Computerized detection of masses in digitized mammograms using single-image segmentation and a multilayer topographic feature analysis

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

BACKGROUND

At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive.

OBJECTIVE

This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients.

METHODS

A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method.

RESULTS

Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models.

CONCLUSIONS

This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

Fully Convolutional DenseNet with Multiscale Context for Automated Breast Tumor Segmentation

Breast tumor segmentation plays a crucial role in subsequent disease diagnosis, and most algorithms need interactive prior to firstly locate tumors and perform segmentation based on tumor-centric candidates. In this paper, we propose a fully convolutional network to achieve automatic segmentation of breast tumor in an end-to-end manner. Considering the diversity of shape and size for malignant tumors in the digital mammograms, we introduce multiscale image information into the fully convolutional dense network architecture to improve the segmentation precision. Multiple sampling rates of atrous convolution are concatenated to acquire different field-of-views of image features without adding additional number of parameters to avoid over fitting. Weighted loss function is also employed during training according to the proportion of the tumor pixels in the entire image, in order to weaken unbalanced classes problem. Qualitative and quantitative comparisons demonstrate that the proposed algorithm can achieve automatic tumor segmentation and has high segmentation precision for various size and shapes of tumor images without preprocessing and postprocessing.

Applying a new computer-aided detection scheme generated imaging marker to predict short-term breast cancer risk

This study aims to investigate the feasibility of identifying a new quantitative imaging marker based on false-positives generated by a computer-aided detection (CAD) scheme to help predict short-term breast cancer risk. An image dataset including four view mammograms acquired from 1044 women was retrospectively assembled. All mammograms were originally interpreted as negative by radiologists. In the next subsequent mammography screening, 402 women were diagnosed with breast cancer and 642 remained negative. An existing CAD scheme was applied 'as is' to process each image. From CAD-generated results, four detection features including the total number of (1) initial detection seeds and (2) the final detected false-positive regions, (3) average and (4) sum of detection scores, were computed from each image. Then, by combining the features computed from two bilateral images of left and right breasts from either craniocaudal or mediolateral oblique view, two logistic regression models were trained and tested using a leave-one-case-out cross-validation method to predict the likelihood of each testing case being positive in the next subsequent screening. The new prediction model yielded the maximum prediction accuracy with an area under a ROC curve of AUC  =  0.65  ±  0.017 and the maximum adjusted odds ratio of 4.49 with a 95% confidence interval of (2.95, 6.83). The results also showed an increasing trend in the adjusted odds ratio and risk prediction scores (p  <  0.01). Thus, this study demonstrated that CAD-generated false-positives might include valuable information, which needs to be further explored for identifying and/or developing more effective imaging markers for predicting short-term breast cancer risk.

Prediction of breast cancer risk using a machine learning approach embedded with a locality preserving projection algorithm

In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.

Assessment of global and local region-based bilateral mammographic feature asymmetry to predict short-term breast cancer risk

This study aims to develop and test a new imaging marker-based short-term breast cancer risk prediction model. An age-matched dataset of 566 screening mammography cases was used. All 'prior' images acquired in the two screening series were negative, while in the 'current' screening images, 283 cases were positive for cancer and 283 cases remained negative. For each case, two bilateral cranio-caudal view mammograms acquired from the 'prior' negative screenings were selected and processed by a computer-aided image processing scheme, which segmented the entire breast area into nine strip-based local regions, extracted the element regions using difference of Gaussian filters, and computed both global- and local-based bilateral asymmetrical image features. An initial feature pool included 190 features related to the spatial distribution and structural similarity of grayscale values, as well as of the magnitude and phase responses of multidirectional Gabor filters. Next, a short-term breast cancer risk prediction model based on a generalized linear model was built using an embedded stepwise regression analysis method to select features and a leave-one-case-out cross-validation method to predict the likelihood of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) values significantly increased from 0.5863  ±  0.0237 to 0.6870  ±  0.0220 when the model trained by the image features extracted from the global regions and by the features extracted from both the global and the matched local regions (p  =  0.0001). The odds ratio values monotonically increased from 1.00-8.11 with a significantly increasing trend in slope (p  =  0.0028) as the model-generated risk score increased. In addition, the AUC values were 0.6555  ±  0.0437, 0.6958  ±  0.0290, and 0.7054  ±  0.0529 for the three age groups of 37-49, 50-65, and 66-87 years old, respectively. AUC values of 0.6529  ±  0.1100, 0.6820  ±  0.0353, 0.6836  ±  0.0302 and 0.8043  ±  0.1067 were yielded for the four mammography density sub-groups (BIRADS from 1-4), respectively. This study demonstrated that bilateral asymmetry features extracted from local regions combined with the global region in bilateral negative mammograms could be used as a new imaging marker to assist in the prediction of short-term breast cancer risk.

Developing a new case based computer-aided detection scheme and an adaptive cueing method to improve performance in detecting mammographic lesions

The purpose of this study is to evaluate a new method to improve performance of computer-aided detection (CAD) schemes of screening mammograms with two approaches. In the first approach, we developed a new case based CAD scheme using a set of optimally selected global mammographic density, texture, spiculation, and structural similarity features computed from all four full-field digital mammography images of the craniocaudal (CC) and mediolateral oblique (MLO) views by using a modified fast and accurate sequential floating forward selection feature selection algorithm. Selected features were then applied to a 'scoring fusion' artificial neural network classification scheme to produce a final case based risk score. In the second approach, we combined the case based risk score with the conventional lesion based scores of a conventional lesion based CAD scheme using a new adaptive cueing method that is integrated with the case based risk scores. We evaluated our methods using a ten-fold cross-validation scheme on 924 cases (476 cancer and 448 recalled or negative), whereby each case had all four images from the CC and MLO views. The area under the receiver operating characteristic curve was AUC  =  0.793  ±  0.015 and the odds ratio monotonically increased from 1 to 37.21 as CAD-generated case based detection scores increased. Using the new adaptive cueing method, the region based and case based sensitivities of the conventional CAD scheme at a false positive rate of 0.71 per image increased by 2.4% and 0.8%, respectively. The study demonstrated that supplementary information can be derived by computing global mammographic density image features to improve CAD-cueing performance on the suspicious mammographic lesions.

Early prediction of clinical benefit of treating ovarian cancer using quantitative CT image feature analysis

BACKGROUND

In current clinical trials of treating ovarian cancer patients, how to accurately predict patients' response to the chemotherapy at an early stage remains an important and unsolved challenge.

PURPOSE

To investigate feasibility of applying a new quantitative image analysis method for predicting early response of ovarian cancer patients to chemotherapy in clinical trials.

MATERIAL AND METHODS

A dataset of 30 patients was retrospectively selected in this study, among which 12 were responders with 6-month progression-free survival (PFS) and 18 were non-responders. A computer-aided detection scheme was developed to segment tumors depicted on two sets of CT images acquired pre-treatment and 4-6 weeks post treatment. The scheme computed changes of three image features related to the tumor volume, density, and density variance. We analyzed performance of using each image feature and applying a decision tree to predict patients' 6-month PFS. The prediction accuracy of using quantitative image features was also compared with the clinical record based on the Response Evaluation Criteria in Solid Tumors (RECIST) guideline.

RESULTS

The areas under receiver operating characteristic curve (AUC) were 0.773 ± 0.086, 0.680 ± 0.109, and 0.668 ± 0.101, when using each of three features, respectively. AUC value increased to 0.831 ± 0.078 when combining these features together. The decision-tree classifier achieved a higher predicting accuracy (76.7%) than using RECIST guideline (60.0%).

CONCLUSION

This study demonstrated the potential of using a quantitative image feature analysis method to improve accuracy of predicting early response of ovarian cancer patients to the chemotherapy in clinical trials.

A new and fast image feature selection method for developing an optimal mammographic mass detection scheme

PURPOSE

Selecting optimal features from a large image feature pool remains a major challenge in developing computer-aided detection (CAD) schemes of medical images. The objective of this study is to investigate a new approach to significantly improve efficacy of image feature selection and classifier optimization in developing a CAD scheme of mammographic masses.

METHODS

An image dataset including 1600 regions of interest (ROIs) in which 800 are positive (depicting malignant masses) and 800 are negative (depicting CAD-generated false positive regions) was used in this study. After segmentation of each suspicious lesion by a multilayer topographic region growth algorithm, 271 features were computed in different feature categories including shape, texture, contrast, isodensity, spiculation, local topological features, as well as the features related to the presence and location of fat and calcifications. Besides computing features from the original images, the authors also computed new texture features from the dilated lesion segments. In order to select optimal features from this initial feature pool and build a highly performing classifier, the authors examined and compared four feature selection methods to optimize an artificial neural network (ANN) based classifier, namely: (1) Phased Searching with NEAT in a Time-Scaled Framework, (2) A sequential floating forward selection (SFFS) method, (3) A genetic algorithm (GA), and (4) A sequential forward selection (SFS) method. Performances of the four approaches were assessed using a tenfold cross validation method.

RESULTS

Among these four methods, SFFS has highest efficacy, which takes 3%-5% of computational time as compared to GA approach, and yields the highest performance level with the area under a receiver operating characteristic curve (AUC) = 0.864 ± 0.034. The results also demonstrated that except using GA, including the new texture features computed from the dilated mass segments improved the AUC results of the ANNs optimized using other three feature selection methods. In addition, among 271 features, the shape, local morphological features, fat and calcification based features were the most frequently selected features to build ANNs.

CONCLUSIONS

Although conventional GA is a powerful tool in optimizing classifiers used in CAD schemes of medical images, it is very computationally intensive. This study demonstrated that using a new SFFS based approach enabled to significantly improve efficacy of image feature selection for developing CAD schemes.

Optimization of Network Topology in Computer-Aided Detection Schemes Using Phased Searching with NEAT in a Time-Scaled Framework

In the field of computer-aided mammographic mass detection, many different features and classifiers have been tested. Frequently, the relevant features and optimal topology for the artificial neural network (ANN)-based approaches at the classification stage are unknown, and thus determined by trial-and-error experiments. In this study, we analyzed a classifier that evolves ANNs using genetic algorithms (GAs), which combines feature selection with the learning task. The classifier named "Phased Searching with NEAT in a Time-Scaled Framework" was analyzed using a dataset with 800 malignant and 800 normal tissue regions in a 10-fold cross-validation framework. The classification performance measured by the area under a receiver operating characteristic (ROC) curve was 0.856 ± 0.029. The result was also compared with four other well-established classifiers that include fixed-topology ANNs, support vector machines (SVMs), linear discriminant analysis (LDA), and bagged decision trees. The results show that Phased Searching outperformed the LDA and bagged decision tree classifiers, and was only significantly outperformed by SVM. Furthermore, the Phased Searching method required fewer features and discarded superfluous structure or topology, thus incurring a lower feature computational and training and validation time requirement. Analyses performed on the network complexities evolved by Phased Searching indicate that it can evolve optimal network topologies based on its complexification and simplification parameter selection process. From the results, the study also concluded that the three classifiers - SVM, fixed-topology ANN, and Phased Searching with NeuroEvolution of Augmenting Topologies (NEAT) in a Time-Scaled Framework - are performing comparably well in our mammographic mass detection scheme.

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.

Biplane correlation imaging: a feasibility study based on phantom and human data

The objective of this study was to implement and evaluate the performance of a biplane correlation imaging (BCI) technique aimed to reduce the effect of anatomic noise and improve the detection of lung nodules in chest radiographs. Seventy-one low-dose posterior-anterior images were acquired from an anthropomorphic chest phantom with 0.28° angular separations over a range of ±10° along the vertical axis within an 11 s interval. Similar data were acquired from 19 human subjects with institutional review board approval and informed consent. The data were incorporated into a computer-aided detection (CAD) algorithm in which suspect lesions were identified by examining the geometrical correlation of the detected signals that remained relatively constant against variable anatomic backgrounds. The data were analyzed to determine the effect of angular separation, and the overall sensitivity and false-positives for lung nodule detection. The best performance was achieved for angular separations of the projection pairs greater than 5°. Within that range, the technique provided an order of magnitude decrease in the number of false-positive reports when compared with CAD analysis of single-view images. Overall, the technique yielded ~1.1 false-positive per patient with an average sensitivity of 75%. The results indicated that the incorporation of angular information can offer a reduction in the number of false-positives without a notable reduction in sensitivity. The findings suggest that the BCI technique has the potential for clinical implementation as a cost-effective technique to improve the detection of subtle lung nodules with lowered rate of false-positives.

Computer-aided detection of breast masses depicted on full-field digital mammograms: a performance assessment

OBJECTIVES

To investigate the feasibility of converting a computer-aided detection (CAD) scheme for digitised screen-film mammograms to full-field digital mammograms (FFDMs) and assessing CAD performance on a large database.

METHODS

The database included 6478 FFDM images acquired on 1120 females, with 525 cancer cases and 595 negative cases. The database was divided into five case groups: (1) cancer detected during screening, (2) interval cancers, (3) "high-risk" recommended for surgical excision, (4) recalled but negative and (5) negative (not recalled). A previously developed CAD scheme for masses depicted on digitised images was converted and re-optimised for FFDM images while keeping the same image-processing structure. CAD performance was analysed on the entire database.

RESULTS

The case-based sensitivity was 75.6% (397/525) for the current mammograms and 40.8% (42/103) for the prior mammograms deemed negative during clinical interpretation but "visible" during retrospective review. The region-based sensitivity was 58.1% (618/1064) for the current mammograms and 28.4% (57/201) for the prior mammograms. The CAD scheme marked 55.7% (221/397) and 35.7% (15/42) of the masses on both views of the current and the prior examinations, respectively. The overall CAD-cued false-positive rate was 0.32 per image, ranging from 0.29 to 0.51 for the five case groups.

CONCLUSION

This study indicated that (1) digitised image-based CAD can be converted for FFDMs while performing at a comparable, or better, level; (2) CAD detects a substantial fraction of cancers depicted on prior examinations, albeit most having been marked only on one view; and (3) CAD tends to mark more false-positive results on "difficult" negative cases that are more visually difficult for radiologists to interpret.

Computer-aided detection; the effect of training databases on detection of subtle breast masses

RATIONALE AND OBJECTIVES

Lesion conspicuity is typically highly correlated with visual difficulty for lesion detection, and computer-aided detection (CAD) has been widely used as a "second reader" in mammography. Hence, increasing CAD sensitivity in detecting subtle cancers without increasing false-positive rates is important. The aim of this study was to investigate the effect of training database case selection on CAD performance in detecting low-conspicuity breast masses.

MATERIALS AND METHODS

A full-field digital mammographic image database that included 525 cases depicting malignant masses was randomly partitioned into three subsets. A CAD scheme was applied to detect all initially suspected mass regions and compute region conspicuity. Training samples were iteratively selected from two of the subsets. Four types of training data sets-(1) one including all available true-positive mass regions in the two subsets ("all"), (2) one including 350 randomly selected mass regions ("diverse"), (3) one including 350 high-conspicuity mass regions ("easy"), and (4) one including 350 low-conspicuity mass regions ("difficult")-were assembled. In each training data set, the same number of randomly selected false-positive regions as the true-positives were also included. Two classifiers, an artificial neural network (ANN) and a k-nearest neighbor (KNN) algorithm, were trained using each of the four training data sets and tested on all suspected regions in the remaining data set. Using a threefold cross-validation method, the performance changes of the CAD schemes trained using one of the four training data sets were computed and compared.

RESULTS

CAD initially detected 1025 true-positive mass regions depicted on 507 cases (97% case-based sensitivity) and 9569 false-positive regions (3.5 per image) in the entire database. Using the all training data set, CAD achieved the highest overall performance on the entire testing database. However, CAD detected the highest number of low-conspicuity masses when the difficult training data set was used for training. Results did agree for both ANN-based and KNN-based classifiers in all tests. Compared to the use of the all training data set, the sensitivity of the schemes trained using the difficult data set decreased by 8.6% and 8.4% for the ANN and KNN algorithm on the entire database, respectively, but the detection of low-conspicuity masses increased by 7.1% and 15.1% for the ANN and KNN algorithm at a false-positive rate of 0.3 per image.

CONCLUSIONS

CAD performance depends on the size, diversity, and difficulty level of the training database. To increase CAD sensitivity in detecting subtle cancer, one should increase the fraction of difficult cases in the training database rather than simply increasing the training data set size.

Hybrid segmentation of mass in mammograms using template matching and dynamic programming

RATIONALE AND OBJECTIVES

Accurate image segmentation for breast lesions is a critical step in computer-aided diagnosis systems. The objective of this study was to develop a robust method for the automatic segmentation of breast masses on mammograms to extract feasible features for computer-aided diagnosis systems.

MATERIALS AND METHODS

The data set used in this study consisted of 483 regions of interest extracted from 328 patients. A hybrid method for segmenting breast masses was proposed on the basis of the template-matching and dynamic programming techniques. First, a template-matching technique was used to locate and obtain the rough region of masses. Then, on the basis of this rough region, a local cost function for dynamic programming was defined. Finally, the optimal contour was derived by applying dynamic programming as an optimization technique. The performance of this proposed segmentation method was evaluated using area-based and boundary distance-based similarity measures based on radiologists' manually marked annotations. A comparison with three different segmentation algorithms on the data set was provided.

RESULTS

The mean overlap percentage for our proposed hybrid method was 0.727 ± 0.127, whereas those for Timp and Karssemeijer's dynamic programming method, Song et al's plane-fitting and dynamic programming method, and the normalized cut segmentation method were 0.657 ± 0.216, 0.636 ± 0.190, and 0.562 ± 0.199, respectively. All P values for the measure distribution of our proposed method and the other three algorithms were <.001.

CONCLUSIONS

A hybrid method based on the template-matching and dynamic programming techniques was proposed to segment breast masses on mammograms. Evaluation results indicate that the proposed segmentation method can improve the accuracy of mass segmentation compared to three other algorithms. The proposed segmentation method shows better performance and has great potential in improving the accuracy of computer-aided diagnosis systems in interpreting mammograms.

Breast mass segmentation in mammography using plane fitting and dynamic programming

RATIONALE AND OBJECTIVES

Segmentation is an important and challenging task in a computer-aided diagnosis (CAD) system. Accurate segmentation could improve the accuracy in lesion detection and characterization. The objective of this study is to develop and test a new segmentation method that aims at improving the performance level of breast mass segmentation in mammography, which could be used to provide accurate features for classification.

MATERIALS AND METHODS

This automated segmentation method consists of two main steps and combines the edge gradient, the pixel intensity, as well as the shape characteristics of the lesions to achieve good segmentation results. First, a plane fitting method was applied to a background-trend corrected region-of-interest (ROI) of a mass to obtain the edge candidate points. Second, dynamic programming technique was used to find the "optimal" contour of the mass from the edge candidate points. Area-based similarity measures based on the radiologist's manually marked annotation and the segmented region were employed as criteria to evaluate the performance level of the segmentation method. With the evaluation criteria, the new method was compared with 1) the dynamic programming method developed by Timp and Karssemeijer, and 2) the normalized cut segmentation method, based on 337 ROIs extracted from a publicly available image database.

RESULTS

The experimental results indicate that our segmentation method can achieve a higher performance level than the other two methods, and the improvements in segmentation performance level were statistically significant. For instance, the mean overlap percentage for the new algorithm was 0.71, whereas those for Timp's dynamic programming method and the normalized cut segmentation method were 0.63 (P < .001) and 0.61 (P < .001), respectively.

CONCLUSIONS

We developed a new segmentation method by use of plane fitting and dynamic programming, which achieved a relatively high performance level. The new segmentation method would be useful for improving the accuracy of computerized detection and classification of breast cancer in mammography.

Computer-Aided Diagnosis in Mammography Using Content-based Image Retrieval Approaches: Current Status and Future Perspectives

As the rapid advance of digital imaging technologies, the content-based image retrieval (CBIR) has became one of the most vivid research areas in computer vision. In the last several years, developing computer-aided detection and/or diagnosis (CAD) schemes that use CBIR to search for the clinically relevant and visually similar medical images (or regions) depicting suspicious lesions has also been attracting research interest. CBIR-based CAD schemes have potential to provide radiologists with "visual aid" and increase their confidence in accepting CAD-cued results in the decision making. The CAD performance and reliability depends on a number of factors including the optimization of lesion segmentation, feature selection, reference database size, computational efficiency, and relationship between the clinical relevance and visual similarity of the CAD results. By presenting and comparing a number of approaches commonly used in previous studies, this article identifies and discusses the optimal approaches in developing CBIR-based CAD schemes and assessing their performance. Although preliminary studies have suggested that using CBIR-based CAD schemes might improve radiologists' performance and/or increase their confidence in the decision making, this technology is still in the early development stage. Much research work is needed before the CBIR-based CAD schemes can be accepted in the clinical practice.

Computer-aided evaluation of screening mammograms based on local texture models

We propose a new approach to diagnostic evaluation of screening mammograms based on local statistical texture models. The local evaluation tool has the form of a multivariate probability density of gray levels in a suitably chosen search window. First, the density function in the form of Gaussian mixture is estimated from data obtained by scanning of the mammogram with the search window. Then we evaluate the estimated mixture at each position and display the corresponding log-likelihood value as a gray level at the window center. The resulting log-likelihood image closely correlates with the structural details of the original mammogram and emphasizes unusual places. We assume that, in parallel use, the log-likelihood image may provide additional information to facilitate the identification of malignant lesions as atypical locations of high novelty.

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.

Improving performance of content-based image retrieval schemes in searching for similar breast mass regions: an assessment

This study aims to assess three methods commonly used in content-based image retrieval (CBIR) schemes and investigate the approaches to improve scheme performance. A reference database involving 3000 regions of interest (ROIs) was established. Among them, 400 ROIs were randomly selected to form a testing dataset. Three methods, namely mutual information, Pearson's correlation and a multi-feature-based k-nearest neighbor (KNN) algorithm, were applied to search for the 15 'the most similar' reference ROIs to each testing ROI. The clinical relevance and visual similarity of searching results were evaluated using the areas under receiver operating characteristic (ROC) curves (A(Z)) and average mean square difference (MSD) of the mass boundary spiculation level ratings between testing and selected ROIs, respectively. The results showed that the A(Z) values were 0.893 +/- 0.009, 0.606 +/- 0.021 and 0.699 +/- 0.026 for the use of KNN, mutual information and Pearson's correlation, respectively. The A(Z) values increased to 0.724 +/- 0.017 and 0.787 +/- 0.016 for mutual information and Pearson's correlation when using ROIs with the size adaptively adjusted based on actual mass size. The corresponding MSD values were 2.107 +/- 0.718, 2.301 +/- 0.733 and 2.298 +/- 0.743. The study demonstrates that due to the diversity of medical images, CBIR schemes using multiple image features and mass size-based ROIs can achieve significantly improved performance.

Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM

The roles of physicists in medical imaging have expanded over the years, from the study of imaging systems (sources and detectors) and dose to the assessment of image quality and perception, the development of image processing techniques, and the development of image analysis methods to assist in detection and diagnosis. The latter is a natural extension of medical physicists' goals in developing imaging techniques to help physicians acquire diagnostic information and improve clinical decisions. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterize abnormalities that are found. Since the 1950s, the potential use of computers had been considered for analysis of radiographic abnormalities. In the mid-1980s, however, medical physicists and radiologists began major research efforts for computer-aided detection or computer-aided diagnosis (CAD), that is, using the computer output as an aid to radiologists-as opposed to a completely automatic computer interpretation-focusing initially on methods for the detection of lesions on chest radiographs and mammograms. Since then, extensive investigations of computerized image analysis for detection or diagnosis of abnormalities in a variety of 2D and 3D medical images have been conducted. The growth of CAD over the past 20 years has been tremendous-from the early days of time-consuming film digitization and CPU-intensive computations on a limited number of cases to its current status in which developed CAD approaches are evaluated rigorously on large clinically relevant databases. CAD research by medical physicists includes many aspects-collecting relevant normal and pathological cases; developing computer algorithms appropriate for the medical interpretation task including those for segmentation, feature extraction, and classifier design; developing methodology for assessing CAD performance; validating the algorithms using appropriate cases to measure performance and robustness; conducting observer studies with which to evaluate radiologists in the diagnostic task without and with the use of the computer aid; and ultimately assessing performance with a clinical trial. Medical physicists also have an important role in quantitative imaging, by validating the quantitative integrity of scanners and developing imaging techniques, and image analysis tools that extract quantitative data in a more accurate and automated fashion. As imaging systems become more complex and the need for better quantitative information from images grows, the future includes the combined research efforts from physicists working in CAD with those working on quantitative imaging systems to readily yield information on morphology, function, molecular structure, and more-from animal imaging research to clinical patient care. A historical review of CAD and a discussion of challenges for the future are presented here, along with the extension to quantitative image analysis.

Automated detection of breast mass spiculation levels and evaluation of scheme performance

RATIONALE AND OBJECTIVES

Although the spiculation levels of breast mass boundaries are a primary sign of malignancy for masses detected on mammography, developing an automated computerized method to detect spiculation levels and quantitatively evaluating the performance of such a method is a difficult task. The objectives of this study were to (1) develop and test a new method to improve mass segmentation and detect mass boundary spiculation levels and (2) assess the performance of this method using a relatively large imaging data set.

MATERIALS AND METHODS

The fully automated method developed for this study includes three image-processing steps. In the first step, the principle of maximum entropy is applied in the selected region of interest (ROI) after correcting the background trend to enhance the initial outlines of a mass. In the second step, an active-contour model is used to refine the initial outlines. In the third step, spiculated lines connected to the mass boundary are detected and identified using a special line detector. A quantitative spiculation index is computed to assess the degree of spiculation. To develop and evaluate this automated method, 211 ROIs depicting masses were extracted from a publicly available image database. Among these ROIs, 106 depicted circumscribed mass regions and 105 involved spiculated mass regions. The performance of the method was evaluated using receiver-operating characteristic (ROC) analysis.

RESULTS

The computed area under the ROC curve, when applying the method to the data set, was 0.701 +/- 0.027. By setting up a threshold at a spiculation index of 5.0, the method achieved an overall classification accuracy of 66.4%, with 54.3% sensitivity and 78.3% specificity.

CONCLUSIONS

In this study, a new computerized method with a number of unique characteristics was developed to detect spiculated mass regions, and a simple spiculation index was applied to quantify mass spiculation levels. Although this quantitative index can be used to distinguish between spiculated and circumscribed masses, the results also suggest that the automated detection of mass spiculation levels remains a technical challenge.

Automated breast mass detection in 3D reconstructed tomosynthesis volumes: a featureless approach

The purpose of this study was to propose and implement a computer aided detection (CADe) tool for breast tomosynthesis. This task was accomplished in two stages-a highly sensitive mass detector followed by a false positive (FP) reduction stage. Breast tomosynthesis data from 100 human subject cases were used, of which 25 subjects had one or more mass lesions and the rest were normal. For stage 1, filter parameters were optimized via a grid search. The CADe identified suspicious locations were reconstructed to yield 3D CADe volumes of interest. The first stage yielded a maximum sensitivity of 93% with 7.7 FPs/breast volume. Unlike traditional CADe algorithms in which the second stage FP reduction is done via feature extraction and analysis, instead information theory principles were used with mutual information as a similarity metric. Three schemes were proposed, all using leave-one-case-out cross validation sampling. The three schemes, A, B, and C, differed in the composition of their knowledge base of regions of interest (ROIs). Scheme A's knowledge base was comprised of all the mass and FP ROIs generated by the first stage of the algorithm. Scheme B had a knowledge base that contained information from mass ROIs and randomly extracted normal ROIs. Scheme C had information from three sources of information-masses, FPs, and normal ROIs. Also, performance was assessed as a function of the composition of the knowledge base in terms of the number of FP or normal ROIs needed by the system to reach optimal performance. The results indicated that the knowledge base needed no more than 20 times as many FPs and 30 times as many normal ROIs as masses to attain maximal performance. The best overall system performance was 85% sensitivity with 2.4 FPs per breast volume for scheme A, 3.6 FPs per breast volume for scheme B, and 3 FPs per breast volume for scheme C.

Computational Systems Bioinformatics and Bioimaging for Pathway Analysis and Drug Screening

The premise of today's drug development is that the mechanism of a disease is highly dependent upon underlying signaling and cellular pathways. Such pathways are often composed of complexes of physically interacting genes, proteins, or biochemical activities coordinated by metabolic intermediates, ions, and other small solutes and are investigated with molecular biology approaches in genomics, proteomics, and metabonomics. Nevertheless, the recent declines in the pharmaceutical industry's revenues indicate such approaches alone may not be adequate in creating successful new drugs. Our observation is that combining methods of genomics, proteomics, and metabonomics with techniques of bioimaging will systematically provide powerful means to decode or better understand molecular interactions and pathways that lead to disease and potentially generate new insights and indications for drug targets. The former methods provide the profiles of genes, proteins, and metabolites, whereas the latter techniques generate objective, quantitative phenotypes correlating to the molecular profiles and interactions. In this paper, we describe pathway reconstruction and target validation based on the proposed systems biologic approach and show selected application examples for pathway analysis and drug screening.

Optimization of reference library used in content-based medical image retrieval scheme

Building an optimal image reference library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of reference library and (2) a new reference selection strategy to optimize the library and improve I-CAD performance. The authors assembled a reference library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve references that are considered similar to the testing sample from the library. The area under receiver operating characteristic curve (Az) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased reference library size and tested I-CAD performance. The result indicates that scheme performance improves initially from Az= 0.715 to 0.874 and then plateaus when the library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should be removed if it performs poorly compared to a group of similar ROIs in a large and diverse reference library, the authors applied a new strategy to identify "poorly effective" references. By removing 174 identified ROIs from the reference library, I-CAD performance significantly increases to Az = 0.914 (p < 0.01). The study demonstrates that increasing reference library size and removing poorly effective references can significantly improve I-CAD performance.

Interactive computer-aided diagnosis of breast masses: computerized selection of visually similar image sets from a reference library

RATIONALE AND OBJECTIVES

The clinical utility of interactive computer-aided diagnosis (ICAD) systems depends on clinical relevance and visual similarity between the queried breast lesions and the ICAD-selected reference regions. The objective of this study is to develop and test a new ICAD scheme that aims improve visual similarity of ICAD-selected reference regions.

MATERIALS AND METHODS

A large and diverse reference library involving 3,000 regions of interests was established. For each queried breast mass lesion by the observer, the ICAD scheme segments the lesion, classifies its boundary spiculation level, and computes 14 image features representing the segmented lesion and its surrounding tissue background. A conditioned k-nearest neighbor algorithm is applied to select a set of the 25 most "similar" lesions from the reference library. After computing the mutual information between the queried lesion and each of these initially selected 25 lesions, the scheme displays the six reference lesions with the highest mutual information scores. To evaluate the automated selection process of the six "visually similar" lesions to the queried lesion, we conducted a two-alternative forced-choice observer preference study using 85 queried mass lesions. Two sets of reference lesions selected by one new automated ICAD scheme and the other previously reported scheme using a subjective rating method were randomly displayed on the left and right side of the queried lesion. Nine observers were asked to decide for each of the 85 queried lesions which one of the two reference sets was "more visually similar" to the queried lesion.

RESULTS

In classification of mass boundary spiculation levels, the overall agreement rate between the automated scheme and an observer is 58.8% (Kappa = 0.31). In observer preference study, the nine observers preferred on average the reference lesion sets selected by the automated scheme as being more visually similar than the set selected by the subjective rating approach in 53.2% of the queried lesions. The results were not significantly different for the two methods (P = .128).

CONCLUSIONS

This study suggests that using the new automated ICAD scheme, the interobserver variability related issues can thus be avoided. Furthermore, the new scheme maintains the similar performance level as the previous scheme using the subjective rating method that can select reference sets that are significantly more visually similar (P < .05) than when using traditional ICAD schemes in which the mass boundary spiculation levels are not accurately detected and quantified.

Multiprojection correlation imaging for improved detection of pulmonary nodules

OBJECTIVE

The purpose of this study was the development and preliminary evaluation of multiprojection correlation imaging with 3D computer-aided detection (CAD) on chest radiographs for cost- and dose-effective improvement of early detection of pulmonary nodules.

SUBJECTS AND METHODS

Digital chest radiographs of 10 configurations of a chest phantom and of seven human subjects were acquired in multiple angular projections with an acquisition time of 11 seconds (single breath-hold) and total exposure comparable with that of a posteroanterior chest radiograph. An initial 2D CAD algorithm with two difference-of-gaussians filters and multilevel thresholds was developed with an independent database of 44 single-view chest radiographs with confirmed lesions. This 2D CAD algorithm was used on each projection image to find likely suspect nodules. The CAD outputs were reconstructed in 3D, reinforcing signals associated with true nodules while simultaneously decreasing false-positive findings produced by overlapping anatomic features. The performance of correlation imaging was tested on two to 15 projection images.

RESULTS

Optimum performance of correlation imaging was attained when nine projection images were used. Compared with conventional, single-view CAD, correlation imaging decreased as much as 79% the frequency of false-positive findings in phantom cases at a sensitivity level of 65%. The corresponding reduction in false-positive findings in the cases of human subjects was 78%.

CONCLUSION

Although limited by a relatively simple CAD implementation and a small number of cases, the findings suggest that correlation imaging performs substantially better than single-view CAD and may greatly enhance identification of subtle solitary pulmonary nodules on chest radiographs.

Computerized detection of breast masses in digitized mammograms

We propose a system to detect malignant masses on mammograms. We investigated the behavior of an iris filter at different scales. After iris filter was applied, suspicious regions were segmented by means of an adaptive threshold. Suspected regions were characterized with features based on the iris filter output and, gray level, texture, contour-related, and morphological features extracted from the image. A backpropagation neural network classifier was trained to reduce the number of false positives. The system was developed and evaluated with two completely independent data sets. Results for a test set of 66 malignant and 49 normal cases, evaluated with free-response receiver operating characteristic analysis, yielded a sensitivity of 88% and 94% at 1.02 false positives per image for lesion-based and case-based evaluation, respectively. Results suggest that the proposed method could help radiologists as a second reader in mammographic screening.

Characterization of difference of Gaussian filters in the detection of mammographic regions

In this article, we present a characterization of the effect of difference of Gaussians (DoG) filters in the detection of mammographic regions. DoG filters have been used previously in mammographic mass computer-aided detection (CAD) systems. As DoG filters are constructed from the subtraction of two bivariate Gaussian distributions, they require the specification of three parameters: the size of the filter template and the standard deviations of the constituent Gaussians. The influence of these three parameters in the detection of mammographic masses has not been characterized. In this work, we aim to determine how the parameters affect (1) the physical descriptors of the detected regions, (2) the true and false positive rates, and (3) the classification performance of the individual descriptors. To this end, 30 DoG filters are created from the combination of three template sizes and four values for each of the Gaussians' standard deviations. The filters are used to detect regions in a study database of 181 craniocaudal-view mammograms extracted from the Digital Database for Screening Mammography. To describe the physical characteristics of the identified regions, morphological and textural features are extracted from each of the detected regions. Differences in the mean values of the features caused by altering the DoG parameters are examined through statistical and empirical comparisons. The parameters' effects on the true and false positive rate are determined by examining the mean malignant sensitivities and false positives per image (FPpI). Finally, the effect on the classification performance is described by examining the variation in FPpI at the point where 81% of the malignant masses in the study database are detected. Overall, the findings of the study indicate that increasing the standard deviations of the Gaussians used to construct a DoG filter results in a dramatic decrease in the number of regions identified at the expense of missing a small number of malignancies. The sharp reduction in the number of identified regions allowed the identification of textural differences between large and small mammographic regions. We find that the classification performances of the features that achieve the lowest average FPpI are influenced by all three of the parameters.

Dual system approach to computer-aided detection of breast masses on mammograms

In this study, our purpose was to improve the performance of our mass detection system by using a new dual system approach which combines a computer-added detection (CAD) system optimized with "average" masses with another CAD system optimized with "subtle" masses. The two single CAD systems have similar image processing steps, which include prescreening, object segmentation, morphological and texture feature extraction, and false positive (FP) reduction by rule-based and linear discriminant analysis (LDA) classifiers. A feed-forward backpropagation artificial neural network was trained to merge the scores from the LDA classifiers in the two single CAD systems and differentiate true masses from normal tissue. For an unknown test mammogram, the two single CAD systems are applied to the image in parallel to detect suspicious objects. A total of three data sets were used for training and testing the systems. The first data set of 230 current mammograms, referred to as the average mass set, was collected from 115 patients. We also collected 264 mammograms, referred to as the subtle mass set, which were one to two years prior to the current exam from these patients. Both the average and the subtle mass sets were partitioned into two independent data sets in a cross validation training and testing scheme. A third data set containing 65 cases with 260 normal mammograms was used to estimate the FP marker rates during testing. When the single CAD system trained on the average mass set was applied to the test set with average masses, the FP marker rates were 2.2, 1.8, and 1.5 per image at the case-based sensitivities of 90%, 85%, and 80%, respectively. With the dual CAD system, the FP marker rates were reduced to 1.2, 0.9, and 0.7 per image, respectively, at the same case-based sensitivities. Statistically significant (p < 0.05) improvements on the free response receiver operating characteristic curves were observed when the dual system and the single system were compared using the test sets with either average masses or subtle masses.

A completely automated CAD system for mass detection in a large mammographic database

Mass localization plays a crucial role in computer-aided detection (CAD) systems for the classification of suspicious regions in mammograms. In this article we present a completely automated classification system for the detection of masses in digitized mammographic images. The tool system we discuss consists in three processing levels: (a) Image segmentation for the localization of regions of interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima of the mammogram. (b) ROI characterization by means of textural features computed from the gray tone spatial dependence matrix (GTSDM), containing second-order spatial statistics information on the pixel gray level intensity. As the images under study were recorded in different centers and with different machine settings, eight GTSDM features were selected so as to be invariant under monotonic transformation. In this way, the images do not need to be normalized, as the adopted features depend on the texture only, rather than on the gray tone levels, too. (c) ROI classification by means of a neural network, with supervision provided by the radiologist's diagnosis. The CAD system was evaluated on a large database of 3369 mammographic images [2307 negative, 1062 pathological (or positive), containing at least one confirmed mass, as diagnosed by an expert radiologist]. To assess the performance of the system, receiver operating characteristic (ROC) and free-response ROC analysis were employed. The area under the ROC curve was found to be Az = 0.783 +/- 0.008 for the ROI-based classification. When evaluating the accuracy of the CAD against the radiologist-drawn boundaries, 4.23 false positives per image are found at 80% of mass sensitivity.

Computerized mass detection for digital breast tomosynthesis directly from the projection images

Digital breast tomosynthesis (DBT) has recently emerged as a new and promising three-dimensional modality in breast imaging. In DBT, the breast volume is reconstructed from 11 projection images, taken at source angles equally spaced over an arc of 50 degrees. Reconstruction algorithms for this modality are not fully optimized yet. Because computerized lesion detection in the reconstructed breast volume will be affected by the reconstruction technique, we are developing a novel mass detection algorithm that operates instead on the set of raw projection images. Mass detection is done in three stages. First, lesion candidates are obtained for each projection image separately, using a mass detection algorithm that was initially developed for screen-film mammography. Second, the locations of a lesion candidate are backprojected into the breast volume. In this feature volume, voxel intensities are a combined measure of detection frequency (e.g., the number of projections in which a given lesion candidate was detected), and a measure of the angular range over which a given lesion was detected. Third, features are extracted after reprojecting the three-dimensional (3-D) locations of lesion candidates into projection images. Features are combined using linear discriminant analysis. The database used to test the algorithm consisted of 21 mass cases (13 malignant, 8 benign) and 15 cases without mass lesions. Based on this database, the algorithm yielded a sensitivity of 90% at 1.5 false positives per breast volume. Algorithm performance is positively biased because this dataset was used for development, training, and testing, and because the number of algorithm parameters was approximately the same as the number.of patient cases. Our results indicate that computerized mass detection in the sequence of projection images for DBT may be effective despite the higher noise level in those images.

Computer-aided detection of breast masses on full field digital mammograms

We are developing a computer-aided detection (CAD) system for breast masses on full field digital mammographic (FFDM) images. To develop a CAD system that is independent of the FFDM manufacturer's proprietary preprocessing methods, we used the raw FFDM image as input and developed a multiresolution preprocessing scheme for image enhancement. A two-stage prescreening method that combines gradient field analysis with gray level information was developed to identify mass candidates on the processed images. The suspicious structure in each identified region was extracted by clustering-based region growing. Morphological and spatial gray-level dependence texture features were extracted for each suspicious object. Stepwise linear discriminant analysis (LDA) with simplex optimization was used to select the most useful features. Finally, rule-based and LDA classifiers were designed to differentiate masses from normal tissues. Two data sets were collected: a mass data set containing 110 cases of two-view mammograms with a total of 220 images, and a no-mass data set containing 90 cases of two-view mammograms with a total of 180 images. All cases were acquired with a GE Senographe 2000D FFDM system. The true locations of the masses were identified by an experienced radiologist. Free-response receiver operating characteristic analysis was used to evaluate the performance of the CAD system. It was found that our CAD system achieved a case-based sensitivity of 70%, 80%, and 90% at 0.72, 1.08, and 1.82 false positive (FP) marks/image on the mass data set. The FP rates on the no-mass data set were 0.85, 1.31, and 2.14 FP marks/image, respectively, at the corresponding sensitivities. This study demonstrated the usefulness of our CAD techniques for automated detection of masses on FFDM images.

Computer-aided detection performance in mammographic examination of masses: assessment

PURPOSE

To compare performance of two computer-aided detection (CAD) systems and an in-house scheme applied to five groups of sequentially acquired screening mammograms.

MATERIALS AND METHODS

Two hundred nineteen film-based mammographic examinations, classified into five groups, were included in this study. Group 1 included 58 examinations in which verified malignant masses were detected during screening; group 2, 39 in which all available latest examinations were performed prior to diagnosis of these malignant masses (subset of 39 women from group 1); group 3, 22 in which findings were interpreted as negative but were verified as cancer within 1 year from the negative interpretation (missed cancers); group 4, 50 in which findings were negative and patients were not recalled for additional procedures; and group 5, 50 in which patients were recalled for additional procedures and findings were negative for cancer. In all examinations, images were processed with two Food and Drug Administration-approved commercially available CAD systems and an in-house scheme. Performance levels in terms of true-positive detection rates and number of false-positive identifications per image and per examination were compared.

RESULTS

Mass detection rates in positive examinations (group 1) were 67%-72%. Detection rates among three systems were not significantly different (P > .05). In 50 negative screening examinations (group 4), false-positive rates ranged from 1.08 to 1.68 per four-view examination. Performance level differences among systems were significant for false-positive rates (P = .008). Performance of all systems was at levels lower than publicly suggested in some retrospective studies. False-positive CAD cueing rates were significantly higher for negative examinations in which patients were recalled (group 5) than they were for those in which patients were not recalled (group 4) (P < or = .002).

CONCLUSION

Performance of CAD systems for mass detection at mammography varies significantly, depending on examination and system used. Actual performance of all systems in clinical environment can be improved.

Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system

In previous research, we have developed a computer-aided detection (CAD) system designed to detect masses in mammograms. The previous version of our system employed a simple but imprecise method to localize the masses. In this research, we present a more robust segmentation routine for use with mammographic masses. Our hypothesis is that by more accurately describing the morphology of the masses, we can improve the CAD system's ability to distinguish masses from other mammographic structures. To test this hypothesis, we incorporated the new segmentation routine into our CAD system and examined the change in performance. The developed iterative, linear segmentation routine is a gray level-based procedure. Using the identified regions from the previous CAD system as the initial seeds, the new segmentation algorithm refines the suspicious mass borders by making estimates of the interior and exterior pixels. These estimates are then passed to a linear discriminant, which determines the optimal threshold between the interior and exterior pixels. After applying the threshold and identifying the object's outline, two constraints on the border are applied to reduce the influence of background noise. After the border is constrained, the process repeats until a stopping criterion is reached. The segmentation routine was tested on a study database of 183 mammographic images extracted from the Digital Database for Screening Mammography. Eighty-three of the images contained 50 malignant and 50 benign masses; 100 images contained no masses. The previously developed CAD system was used to locate a set of suspicious regions of interest (ROIs) within the images. To assess the performance of the segmentation algorithm, a set of 20 features was measured from the suspicious regions before and after the application of the developed segmentation routine. Receiver operating characteristic (ROC) analysis was employed on the ROIs to examine the discriminatory capabilities of each individual feature before and after the segmentation routine. A statistically significant performance increase was found in many of the individual features, particularly those describing the mass borders. To examine how the incorporation of the segmentation routine affected the performance of the overall CAD system, free-response ROC (FROC) analysis was employed. When considering only malignant masses, the FROC performance of the system with the segmentation routine appeared better than the previous system. When detecting 90% of the malignant masses, the previous system achieved 4.9 false positives per image (FPpI) compared to the post-segmentation system's 4.2 FPpI. At 80% sensitivity, the respective FPpI were 3.5 and 1.6.

Computer-Aided Detection Schemes: The Effect of Limiting the Number of Cued Regions in Each Case

OBJECTIVE

We assessed performance changes of a mammographic computer-aided detection scheme when we restricted the maximum number of regions that could be identified (cued) as showing positive findings in each case.

MATERIALS AND METHODS

A computer-aided detection scheme was applied to 500 cases (or 2,000 images), including 300 cases in which mammograms showed verified malignant masses. We evaluated the overall case-based performance of the scheme using a free-response receiver operating characteristic approach, and we measured detection sensitivity at a fixed false-positive detection rate of 0.4 per image after gradually reducing the maximum number of cued regions allowed for each case from seven to one.

RESULTS

The original computer-aided detection scheme achieved a maximum case-based sensitivity of 97% at 3.3 false-positive detected regions per image. For a detection decision score set at 0.565, the scheme had a 79% (237/300) case-based sensitivity, with 0.4 false-positive detected regions per image. After limiting the number of maximum allowed cued regions per case, the false-positive rates decreased faster than the true-positive rates. At a maximum of two cued regions per case, the false-positive rate decreased from 0.4 to 0.21 per image, whereas detection sensitivity decreased from 237 to 220 masses. To maintain sensitivity at 79%, we reduced the detection decision score to as low as 0.36, which resulted in a reduction of false-positive detected regions from 0.4 to 0.3 per image and a reduction in region-based sensitivity from 66.1% to 61.4%.

CONCLUSION

Limiting the maximum number of cued regions per case can improve the overall case-based performance of computer-aided detection schemes in mammography.

Computer-Aided Detection (CAD) in Screening Mammography:Sensitivity of Commercial CAD Systems for Detecting Architectural Distortion

OBJECTIVE

Computer-aided detection (CAD) algorithms have successfully revealed breast masses and microcalcifications on screening mammography. The purpose of our study was to evaluate the sensitivity of commercially available CAD systems for revealing architectural distortion, the third most common appearance of breast cancer.

MATERIALS AND METHODS

Two commercially available CAD systems were used to evaluate screening mammograms obtained in 43 patients with 45 mammographically detected regions of architectural distortion. For each CAD system, we determined the sensitivity for revealing architectural distortion on at least one image of the two-view mammographic examination (case sensitivity) and for each individual mammogram (image sensitivity). Surgical biopsy results were available for each case of architectural distortion.

RESULTS

Architectural distortion was deemed present and actionable by a panel of expert breast imagers in 80 views of the 45 cases. One CAD system detected distortion in 22 of 45 cases of distortion (case sensitivity, 49%) and in 30 of 80 mammograms (image sensitivity, 38%); it displayed 0.7 false-positive marks per image. Another CAD system identified distortion in 15 of 45 cases (case sensitivity, 33%) and 17 of 80 mammograms (image sensitivity, 21%); it displayed 1.27 false-positive marks per image. Sensitivity for malignancy-caused distortion was similar to or lower than sensitivity for all causes of distortion.

CONCLUSION

Fewer than one half of the cases of architectural distortion were detected by the two most widely available CAD systems used for interpretations of screening mammograms. Considerable improvement in the sensitivity of CAD systems is needed for detecting this type of lesion. Practicing breast imagers who use CAD systems should remain vigilant for architectural distortion.

Performance change of mammographic CAD schemes optimized with most-recent and prior image databases

RATIONALE AND OBJECTIVES

The authors evaluated performance changes in the detection of masses on "current" (latest) and "prior" images by computer-aided diagnosis (CAD) schemes that had been optimized with databases of current and prior mammograms.

MATERIALS AND METHODS

The authors selected 260 pairs of matched consecutive mammograms. Each current image depicted one or two verified masses. All prior images had been interpreted originally as negative or probably benign. A CAD scheme initially detected 261 mass regions and 465 false-positive regions on the current images, and 252 corresponding mass regions (early signs) and 471 false-positive regions on prior images. These regions were divided into two training and two testing databases. The current and prior training databases were used to optimize two CAD schemes with a genetic algorithm. These schemes were evaluated with two independent testing databases.

RESULTS

The scheme optimized with current images produced areas under the receiver operating characteristic curve of (0.89 +/- 0.01 and 0.65 +/- 0.02 when tested with current images and prior images, respectively. The scheme optimized with prior images produced areas under the receiver operating characteristic curve of 0.81 +/- 0.02 and 0.71 +/- 0.02 when tested with current images and prior images, respectively. Performance changes for both current and prior testing databases were significant (P < .01) for the two schemes.

CONCLUSION

CAD schemes trained with current images do not perform optimally in detecting masses depicted on prior images. To optimize CAD schemes for early detection, it may be important to include in the training database a large fraction of prior images originally reported as negative and later proven to be positive.

Computer-aided detection in mammography: an assessment of performance on current and prior images

RATIONALE AND OBJECTIVES

The authors assessed and compared the performance of a computer-aided detection (CAD) scheme for the detection of masses and microcalcification clusters on a set of images collected from two consecutive ("current" and "prior") mammographic examinations.

MATERIALS AND METHODS

A previously developed CAD scheme was used to assess two consecutive screening mammograms from 200 cases in which the current mammogram showed a mass or cluster of microcalcifications that resulted in breast biopsy. The latest prior examinations had been initially interpreted as negative or definitely benign findings (Breast Imaging Reporting and Data System rating, 1 or 2). The study involved images of 400 examinations acquired in 200 patients. Radiologists identified 172 masses and 128 clusters of microcalcifications on the current images. The performance of the CAD scheme was analyzed and compared for the current and latest prior images.

RESULTS

There were significant differences (P < .01) between current and prior images in many feature values. The performance of the CAD scheme was significantly lower for prior than for current images (P < .01). At 0.5 and 0.2 false-positive mass and cluster cues per image, the scheme detected 78 malignant masses (78%) and 63 malignant clusters (80%) on current images. Only 42% of malignant cases were detected on prior images, including 40 masses (40%) and 36 microcalcification clusters (46%).

CONCLUSION

CAD schemes can detect a substantial fraction of masses and microcalcification clusters depicted on prior images. To improve performance with prior images, the scheme may have to be adaptively reoptimized with increasingly more subtle abnormalities.

Soft-copy mammographic readings with different computer-assisted detection cuing environments: preliminary findings

PURPOSE

To assess the performance of radiologists in the detection of masses and microcalcification clusters on digitized mammograms by using different computer-assisted detection (CAD) cuing environments.

MATERIALS AND METHODS

Two hundred nine digitized mammograms depicting 57 verified masses and 38 microcalcification clusters in 85 positive and 35 negative cases were interpreted independently by seven radiologists using five display modes. Except for the first mode, for which no CAD results were provided, suspicious regions identified with a CAD scheme were cued in all the other modes by using a combination of two cuing sensitivities (90% and 50%) and two false-positive rates (0.5 and 2.0 per image). A receiver operating characteristic study was performed by using soft-copy images.

RESULTS

CAD cuing at 90% sensitivity and a rate of 0.5 false-positive region per image improved observer performance levels significantly (P < .01). As accuracy of CAD cuing decreased so did observer performances (P < .01). Cuing specificity affected mass detection more significantly, while cuing sensitivity affected detection of microcalcification clusters more significantly (P < .01). Reduction of cuing sensitivity and specificity significantly increased false-negative rates in noncued areas (P < .05). Trends were consistent for all observers.

CONCLUSION

CAD systems have the potential to significantly improve diagnostic performance in mammography. However, poorly performing schemes could adversely affect observer performance in both cued and noncued areas.

Performance gain in computer-assisted detection schemes by averaging scores generated from artificial neural networks with adaptive filtering

The authors investigated a new method to optimize artificial neural networks (ANNs) with adaptive filtering used in computer-assisted detection schemes in digitized mammograms and to assess performance changes when averaging classification scores from three sets of optimized schemes. Two independent training and testing image databases involving 978 and 830 digitized mammograms, respectively, were used in this study. In the training data set, initial filtering and subtraction resulted in the identification of 592 mass regions and 3790 suspicious, but actually negative regions. These regions (including both true-positive and negative regions) were segmented into three subsets three times based on the calculation of the values of three features as segmentation indices. The indices were "mass" size multiplied by their digital value contrast, conspicuity, and circularity. Nine ANN-based classifiers were separately optimized using a genetic algorithm for each subset of regions. Each region was assigned three classification scores after applying the three adaptive ANNs. The performance gain of the CAD scheme after averaging the three scores for each suspicious region was tested using an independent data set and a ROC methodology. The experimental results showed that the areas under ROC curves (Az) for the testing database using three sets of optimized ANNs individually were 0.84+/-0.01, 0.83+/-0.01, and 0.84+/-0.01, respectively. The between-index correlations of three A values were 0.013, -0.007, and 0.086. Similar to averaging diagnostic ratings from independent observers, by averaging three ANN-generated scores for each testing region, the performance of the CAD scheme was significantly improved (p<0.001) with Az value of 0.95+/-0.01.

Knowledge-based computer-aided detection of masses on digitized mammograms: a preliminary assessment

The purpose of this work was to develop and evaluate a computer-aided detection (CAD) scheme for the improvement of mass identification on digitized mammograms using a knowledge-based approach. Three hundred pathologically verified masses and 300 negative, but suspicious, regions, as initially identified by a rule-based CAD scheme, were randomly selected from a large clinical database for development purposes. In addition, 500 different positive and 500 negative regions were used to test the scheme. This suspicious region pruning scheme includes a learning process to establish a knowledge base that is then used to determine whether a previously identified suspicious region is likely to depict a true mass. This is accomplished by quantitatively characterizing the set of known masses, measuring "similarity" between a suspicious region and a "known" mass, then deriving a composite "likelihood" measure based on all "known" masses to determine the state of the suspicious region. To assess the performance of this method, receiver-operating characteristic (ROC) analyses were employed. Using a leave-one-out validation method with the development set of 600 regions, the knowledge-based CAD scheme achieved an area under the ROC curve of 0.83. Fifty-one percent of the previously identified false-positive regions were eliminated, while maintaining 90% sensitivity. During testing of the 1,000 independent regions, an area under the ROC curve as high as 0.80 was achieved. Knowledge-based approaches can yield a significant reduction in false-positive detections while maintaining reasonable sensitivity. This approach has the potential of improving the performance of other rule-based CAD schemes.

Computerized radiographic mass detection--part I: Lesion site selection by morphological enhancement and contextual segmentation

This paper presents a statistical model supported approach for enhanced segmentation and extraction of suspicious mass areas from mammographic images. With an appropriate statistical description of various discriminate characteristics of both true and false candidates from the localized areas, an improved mass detection may be achieved in computer-assisted diagnosis (CAD). In this study, one type of morphological operation is derived to enhance disease patterns of suspected masses by cleaning up unrelated background clutters, and a model-based image segmentation is performed to localize the suspected mass areas using stochastic relaxation labeling scheme. We discuss the importance of model selection when a finite generalized Gaussian mixture is employed, and use the information theoretic criteria to determine the optimal model structure and parameters. Examples are presented to show the effectiveness of the proposed methods on mass lesion enhancement and segmentation when applied to mammographical images. Experimental results demonstrate that the proposed method achieves a very satisfactory performance as a preprocessing procedure for mass detection in CAD.

False-positive reduction in CAD mass detection using a competitive classification strategy

High false-positive (FP) rate remains to be one of the major problems to be solved in CAD study because too many false-positively cued signals will potentially degrade the performance of detecting true-positive regions and increase the call-back rate in CAD environment. In this paper, we proposed a novel classification method for FP reduction, where the conventional "hard" decision classifier is cascaded with a "soft" decision classification with the objective to reduce false-positives in the cases with multiple FPs retained after the "hard" decision classification. The "soft" classification takes a competitive classification strategy in which only the "best" ones are selected from the pre-classified suspicious regions as the true mass in each case. A neural network structure is designed to implement the proposed competitive classification. Comparative studies of FP reduction on a database of 79 images by a "hard" decision classification and a combined "hard"-"soft" classification method demonstrated the efficiency of the proposed classification strategy. For example, for the high FP sub-database which has only 31.7% of total images but accounts for 63.5% of whole FPs generated in single "hard" classification, the FPs can be reduced for 56% (from 8.36 to 3.72 per image) by using the proposed method at the cost of 1% TP loss (from 69% to 68%) in whole database, while it can only be reduced for 27% (from 8.36 to 6.08 per image) by simply increasing the threshold of "hard" classifier with a cost of TP loss as high as 14% (from 69% to 55%). On the average in whole database, the FP reduction by hybrid "hard"-"soft" classification is 1.58 per image as compared to 1.11 by "hard" classification at the TP costs described above. Because the cases with high dense tissue are of higher risk of cancer incidence and false-negative detection in mammogram screening, and usually generate more FPs in CAD detection, the method proposed in this paper will be very helpful in improving the performance of early detection of breast cancer with CAD.