustering algorithm followed by morphological filtering for initial mass segmentation. The initial segmentation was refined by the 3D level set (LS) method. The velocity field of the LS method was formulated in terms of the mean curvature which guaranteed the smoothness of the surface, the Sobel edge information which attracted the zero LS to the desired mass margin, and the FCM membership function which improved segmentation accuracy. The method was evaluated on 50 DCE-MR scans of 25 patients who underwent neoadjuvant chemotherapy. Each patient had pre- and postchemotherapy DCE-MR scans on a 1.5 T magnet. The in-plane pixel size ranged from 0.546 to 0.703 mm and the slice thickness ranged from 2.5 to 4.5 mm. The flip angle was 15 degrees, repetition time ranged from 5.98 to 6.7 ms, and echo time ranged from 1.2 to 1.3 ms. Computer segmentation was applied to the coronal T1-weighted images. For comparison, the same radiologist who marked the VOI also manually segmented the mass on each slice. The performance of the automated method was quantified using an overlap measure, defined as the ratio of the intersection of the computer and the manual segmentation volumes to the manual segmentation volume. Pre- and postchemotherapy masses had overlap measures of 0.81 +/- 0.13 (mean +/- s.d.) and 0.71 +/- 0.22, respectively. The percentage volume reduction (PVR) estimated by computer and the radiologist were 55.5 +/- 43.0% (mean +/- s.d.) and 57.8 +/- 51.3%, respectively. Paired Student's t test indicated that the difference between the mean PVRs estimated by computer and the radiologist did not reach statistical significance (p = 0.641). The automated mass segmentation method may have the potential to assist physicians in monitoring volume change in breast masses in response to treatment.

Multi-modality CADx: ROC study of the effect on radiologists' accuracy in characterizing breast masses on mammograms and 3D ultrasound images

RATIONALE AND OBJECTIVES

To investigate the effect of a computer-aided diagnosis (CADx) system on radiologists' performance in discriminating malignant and benign masses on mammograms and three-dimensional (3D) ultrasound (US) images.

MATERIALS AND METHODS

Our dataset contained mammograms and 3D US volumes from 67 women (median age, 51; range: 27-86) with 67 biopsy-proven breast masses (32 benign and 35 malignant). A CADx system was designed to automatically delineate the mass boundaries on mammograms and the US volumes, extract features, and merge the extracted features into a multi-modality malignancy score. Ten experienced readers (subspecialty academic breast imaging radiologists) first viewed the mammograms alone, and provided likelihood of malignancy (LM) ratings and Breast Imaging and Reporting System assessments. Subsequently, the reader viewed the US images with the mammograms, and provided LM and action category ratings. Finally, the CADx score was shown and the reader had the opportunity to revise the ratings. The LM ratings were analyzed using receiver-operating characteristic (ROC) methodology, and the action category ratings were used to determine the sensitivity and specificity of cancer diagnosis.

RESULTS

Without CADx, readers' average area under the ROC curve, A(z), was 0.93 (range, 0.86-0.96) for combined assessment of the mass on both the US volume and mammograms. With CADx, their average A(z) increased to 0.95 (range, 0.91-0.98), which was borderline significant (P = .05). The average sensitivity of the readers increased from 98% to 99% with CADx, while the average specificity increased from 27% to 29%. The change in sensitivity with CADx did not achieve statistical significance for the individual radiologists, and the change in specificity was statistically significant for one of the radiologists.

CONCLUSIONS

A well-trained CADx system that combines features extracted from mammograms and US images may have the potential to improve radiologists' performance in distinguishing malignant from benign breast masses and making decisions about biopsies.

Improving performance of computer-aided detection scheme by combining results from two machine learning classifiers

RATIONALE AND OBJECTIVES

Global data-based and local instance-based machine-learning methods and classifiers have been widely used to optimize computer-aided detection and diagnosis (CAD) schemes to classify between true-positive and false-positive detections. In this study, the correlation between these two types of classifiers was investigated using a new independent testing data set, and the potential improvement of a CAD scheme's performance by combining the results of the two classifiers in detecting breast masses was assessed.

MATERIALS AND METHODS

The CAD scheme first used image filtering and a multilayer topographic region growth algorithm to detect and segment suspicious mass regions. The scheme then used an image feature-based classifier to classify these regions into true-positive and false-positive regions. Two classifiers were used in this study. One was a global data-based machine-learning classifier, an artificial neural network (ANN), and the other was a local instance-based machine-learning classifier, a k-nearest neighbor (KNN) algorithm. An independent image database including 400 mammographic examinations was used in this study. Of these, 200 were cancer cases and 200 were negative cases. The preoptimized CAD scheme was applied twice to the database using the two different classifiers. The correlation between the two sets of classification results was analyzed. Three sets of CAD performance results using the ANN, KNN, and average detection scores from both classifiers were assessed and compared using the free-response receiver-operating characteristic method.

RESULTS

The results showed that the ANN achieved higher performance than the KNN algorithm, with a normalized area under the performance curve (AUC) of 0.891 versus 0.845. The correlation coefficients between the detection scores generated by the two classifiers were 0.436 and 0.161 for the true-positive and false-positive detections, respectively. The average detection scores of the two classifiers improved CAD performance and reliability by increasing the AUC to 0.912 and reducing the standard error of the estimated AUC by 14.4%. The detection sensitivity was also increased from 75.8% (ANN) and 65.9% (KNN) to 80.3% at a false-positive detection rate of 0.3 per image.

CONCLUSIONS

This study demonstrates that two global data-based and local data-based machine-learning classifiers (ANN and KNN) generated low correlated detection results and that combining the detection scores of these two classifiers significantly improved overall CAD performance (P < .01) and reduced standard error in CAD performance assessment.