Medical Volume Data Research Articles

Creation of a Medical Knowledge Base for Unify the Development of Clinical Decision Support Systems Based on the National Metathesaurus

Background: The rapid growth in the volume of medical data, the extensive possibilities of information technology, the transfer of medical document flow to electronic format generates a high demand for the introduction of information and reference assistance tools and clinical decision support systems (CDSS). Work on the creation of CDSS currently combines the expert activities of doctors with the work of information technology specialists, mathematical statisticians, data scientists, knowledge engineers. Most of the developments involving the formation of knowledge bases are created in isolation, without the use of universal approaches that allow combining various solutions. At the heart of any medical knowledge base (MKB) there is a thesaurus, which is a systematized dictionary of terms that helps to standardize terminology, which makes it possible to speed up the search and exchange of information. It includes concept terms and relationships between them, as well as synonyms and various attributes. Aims — creation of a national medical metathesaurus, built on the ontological principle and the development of MKB based on it. Methods. International systematized dictionary of medical terms UMLS (Unified Medical Language System); clinical recommendations for 22 groups of nosologies; reference books of the federal portal of normative reference information of the Ministry of Health of the Russian Federation; electronic medical records – 330 thousand (dataset MIMIC-IV); abstracts of PubMed publications-28 million. Semantic analyzers SemRep (Semantic Repository) and MetaMap were used; methods for evaluating lexical similarity, connectivity, contextual combinability of entities in a subgraph, and mathematical statistics. Results. The first version of the Unified National Medical Nomenclature (UNMN) has been created. It is proved that ontological models are an effective way of presenting structured information. Components of information search engines have been created. Analytical tools for working with metathesaurus have been developed. Conclusions. On the basis of the UNMN and the created tools, it is possible to automate the formation of a clinical picture of the disease (knowledge base) and single-platform development of the CDSS.

The Role of ArtificiaI Intelligence in Brain Tumor Diagnosis: An Evaluation of a Machine Learning Model.

This research study explores of the effectiveness of a machine learning image classification model in the accurate identification of various types of brain tumors. The types of tumors under consideration in this study are gliomas, meningiomas, and pituitary tumors. These are some of the most common types of brain tumors and pose significant challenges in terms of accurate diagnosis and treatment. The machine learning model that is the focus of this study is built on the Google Teachable Machine platform (Alphabet Inc., Mountain View, CA). The Google Teachable Machine is a machine learning image classification platform that is built from Tensorflow, a popular open-source platform for machine learning. The Google Teachable Machine model was specifically evaluated for its ability to differentiate between normal brains and the aforementioned types of tumors in MRI images. MRI images are a common tool in the diagnosis of brain tumors, but the challenge lies in the accurate classification of the tumors. This is where the machine learning model comes into play. The model is trained to recognize patterns in the MRI images that correspond to the different types of tumors. The performance of the machine learning model was assessed using several metrics. These include precision, recall, and F1 score. These metrics were generated from a confusion matrix analysis and performance graphs. A confusion matrix is a table that is often used to describe the performance of a classification model. Precision is a measure of the model's ability to correctly identify positive instances among all instances it identified as positive. Recall, on the other hand, measures the model's ability to correctly identify positive instances among all actual positive instances. The F1 score is a measure that combines precision and recall providing a single metric for model performance. The results of the study were promising. The Google Teachable Machine model demonstrated high performance, with accuracy, precision, recall, and F1 scores ranging between 0.84 and 1.00. This suggests that the model is highly effective in accurately classifying the different types of brain tumors. This study provides insights into the potential of machine learning models in the accurate classification of brain tumors. The findings of this study lay the groundwork for further research in this area and have implications for the diagnosis and treatment of brain tumors. The study also highlights the potential of machine learning in enhancing the field of medical imaging and diagnosis. With the increasing complexity and volume of medical data, machine learning models like the one evaluated in this study could play a crucial role in improving the accuracy and efficiency of diagnoses. Furthermore, the study underscores the importance of continued research and development in this field to further refine these models and overcome any potential limitations or challenges. Overall, the study contributes to the field of medical imaging and machine learning and sets the stage for future research and advancements in this area.

CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare

In the era of modern healthcare, swiftly generating medical question summaries is crucial for informed and timely patient care. Despite the increasing complexity and volume of medical data, existing studies have focused solely on text-based summarization, neglecting the integration of visual information. Recognizing the untapped potential of combining textual queries with visual representations of medical conditions, we introduce the Multimodal Medical Question Summarization (MMQS) Dataset. This dataset, a major contribution of our work, pairs medical queries with visual aids, facilitating a richer and more nuanced understanding of patient needs. We also propose a framework, utilizing the power of Contrastive Language Image Pretraining(CLIP) and Large Language Models(LLMs), consisting of four modules that identify medical disorders, generate relevant context, filter medical concepts, and craft visually aware summaries. Our comprehensive framework harnesses the power of CLIP, a multimodal foundation model, and various general-purpose LLMs, comprising four main modules: the medical disorder identification module, the relevant context generation module, the context filtration module for distilling relevant medical concepts and knowledge, and finally, a general-purpose LLM to generate visually aware medical question summaries. Leveraging our MMQS dataset, we showcase how visual cues from images enhance the generation of medically nuanced summaries. This multimodal approach not only enhances the decision-making process in healthcare but also fosters a more nuanced understanding of patient queries, laying the groundwork for future research in personalized and responsive medical care. Disclaimer: The article features graphic medical imagery, a result of the subject's inherent requirements.

A Transfer Function Design for Medical Volume Data Using a Knowledge Database Based on Deep Image and Primitive Intensity Profile Features Retrieval

A Transfer Function Design for Medical Volume Data Using a Knowledge Database Based on Deep Image and Primitive Intensity Profile Features Retrieval

Clutch & Grasp: Activation gestures and grip styles for device-based interaction in medical spatial augmented reality

Presenting medical volume data using augmented reality (AR) can facilitate the identification of anatomical structures, the perception of their spatial relations and the development of mental maps compared to more commonly used monitors. However, interaction methods explored in these conventional settings may not be applicable in AR environments, or perform differently. In terms of mode activation, gestural interaction was shown to be a viable, touchless alternative to traditional input devices, which is desirable in sterile medical use cases. Therefore, we present a user study (n = 21) comparing hand and foot gestures with voice commands for the activation of interaction modes within a projector-based, spatial AR prototype to visualize medical volume data. Interaction itself was performed via hand movements captured by a data glove. Consistent, statistically significant results across measured variables suggest advantages of voice commands. In addition, a second experiment (n = 17) compared the hand-based interaction with two motion-sensitive devices held in power and in precision grip respectively. All modes were activated using voice commands. No considerable differences between tested grip styles could be determined. The findings suggest that the choice of preferable interaction devices is user and use case dependent.

Medical volume data real-time optical reconstruction on light field display with a directional diffuser

In this paper, we proposed an optical reconstruction approach by use of a new type of light field display device(LFDD) with a directional diffuser. The directional diffuser can improve imaging quality of the traditional light field display device. Special ray casting algorithm is applied to render the medical volume data in real time for LFDD. Four different kinds of medical data have been applied for testing the validity of the algorithm and better results have been achieved. The experimental results shows that the number of LFDD’s viewpoints can reach 90 × 90 with 40 degree× 40 degree viewing angle, and the rendering efficiency can reach 30–40 fps for common medial volume data.

Robust Watermarking Algorithm for Medical Volume Data Based on Polar Cosine Transform and 3D-DCT

Robust Watermarking Algorithm for Medical Volume Data Based on Polar Cosine Transform and 3D-DCT

Methods Used to Compare Narrative Clinical Practice Guidelines: A Scoping Review.

Guideline-based clinical decision support systems (CDSSs) need the most recent evidence for reliable performance, making the provision of regularly updated clinical practice guidelines (CPGs) a major issue. Some international guidelines are renewed in short intervals and can be used for checking the status of given national guidelines with regard to the most recent evidence. Considering the volume of medical data and the number of CPGs published, computerized comparison of clinical guidelines can be an effective method. We performed a scoping review to evaluate the methods used for comparing two CPGs. We searched for methods for extracting CPG components and for methods used for comparing CPGs at different levels of abstraction. In each case, computerized and semi-computerized methods were recognized. Expert knowledge has yet a determinant role for assessing the comparisons, this role being more prominent for the extraction of semantic rules and the resolution of inconsistencies.

Does Gastroenterology Need Artificial Intelligence?

Aim. An outlook of trends and perspectives in gastroenterology in the age of digital healthcare.Key points. Diagnosis gradually transforms to the task of image recognition. Tuning a diagnostic algorithm (DA) necessarily requires a statistically representative training set of images. In transition towards electronic medical records (EMR), such data will be generated automatically. Advances in machine image recognition and the upcoming availability of a large amount of medical data suitable for configuring DA both pave the way towards efficient computerassisted diagnosis.Conclusion. The growing volumes of medical data enforce, and advances in machine image recognition enable, the transition towards computer-assisted medical diagnosis.

Deep learning network for medical volume data segmentation based on multi axial plane fusion

Background and Objective: High-dimensional data generally contains more accurate information for medical image, e.g., computerized tomography (CT) data can depict the three dimensional structure of organs more precisely. However, the data in high-dimension often needs enormous computation and has high memory requirements in the deep learning convolution networks, while dimensional reduction usually leads to performance degradation. Methods: In this paper, a two-dimensional deep learning segmentation network was proposed for medical volume data based on multi-pinacoidal plane fusion to cover more information under the control of computation.This approach has conducive compatibility while using the model proposed to extract the global information between different inputs layers. Results: Our approach has worked in different backbone network. Using the approach, DeepUnet’s Dice coefficient (Dice) and Positive Predictive Value (PPV) are 0.883 and 0.982 showing the satisfied progress. Various backbones can enjoy the profit of the method. Conclusions: Through the comparison of different backbones, it can be found that the proposed network with multi-pinacoidal plane fusion can achieve better results both quantitively and qualitatively.

A direct slicing technique for the 3D printing of implicitly represented medical models

In conventional medical image printing methods, volumetric medical data needs to be conversed into STereo Lithography (STL) format, the most commonly used format for representing geometric models for 3D printing. However, this STL conversion process is not only time consuming, but more importantly, it often leads to the loss of accuracy. It has become a critical factor hindering the printing efficiency and precision of organ models. By examining the key characteristics of discrete medical volume data, this paper proposes a direct slicing technique for printing implicitly represented 3D medical models. The proposed method mainly consists of three algorithms: (1) A layer-based contour extraction algorithm for discrete volume data; (2) An inner shell construction algorithm based on discrete point differential indentation; (3) An infill generation algorithm based on the constructed virtual contour and scan lines. The proposed method has been applied to the slicing of several organ models for experiments, and the ratios of time cost and memory cost between the conventional method and the proposed method are about 4–100 and 1.1 to 1.4 respectively, which demonstrate that the proposed method has a great improvement in both time and space performance when compared with the conventional STL-based method. Our technique extends the direct input format of geometric models for additive manufacturing. That is, discrete volume data can be used as a direct input for additive manufacturing without conversion to STL format.

Evaluation of Applying Surface Simplification Techniques in Medical Volume Data

Evaluation of Applying Surface Simplification Techniques in Medical Volume Data

A Transfer Learning-Based Active Learning Framework for Brain Tumor Classification.

Brain tumor is one of the leading causes of cancer-related death globally among children and adults. Precise classification of brain tumor grade (low-grade and high-grade glioma) at an early stage plays a key role in successful prognosis and treatment planning. With recent advances in deep learning, artificial intelligence–enabled brain tumor grading systems can assist radiologists in the interpretation of medical images within seconds. The performance of deep learning techniques is, however, highly depended on the size of the annotated dataset. It is extremely challenging to label a large quantity of medical images, given the complexity and volume of medical data. In this work, we propose a novel transfer learning–based active learning framework to reduce the annotation cost while maintaining stability and robustness of the model performance for brain tumor classification. In this retrospective research, we employed a 2D slice–based approach to train and fine-tune our model on the magnetic resonance imaging (MRI) training dataset of 203 patients and a validation dataset of 66 patients which was used as the baseline. With our proposed method, the model achieved area under receiver operating characteristic (ROC) curve (AUC) of 82.89% on a separate test dataset of 66 patients, which was 2.92% higher than the baseline AUC while saving at least 40% of labeling cost. In order to further examine the robustness of our method, we created a balanced dataset, which underwent the same procedure. The model achieved AUC of 82% compared with AUC of 78.48% for the baseline, which reassures the robustness and stability of our proposed transfer learning augmented with active learning framework while significantly reducing the size of training data.

Surface Reconstruction: Roles in the Field of Computer Vision and Computer Graphics

Surface Reconstruction is the most potent aspect of 3D computer vision. It allows recapturing or imitating of the shape of real objects. It also provides sufficient knowledge regarding the mathematical foundation for rendering applications which are widely used for analyzing medical volume data, modeling, 3D interior designing, architectural designing. In our paper, we have mentioned various algorithms and approaches for surface reconstruction and their applications. Moreover, we have tried to emphasize the necessity of surface reconstruction for solving image analysis related problem.

Using virtual 3D-models in surgical planning: workflow of an immersive virtual reality application in liver surgery

PurposeThree-dimensional (3D) surgical planning is widely accepted in liver surgery. Currently, the 3D reconstructions are usually presented as 3D PDF data on regular monitors. 3D-printed liver models are sometimes used for education and planning.MethodsWe developed an immersive virtual reality (VR) application that enables the presentation of preoperative 3D models. The 3D reconstructions are exported as STL files and easily imported into the application, which creates the virtual model automatically. The presentation is possible in “OpenVR”-ready VR headsets. To interact with the 3D liver model, VR controllers are used. Scaling is possible, as well as changing the opacity from invisible over transparent to fully opaque. In addition, the surgeon can draw potential resection lines on the surface of the liver. All these functions can be used in a single or multi-user mode.ResultsFive highly experienced HPB surgeons of our department evaluated the VR application after using it for the very first time and considered it helpful according to the “System Usability Scale” (SUS) with a score of 76.6%. Especially with the subitem “necessary learning effort,” it was shown that the application is easy to use.ConclusionWe introduce an immersive, interactive presentation of medical volume data for preoperative 3D liver surgery planning. The application is easy to use and may have advantages over 3D PDF and 3D print in preoperative liver surgery planning. Prospective trials are needed to evaluate the optimal presentation mode of 3D liver models.

Probabilistic Slider: A Tool for Visualizing Fuzzy Segmentation Uncertainties

Visualization of classification uncertainty of the medical materials is very significant, as different classifications may lead to different visualization results, and different results may cause completely different diagnosis or pre-operative planning decisions, and thus have different consequences to patients. Traditional Direct Volume Rendering (DVR) enables medical experts to visualize the classification uncertainty by random adjustment of the transfer function. However, three main problems exist by using this method: first, the resulting renderings do not indicate any quantitative information about the classification uncertainty of different materials; second, the resulting renderings are randomly revealed by random adjustment of the TF; third, both classification task and optical property assignment task are mixed together in one step. These problems may make this method (1) fail to enable medical experts to make accurate diagnosis or pre-operative planning decision; (2) unable to provide medical experts with a clear concept of how medical volume data are classified. To address these problems, we proposed a probabilistic slider system, which compared to the traditional DVR, enables medical experts to make more accurate diagnosis or pre-operative planning decision, and have a clearer concept of how the medical volume data being classified.

Dental implants success prediction by classifier ensemble on imbalanced data

BackgroundIn recent years, increasing advances in data storage have led to an increase in the volume of medical data. Data mining has a significant role in different aspects of medical sciences, including extracting knowledge from the volume of data, diagnosing diseases, determining the effectiveness of drugs, identifying treatment methods, and predicting the success of treatment. The dental implant is one of the most common methods for tooth root replacement used in prosthetic dentistry. ObjectiveAccurate prediction of implant success or failure before the surgery is an interesting and challenging topic for dentists. However, imbalanced data is one of the main problems in any medical data mining application. This problem occurs when samples of one or more classes of data are scarce or difficult to collect. This challenge poses severe problems in extracting knowledge from data. MethodsIn this paper, we present a new approach for predicting the success or failure of dental implants in the presence of imbalanced data. To this aim, first, the imbalanced data is clustered, and then each cluster is balanced by SMOTE algorithm. In the next step, the balanced data are classified by an ensemble of four well-known classifiers, including the decision tree, the support vector machine, the k-nearest neighbor, and the Naïve Bayes. To improve the classification accuracy, an optimal weight is determined for each classifier using the genetic algorithm. Thus, each classifier will have a different effect on determining the final decision. Results: The proposed method was applied to a dataset consists of 224 patients who underwent implant and bone graft treatments at the Faculty of Dentistry of the University of Tehran, Iran. Different criteria were used to evaluate the proposed method, including accuracy, sensitivity, specificity, AUC, and G-mean. The evaluation results show that the proposed ensemble algorithm provides a more accurate implant success prediction on imbalanced data compared to using the single-use of each classifier and also state-of-the-art researches. ConclusionsThis paper presents a novel ensemble method algorithm to predict the success or failure of dental implants for imbalanced data. The obtained results reported that the use of the hybrid algorithm increases the accuracy parameter by about 5.5%, the sensitivity parameter by about 0.3%, and the specificity parameter with a significant amount of about 25%, in comparison to the best results achieved by single classifiers.

ONTOLOGY AS A MEANS OF PRESENTATION OF MEDICAL INFORMATION

Today information and communication technologies (ICTs) play a crucial role in many, if not all, areas of human activity, radically affecting users, their work and the work environment. Modern ICT provides the collection and processing of information, data storage, accumulation and generation of knowledge, organization and acceleration of communication. To implement a variety of services, information systems are being developed, the services of which are closely related to the design of user activities in a social context. Therefore, an important component of the context in which the information service is built-in is the so-called subject area (domain). Having an accurate representation of the conceptualization of the subject area becomes even more important when there is a need to integrate different independently developed information systems (or models on which these systems are based). The ability of systems to interact (ie work together) while having compatible semantics of the real world is known as semantic compatibility. The article considers the medical ontological information systems that can be used to present semantic data. Problems of processing, presentation, use and integration of large volumes of medical data are considered. An analysis of various ontologies in the field of health care, which facilitate the reuse and exchange of medical knowledge. The issues of the electronic medical records and personal medical records as an important component in the quality of medical services are addressed. It also reveals the terminology of biomedical ontology, provides a comprehensive description of the benefits of this system, as well as details the ways of semantic interoperability in the field of health care. Interoperability is ensured by indexing the results of the integration of transdisciplinary semantically related contexts of distributed heterogeneous information resources (Big Data). The examples of the use of ontology in the systemic biomedicine are given, as well as the peculiarities of the obtaining implicitly given data.

Visualization of Medical Volume Data Based on Improved K-Means Clustering and Segmentation Rules

Accurate extraction and visualization of the target features are important in medical visualization, allowing the user to get a meaningful view of their targets. The traditional way to generate visualization results is 1D TF-based volume visualization, which uses a 1D -TF to determine the optical properties of each voxel. However, it is difficult to distinguish multiple targets by using the 1D TF-based volume visualization. It is also challenging to distinguish accurate targets when the objects’ intensity values are similar in volume. Using the traditional transfer function usually fails to extract important target features and generates less accurate results. In this paper, we proposed extracting and segmentation techniques based on K-means algorithm that allows the users to segment and enhances single or multiple targets by a single point to view the features in 3D view. We have applied it to various univariate or multivariate volume datasets from the medical field to demonstrate its effectiveness. Moreover, we have performed both qualitative and quantitative experiments to compare its results against the results from two state-of-the-art techniques and the ground truths. The experimental results showed that our method is able to generate the closest results to the ground truth.

Robust Watermarking Algorithm for Medical Volume Data in Internet of Medical Things

The advancement of 5G technology, big data and cloud storage has promoted the rapid development of the Internet of Medical Things (IoMT). Based on the strict security requirements and high level of accuracy required for disease diagnosis and pathological analysis, 3D medical volume data have been created in large numbers. The IoMT facilitates the rapid transfer of medical information and also makes the protection of pathological information and privacy information of patients increasingly prominent. To solve the security problem, a robust zero-watermarking algorithm based on 3D hyperchaos and 3D dual-tree complex wavelet transform is proposed according to the selected feature of medical volume data. The feature combines human visual features with improved perceptual hashing techniques. It is a robust and efficient binary sequence. When implementing the proposed algorithm, the watermark is first scrambled with 3D hyperchaos to enhance security. Then, 3D DTCWT-DCT transformation is applied to medical volume data, and the low-frequency coefficients that can represent the features are selected and binarized to generate the secret key to complete the watermark embedding and extraction. Zero embedding and blind extraction ensure that the original medical volume data is not altered in any form, which meets the special requirements for diagnosis. Simulation results show that the algorithm is robust and can effectively resist common attacks and geometric attacks. It used fewer robust features to effectively bound medical volume data and watermark information, saved bandwidth, and satisfied the security of transmission and storage of medical volume data in the Internet of medical things. In particular, compared with state-of-the-art technology, the proposed algorithm improves the average NC value by 46.67% under geometric attacks.