Chest X-ray (CXR) images have a high potential in the monitoring and examination of various lung diseases, including COVID-19. However, the screening of a large number of patients with diagnostic hypothesis for COVID-19 poses a major challenge for physicians. In this paper, we propose a deep learning-based approach that can simultaneously suggest a diagnose and localize lung opacity areas in CXR images. We used a public dataset containing 5, 639 posteroanterior CXR images. Due to unbalanced classes (69.2% of the images are COVID-19 positive), data augmentation was applied only to images belonging to the normal category. We split the dataset into train and test sets with proportional rate at 90:10. To the classification task, we applied 5-fold cross-validation to the training set. The EfficientNetB4 architecture was used to perform this classification. We used a YOLOv5 pre-trained in COCO dataset to the detection task. Evaluations were based on accuracy and area under the ROC curve (AUROC) metrics to the classification task and mean average precision (mAP) to the detection task. The classification task achieved an average accuracy of 0.83 ± 0.01 (95% CI [0.81, 0.84]) and AUC of 0.88 ± 0.02 (95% CI [0.85, 0.89]) in 5-fold over the test dataset. The best result was reached in fold 3 (0.84 and 0.89 of accuracy and AUC, respectively). Positive results were evaluated by the opacity detector, which achieved a mAP of 59.51%. Thus, the good performance and rapid diagnostic prediction make the system a promising means to assist radiologists in decision making tasks.
The SARS-CoV-2 (COVID-19) disease rapidly spread worldwide, thus increasing the need to create new strategies to fight it. Several researchers in different fields have attempted to develop methods to early identifying it and mitigating its effects. The Deep Learning (DL) approach, such as the Convolutional Neural Networks (CNNs), has been increasingly used in COVID-19 diagnoses. These models intend to support decision-making and are doing well to detecting patient status early. Although DL models have good accuracy to support diagnosis, they are vulnerable to Adversarial Attacks. These attacks are new methods to make DL models biased by adding small perturbations on the original image. This paper investigates the impact of Adversarial Attacks on DL models for classifying X-ray images of COVID-19 cases. We focused on the attack Fast Gradient Sign Method (FGSM), which aims to add perturbations to the testing images by combining a perturbation matrix, producing a crafted image. We conduct the experiments analyzing the model’s performance attack-free and adding attacks. The following CNNs models were selected: DenseNet201, ResNet-50V2, MobileNetV2, NasNet and VGG16. In the attack-free environment, we reach precision around 99%. When it adds the attack, our results revealed that all models suffer from performance reduction, and the most affected was MobileNet that reduced its ability from 98.61% to 67.73%. However, the VGG16 network showed to be the least affected by the attacks. Our finds describe that DL models for COVID-19 are vulnerable to Adversarial Examples. The FGSM was capable of fooling the model, resulting in a significant reduction in the DL performance.
KEYWORDS: Breast, Elastography, Breast cancer, Mammography, Color imaging, Databases, Ultrasonography, Diagnostics, Visualization, RGB color model, Visual analytics, Cancer
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.
KEYWORDS: Mammography, Breast, Digital mammography, Breast cancer, Image quality, Tissues, Image analysis, Computer aided diagnosis and therapy, Digital imaging, Data acquisition
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.
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.
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.
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.
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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.