Karem D. Marcomini

Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images

This research presents a methodology for the automatic detection and characterization of breast sonographic findings. We performed the tests in ultrasound images obtained from breast phantoms made of tissue mimicking material. When the results were considerable, we applied the same techniques to clinical examinations. The process was started employing preprocessing (Wiener filter, equalization, and median filter) to minimize noise. Then, five segmentation techniques were investigated to determine the most concise representation of the lesion contour, enabling us to consider the neural network SOM as the most relevant. After the delimitation of the object, the most expressive features were defined to the morphological description of the finding, generating the input data to the neural Multilayer Perceptron (MLP) classifier. The accuracy achieved during training with simulated images was 94.2%, producing an AUC of 0.92. To evaluating the data generalization, the classification was performed with a group of unknown images to the system, both to simulators and to clinical trials, resulting in an accuracy of 90% and 81%, respectively. The proposed classifier proved to be an important tool for the diagnosis in breast ultrasound.

Quantitative evaluation of automatic methods for lesions detection in breast ultrasound images

Ultrasound (US) is a useful diagnostic tool to distinguish benign from malignant breast masses, providing more detailed evaluation in dense breasts. Due to the subjectivity in the images interpretation, computer-aid diagnosis (CAD) schemes have been developed, increasing the mammography analysis process to include ultrasound images as complementary exams. As one of most important task in the evaluation of this kind of images is the mass detection and its contours interpretation, automated segmentation techniques have been investigated in order to determine a quite suitable procedure to perform such an analysis. Thus, the main goal in this work is investigating the effect of some processing techniques used to provide information on the determination of suspicious breast lesions as well as their accurate boundaries in ultrasound images. In tests, 80 phantom and 50 clinical ultrasound images were preprocessed, and 5 segmentation techniques were tested. By using quantitative evaluation metrics the results were compared to a reference image delineated by an experienced radiologist. A self-organizing map artificial neural network has provided the most relevant results, demonstrating high accuracy and low error rate in the lesions representation, corresponding hence to the segmentation process for US images in our CAD scheme under tests.

Proposal of Semi-automatic Classification of Breast Lesions for Strain Sonoelastography Using a Dedicated CAD System

The aim of this study was to develop a tool to classify breast lesions using ultrasound elastography. Our dataset included a total of 78 patients enrolled for percutaneous biopsy of 85 breast lesions. These lesions were classified into three sonoelastographic scores, where scores of 1 and 2 were considered negative --- soft and intermediate respectively; the score 3 was considered positive --- hard. The visual classification of elastography performed by two radiologists was compared with our semi-automatic method. This classification aims to segment the red pixels found in the color elastography, quantify them and characterize the lesion by comparing the areas in red with the manually segmented lesion by the two radiologists. Our semi-automated technique had comparable performance to that of the two radiologists: sensitivity of 54.5i¾?% and specificity of 90.5i¾?%. The agreement kappa was greater than 0.8 for all observers. Thus, we concluded that the proposed method achieved a high rate of agreement between observers. In addition, the method presented high diagnostic specificity in classifying breast elastography images. By including more image features in the future, we expect our classifier can be use to standardize the classification of breast elastography.

Development of a computer tool to detect and classify nodules in ultrasound breast images

Due to the high incidence rate of breast cancer in women, many procedures have been developed to assist the diagnosis and early detection. Currently, ultrasonography has proved as a useful tool in distinguishing benign and malignant masses. In this context, the computer-aided diagnosis schemes have provided to the specialist a second opinion more accurately and reliably, minimizing the visual subjectivity between observers. Thus, we propose the application of an automatic detection method based on the use of the technique of active contour in order to show precisely the contour of the lesion and provide a better understanding of their morphology. For this, a total of 144 images of phantoms were segmented and submitted to morphological operations of opening and closing for smoothing the edges. Then morphological features were extracted and selected to work as input parameters for the neural classifier Multilayer Perceptron which obtained 95.34% correct classification of data and Az of 0.96.

The Feasibility of Classifying Breast Masses Using a Computer-Assisted Diagnosis (CAD) System Based on Ultrasound Elastography and BI-RADS Lexicon

Objectives: To determine the applicability of a computer-aided diagnostic system strain elastography system for the classification of breast masses diagnosed by ultrasound and scored using the criteria proposed by the breast imaging and reporting data system ultrasound lexicon and to determine the diagnostic accuracy and interobserver variability. Methods: This prospective study was conducted between March 1, 2016, and May 30, 2016. A total of 83 breast masses subjected to percutaneous biopsy were included. Ultrasound elastography images before biopsy were interpreted by 3 radiologists with and without the aid of computer-aided diagnostic system for strain elastography. The parameters evaluated by each radiologist results were sensitivity, specificity, and diagnostic accuracy, with and without computer-aided diagnostic system for strain elastography. Interobserver variability was assessed using a weighted κ test and an intraclass correlation coefficient. The areas under the receiver operating characteristic curves were also calculated. Results: The areas under the receiver operating characteristic curve were 0.835, 0.801, and 0.765 for readers 1, 2, and 3, respectively, without computer-aided diagnostic system for strain elastography, and 0.900, 0.926, and 0.868, respectively, with computer-aided diagnostic system for strain elastography. The intraclass correlation coefficient between the 3 readers was 0.6713 without computer-aided diagnostic system for strain elastography and 0.811 with computer-aided diagnostic system for strain elastography. Conclusion: The proposed computer-aided diagnostic system for strain elastography system has the potential to improve the diagnostic performance of radiologists in breast examination using ultrasound associated with elastography.

Evaluation of a Computer-Aided Diagnosis System in the Classification of Lesions in Breast Strain Elastography Imaging

Purpose: Evaluation of the performance of a computer-aided diagnosis (CAD) system based on the quantified color distribution in strain elastography imaging to evaluate the malignancy of breast tumors. Methods: The database consisted of 31 malignant and 52 benign lesions. A radiologist who was blinded to the diagnosis performed the visual analysis of the lesions. After six months with no eye contact on the breast images, the same radiologist and other two radiologists manually drew the contour of the lesions in B-mode ultrasound, which was masked in the elastography image. In order to measure the amount of hard tissue in a lesion, we developed a CAD system able to identify the amount of hard tissue, represented by red color, and quantify its predominance in a lesion, allowing classification as soft, intermediate, or hard. The data obtained with the CAD system were compared with the visual analysis. We calculated the sensitivity, specificity, and area under the curve (AUC) for the classification using the CAD system from the manual delineation of the contour by each radiologist. Results: The performance of the CAD system for the most experienced radiologist achieved sensitivity of 70.97%, specificity of 88.46%, and AUC of 0.853. The system presented better performance compared with his visual diagnosis, whose sensitivity, specificity, and AUC were 61.29%, 88.46%, and 0.829, respectively. The system obtained sensitivity, specificity, and AUC of 67.70%, 84.60%, and 0.783, respectively, for images segmented by Radiologist 2, and 51.60%, 92.30%, and 0.771, respectively, for those segmented by the Resident. The intra-class correlation coefficient was 0.748. The inter-observer agreement of the CAD system with the different contours was good in all comparisons. Conclusions: The proposed CAD system can improve the radiologist performance for classifying breast masses, with excellent inter-observer agreement. It could be a promising tool for clinical use.

Agreement between a computer-assisted tool and radiologists to classify lesions in breast elastography images

Breast elastography is a new sonographic technique that provides additional information to evaluate tissue stiffness. However, interpreting breast elastography images can vary depending on the radiologist. In order to provide quantitative and less subjective data regarding the stiffness of a lesion, we developed a tool to measure the amount of hard area in a lesion from the 2D image. The database consisted of 78 patients with 83 breast lesions (31 malignant and 52 benign). Two radiologists and one resident manually drew the contour of the lesions in B-mode ultrasound images and the contour was mapped in the elastography image. By using the system proposed, the radiologists obtained a very good diagnostic agreement among themselves (kappa = 0.86), achieving the same sensitivity and specificity (80.7 and 88.5, respectively), and an AUC of 0.883 for Radiologist 1 and 0.892 for Radiologist 2. The Resident had less interobserver agreement, as well as lower specificity and AUC, which may be related to less experience. Furthermore, the radiologists had an agreement with the tool used in the automatic method higher than 90%. Thus, the method developed was useful in aiding the diagnosis of breast lesions in strain elastography, minimizing its subjectivity.

Observer study to evaluate the simulation of mammographic calcification clusters

Numerous breast phantoms have been developed to be as realistic as possible to ensure the accuracy of image quality analysis, covering a greater range of applications. In this study, we simulated three different densities of the breast parenchyma using paraffin gel, acrylic plates and PVC films. Hydroxyapatite was used to simulate calcification clusters. From the images acquired with a GE Senographe DR 2000D mammography system, we selected 68 regions of interest (ROIs) with and 68 without a simulated calcification cluster. To validate the phantom simulation, we selected 136 ROIs from the University of South Florida’s Digital Database for Screening Mammography (DDSM). Seven trained observers performed two observer experiments by using a high-resolution monitor Barco mod. E-3620. In the first experiment, the observers had to distinguish between real or phantom ROIs (with and without calcification). In the second one, the observers had to indicate the ROI with calcifications between a pair of ROIs. Results from our study show that the hydroxyapatite calcifications had poor contrast in the simulated breast parenchyma, thus observers had more difficulty in identifying the presence of calcification clusters in phantom images. Preliminary analysis of the power spectrum was conducted to investigate the radiographic density and the contrast thresholds for calcification detection. The values obtained for the power spectrum exponent (β) were comparable with those found in the literature.

Segmentation techniques evaluation based on a single compact breast mass classification scheme

In this work some segmentation techniques are evaluated by using a simple centroid-based classification system regarding breast mass delineation in digital mammography images. The aim is to determine the best one for future CADx developments. Six techniques were tested: Otsu, SOM, EICAMM, Fuzzy C-Means, K-Means and Level-Set. All of them were applied to segment 317 mammography images from DDSM database. A single compact set of attributes was extracted and two centroids were defined, one for malignant and another for benign cases. The final classification was based on proximity with a given centroid and the best results were presented by the Level-Set technique with a 68.1% of Accuracy, which indicates this method as the most promising for breast masses segmentation aiming a more precise interpretation in schemes CADx.

Investigating materials for breast nodules simulation by using segmentation and similarity analysis of digital images

The task of identifying the malignancy of nodular lesions on mammograms becomes quite complex due to overlapped structures or even to the granular fibrous tissue which can cause confusion in classifying masses shape, leading to unnecessary biopsies. Efforts to develop methods for automatic masses detection in CADe (Computer Aided Detection) schemes have been made with the aim of assisting radiologists and working as a second opinion. The validation of these methods may be accomplished for instance by using databases with clinical images or acquired through breast phantoms. With this aim, some types of materials were tested in order to produce radiographic phantom images which could characterize a good enough approach to the typical mammograms corresponding to actual breast nodules. Therefore different nodules patterns were physically produced and used on a previous developed breast phantom. Their characteristics were tested according to the digital images obtained from phantom exposures at a LORAD M-IV mammography unit. Two analysis were realized the first one by the segmentation of regions of interest containing the simulated nodules by an automated segmentation technique as well as by an experienced radiologist who has delineated the contour of each nodule by means of a graphic display digitizer. Both results were compared by using evaluation metrics. The second one used measure of quality Structural Similarity (SSIM) to generate quantitative data related to the texture produced by each material. Although all the tested materials proved to be suitable for the study, the PVC film yielded the best results.