A publicly available deep learning model and dataset for segmentation of breast, fibroglandular tissue, and vessels in breast MRI.

Breast density, or the amount of fibroglandular tissue (FGT) relative to the overall breast volume, increases the risk of developing breast cancer. Although previous studies have utilized deep learning to assess breast density, the limited public availability of data and quantitative tools hinders the development of better assessment tools. Our objective was to (1) create and share a large dataset of pixel-wise annotations according to well-defined criteria, and (2) develop, evaluate, and share an automated segmentation method for breast, FGT, and blood vessels using convolutional neural networks. We used the Duke Breast Cancer MRI dataset to randomly select 100 MRI studies and manually annotated the breast, FGT, and blood vessels for each study. Model performance was evaluated using the Dice similarity coefficient (DSC). The model achieved DSC values of 0.92 for breast, 0.86 for FGT, and 0.65 for blood vessels on the test set. The correlation between our model's predicted breast density and the manually generated masks was 0.95. The correlation between the predicted breast density and qualitative radiologist assessment was 0.75. Our automated models can accurately segment breast, FGT, and blood vessels using pre-contrast breast MRI data. The data and the models were made publicly available.

Detection of Lung Tumors in CT Scan Images using Convolutional Neural Networks.

Changing the human being's lifestyle, has caused, or exacerbated many diseases. One of these diseases is cancer, and among all kind of cancers like, brain and pulmonary; lungs cancer is fatal. The cancers could be detected early to save lives using Computer Aided Diagnosis (CAD) systems. CT scans medical images are one the best images in detecting these tumors in lung that are especially accepted among doctors. However, location and random shape of tumors, and the poor quality of CT scans images are one the biggest challenges for physicians in identifying these tumors. Therefore, deep learning algorithms have been highly regarded by researchers. This paper presents a new method for identifying tumors and pulmonary nodules in CT scans images based on convolution neural network algorithm with which tumor is accurately identified. The active counter algorithm will show the detected tumor. The proposed method is qualitatively measured by the sensitivity assessment criteria and dice similarity criteria. The obtained results with 98.33% accuracy 99.25% validity and 98.18% dice similarity criterion show the superiority of the proposed method.

Microscopic retinal blood vessels detection and segmentation using support vector machine and K-nearest neighbors.

The retina is the deepest layer of texture covering the rear of the eye, recorded by fundus images. Vessel detection and segmentation are useful in disease diagnosis. The retina's blood vessels could help diagnose maladies such as glaucoma, diabetic retinopathy, and blood pressure. A mix of supervised and unsupervised strategies exists for the detection and segmentation of blood vessels images. The tree structure of retinal blood vessels, their random area, and different thickness have caused vessel detection difficulties at machine learning calculations. Since the green band of retinal images conveys more information about the vessels, they are utilized for microscopic vessels detection. The current research proposes an administered calculation for segmentation of retinal vessels, where two upgrading stages depending on filtering and comparative histogram were applied after pre-processing and image quality improvement. At that point, statistical features of vessel tracking, maximum curvature and curvelet coefficient are extracted for each pixel. The extracted features are classified by support vector machine and the k-nearest neighbors. The morphological operators then enhance the classified image at the final stage to segment with higher accuracy. The dice coefficient is utilized for the evaluation of the proposed method. The proposed approach is concluded to be better than different strategies with a normal of 92%.

Identity verification using palm print microscopic images based on median robust extended local binary pattern features and k-nearest neighbor classifier.

Automatic identity verification is one of the most critical and research-demanding areas. One of the most effective and reliable identity verification methods is using unique human biological characteristics and biometrics. Among all types of biometrics, palm print is recognized as one of the most accurate and reliable identity verification methods. However, this biometrics domain also has several critical challenges: image rotation, image displacement, change in image scaling, presence of noise in the image due to devices, region of interest (ROI) detection, or user error. For this purpose, a new method of identity verification based on median robust extended local binary pattern (MRELBP) is introduced in this study. In this system, after normalizing the images and extracting the ROI from the microscopic input image, the images enter the feature extraction step with the MRELBP algorithm. Next, these features are reduced by the dimensionality reduction step, and finally, feature vectors are classified using the k-nearest neighbor classifier. The microscopic images used in this study were selected from IITD and CASIA data sets, and the identity verification rate for these two data sets without challenge was 97.2% and 96.6%, respectively. In addition, computed detection rates have been broadly stable against changes such as salt-and-pepper noise up to 0.16, rotation up to 5°, displacement up to 6 pixels, and scale change up to 94%.

Authentication through gender classification from iris images using support vector machine.

Soft biometric information, such as gender, iris, and voice, can be helpful in various applications, such as security, authentication, and validation. Iris is secure biometrics with low forgery and error rates due to its highly certain features are being used in the last few decades. Iris recognition could be used both independently and in part for secure recognition and authentication systems. Existing iris-based gender classification techniques have low accuracy rates as well as high computational complexity. Accordingly, this paper presents an authentication approach through gender classification from iris images using support vector machine (SVM) that has an excellent response to sustained changes using the Zernike, Legendre invariant moments, and Gradient-oriented histogram. In this study, invariant moments are used as feature extraction from iris images. After extracting these descriptors' attributes, the attributes are categorized through keycode fusion. SVM is employed for gender classification using a fused feature vector. The proposed approach is evaluated on the CVBL data set and results are compared in state of the art based on local binary patterns and Gabor filters. The proposed approach came out with 98% gender classification rate with low computational complexity that could be used as an authentication measure.

Brain tumor segmentation using K-means clustering and deep learning with synthetic data augmentation for classification.

Image processing plays a major role in neurologists' clinical diagnosis in the medical field. Several types of imagery are used for diagnostics, tumor segmentation, and classification. Magnetic resonance imaging (MRI) is favored among all modalities due to its noninvasive nature and better representation of internal tumor information. Indeed, early diagnosis may increase the chances of being lifesaving. However, the manual dissection and classification of brain tumors based on MRI is vulnerable to error, time-consuming, and formidable task. Consequently, this article presents a deep learning approach to classify brain tumors using an MRI data analysis to assist practitioners. The recommended method comprises three main phases: preprocessing, brain tumor segmentation using k-means clustering, and finally, classify tumors into their respective categories (benign/malignant) using MRI data through a finetuned VGG19 (i.e., 19 layered Visual Geometric Group) model. Moreover, for better classification accuracy, the synthetic data augmentation concept i s introduced to increase available data size for classifier training. The proposed approach was evaluated on BraTS 2015 benchmarks data sets through rigorous experiments. The results endorse the effectiveness of the proposed strategy and it achieved better accuracy compared to the previously reported state of the art techniques.