Objective breast tissue image classification using Quantitative Transmission ultrasound tomography.
Ontology highlight
ABSTRACT:
SUBMITTER: Malik B
PROVIDER: S-EPMC5146962 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeBreast density is important in the evaluation of breast cancer risk. At present, breast density is evaluated using two-dimensional projections from mammography with or without tomosynthesis using either (a) subjective assessment or (b) a computer-aided approach. The purpose of this work is twofold: (a) to establish an algorithm for quantitative assessment of breast density using quantitative three-dimensional transmission ultrasound imaging; and (b) to determine how these quantitative assessments compare with both subjective and objective mammographic assessments of breast density.MethodsWe described and verified a threshold-based segmentation algorithm to give a quantitative breast density (QBD) on ultrasound tomography images of phantoms of known geometric forms. We also used the algorithm and transmission ultrasound tomography to quantitatively determine breast density by separating fibroglandular tissue from fat and skin, based on imaged, quantitative tissue characteristics, and compared the quantitative tomography segmentation results with subjective and objective mammographic assessments.ResultsQuantitative breast density (QBD) measured in phantoms demonstrates high quantitative accuracy with respect to geometric volumes with average difference of less than 0.1% of the total phantom volumes. There is a strong correlation between QBD and both subjective mammographic assessments of Breast Imaging - Reporting and Data System (BI-RADS) breast composition categories and Volpara density scores - the Spearman correlation coefficients for the two comparisons were calculated to be 0.90 (95% CI: 0.71-0.96) and 0.96 (95% CI: 0.92-0.98), respectively.ConclusionsThe calculation of breast density using ultrasound tomography and the described segmentation algorithm is quantitatively accurate in phantoms and highly correlated with both subjective and Food and Drug Administration (FDA)-cleared objective assessments of breast density.
| S-EPMC6618090 | biostudies-literature
Project description:BackgroundUltrasound (US) is widely used in the clinical diagnosis of thyroid nodules. Artificial intelligence-powered US is becoming an important issue in the research community. This study aimed to develop an improved deep learning model-based algorithm to classify benign and malignant thyroid nodules (TNs) using thyroid US images.MethodsIn total, 592 patients with 600 TNs were included in the internal training, validation, and testing data set; 187 patients with 200 TNs were recruited for the external test data set. We developed a Visual Geometry Group (VGG)-16T model, based on the VGG-16 architecture, but with additional batch normalization (BN) and dropout layers in addition to the fully connected layers. We conducted a 10-fold cross-validation to analyze the performance of the VGG-16T model using a data set of gray-scale US images from 5 different brands of US machines.ResultsFor the internal data set, the VGG-16T model had 87.43% sensitivity, 85.43% specificity, and 86.43% accuracy. For the external data set, the VGG-16T model achieved an area under the curve (AUC) of 0.829 [95% confidence interval (CI): 0.770-0.879], a radiologist with 15 years' working experience achieved an AUC of 0.705 (95% CI: 0.659-0.801), a radiologist with 10 years' experience achieved an AUC of 0.725 (95% CI: 0.653-0.797), and a radiologist with 5 years' experience achieved an AUC of 0.660 (95% CI: 0.584-0.736).ConclusionsThe VGG-16T model had high specificity, sensitivity, and accuracy in differentiating between malignant and benign TNs. Its diagnostic performance was superior to that of experienced radiologists. Thus, the proposed improved deep-learning model can assist radiologists to diagnose thyroid cancer.
| S-EPMC8576712 | biostudies-literature
Project description:Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.
| S-EPMC9502699 | biostudies-literature
Project description:Mammographic percent density (MPD) is an independent risk factor for developing breast cancer, but its inclusion in clinical risk models provides only modest improvements in individualized risk prediction, and MPD is not typically assessed in younger women because of ionizing radiation concerns. Previous studies have shown that tissue sound speed, derived from whole breast ultrasound tomography (UST), a non-ionizing modality, is a potential surrogate marker of breast density, but prior to this study, sound speed has not been directly linked to breast cancer risk. To that end, we explored the relation of sound speed and MPD with breast cancer risk in a case-control study, including 61 cases with recent breast cancer diagnoses and a comparison group of 165 women, frequency matched to cases on age, race, and menopausal status, and with a recent negative mammogram and no personal history of breast cancer. Multivariable odds ratios (ORs) and 95% confidence intervals (CIs) were estimated for the relation of quartiles of MPD and sound speed with breast cancer risk adjusted for matching factors. Elevated MPD was associated with increased breast cancer risk, although the trend did not reach statistical significance (OR per quartile = 1.27, 95% CI: 0.95, 1.70; ptrend = 0.10). In contrast, elevated sound speed was significantly associated with breast cancer risk in a dose-response fashion (OR per quartile = 1.83, 95% CI: 1.32, 2.54; ptrend = 0.0003). The OR trend for sound speed was statistically significantly different from that observed for MPD (p = 0.005). These findings suggest that whole breast sound speed may be more strongly associated with breast cancer risk than MPD and offer future opportunities for refining the magnitude and precision of risk associations in larger, population-based studies, including women younger than usual screening ages.
| S-EPMC7074100 | biostudies-literature
Project description:Breast cancer diagnosis is one of the many areas that has taken advantage of artificial intelligence to achieve better performance, despite the fact that the availability of a large medical image dataset remains a challenge. Transfer learning (TL) is a phenomenon that enables deep learning algorithms to overcome the issue of shortage of training data in constructing an efficient model by transferring knowledge from a given source task to a target task. However, in most cases, ImageNet (natural images) pre-trained models that do not include medical images, are utilized for transfer learning to medical images. Considering the utilization of microscopic cancer cell line images that can be acquired in large amount, we argue that learning from both natural and medical datasets improves performance in ultrasound breast cancer image classification. The proposed multistage transfer learning (MSTL) algorithm was implemented using three pre-trained models: EfficientNetB2, InceptionV3, and ResNet50 with three optimizers: Adam, Adagrad, and stochastic gradient de-scent (SGD). Dataset sizes of 20,400 cancer cell images, 200 ultrasound images from Mendeley and 400 ultrasound images from the MT-Small-Dataset were used. ResNet50-Adagrad-based MSTL achieved a test accuracy of 99 ± 0.612% on the Mendeley dataset and 98.7 ± 1.1% on the MT-Small-Dataset, averaging over 5-fold cross validation. A p-value of 0.01191 was achieved when comparing MSTL against ImageNet based TL for the Mendeley dataset. The result is a significant improvement in the performance of artificial intelligence methods for ultrasound breast cancer classification compared to state-of-the-art methods and could remarkably improve the early diagnosis of breast cancer in young women.
| S-EPMC8775102 | biostudies-literature
Project description:We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL). After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM). Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.
| S-EPMC5463197 | biostudies-other
Project description:To investigate whether biologic image composition of mammographic lesions can improve upon existing mammographic quantitative image analysis (QIA) in estimating the probability of malignancy.The study population consisted of 45 breast lesions imaged with dual-energy mammography prior to breast biopsy with final diagnosis resulting in 10 invasive ductal carcinomas, 5 ductal carcinomain situ, 11 fibroadenomas, and 19 other benign diagnoses. Analysis was threefold: (1) The raw low-energy mammographic images were analyzed with an established in-house QIA method, "QIA alone," (2) the three-compartment breast (3CB) composition measure-derived from the dual-energy mammography-of water, lipid, and protein thickness were assessed, "3CB alone", and (3) information from QIA and 3CB was combined, "QIA + 3CB." Analysis was initiated from radiologist-indicated lesion centers and was otherwise fully automated. Steps of the QIA and 3CB methods were lesion segmentation, characterization, and subsequent classification for malignancy in leave-one-case-out cross-validation. Performance assessment included box plots, Bland-Altman plots, and Receiver Operating Characteristic (ROC) analysis.The area under the ROC curve (AUC) for distinguishing between benign and malignant lesions (invasive and DCIS) was 0.81 (standard error 0.07) for the "QIA alone" method, 0.72 (0.07) for "3CB alone" method, and 0.86 (0.04) for "QIA+3CB" combined. The difference in AUC was 0.043 between "QIA + 3CB" and "QIA alone" but failed to reach statistical significance (95% confidence interval [-0.17 to + 0.26]).In this pilot study analyzing the new 3CB imaging modality, knowledge of the composition of breast lesions and their periphery appeared additive in combination with existing mammographic QIA methods for the distinction between different benign and malignant lesion types.
| S-EPMC3978370 | biostudies-other
Project description:The purpose of this study was to develop an automated method for classifying liver fibrosis stage ≥F2 based on ultrasound shear wave elastography (SWE) and to assess the system's performance in comparison with a reference manual approach. The reference approach consists of manually selecting a region of interest from each of eight or more SWE images, computing the mean tissue stiffness within each of the regions of interest and computing a resulting stiffness value as the median of the means. The 527-subject database consisted of 5526 SWE images and pathologist-scored biopsies, with data collected from a single system at a single site. The automated method integrates three modules that assess SWE image quality, select a region of interest from each SWE measurement and perform machine learning-based, multi-image SWE classification for fibrosis stage ≥F2. Several classification methods were developed and tested using fivefold cross-validation with training, validation and test sets partitioned by subject. Performance metrics were area under receiver operating characteristic curve (AUROC), specificity at 95% sensitivity and number of SWE images required. The final automated method yielded an AUROC of 0.93 (95% confidence interval: 0.90-0.94) versus 0.69 (95% confidence interval: 0.65-0.72) for the reference method, 71% specificity with 95% sensitivity versus 5% and four images per decision versus eight or more. In conclusion, the automated method reported in this study significantly improved the accuracy for ≥F2 classification of SWE measurements as well as reduced the number of measurements needed, which has the potential to reduce clinical workflow.
| S-EPMC7483774 | biostudies-literature
Project description:This article introduces new methods for performing classification of complex, high-dimensional functional data using the functional mixed model (FMM) framework. The FMM relates a functional response to a set of predictors through functional fixed and random effects, which allows it to account for various factors and between-function correlations. The methods include training and prediction steps. In the training steps we train the FMM model by treating class designation as one of the fixed effects, and in the prediction steps we classify the new objects using posterior predictive probabilities of class. Through a Bayesian scheme, we are able to adjust for factors affecting both the functions and the class designations. While the methods can be used in any FMM framework, we provide details for two specific Bayesian approaches: the Gaussian, wavelet-based FMM (G-WFMM) and the robust, wavelet-based FMM (R-WFMM). Both methods perform modeling in the wavelet space, which yields parsimonious representations for the functions, and can naturally adapt to local features and complex nonstationarities in the functions. The R-WFMM allows potentially heavier tails for features of the functions indexed by particular wavelet coefficients, leading to a down-weighting of outliers that makes the method robust to outlying functions or regions of functions. The models are applied to a pancreatic cancer mass spectroscopy data set and compared with other recently developed functional classification methods.
| S-EPMC3443537 | biostudies-literature
Project description:Recent published results in inverse scattering generally show the difficulty in dealing with moderate to high contrast inhomogeneities when employing linearized or iteratively linearized algorithms (e.g., distorted Born iterative method). This paper presents a fully nonlinear algorithm utilizing full wave field data, that results in ultrasound computed tomographic images from a laboratory breast scanner, and shows several such unique images from volunteer subjects. The forward problem, data collection process and inverse scattering algorithm used are discussed. A functional that represents the "best fit" between predicted and measured data is minimized, and therefore requires a very fast forward problem solver, Jacobian calculation, and gradient estimation, all of which are described. The data collection device is described. The algorithm and device yield quantitative estimates of human breast tissue in vivo. Several high resolution images, measuring ∼150 by 150 wavelengths, obtained from the 2D inverse scattering algorithms, using data collected from a first prototype, are shown and discussed. The quantitative values are compared with previous published work.
| S-EPMC3356315 | biostudies-other