Showing papers in "Computer Methods and Programs in Biomedicine in 2018"

TL;DR: This review paper depicts the application of various deep learning algorithms used till recently, but in future it will be used for more healthcare areas to improve the quality of diagnosis.

TL;DR: An open-source platform is implemented based on TensorFlow APIs for deep learning in medical imaging domain that facilitates warm starts with established pre-trained networks, adapting existing neural network architectures to new problems, and rapid prototyping of new solutions.

TL;DR: It was discovered in this research that the EEG signals from the right hemisphere are more distinctive in depression than those from the left hemisphere, consistent with recent research and revelation that the depression is associated with a hyperactive right hemisphere.

TL;DR: No single segmentation approach is suitable for all the different anatomical region or imaging modalities, thus the primary goal of this review was to provide an up to date source of information about the state of the art of the vessel segmentation algorithms so that the most suitable methods can be chosen according to the specific task.

TL;DR: A new strategy, which applies deep learning to an ensemble approach that incorporates multiple different machine learning models, which increases the prediction accuracy of cancer for all the tested RNA-seq data sets as compared to using a single classifier or the majority voting algorithm.

TL;DR: Using the full spatial resolutions of the input image could enable to learn better specific and prominent features, leading to an improvement in the segmentation performance.

TL;DR: A Computer-aided Diagnosis (CAD) system based on deep Convolutional Neural Networks that aims to help the radiologist classify mammography mass lesions and can indeed be used to predict if the mass lesions are benign or malignant.

TL;DR: A novel Computer-Aided Diagnosis (CAD) system based on one of the regional deep learning techniques, a ROI-based Convolutional Neural Network (CNN) which is called You Only Look Once (YOLO) can handle detection and classification simultaneously in one framework.

TL;DR: A general analysis of the current status of CAD systems according to the used image modalities and the machine learning based classifiers is provided.

TL;DR: The proposed artificial intelligence based diagnostic model is found to be highly reliable for diagnosing TPE based on simple clinical signs, blood samples and pleural effusion samples and can be widely used in clinical practice and further evaluated for use as a substitute of invasive pleural biopsies.

TL;DR: The proposed three end-to-end Incremental Deep Convolutional Neural Networks models for fully automatic Brain Tumor Segmentation are effective for the segmentation of brain tumors and allow to obtain high accurate results.

TL;DR: An overview of the state of the art as articulated in prominent recent publications focusing on automated detection of cervical cancer from pap-smear images indicates that there are still weaknesses in the available techniques that result in low accuracy of classification in some classes of cells.

TL;DR: This paper proposes a novel method for red lesion detection based on combining both deep learned and domain knowledge that reported the highest performance on a per-lesion basis on DIARETDB1 and e-ophtha, and for screening and need for referral on MESSIDOR compared to a second human expert.

TL;DR: The proposed 3D supervoxel based learning method provides a close match to expert delineation across all tumour grades, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management.

TL;DR: The preliminary study confirms that single-channel EEG analysis, employing the combination of measures, can provide discrimination of depression at the level of multichannel EEG analysis and shows that there is no single superior measure for detection of depression.

TL;DR: Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications and is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain.

TL;DR: The results demonstrate the high performance-potential of the PSO algorithm in the identification of optimal CNN hyperparameters for lung nodule candidate classification into nodules and non-nodules, increasing the sensitivity rates in the FP reduction step of CAD systems.

TL;DR: This study suggests awareness should be created among elderly populations regarding the use of WDs for the early detection and prevention of complications and emergencies and that devices should be tested on elderly groups as well, considering sex equality, and on both healthy and sick participants for better insights.

TL;DR: An overview of prediction models for hospital readmission is given, the data analysis methods and algorithms used for building the models are described, and their results are synthesized.

TL;DR: This study approved the effectiveness of applying different fuzzy methods in diseases diagnosis process, presenting new insights for researchers about what kind of diseases which have been more focused will help to determine the diagnostic aspects of medical disciplines that are being neglected.

TL;DR: A Deep Learning (DL)-based paradigm that computes nearly seven million weights per image when passed through a 22 layered neural network during the cross-validation (training and testing) paradigm shows a superior performance for liver detection and risk stratification compared to conventional machine learning systems: SVM and ELM.

TL;DR: Extended experiments support that the fine-grained leukocyte classifier could be used in real medical applications, assist doctors in diagnosing diseases, reduce human power significantly.

TL;DR: The proposed methods are found to be capable of handling the nonstationary and multicomponent variations of sEMG signals recorded in dynamic fatiguing contractions and the combination of EMBD- polynomial kernel based SVM could be used to detect the dynamic muscle fatigue conditions.

TL;DR: Results have revealed the effectiveness and diagnostic significance of proposed model for non-invasive and automatic diabetes diagnosis.

TL;DR: A computer-aided detection (CAD) system is proposed to make an accurate, reliable and fast diagnosis of glaucoma based on the optic nerve features of fundus imaging to assist the clinicians to alleviate their workload significantly.

TL;DR: Non-Sub sampled Contourlet Transform (NSCT) is used to enhance the brain image and then texture features are extracted from the enhanced brain image to identify tumor regions in Glioma brain image.

TL;DR: The radiomics characterization approach presented great potential to be used in a computational model to aid lung cancer histopathological subtype diagnosis as a "virtual biopsy" and metastatic prediction for therapy decision support without the necessity of a whole-body imaging scanning.

TL;DR: A novel method combining support vector machine and genetic algorithm to build the risk prediction model, which simultaneously involves feature selection and the processing of imbalanced data is presented, which outperforms other popular algorithms in identifying diabetic patients who may be readmitted.

TL;DR: This new algorithm reliably distinguishes those with normal coronary arteries from those with CAD which may obviate the need for angiography in the normal group.

TL;DR: The background of recent studies on wheelchair control based on BCI for disability and map the literature survey into a coherent taxonomy is determined to provide researchers and developers with a clear understanding of this platform and highlight the challenges and gaps in the current and future studies.