Dimensional Medical Images Research Articles

An Enhanced Compression Method for Medical Images Using SPIHT Encoder for Fog Computing

When it comes to filtering and compressing data before sending it to a cloud server, fog computing is a rummage sale. Fog computing enables an alternate method to reduce the complexity of medical image processing and steadily improve its dependability. Medical images are produced by imaging processing modalities using X-rays, computed tomography (CT) scans, magnetic resonance imaging (MRI) scans, and ultrasound (US). These medical images are large and have a huge amount of storage. This problem is being solved by making use of compression. In this area, lots of work is done. However, before adding more techniques to Fog, getting a high compression ratio (CR) in a shorter time is required, therefore consuming less network traffic. Le Gall5/3 integer wavelet transform (IWT) and a set partitioning in hierarchical trees (SPIHT) encoder were used in this study’s implementation of an image compression technique. MRI is used in the experiments. The suggested technique uses a modified CR and less compression time (CT) to compress the medical image. The proposed approach results in an average CR of 84.8895%. A 40.92% peak signal-to-noise ratio (PSNR) PNSR value is present. Using the Huffman coding, the proposed approach reduces the CT by 36.7434 s compared to the IWT. Regarding CR, the suggested technique outperforms IWTs with Huffman coding by 12%. The current approach has a 72.36% CR. The suggested work’s shortcoming is that the high CR caused a decline in the quality of the medical images. PSNR values can be raised, and more effort can be made to compress colored medical images and 3-dimensional medical images.

3D shape reconstruction of the femur from planar X-ray images using statistical shape and appearance models

Major trauma is a condition that can result in severe bone damage. Customised orthopaedic reconstruction allows for limb salvage surgery and helps to restore joint alignment. For the best possible outcome three dimensional (3D) medical imaging is necessary, but its availability and access, especially in developing countries, can be challenging. In this study, 3D bone shapes of the femur reconstructed from planar radiographs representing bone defects were evaluated for use in orthopaedic surgery. Statistical shape and appearance models generated from 40 cadaveric X-ray computed tomography (CT) images were used to reconstruct 3D bone shapes. The reconstruction simulated bone defects of between 0% and 50% of the whole bone, and the prediction accuracy using anterior–posterior (AP) and anterior–posterior/medial–lateral (AP/ML) X-rays were compared. As error metrics for the comparison, measures evaluating the distance between contour lines of the projections as well as a measure comparing similarities in image intensities were used. The results were evaluated using the root-mean-square distance for surface error as well as differences in commonly used anatomical measures, including bow, femoral neck, diaphyseal–condylar and version angles between reconstructed surfaces from the shape model and the intact shape reconstructed from the CT image. The reconstructions had average surface errors between 1.59 and 3.59 mm with reconstructions using the contour error metric from the AP/ML directions being the most accurate. Predictions of bow and femoral neck angles were well below the clinical threshold accuracy of 3°, diaphyseal–condylar angles were around the threshold of 3° and only version angle predictions of between 5.3° and 9.3° were above the clinical threshold, but below the range reported in clinical practice using computer navigation (i.e., 17° internal to 15° external rotation). This study shows that the reconstructions from partly available planar images using statistical shape and appearance models had an accuracy which would support their potential use in orthopaedic reconstruction.

Classification regularized dimensionality reduction improves ultrasound thyroid nodule diagnostic accuracy and inter-observer consistency

ProblemConvolutional Neural Networks (CNNs) for medical image analysis usually only output a probability value, providing no further information about the original image or inter-relationships between different images. Dimensionality Reduction Techniques (DRTs) are used for visualization of high dimensional medical image data, but they are not intended for discriminative classification analysis. AimWe develop an interactive phenotype distribution field visualization system for medical images to accurately reflect the pathological characteristics of lesions and their similarity to assist radiologists in diagnosis and medical research. MethodsWe propose a novel method, Classification Regularized Uniform Manifold Approximation and Projection (UMAP) referred as CReUMAP, combining the advantages of CNN and DRT, to project the extracted feature vector fused with the malignant probability predicted by a CNN to a two-dimensional space, and then apply a spatial segmentation classifier trained on 2614 ultrasound images for prediction of thyroid nodule malignancy and guidance to radiologists. ResultsThe CReUMAP embedding correlates well with the TI-RADS categories of thyroid nodules. The parametric version that embeds external test dataset of 303 images in presence of the training data with known pathological diagnosis improves the benign and malignant nodule diagnostic accuracy (p-value = 0.016) and confidence (p-value = 1.902 × 10−6) of eight radiologists of different experience levels significantly as well as their inter-observer agreements (kappa≥0.75). CReUMAP achieve 90.8% accuracy, 92.1% sensitivity and 88.6% specificity in test set. ConclusionCReUMAP embedding is well correlated with the pathological diagnosis of thyroid nodules, and helps radiologists achieve more accurate, confident and consistent diagnosis. It allows a medical center to generate its locally adapted embedding using an already-trained classification model in an updateable manner on an ever-growing local database as long as the extracted feature vectors and predicted diagnostic probabilities of the correspondent classification model can be outputted.

New approach to establish a surgical planning in infantile vallecular cyst synchronous with laryngomalacia based on aerodynamic analysis

Background and objectivesA large proportion of infants with vallecular cyst (VC) have coexisting laryngomalacia (LM). Feeding difficulties, regurgitation, occasional cough, and sleep-disordered breathing are the common symptoms in moderate to severe cases. The surgical management of these cases is more challenging and remains controversial. The purpose of this study is to help surgeons select the effective surgical strategies by computer-aided design (CAD) and computational fluid dynamics (CFD) simulations of the upper airway flow characteristics. MethodsThe three dimensional (3D) geometric model of the upper airway was reconstructed based on two dimensional (2D) medical images of the patient with VC accompanied with LM. Virtual surgeries were carried out preoperatively to simulate three possible post-operative states in silico. The different outcomes of virtual surgical strategies were predicted based on computational evaluations of airway fluid dynamics including pressure, resistance, velocity, and wall shear stress (WSS). ResultsThe CFD results of this study suggested the importance of the angle between the rim of epiglottis and arytenoid epiglottic (AE) fold. There was a small impact on the upper airway flow field while the VC was removed and the angle of epiglottis was unchanged. The partial lifting of epiglottis can further improve the flow field. With performing supraglottoplasty (SGP) and the marsupialization of VC, epiglottis was completely recovered, and the flow field was significantly improved. The clinical symptoms of this patient improved greatly after surgeries and no recurrence or growth retardation were noted during 1-year follow-up. The clinical prognosis was consistent with the prediction of the CFD results. ConclusionsThe state of epiglottis needs to be carefully checked to evaluate the necessity of performing further SGP in the patients with VC accompanied with LM. CFD and CAD could be developed as a new approach to help surgeons predict the post-operative outcomes through quantification of the airflow dynamics, and make the optimal and individualized surgical approaches for patients with airway obstruction.

Transformer based tooth classification from cone-beam computed tomography for dental charting

Dental charting is a useful tool in physical examination, dental surgery, and forensic identification. However, manual dental charting faces some difficulties, such as inaccuracy and psychiatric burden in forensic identification. As a critical step of dental charting, tooth classification can be completed on dental cone-beam computed tomography (CBCT) automatically to solve the above difficulties. In this paper, we build a deep neuron network which accepts a 3D CBCT image patch that contains the region of interest (ROI) of a tooth as input and then outputs the type of the tooth. Although Transformer-based neural networks outperform CNN-based neural networks in many natural image processing tasks, they are difficult to apply to 3D medical images. Therefore, we combine the advantages of CNN and Transformer structure to improve the existing methods and propose the Grouped Bottleneck Transformer to overcome the drawbacks of the Transformer, namely the requirement of large training dataset and high computational complexity. We conducted an experiment on a clinical data set containing 450 training samples and 104 testing samples. Experiments show that our network can achieve a classification accuracy of 91.3% and an AUC score of 99.7%. To further evaluate the effectiveness of our method, we tested our network on the publicly available medical image classification dataset MedMNIST3D. The result shows that our network outperforms other networks on 5 out of 6 3-dimensional medical image subsets.

Volume and Perfusion Index Evaluation by 3D SPECT Image Processing in Lung Embolism

Lung status during pulmonary embolism and patient follow-up, should be evaluated and the accurate estimation of lungs volume is important; By 3-dimensional (3D) medical imaging data and diagnosis of patient embolism become much more reliable.

COMPUTATIONAL 2D and 3D MEDICAL IMAGE DATA COMPRESSION MODELS.

In this world of big data, the development and exploitation of medical technology is vastly increasing and especially in big biomedical imaging modalities available across medicine. At the same instant, acquisition, processing, storing and transmission of such huge medical data requires efficient and robust data compression models. Over the last two decades, numerous compression mechanisms, techniques and algorithms were proposed by many researchers. This work provides a detailed status of these existing computational compression methods for medical imaging data. Appropriate classification, performance metrics, practical issues and challenges in enhancing the two dimensional (2D) and three dimensional (3D) medical image compression arena are reviewed in detail.

A Novel Volume-based Cone-beam Computed Tomographic Periapical Index

IntroductionThe purpose of this study was to evaluate the variations in the volume of periapical lesions scored using a cone-beam computed tomographic periapical index (CBCTPAI) and to develop a new volume-based periapical index. MethodsCone-beam computed tomographic images were obtained from InteleViewer (Intelerad Medical Systems Incorporated, Montreal, Canada). Teeth with a periapical radiolucency or with a history of endodontic treatment were included in this study. Using 3-dimensional medical imaging processing software (Mimics Research; Materialise NV, Leuven, Belgium), the maximum diameter of 273 periapical lesions and their corresponding CBCTPAI score was determined. The software was then used to determine the volume of the lesions using a semiautomatic segmentation technique. ResultsThere was a substantial variation in the volume for CBCTPAI scores 3, 4, and 5, which was demonstrated by the variance and range, thus making it difficult to use the current CBCTPAI as a method to predict volume and treatment outcomes. A new index, the cone-beam computed tomographic periapical volume index (CBCTPAVI), was developed using partition classification analysis. The results for the new index demonstrated high levels of sensitivity, specificity, precision, and area under the curve, all at 0.90 or more, except 1 sensitivity for CBCTPAVI 1 at 0.875. Overall, the accurate classification rate was 98.169%, and the root mean square error rate was low at 0.07. ConclusionsThe proposed CBCTPAVI will allow clinicians to classify lesions based on their true 3-dimensional size, accurately assess healing of lesions, and predict treatment outcomes.

Automated identification of clinical features from sparsely annotated 3-dimensional medical imaging

One of the core challenges in applying machine learning and artificial intelligence to medicine is the limited availability of annotated medical data. Unlike in other applications of machine learning, where an abundance of labeled data is available, the labeling and annotation of medical data and images require a major effort of manual work by expert clinicians who do not have the time to annotate manually. In this work, we propose a new deep learning technique (SLIVER-net), to predict clinical features from 3-dimensional volumes using a limited number of manually annotated examples. SLIVER-net is based on transfer learning, where we borrow information about the structure and parameters of the network from publicly available large datasets. Since public volume data are scarce, we use 2D images and account for the 3-dimensional structure using a novel deep learning method which tiles the volume scans, and then adds layers that leverage the 3D structure. In order to illustrate its utility, we apply SLIVER-net to predict risk factors for progression of age-related macular degeneration (AMD), a leading cause of blindness, from optical coherence tomography (OCT) volumes acquired from multiple sites. SLIVER-net successfully predicts these factors despite being trained with a relatively small number of annotated volumes (hundreds) and only dozens of positive training examples. Our empirical evaluation demonstrates that SLIVER-net significantly outperforms standard state-of-the-art deep learning techniques used for medical volumes, and its performance is generalizable as it was validated on an external testing set. In a direct comparison with a clinician panel, we find that SLIVER-net also outperforms junior specialists, and identifies AMD progression risk factors similarly to expert retina specialists.

A deep learning based framework for the registration of three dimensional multi-modal medical images of the head

Image registration is a fundamental task in image analysis in which the transform that moves the coordinate system of one image to another is calculated. Registration of multi-modal medical images has important implications for clinical diagnosis, treatment planning, and image-guided surgery as it provides the means of bringing together complimentary information obtained from different image modalities. However, since different image modalities have different properties due to their different acquisition methods, it remains a challenging task to find a fast and accurate match between multi-modal images. Furthermore, due to reasons such as ethical issues and need for human expert intervention, it is difficult to collect a large database of labelled multi-modal medical images. In addition, manual input is required to determine the fixed and moving images as input to registration algorithms. In this paper, we address these issues and introduce a registration framework that (1) creates synthetic data to augment existing datasets, (2) generates ground truth data to be used in the training and testing of algorithms, (3) registers (using a combination of deep learning and conventional machine learning methods) multi-modal images in an accurate and fast manner, and (4) automatically classifies the image modality so that the process of registration can be fully automated. We validate the performance of the proposed framework on CT and MRI images of the head obtained from a publicly available registration database.

Design Considerations for Interacting and Navigating with 2 Dimensional and 3 Dimensional Medical Images in Virtual, Augmented and Mixed Reality Medical Applications.

The extended realities, including virtual, augmented, and mixed realities (VAMR) have recently experienced significant hardware improvement resulting in an expansion in medical applications. These applications can be classified by the target end user (for instance, classifying applications as patient-centric, physician-centric, or both) or by use case (for instance educational, diagnostic tools, therapeutic tools, or some combination). When developing medical applications in VAMR, careful consideration of both the target end user and use case must heavily influence design considerations, particularly methods and tools for interaction and navigation. Medical imaging consists of both 2-dimensional and 3-dimensional medical imaging which impacts design, interaction, and navigation. Additionally, medical applications need to comply with regulatory considerations which will also influence interaction and design considerations. In this manuscript, the authors explore these considerations using three VAMR tools being developed for cardiac electrophysiology procedures.

Improving the slice interaction of 2.5D CNN for automatic pancreas segmentation.

Volumetric pancreas segmentation can be used in the diagnosis of pancreatic diseases, the research about diabetes and surgical planning. Since manual delineation is time-consuming and laborious, we develop a deep learning-based framework for automatic pancreas segmentation in three dimensional (3D) medical images. A two-stage framework is designed for automatic pancreas delineation. In the localization stage, a Square Root Dice loss is developed to handle the trade-off between sensitivity and specificity. In refinement stage, a novel 2.5D slice interaction network with slice correlation module is proposed to capture the non-local cross-slice information at multiple feature levels. Also a self-supervised learning-based pre-training method, slice shuffle, is designed to encourage the inter-slice communication. To further improve the accuracy and robustness, ensemble learning and a recurrent refinement process are adopted in the segmentation flow. The segmentation technique is validated in a public dataset (NIH Pancreas-CT) with 82 abdominal contrast-enhanced 3D CT scans. Fourfold cross-validation is performed to assess the capability and robustness of our method. The dice similarity coefficient, sensitivity, and specificity of our results are 86.21±4.37%, 87.49±6.38% and 85.11±6.49% respectively, which is the state-of-the-art performance in this dataset. We proposed an automatic pancreas segmentation framework and validate in an open dataset. It is found that 2.5D network benefits from multi-level slice interaction and suitable self-supervised learning method for pre-training can boost the performance of neural network. This technique could provide new image findings for the routine diagnosis of pancreatic disease.

G-Code Generator from Bone DICOM CT with Cloud

A three dimensional (3D) medical image can provide a sense of reality for a doctor. A 3D printer can transform a 3D image into a 3D object, which provides communication between the doctor and his/her patients. One step to make the 3D object is to generate the g-code using a software. However, the existing software for creating the g-code still uses the user interface (a manual process). This study aims to generate g-code from Digital Imaging and Communications in Medicine (DICOM) format in Computerized Tomography (CT) through the cloud. The g-code generator is implemented using Phyton version 3 and runs on a computer using Linux (Ubuntu 18.4) as the operating system. The computer specification is intel core i9-9900K with motherboard Gigabyte Z390 Aorus Elite and graphic card Gigabyte GV-N208TGAMING OC11GC (memory 11GB). The medical image object is a bone that comprises craniofacial bone and thoracic vertebra, taken from multi-slice CT in DICOM format. The g-code file is suitable for a specific 3D printer. The performance criteria are the transferred data and visual shape comparison between the output from InVesalius 3.1 software and 3D printer (manually). The justification of the visual shape match from three radiology doctors for craniofacial bone and a thoracic vertebra is approximately 100% matching.

Virtual Preoperative Simulation for Excision of Spinal Tumors: Surgeon Processing of Medical Computer-Assisted Design Software.

As medical computer-aided design (CAD) has improved, virtual 3-dimensional medical images have been gaining more easily without any special practice. These images can be applied to various clinical fields. This article illustrates virtual preoperative simulation for excision of spinal tumors using medical CAD software. The software was used directly by the surgeon. The process of virtual preoperative simulation for spinal tumor surgery was found to be not inordinately complicated. And, virtual simulation was helpful in determining surgical steps as well as understanding the surgical anatomy.

Implementation of 2-Dimensional Medical Image Reconstruction Algorithm for Photoacoustic Imaging

In this paper, we review and discuss our proposed image reconstruction algorithm for two dimensional stereo photo-acoustic medical imaging system. The proposed algorithms aim to evaluate the existence possibility of acoustic source within a search area by using the geometric information which is the distance between each sensor element of ultrasound probe and corresponding searching point. Besides, we implemented the hardware and software aspects of an photo-acoustic imaging system that is described in hardware implementation section of this paper. At the end of this paper, some simulation results are presented which utilized the proposed algorithm while compared the image quality of its and conventional k-wave algorithm in which FFT should be used. The simulation results proved the effectiveness of the proposed reconstruction algorithm.

Spatial classification rule with distance in three dimensional space

Spatial Classification Rule with Distance (SCRD) method is used in two dimensional coordinate system, which limits the usage of existing spatial information in MRI, CT and other three dimensional (layered) images. The SCRD method is extended to be applied in three dimensional coordinate space. Artificial experiment is performed in order to show ability to use SCRD method with three dimensional medical or other similar images where training sample is available.

3D Medical Image Compression: A Review

In this paper a comprehensive survey of the state of the art lossy and lossless techniques available in the literature has been presented and the merits and pitfalls of each technique are analyzed. This study congregates the pioneer works in two dimensional (2D) compression techniques, both in pixel domain and transform domain. The evolution of compression of three dimensional (3D) medical images from 2D compression has also been discussed. Compressed medical image has to be both diagnostically lossless and less bandwidth in addition to visual quality. Region of Interest coding (ROI) which achieves diagnostic quality image with less bandwidth has been explored. In spite of proven compression technologies, only the lossless compression has been used widely around the world and the reason for the same has been investigated. In addition it also investigates several factors; why one needs to go for lossy compression.

Integrated Front End Electronics Design for Micromachined Ultrasound Transducers

Chip level integration of two dimensional (2D) capacitive micromachined ultrasound transducer (CMUT) array with custom integrated circuit (IC) for the real-time three dimensional (3D) medical imaging is described. Front-end electronics IC contains 4096 pulsers, producing 50 V pulses and 4096 low noise 12 MHz band preamplifiers with switches. 256 multiplexers, having 16 outputs each are used for readout of the signal from transducer elements. This scheme enables the control of transducer apertures containing 256 elements for transmit and receive.

Fast Covariance Estimation for High-dimensional Functional Data.

We propose two fast covariance smoothing methods and associated software that scale up linearly with the number of observations per function. Most available methods and software cannot smooth covariance matrices of dimension J > 500; a recently introduced sandwich smoother is an exception but is not adapted to smooth covariance matrices of large dimensions, such as J = 10, 000. We introduce two new methods that circumvent those problems: 1) a fast implementation of the sandwich smoother for covariance smoothing; and 2) a two-step procedure that first obtains the singular value decomposition of the data matrix and then smoothes the eigenvectors. These new approaches are at least an order of magnitude faster in high dimensions and drastically reduce computer memory requirements. The new approaches provide instantaneous (a few seconds) smoothing for matrices of dimension J = 10,000 and very fast (< 10 minutes) smoothing for J = 100, 000. R functions, simulations, and data analysis provide ready to use, reproducible, and scalable tools for practical data analysis of noisy high-dimensional functional data.

3D multiwavelet based block coding algorithm for compression of volumetric medical images

ABSTRACTThree dimensional (3D) medical images possess some specific characteristics that should be utilized by an efficient compression scheme. In this article, one such compression scheme for volumetric 3D medical image data is presented. Two processes involved in this scheme are decorrelation and encoding. Decorrelation of the 3D data is realized through 3D multiwavelet transform with apt prefiltering so as to give good representation of the image which could be exploited by the encoder. Encoding is done through proposed Block Coding Algorithm, which is embedded, block based, and wavelet transform coding algorithm without maintaining any list structures. The idea behind this algorithm is to sort the 3D transform coefficients in to a 1D array with respect to declining thresholds and to use state table to keep track of the blocks and coefficients that has been coded. In the experiment conducted on various 3D magnetic resonance and computed tomography images of human brain with multiwavelets such as Geronimo–Hardin–Massopust, Chui‐Lian, and orthogonal symmetric/antisymmetric (SA4), efficiency of the proposed scheme was weighed against the state of art encoders such as 3D Set Partitioning in Hierarchical Trees, 2D Set Partitioned Embedded BloCK Coder, and No List SPIHT. Attributes used for performance measurements are peak signal to noise ratio, bit rate, and structural similarity index of reconstructed image with respect to original image. © 2014 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 24, 182–192, 2014