Detection Of Breast Masses Research Articles

YOLO-LOGO: A transformer-based YOLO segmentation model for breast mass detection and segmentation in digital mammograms

Background and objectiveBoth mass detection and segmentation in digital mammograms play a crucial role in early breast cancer detection and treatment. Furthermore, clinical experience has shown that they are the upstream tasks of pathological classification of breast lesions. Recent advancements in deep learning have made the analyses faster and more accurate. This study aims to develop a deep learning model architecture for breast cancer mass detection and segmentation using the mammography. MethodsIn this work we proposed a double shot model for mass detection and segmentation simultaneously using a combination of YOLO (You Only Look Once) and LOGO (Local-Global) architectures. Firstly, we adopted YoloV5L6, the state-of-the-art object detection model, to position and crop the breast mass in mammograms with a high resolution; Secondly, to balance training efficiency and segmentation performance, we modified the LOGO training strategy to train the whole images and cropped images on the global and local transformer branches separately. The two branches were then merged to form the final segmentation decision. ResultsThe proposed YOLO-LOGO model was tested on two independent mammography datasets (CBIS-DDSM and INBreast). The proposed model performs significantly better than previous works. It achieves true positive rate 95.7% and mean average precision 65.0% for mass detection on CBIS-DDSM dataset. Its performance for mass segmentation on CBIS-DDSM dataset is F1-score=74.5% and IoU=64.0%. The similar performance trend is observed in another independent dataset INBreast as well. ConclusionsThe proposed model has a higher efficiency and better performance, reduces computational requirements, and improves the versatility and accuracy of computer-aided breast cancer diagnosis. Hence it has the potential to enable more assistance for doctors in early breast cancer detection and treatment, thereby reducing mortality.

Noise reduction and mammography image segmentation optimization with novel QIMFT-SSA method

Breast cancer is one of the most dreaded diseases that affects women worldwide and has led to many deaths. Early detection of breast masses prolongs life expectancy in women and hence the development of an automated system for breast masses supports radiologists for accurate diagnosis. In fact, providing an optimal approach with the highest speed and more accuracy is an approach provided by computer-aided design techniques to determine the exact area of breast tumors to use a decision support management system as an assistant to physicians. This study proposes an optimal approach to noise reduction in mammographic images and to identify salt and pepper, Gaussian, Poisson and impact noises to determine the exact mass detection operation after these noise reduction. It therefore offers a method for noise reduction operations called Quantum Inverse MFT Filtering and a method for precision mass segmentation called the Optimal Social Spider Algorithm (SSA) in mammographic images. The hybrid approach called QIMFT-SSA is evaluated in terms of criteria compared to previous methods such as peak Signal-to-Noise Ratio (PSNR) and Mean-Squared Error (MSE) in noise reduction and accuracy of detection for mass area recognition. The proposed method presents more performance of noise reduction and segmentation in comparison to state-of-arts methods. supported the work.

Intraradiological pathology-calibrated electrical impedance spectroscopy in the evaluation of excision-required breast lesions.

Evaluating a real-time complementary bioelectrical diagnostic device based on electrical impedance spectroscopy (EIS) for improving breast imaging-reporting and data system (BI-RADS) scoring accuracy, especially in high-risk or borderline breast diseases. The primary purpose is to characterize breast tumors based on their dielectric properties. Early detection of high-risk lesions and increasing the accuracy of tumor sampling and pathological diagnosis are secondary objectives of the study. The tumor detection probe (TDP) was first applied to the mouse model for electrical safety evaluations by electrical current measurement. Then it was utilized for characterization of 138 human palpable breast lesions that were to undergo core needle biopsy (CNB), vacuum-assisted biopsy (VAB), or fine needle aspiration (FNA) on the surgeon's requests. Impedance phase slope (IPS) in frequency ranges of 100- 500kHz and impedance magnitude in f=1kHz were extracted as the classification parameters. Consistency of radiological and pathological declarations for the excisional recommendation was then compared with the IPS values. Considering pathological results as the gold standard, meaningful correlations between IPS and pathophysiological status of lesions recommended for excision (such as atypical ductal hyperplasia, papillary lesions, complex sclerosing adenosis, and fibroadenoma) were observed (p<0.0001). These pathophysiological properties may include cell size, membrane permeability, packing density, adenosis, cytoplasm structure, etc. Benign breast lesions showed IPS values greater than 0, while high-risk proliferative, precancerous, or cancerous lesions had negative IPS values. Statistical analysis showed 95% sensitivity with area under the curve (AUC) equal to 0.92. Borderline breast diseases and high-risk lesions that should be excised according to standard guidelines can be diagnosed with TDP before any sampling process. It is an important outcome for high-risk lesions that are radiologically underestimated to BI-RADS3, specifically in younger patients with dense breast masses that present challenges in mammographic and sonographic evaluations. Also, the lowest IPS value detects the most pathologic portions of the tumor for increasing sampling accuracy in large tumors. Precise detection of high-risk breast masses, which may be declared BI-RADS3 instead of BI-RADS4a.

Automatic Breast Mass Segmentation and Classification Using Subtraction of Temporally Sequential Digital Mammograms

Cancer remains a major cause of morbidity and mortality globally, with 1 in 5 of all new cancers arising in the breast. The introduction of mammography for the radiological diagnosis of breast abnormalities, significantly decreased their mortality rates. Accurate detection and classification of breast masses in mammograms is especially challenging for various reasons, including low contrast and the normal variations of breast tissue density. Various Computer-Aided Diagnosis (CAD) systems are being developed to assist radiologists with the accurate classification of breast abnormalities. In this study, subtraction of temporally sequential digital mammograms and machine learning are proposed for the automatic segmentation and classification of masses. The performance of the algorithm was evaluated on a dataset created especially for the purposes of this study, with 320 images from 80 patients (two time points and two views of each breast) with precisely annotated mass locations by two radiologists. Ninety-six features were extracted and ten classifiers were tested in a leave-one-patient-out and k-fold cross-validation process. Using Neural Networks, the detection of masses was 99.9% accurate. The classification accuracy of the masses as benign or suspicious increased from 92.6%, using the state-of-the-art temporal analysis, to 98%, using the proposed methodology. The improvement was statistically significant (p-value < 0.05). These results demonstrate the effectiveness of the subtraction of temporally consecutive mammograms for the diagnosis of breast masses. Clinical and Translational Impact Statement: The proposed algorithm has the potential to substantially contribute to the development of automated breast cancer Computer-Aided Diagnosis systems with significant impact on patient prognosis.

Determining the relative frequency of ultrasound findings in women under 30 years of age with a breast mass.

Mammography and ultrasound are the most reliable and common imaging techniques for early detection of breast mass. The aim of this study was to determine the relative frequency of ultrasound findings in women under 30 years of age by a feeling of mass in the breast. This cross-sectional study was performed on women under 30 years of age with a feeling of mass in the breast. The result evaluated in this study was the final opinion of the radiologist on the ultrasound report, which was expressed in the form of Breast imaging-reporting and data system (BIRADS) based on one to five scores. Ultrasound status of patients was reported to be normal, fibrocystic changes, and tumors (solid-cystic-mixed). The obtained data were analyzed using SPSS statistical software version 23. Significance level was considered to be < 0.05. The most common reason for referral was palpable mass in the left breast (56.2%). The shape of the mass was oval in most cases (91.2%). The highest frequency in terms of mass margin was related to Macrolobulated (82.4%), Hypoechoic (85%), and Solid (87.6%). Most of masses belonged to 12 o'clock (21.2%). According to the standard sonography report based on BIRADS, the highest frequency belonged to B4a (57.5%). Pathology report showed that the highest frequency was related to fibroadenoma (71.4%). Considering that most of the cases in this research with a feeling of mass in the breast in women under 30 years of age were BIRADS 4, and among the cases that underwent biopsy, 14.5% were diagnosed with cancer pathology. Therefore, ultrasound examination is very important in these cases, even at a young age.

Accuracy of Unenhanced Breast MRI Compared to Dynamic Contrast Enhanced MRI in Detection and Characterization of Breast Masses

Background: Breast cancer is the most frequently diagnosed cancer and the leading cause of cancer death among females worldwide. Obtaining an accurate diagnosis is of considerable importance as it informs the choice of treatment and the prognostic outcomes of the disease. Magnetic resonance imaging (MRI) has a higher sensitivity for the diagnosis of breast cancer than mammography and ultrasound. Objective: We aimed to assess the diagnostic efficacy and efficiency of unenhanced MRI sequences for detection and characterization of breast lesions. Accordingly, we evaluated the breast unenhanced- MRI (UE-MRI) protocol as a reliable alternative for dynamic contrast-enhanced MRI (DCE-MRI). Patients and Methods: 90 female patients underwent MR examination with a diagnostic protocol including UE-MRI sequences (T1WI, T2WI, short TI inversion recovery (STIR) and diffusion weighted imaging (DWI)) and CE-MRI. UE-MRI results were compared with DCE-MRI and the gold standard results having the latter as the reference standard. Results: UE-MRI results obtained sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of 90%, 80%, 90%, 80%, and 86.7% respectively. On the other hand, those for the DCE-MRI were 95%, 90%, 95%, 90%, and 93.3% respectively. It was revealed that there was no significant difference between the two methods. Conclusion: UE-MRI could be considered as a reliable diagnostic tool and an effective substitute for DCE-MRI when contrast administration is not feasible or contraindicated.

An Efficient Method for Automated Breast Mass Segmentation and Classification in Digital Mammograms

Background: Automatic detection and classification of breast masses in mammograms are still challenging tasks. Today, computer-aided diagnosis (CAD) systems are being developed to assist radiologists in interpreting mammograms. Objectives: This study aimed to provide a novel method for automatic segmentation and classification of masses in mammograms to help radiologists make an accurate diagnosis. Materials and Methods: For an efficient mass diagnosis in mammograms, we proposed an automatic scheme to perform both mass detection and classification. First, a combination of several image enhancement algorithms, including contrast-limited adaptive histogram equalization (CLAHE), guided imaging, and median filtering, was investigated to enhance the visual features of breast area and increase the accuracy of segmentation outcomes. Second, the density of discrete wavelet coefficient density (DDWCs), based on the quincunx lifting scheme (QLS), was proposed to find suspicious mass regions or regions of interest (ROIs). Finally, mass lesions that appeared in the mammogram were classified into four categories of benign, probably benign, malignant, and probably malignant, based on the morphological shape. The proposed method was evaluated among 1593 images from the Curated Breast Imaging Subset-Digital Database for Screening Mammography (CBIS-DDSM) dataset. Results: The experimental results revealed that the suspected region localization had 100% sensitivity, with a mean of 6.4 ± 4.5 false positive (FP) detections per image. Moreover, the results showed an overall accuracy of 85.9% and an area under the curve (AUC) of 0.901 for the mass classification algorithm. Conclusion: The present results showed the comparable performance of our proposed method to that of the state-of-the-art methods.

Automatic breast mass detection in mammograms using density of wavelet coefficients and a patch-based CNN.

For the purpose of accurate and efficient mass detection in full-field digital mammograms, weproposeamethodfor automated mass detection that consists oftwostages: suspicious region localization and false-positive (FP) reduction, by classifying these regions into mass and non-mass regions (normal tissues). In the first stage, the density of the wavelet coefficients based on Quincunx Lifting Scheme (DWC-QLS) is used to find suspicious regions (regions of interest, ROIs) in full mammograms. In the second stage, a patch-based CNN classifier is developed as an FP reduction to classify the suspicious regions. The main aim of this stage is to reduce the false-positive suspicious regions while keeping the true-positive suspicious regions. To further improve the performance of the FP reduction, the effectiveness of different transfer learning strategies is further explored and the best fine-tuning strategy in training InceptionV3 model is determined experimentally. The experimental results show that the proposed method can achieve an overall performance of 0.98 TPR @1.43 FPI on the INbreast database. In addition, the suggested segmentation method detects the mass location with 100% sensitivity and average of 5.4 false positives per image. Based on the obtained results,the introduced method was able to successfully detectand classify suspicious regions in digital mammograms and provide better TPR and FPI results in comparison with other state-of-the-art method.

English

BACKGROUND We wanted to evaluate the sensitivity and specificity of ultrasound elastography in the detection and characterization of various breast masses and study its role in differentiating benign vs malignant breast masses with fine needle aspirarion cytology (FNAC) and/or histopathological correlation of its findings. METHODS A total of 120 patients with breast lesions were prospectively evaluated using ultrasonography (USG) in the Department of Radiodiagnosis at Katihar Medical College, Katihar, Bihar. After procuring consent from the patients, B-mode and elastography examination of all the patients was carried out simultaneously, using the Philips EPIQ 5G ultrasound machine. The findings were noted in a proforma for observation and further comparisons. The usefulness of elastography, regarding prediction of the nature of the mass (benign/malignant), delineation of its exact extent, and correlation with clinical/cytological diagnosis was studied. RESULTS A sensitivity of 97.0% and specificity of 86.7% was observed when a cut off value of 3 was used for elasticity score. A specificity of 95.5% and a sensitivity of 93.3% was observed when a cut off of 3.8 was used for strain ratio (SR). In all cases, the extent of the pathology, the local or contiguous spread and vascular involvement, predicted by ultrasound elastography examination corroborated well with the cytological findings. The results of this study are in concordance with results of studies that have been conducted previously. CONCLUSIONS Ultrasound elastography is a simple and rapid method that can improve the sensitivity and specificity of ultrasonography of focal breast lesions and can decrease the rate of unnecessary biopsies. The diagnostic accuracy of combined ultrasound and elastography is quite high and thus improves the diagnostic confidence of the cases under evaluation. KEYWORDS Elastography, Ultrasound, Focal Breast Lesions

A Review Comparative Mamography Image Analysis on Modified CNN Deep Learning Method

This study aims to review classification of breast abnormality acuracy on deep learing using comparative CNN development of concepts and models in various cases and implementation. The CNN based breast mass detection approach to simultaneously localize and classify the mass into either benign or malignant abnormality by exploring all major types of medical image modalities that collected on dataset and hospital. This CNN method modified to R-CNN and SD-CNN based on modification on feature extraction to improve acuracy level. R-CNN adopt RPN and ROI for Feature extraction. The model designed, trained and evaluated to achieved detection acuracy. The proposed model on R-CNN achieved detection accuracy of up to 91.86%, sensitivity of 94.67% and AUC-ROC of 92.2%. SD-CNN study the two-fold applicability of CNN to improve the breast cancer diagnosis. This method recombined images from CEDM in helping the diagnosis of breast lessons using a Deep-CNN method with virtual feature image. The experiment shows the features from LE images can achieve from accuracy of 0.85 and AUC of 0.84, then when adding the recombined imaging features, model performance improves to accuracy of 0.89 with AUC of 0.91 until 0.92

Detection and Segmentation of Breast Masses Based on Multi-Layer Feature Fusion.

In breast mass detection, there are many different sizes of masses in the image. However, when the existing target detection model is directly used to detect the breast mass, it is easy to appear the phenomenon of misdetection and missed detection. Therefore, in order to improve the detection accuracy of breast masses, this paper proposed a target detection model D-Mask R-CNN based on Mask R-CNN, which is suitable for breast masses detection. Firstly, this paper improved the internal structure of FPN, and modified the lateral connection mode in the original FPN structure to dense connection. Secondly, modified the size of the anchor of RPN to improve the location accuracy of breast masses. Finally, Soft-NMS was used to replace the NMS in the original model to reduce the possibility that the correct prediction results may be eliminated during the NMS process. This paper used the CBIS-DDSM dataset for all experiments. The results showed that the mAP value of the improved model for detecting breast masses reached 0.66 in the test set, which was 0.05 higher than that of the original Mask R-CNN.

Towards improved breast mass detection using dual-view mammogram matching.

Breast cancer screening benefits from the visual analysis of multiple views of routine mammograms. As for clinical practice, computer-aided diagnosis (CAD) systems could be enhanced by integrating multi-view information. In this work, we propose a new multi-tasking framework that combines craniocaudal (CC) and mediolateral-oblique (MLO) mammograms for automatic breast mass detection. Rather than addressing mass recognition only, we exploit multi-tasking properties of deep networks to jointly learn mass matching and classification, towards better detection performance. Specifically, we propose a unified Siamese network that combines patch-level mass/non-mass classification and dual-view mass matching to take full advantage of multi-view information. This model is exploited in a full image detection pipeline based on You-Only-Look-Once (YOLO) region proposals. We carry out exhaustive experiments to highlight the contribution of dual-view matching for both patch-level classification and examination-level detection scenarios. Results demonstrate that mass matching highly improves the full-pipeline detection performance by outperforming conventional single-task schemes with 94.78% as Area Under the Curve (AUC) score and a classification accuracy of 0.8791. Interestingly, mass classification also improves the performance of mass matching, which proves the complementarity of both tasks. Our method further guides clinicians by providing accurate dual-view mass correspondences, which suggests that it could act as a relevant second opinion for mammogram interpretation and breast cancer diagnosis.

Breast Mass Detection in Mammography Based on Image Template Matching and CNN.

In recent years, computer vision technology has been widely used in the field of medical image processing. However, there is still a big gap between the existing breast mass detection methods and the real-world application due to the limited detection accuracy. It is known that humans locate the regions of interest quickly and further identify whether these regions are the targets we found. In breast cancer diagnosis, we locate all the potential regions of breast mass by glancing at the mammographic image from top to bottom and from left to right, then further identify whether these regions are a breast mass. Inspired by the process of human detection of breast mass, we proposed a novel breast mass detection method to detect breast mass on a mammographic image by stimulating the process of human detection. The proposed method preprocesses the mammographic image via the mathematical morphology method and locates the suspected regions of breast mass by the image template matching method. Then, it obtains the regions of breast mass by classifying these suspected regions into breast mass and background categories using a convolutional neural network (CNN). The bounding box of breast mass obtained by the mathematical morphology method and image template matching method are roughly due to the mathematical morphology method, which transforms all of the brighter regions into approximate circular areas. For regression of a breast mass bounding box, the optimal solution should be searched in the feasible region and the Particle Swarm Optimization (PSO) is suitable for solving the problem of searching the optimal solution within a certain range. Therefore, we refine the bounding box of breast mass by the PSO algorithm. The proposed breast mass detection method and the compared detection methods were evaluated on the open database Digital Database for Screening Mammography (DDSM). The experimental results demonstrate that the proposed method is superior to all of the compared detection methods in detection performance.

A New Imaging Workup of The Male Breast: Single-View Mammography and Ultrasonography

Background: There is no generally accepted standard radiological approach to male breast diseases. Ultrasonography and mammography are the most preferred methods for imaging. The purpose of this study is to investigate the diagnostic performances of only single-view (mediolateral oblique) mammography and routine two-view mammography in the male breast diseases and also to evaluate the contribution of ultrasonography to the diagnosis and the management of the disease.Methods: Three hundred-twenty male patients’ breast imaging findings were evaluated retrospectively. Only mediolateral oblique and routine two-view mammograms were re-evaluated four months apart by two breast radiologists. The kappa value was calculated to measure consistency between two groups. The sensitivity, specificity, positive and negative predictive value, and detection accuracy of malignancy were calculated for both mammographic examinations and ultrasonography.Results: The accuracy of detection of malignant breast masses according to mediolateral oblique and two-view mammograms, and ultrasonography were 96.3 %, 97.5 %, and 99.5 %, respectively. Consistency between single-view and two-view mammograms was excellent (? = 0.967) and statistically significant (p=0.000). Two-view mammograms did not make any contribution to single-view mammograms.Conclusion: Only mediolateral oblique mammogram is sufficient in terms of characterization, spread and localization of the lesion, as long as mastectomy is preferred and the findings are supported by ultrasonography. Since there is no diagnostic performance difference, only mediolateral oblique view would protect from the potential adverse effects of extra radiation exposure and this is an important advantage.

Principal component regression-based contrast-enhanced ultrasound evaluation system for the management of BI-RADS US 4A breast masses: objective assistance for radiologists

A portion of detected breast masses might be overrated by using the Breast Imaging-Reporting and Data System ultrasonography (BI-RADS US) lexicon. A principal component regression-based contrast-enhanced ultrasound (PCR-CEUS) evaluation system was built to quantitatively illustrate whether CEUS could help radiologists to differentiate 4A masses. The PCR-CEUS evaluation system, based on principal component analysis (PCA) and logistic regression, was verified by random assignment into training and test sets and shown to reduce the data dimension and avoid collinearity in CEUS variables. This prospective study consecutively collected 238 patients with 238 4A masses confirmed pathologically. All enrolled patients accepted CEUS examination. The diagnostic performance of senior and junior radiologists, PCR-CEUS and combined methods was compared. The PCR-CEUS system had consistent diagnostic performance in both the training and test sets, with an area under the curve (AUC) of 0.831 (0.765-0.897), 0.798 (0.7034-0.892) and 0.854 (0.765-0.943) (all P > 0.05). The AUC of the combined diagnostic model (PCR-CEUS + Senior radiologists) was higher than that of senior radiologists, and the combined model had higher sensitivity (0.875 (0.781-0.969) vs. 0.729 (0.603-0.855)) without compromising specificity. Furthermore, the AUC and specificity of the combined model (PCR-CEUS + Junior radiologists) (0.852 (0.787-0.916)) was higher than that of junior radiologists (0.665 (0.592-0.737) (P < 0.00001)). PCR-CEUS demonstrated good ability in differentiating malignant BI-RADS-US 4A masses and was helpful for both senior and junior radiologists.

Breast mass detection in digital mammography based on anchor-free architecture

Background and objectiveAccurate detection of breast masses in mammography images is critical to diagnose early breast cancer, which can greatly improve the patients’ survival rate. However, it is still a big challenge due to the heterogeneity of breast masses and the complexity of their surrounding environment. Therefore, how to develop a robust breast mass detection framework in clinical practical applications to improve patient survival is a topic that researchers need to continue to explore. MethodsTo address these problems, we propose a one-stage object detection architecture, called Breast Mass Detection Network (BMassDNet), based on anchor-free and feature pyramid which makes the detection of breast masses of different sizes well adapted. We introduce a truncation normalization method and combine it with adaptive histogram equalization to enhance the contrast between the breast mass and the surrounding environment. Meanwhile, to solve the overfitting problem caused by small data size, we propose a natural deformation data augmentation method and mend the train data dynamic updating method based on the data complexity to effectively utilize the limited data. Finally, we use transfer learning to assist the training process and to improve the robustness of the model ulteriorly. ResultsOn the INbreast dataset, each image has an average of 0.495 false positives whilst the recall rate is 0.930; On the DDSM dataset, when each image has 0.599 false positives, the recall rate reaches 0.943. ConclusionsThe experimental results on datasets INbreast and DDSM show that the proposed BMassDNet can obtain competitive detection performance over the current top ranked methods.

A computer-aided approach for automatic detection of breast masses in digital mammogram via spectral clustering and support vector machine.

Breast cancer continues to be a widespread health concern all over the world. Mammography is an important method in the early detection of breast abnormalities. In recent years, using an automatic Computer-Aided Detection (CAD) system based on image processing techniques has been a more reliable interpretation in the illustration of breast distortion. In this study, a fully process-integrated approach with developing a CAD system is presented for the detection of breast masses based on texture description, spectral clustering, and Support Vector Machine (SVM). To this end, breast Regions of Interest (ROIs) are automatically detected from digital mammograms via gray-scale enhancement and data cleansing. The ROIs are segmented as labeled multi-sectional patterns using spectral clustering by the means of intensity descriptors relying on the region's histogram and texture descriptors based on the Gray Level Co-occurrence Matrix (GLCM). In the next step, shape and probabilistic features are derived from the segmented sections and given to the Genetic Algorithm (GA) to do the feature selection. The optimal feature vector comprising a fusion of selected shape and probabilistic features is submitted to linear kernel SVM for robust and reliable classification of mass tissues from the non-mass. Linear discrimination analysis (LDA) is also performed to ascertain the significance of the nominated feature space. The classification results of the proposed approach are presented by sensitivity, specificity, and accuracy measures, which are 89.5%, 91.2%, and 90%, respectively.

Breast cancer: One-stage automated detection, segmentation, and classification of digital mammograms using UNet model based-semantic segmentation

Breast cancer is one of the most common cancers in women. It is known as asymptomatic cancer that presents no noticeable symptoms in its early stage. Thus, regular mammography screening helps detect breast cancer early before it spreads to nearby normal tissues or to other organs. Hence, an automated system for early detection of breast cancer in mammograms will assist radiologists in their diagnosis. The rapid advance of deep learning models has considerably arisen much interest in their application to medical imaging problems, particularly for breast cancer diagnosis. In this paper, we propose an end-to-end UNet model for the detection, segmentation, and classification of breast masses in one-stage. The proposed model is evaluated in terms of its performance in segmenting and classifying breast masses using the publicly available datasets, DDSM and INbreast. The mass segmentation and classification evaluation results give an intersection over union (IOU) score of 90.50% and an area under the curve of 99.88% for both DDSM and INbreast datasets. The proposed model scores a dice coefficient of 99.20% and 99.56% and a weighted F1-score of 99.19% and 99.65% for the DDSM and INbreast datasets, respectively. The results show that the proposed model outperforms the existing methodologies.

A hybrid artificial neural network classifier based on feature selection using binary dragonfly optimization for breast cancer detection

Medical image analysis has become a challenging task as it contributes to disease diagnosis. Breast cancer has been the prominent reason for death among women. While analysing mammogram images, there is a need for clear differentiation of between benign and malignant tissues. Also, early detection of breast masses lead to prediction of breast cancer at the initial stage and minimizes risk of death. In this work, the image is preprocessed using Median filter and is segmented using Fuzzy C Means clustering. Fuzzy C-Means clustering algorithm helps in extracting the region of interest by allocating pixels with similar characteristics into a single group. A pixel may be present in various clusters with different membership values. The belongingness of a pixel to a cluster is decided by the highest membership value. Then the statistical, texture and shape features are extracted from the image. Since there may be many features that are less relevant for classification process, prominent features are selected with the help of Binary Dragonfly Optimization Algorithm and the selected features are fed into a Feed Forward Neural Network trained with Back Propagation Learning to classify the mass as benign or malignant. Experiments are conducted over 320 images from mini-MIAS database out of which 200 ROIs are used in training and 120 ROIs are used in testing phase. The region of interest from given mammogram images are extracted successfully and classified with an accuracy of 98.75%.

Feasibility of Harmonic Motion Imaging Using a Single Transducer: In Vivo Imaging of Breast Cancer in a Mouse Model and Human Subjects.

Harmonic motion imaging (HMI) interrogates the mechanical properties of tissues by simultaneously generating and tracking harmonic oscillation using focused ultrasound and imaging transducers, respectively. Instead of using two transducers, the objective of this work is to develop a single transducer HMI (ST-HMI) to both generate and track harmonic motion at "on-axis" to the force for facilitating data acquisition. In ST-HMI, the amplitude-modulated force was generated by modulating excitation pulse duration and tracking of motion was performed by transmitting tracking pulses interleaved between excitation pulses. The feasibility of ST-HMI was performed by imaging two elastic phantoms with three inclusions (N = 6) and comparing it with acoustic radiation force impulse (ARFI) imaging, in vivo longitudinal monitoring of 4T1, orthotropic breast cancer mice (N = 4), and patients (N = 3) with breast masses in vivo. Six inclusions with Young's moduli of 8, 10, 15, 20, 40, and 60 kPa were embedded in a 5 kPa background. The ST-HMI-derived peak-to-peak displacement (P2PD) successfully detected all inclusions with [Formula: see text] of the linear regression between the P2PD ratio of background to inclusion versus Young's moduli ratio of inclusion to background. The contrasts of 10 and 15 kPa inclusions were higher in ST-HMI than ARFI-derived images. In the mouse study, the median P2PD ratio of tumor to non-cancerous tissues was 3.0, 5.1, 6.1, and 7.7 at 1, 2, 3, and 4 weeks post-injection of the tumor cells, respectively. In the clinical study, ST-HMI detected breast masses including fibroadenoma, pseudo angiomatous stromal hyperplasia, and invasive ductal carcinoma with a P2PD ratio of 1.37, 1.61, and 1.78, respectively. These results indicate that ST-HMI can assess the mechanical properties of tissues via generation and tracking of harmonic motion "on-axis" to the ARF. This study is the first step towards translating ST-HMI in clinics.