Search

Designing implants for large and complex cranial defects is a challenging task, even for professional designers. Current efforts on automating the design process focused mainly on convolutional neural networks (CNN), which have produced state-of-the-art results on reconstructing synthetic defects. However, existing CNN-based methods have been difficult to translate to clinical practice in cranioplasty, as their performance on large and complex cranial defects remains unsatisfactory. In this paper, we present a statistical shape model (SSM) built directly on the segmentation masks of the skulls represented as binary voxel occupancy grids and evaluate it on several cranial implant design datasets. Results show that, while CNN-based approaches outperform the SSM on synthetic defects, they are inferior to SSM when it comes to large, complex and real-world defects. Experienced neurosurgeons evaluate the implants generated by the SSM to be feasible for clinical use after minor manual corrections. Datasets and the SSM model are publicly available at https://github.com/Jianningli/ssm. [ABSTRACT FROM AUTHOR]

Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images. [ABSTRACT FROM AUTHOR]

Significant changes have been made on audio-based technologies over years in several different fields. Healthcare is no exception. One of such avenues is health screening based on respiratory sounds. In this paper, we developed a tool to detect respiratory sounds that come from respiratory infection carrying patients. Linear Predictive Cepstral Coefficient (LPCC)-based features were used to characterize such audio clips. With Multilayer Perceptron (MLP)-based classifier, in our experiment, we achieved the highest possible accuracy of 99.22% that was tested on a publicly available respiratory sounds dataset (ICBHI17) (Rocha et al. Physiol. Meas. 40(3):035,001 20) of size 6800+ clips. In addition to other popular machine learning classifiers, our results outperformed common works that exist in the literature. [ABSTRACT FROM AUTHOR]

The distribution of fiducial markers is one of the main factors affected the accuracy of optical navigation system. However, many studies have been focused on improving the fiducial registration accuracy or the target registration accuracy, but few solutions involve optimization model for the distribution of fiducial markers. In this paper, we propose an optimization model for the distribution of fiducial markers to improve the optical navigation accuracy. The strategy of optimization model is reducing the distribution from three dimensional to two dimensional to obtain the 2D optimal distribution by using optimization algorithm in terms of the marker number and the expectation equation of target registration error (TRE), and then extend the 2D optimal distribution in two dimensional to three dimensional to calculate the optimal distribution according to the distance parameter and the expectation equation of TRE. The results of the experiments show that the averaged TRE for the human phantom is approximately 1.00 mm by applying the proposed optimization model, and the averaged TRE for the abdominal phantom is 0.59 mm. The experimental results of liver simulator model and ex-vivo porcine liver model show that the proposed optimization model can be effectively applied in liver intervention. [ABSTRACT FROM AUTHOR]

One of the most common chronic diseases that causes missed school days and workdays is pediatric asthma, producing education, health and economic delays in low and middle-income countries. A patient-centered remarkable therapeutic strategy in the prevention and treatment of chronic diseases is the Therapeutic Patient Education (TPE) which denotes an outstanding difference in the outcomes, from the awareness, to the personal treatment adaption to prevent crises. In this paper, an intervention of TPE with learning objects (LOs) of a pediatric asthma course, designed to train the uncontrolled patient and the caregiver as a team on the specific knowledge to self-control the disease, was carried out at a health facility in Mexico. The Asthma Control Test (ACT) was used and the learning performance was evaluated with formative quizzes. A randomized controlled trial was designed, with pairs of children patients and caregivers during 60 days; the control group was trained with the usual approach, receiving general information about the disease. ACT measures showed statistical significance for the TPE group after the use of the LOs, achieving a controlled state, while the control group did not show difference. Also, the intervention group obtained a higher score in learning performance assessment. The users learned how to avoid risks, the personal triggers of the patient, how to correctly use the different treatments and accessories, consequently, they learned how to self-manage the disease. Our study also confirmed that control of asthma is not only a matter of knowledge, but financial issues to afford the treatment. [ABSTRACT FROM AUTHOR]

Secondary use of medical big data is increasingly popular in healthcare services and clinical research. Understanding the logic behind medical big data demonstrates tendencies in hospital information technology and shows great significance for hospital information systems that are designing and expanding services. Big data has four characteristics - Volume, Variety, Velocity and Value (the 4 Vs) - that make traditional systems incapable of processing these data using standalones. Apache Hadoop MapReduce is a promising software framework for developing applications that process vast amounts of data in parallel with large clusters of commodity hardware in a reliable, fault-tolerant manner. With the Hadoop framework and MapReduce application program interface (API), we can more easily develop our own MapReduce applications to run on a Hadoop framework that can scale up from a single node to thousands of machines. This paper investigates a practical case of a Hadoop-based medical big data processing system. We developed this system to intelligently process medical big data and uncover some features of hospital information system user behaviors. This paper studies user behaviors regarding various data produced by different hospital information systems for daily work. In this paper, we also built a five-node Hadoop cluster to execute distributed MapReduce algorithms. Our distributed algorithms show promise in facilitating efficient data processing with medical big data in healthcare services and clinical research compared with single nodes. Additionally, with medical big data analytics, we can design our hospital information systems to be much more intelligent and easier to use by making personalized recommendations. [ABSTRACT FROM AUTHOR]

With the increasing amount of medical data available on the Web, looking for health information has become one of the most widely searched topics on the Internet. Patients and people of several backgrounds are now using Web search engines to acquire medical information, including information about a specific disease, medical treatment or professional advice. Nonetheless, due to a lack of medical knowledge, many laypeople have difficulties in forming appropriate queries to articulate their inquiries, which deem their search queries to be imprecise due the use of unclear keywords. The use of these ambiguous and vague queries to describe the patients' needs has resulted in a failure of Web search engines to retrieve accurate and relevant information. One of the most natural and promising method to overcome this drawback is Query Expansion. In this paper, an original approach based on Bat Algorithm is proposed to improve the retrieval effectiveness of query expansion in medical field. In contrast to the existing literature, the proposed approach uses Bat Algorithm to find the best expanded query among a set of expanded query candidates, while maintaining low computational complexity. Moreover, this new approach allows the determination of the length of the expanded query empirically. Numerical results on MEDLINE, the on-line medical information database, show that the proposed approach is more effective and efficient compared to the baseline. [ABSTRACT FROM AUTHOR]

B-Mode ultrasound images are degraded by inherent noise called Speckle, which creates a considerable impact on image quality. This noise reduces the accuracy of image analysis and interpretation. Therefore, reduction of speckle noise is an essential task which improves the accuracy of the clinical diagnostics. In this paper, a Multi-directional perfect-reconstruction (PR) filter bank is proposed based on 2-D eigenfilter approach. The proposed method used for the design of two-dimensional (2-D) two-channel linear-phase FIR perfect-reconstruction filter bank. In this method, the fan shaped, diamond shaped and checkerboard shaped filters are designed. The quadratic measure of the error function between the passband and stopband of the filter has been used an objective function. First, the low-pass analysis filter is designed and then the PR condition has been expressed as a set of linear constraints on the corresponding synthesis low-pass filter. Subsequently, the corresponding synthesis filter is designed using the eigenfilter design method with linear constraints. The newly designed 2-D filters are used in translation invariant pyramidal directional filter bank (TIPDFB) for reduction of speckle noise in ultrasound images. The proposed 2-D filters give better symmetry, regularity and frequency selectivity of the filters in comparison to existing design methods. The proposed method is validated on synthetic and real ultrasound data which ensures improvement in the quality of ultrasound images and efficiently suppresses the speckle noise compared to existing methods. [ABSTRACT FROM AUTHOR]

In this paper, the problem of secure transmission of sensitive contents over the public network Internet is addressed by proposing a novel data hiding method in encrypted images with dual-level security. The secret information is divided into three blocks using a specific pattern, followed by an encryption mechanism based on the three-level encryption algorithm (TLEA). The input image is scrambled using a secret key, and the encrypted sub-message blocks are then embedded in the scrambled image by cyclic18 least significant bit (LSB) substitution method, utilizing LSBs and intermediate LSB planes. Furthermore, the cover image and its planes are rotated at different angles using a secret key prior to embedding, deceiving the attacker during data extraction. The usage of message blocks division, TLEA, image scrambling, and the cyclic18 LSB method results in an advanced security system, maintaining the visual transparency of resultant images and increasing the security of embedded data. In addition, employing various secret keys for image scrambling, data encryption, and data hiding using the cyclic18 LSB method makes the data recovery comparatively more challenging for attackers. Experimental results not only validate the effectiveness of the proposed framework in terms of visual quality and security compared to other state-of-the-art methods, but also suggest its feasibility for secure transmission of diagnostically important keyframes to healthcare centers and gastroenterologists during wireless capsule endoscopy. [ABSTRACT FROM AUTHOR]

Recent advances in medical treatment and emergency applications, the need of integrating wireless body area network (WBAN) with cloud computing can be motivated by providing useful and real time information about patients' health state to the doctors and emergency staffs. WBAN is a set of body sensors carried by the patient to collect and transmit numerous health items to medical clouds via wireless and public communication channels. Therefore, a cloud-assisted WBAN facilitates response in case of emergency which can save patients' lives. Since the patient's data is sensitive and private, it is important to provide strong security and protection on the patient's medical data over public and insecure communication channels. In this paper, we address the challenge of participant authentication in mobile emergency medical care systems for patients supervision and propose a secure cloud-assisted architecture for accessing and monitoring health items collected by WBAN. For ensuring a high level of security and providing a mutual authentication property, chaotic maps based authentication and key agreement mechanisms are designed according to the concept of Diffie-Hellman key exchange, which depends on the CMBDLP and CMBDHP problems. Security and performance analyses show how the proposed system guaranteed the patient privacy and the system confidentiality of sensitive medical data while preserving the low computation property in medical treatment and remote medical monitoring. [ABSTRACT FROM AUTHOR]

This paper surveys the problem of predictive / reactive scheduling of an integrated operating theatre with two types of demand for surgery: 1) elective or known demand; 2) emergency or uncertain demand. The stochastic arrival of emergency patients with uncertain surgery time enforces the scheduler to react to disruption and modify scheduling plan of elective patients. We focus on this predictive / reactive scheduling problem which has not been investigated in such way before. As in hospitals, at the time of occurrence a disruption in a surgical suite, the scheduler has not enough time to make the best decision; we propose a new approach based on two-stage stochastic programming model with recourse which determines the best recourse strategy in advance of any disruption occurrence. Using the proposed approach, the primary schedule is generated in such a way that it can absorb disruption with minimum effect on planned elective surgeries. For the first time in operating theatre planning, two new significant sets of performance measures comprising 'robustness' and 'stability' measures are considered in generation of primary schedule which will be shown to be of great importance in efficiency of surgical suite planning. Computational experiments performed on sets of generated problem based on the data obtained from a non-profit hospital. In order to demonstrate efficiency of the proposed method, computational results of the proposed approach are compared with classic approach. [ABSTRACT FROM AUTHOR]

Classification is the problem of identifying a set of categories where new data belong, on the basis of a set of training data whose category membership is known. Its application is wide-spread, such as the medical science domain. The issue of the classification knowledge protection has been paid attention increasingly in recent years because of the popularity of cloud environments. In the paper, we propose a Shaking Sorted-Sampling (triple-S) algorithm for protecting the classification knowledge of a dataset. The triple-S algorithm sorts the data of an original dataset according to the projection results of the principal components analysis so that the features of the adjacent data are similar. Then, we generate noise data with incorrect classes and add those data to the original dataset. In addition, we develop an effective positioning strategy, determining the added positions of noise data in the original dataset, to ensure the restoration of the original dataset after removing those noise data. The experimental results show that the disturbance effect of the triple-S algorithm on the CLC, MySVM, and LibSVM classifiers increases when the noise data ratio increases. In addition, compared with existing methods, the disturbance effect of the triple-S algorithm is more significant on MySVM and LibSVM when a certain amount of the noise data added to the original dataset is reached. [ABSTRACT FROM AUTHOR]

Retinal blood vessels are the source to provide oxygen and nutrition to retina and any change in the normal structure may lead to different retinal abnormalities. Automated detection of vascular structure is very important while designing a computer aided diagnostic system for retinal diseases. Most popular methods for vessel segmentation are based on matched filters and Gabor wavelets which give good response against blood vessels. One major drawback in these techniques is that they also give strong response for lesion (exudates, hemorrhages) boundaries which give rise to false vessels. These false vessels may lead to incorrect detection of vascular changes. In this paper, we propose a new hybrid feature set along with new classification technique for accurate detection of blood vessels. The main motivation is to lower the false positives especially from retinal images with severe disease level. A novel region based hybrid feature set is presented for proper discrimination between true and false vessels. A new modified m-mediods based classification is also presented which uses most discriminating features to categorize vessel regions into true and false vessels. The evaluation of proposed system is done thoroughly on publicly available databases along with a locally gathered database with images of advanced level of retinal diseases. The results demonstrate the validity of the proposed system as compared to existing state of the art techniques. [ABSTRACT FROM AUTHOR]

Millions of people are diagnosed every year with a chest disease in the world. Chronic obstructive pulmonary and pneumonia diseases are two of the most important chest diseases. And these are very common illnesses in Turkey. In this paper, a comparative study on chronic obstructive pulmonary and pneumonia diseases diagnosis was realized by using neural networks and artificial immune systems. For this purpose, three different neural networks structures and one artificial immune system were used. Used neural network structures in this study were multilayer, probabilistic, and learning vector quantization neural networks. The results of the study were compared with the results of the pervious similar studies reported focusing on chronic obstructive pulmonary and pneumonia diseases diagnosis. The chronic obstructive pulmonary and pneumonia diseases dataset were prepared from a chest diseases hospital’s database using patient’s epicrisis reports. [ABSTRACT FROM AUTHOR]

Existing brain region segmentation algorithms based on deep convolutional neural networks (CNN) are inefficient for object boundary segmentation. In order to enhance the segmentation accuracy of brain tissue, this paper proposed an object region segmentation algorithm that combines pixel-level information and semantic information. Firstly, we extract semantic information by CNN with the attention module and get the coarse segmentation results through a specific pixel-level classifier. Then, we exploit conditional random fields to model the relationship between the underlying pixels so as to get local features. Finally, the semantic information and the local pixel-level information are respectively used as the unary potential and the binary potential of the Gibbs distribution, and the combination of both can obtain the fine region segmentation algorithm based on the fusion of pixel-level information and the semantic information. A large number of qualitative and quantitative test results show that our proposed algorithm has higher precision than the existing state-of-the-art deep feature models, which can better solve the problem of rough edge segmentation and produce good 3D visualization effect. [ABSTRACT FROM AUTHOR]

Heart failure with preserved ejection fraction (HFpEF) is a complex and heterogeneous clinical syndrome. For the purpose of assisting HFpEF diagnosis, a non-invasive method using extreme learning machine and heart sound (HS) characteristics was provided in this paper. Firstly, the improved wavelet denoising method was used for signal preprocessing. Then, the logistic regression based hidden semi-Markov model algorithm was utilized to locate the boundary of the first HS and the second HS, therefore, the ratio of diastolic to systolic duration can be calculated. Eleven features were extracted based on multifractal detrended fluctuation analysis to analyze the differences of multifractal behavior of HS between healthy people and HFpEF patients. Afterwards, the statistical analysis was implemented on the extracted HS characteristics to generate the diagnostic feature set. Finally, the extreme learning machine was applied for HFpEF identification by the comparison of performances with support vector machine. The result shows an accuracy of 96.32%, a sensitivity of 95.48% and a specificity of 97.10%, which demonstrates the effectiveness of HS for HFpEF diagnosis. [ABSTRACT FROM AUTHOR]

Big Data and cloud computing are two essential issues in the recent years, empowers computing resources to be given as Information Technology services with high efficiency and effectiveness. So as to protect the security of data holders, data are regularly stored in the cloud in an encrypted form. In any case, encrypted data introduce new challenges for cloud data deduplication, which becomes crucial for big data storage and processing in the cloud along with access control. In this paper dissected the medical big data security utilizing encryption with access control process. Big database reduce process Map-Reduce framework with Optimal Fuzzy C means (OFCM) to Clustered data are accumulated in the cloud and furthermore using classification approach to classify sensitive and non-sensitive data in the cloud to encryption. This security process Triple DES (TDES) to encrypted and stored in the cloud and propose practical optimization techniques that further enhance the scheme's performance, at long last authentication phase with attribute-based access control is used to authenticate data in cloud sim. From the proposed method the clustering, classification and encryption results are compared to existing approaches. [ABSTRACT FROM AUTHOR]

Glaucoma is an eye disease that damages the optic nerve and can lead to irreversible loss of peripheral vision gradually and even blindness without treatment. Thus, diagnosing glaucoma in the early stage is essential for treatment. In this paper, an automatic method for early glaucoma screening is proposed. The proposed method combines structural parameters and textural features extracted from enhanced depth imaging optical coherence tomography (EDI-OCT) images and fundus images. The method first segments anterior the lamina cribrosa surface (ALCS) based on region-aware strategy and residual U-Net and then extracts structural features of the lamina cribrosa, such as lamina cribrosa depth and deformation of lamina cribrosa. In fundus images, scanning lines based on disc center and brightness reduction are used for optic disc segmentation and brightness compensation is utilized for segmenting the optic cup. Afterward, the cup-to-disc ratio (CDR) and textural features are extracted from fundus images. Hybrid features are used for training and classification to screen glaucoma by gcForest in the early stage. The proposed method has given exceptional results with 96.88% accuracy and 91.67% sensitivity. [ABSTRACT FROM AUTHOR]

Artificial intelligence algorithms have been used in a wide range of applications in clinical aided diagnosis, such as automatic MR image segmentation and seizure EEG signal analyses. In recent years, many machine learning-based automatic MR brain image segmentation methods have been proposed as auxiliary methods of medical image analysis in clinical treatment. Nevertheless, many problems regarding precise medical images, which cannot be effectively utilized to improve partition performance, remain to be solved. Due to the poor contrast in grayscale images, the ambiguity and complexity of MR images, and individual variability, the performance of classic algorithms in medical image segmentation still needs improvement. In this paper, we introduce a distributed multitask fuzzy c-means (MT-FCM) clustering algorithm for MR brain image segmentation that can extract knowledge common among different clustering tasks. The proposed distributed MT-FCM algorithm can effectively exploit information common among different but related MR brain image segmentation tasks and can avoid the negative effects caused by noisy data that exist in some MR images. Experimental results on clinical MR brain images demonstrate that the distributed MT-FCM method demonstrates more desirable performance than the classic signal task method. [ABSTRACT FROM AUTHOR]

In this paper we systematically evaluate the performance of several state-of-the-art local feature detectors and descriptors in the context of longitudinal registration of retinal images. Longitudinal (temporal) registration facilitates to track the changes in the retina that has happened over time. A wide number of local feature detectors and descriptors exist and many of them have already applied for retinal image registration, however, no comparative evaluation has been made so far to analyse their respective performance. In this manuscript we evaluate the performance of the widely known and commonly used detectors such as Harris, SIFT, SURF, BRISK, and bifurcation and cross-over points. As of descriptors SIFT, SURF, ALOHA, BRIEF, BRISK and PIIFD are used. Longitudinal retinal image datasets containing a total of 244 images are used for the experiment. The evaluation reveals some potential findings including more robustness of SURF and SIFT keypoints than the commonly used bifurcation and cross-over points, when detected on the vessels. SIFT keypoints can be detected with a reliability of 59% for without pathology images and 45% for with pathology images. For SURF keypoints these values are respectively 58% and 47%. ALOHA descriptor is best suited to describe SURF keypoints, which ensures an overall matching accuracy, distinguishability of 83%, 93% and 78%, 83% for without pathology and with pathology images respectively. [ABSTRACT FROM AUTHOR]