Medical Image Diagnosis Research Articles

Multi-Domain Neumann Network with Sensitivity Maps for Parallel MRI Reconstruction.

MRI is an imaging technology that non-invasively obtains high-quality medical images for diagnosis. However, MRI has the major disadvantage of long scan times which cause patient discomfort and image artifacts. As one of the methods for reducing the long scan time of MRI, the parallel MRI method for reconstructing a high-fidelity MR image from under-sampled multi-coil k-space data is widely used. In this study, we propose a method to reconstruct a high-fidelity MR image from under-sampled multi-coil k-space data using deep-learning. The proposed multi-domain Neumann network with sensitivity maps (MDNNSM) is based on the Neumann network and uses a forward model including coil sensitivity maps for parallel MRI reconstruction. The MDNNSM consists of three main structures: the CNN-based sensitivity reconstruction block estimates coil sensitivity maps from multi-coil under-sampled k-space data; the recursive MR image reconstruction block reconstructs the MR image; and the skip connection accumulates each output and produces the final result. Experiments using the fastMRI T1-weighted brain image dataset were conducted at acceleration factors of 2, 4, and 8. Qualitative and quantitative experimental results show that the proposed MDNNSM method reconstructs MR images more accurately than other methods, including the generalized autocalibrating partially parallel acquisitions (GRAPPA) method and the original Neumann network.

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.

Automatic Medical Image Diagnosis: Highlights from the 2021 IEEE 5-Minute Video Clip Contest [SP Competitions

The annual IEEE 5-Minute Video Clip Contest (5-MICC) was launched in 2020 by the IEEE Signal Processing Society (SPS), and the selected topic for the competition at IEEE ICIP 2021 was “Automatic Medical Image Diagnosis.” The organizing committee selected three finalist videos and placed them online for public voting. The first one addresses a deep learning system that targets enhancement and disease diagnostic in otoscopy images, the second concerns the use of neural networks for cancer detection in tissue scans, and the third deals with a deep learning tool for automatic COVID-19 diagnosis. Taking the public voting results from more than 1,300 participants into consideration, the panel of judges decided the final rankings of the three videos. This article presents an overview of this virtual edition of the 5-MICC at ICIP 2021, describing the competition setup, the teams, and their approaches.

Orchard Boumans Algorithm and MRF Approach Based on Full Threshold Segmentation for Dental X-Ray Images

Dental X-ray segmentation uses different image processing (IP) methods helpful in diagnosing medical applications, clinical purposes & in real-time. These methods aim to define the segmentation of various tooth structures in dental X-rays which are utilized to identify caries, tooth fractures, treatment of root canals, periodontal diseases, etc. The manual segmentation of Dental X-ray images for medical diagnosis is very complex and time-consuming from broad clinical databases. Orchard & Bouman is a color quantization approach used to evaluate a successful cluster division using an eigenvector of a color covariance matrix. It is repeated until the number of target clusters is reached. It is optimal for large clusters with Gaussian distributions to integrate different types of information on probabilism and spatial constraint by iteratively upgrading the later probability of the proposed model. Results of segmentation are achieved when iteration converges. Testing the proposed model's effectiveness will involve texture, distance sensing, and nature images. Experimental results show that our model achieves a higher segmentation precision with approximately 78.98 PSNR than MRF models based on pixels or regions.

AI to automate brain tumor classification using visual geometric group (VGG) 16

A brain is the most important part of our body, which authorize the center capacities which attributes inside actual body and predictable with the National mind tumor Society, around 700,000 individuals acknowledge a cerebrum tumor, and in this manner, the figure will ascend to 787,000 by the peak point of 2020. Clinical imaging for medical diagnosis of a variety of disorders has benefited from ongoing advancements in the field of deep understanding. Task CNN is the most common and widely used AI computation for visual learning and image identification. Essentially, we show the Convolutional Neural Network (CNN) strategy, together with Data Augmentation and Image Processing, to sort cerebrum MRI examination images into carcinogenic and non-harmful categories in our hypothesis. A programmable mind tumour layout based on deep learning-based Visual Geometric Group (VGG) 16 is shown in this study. The model (VGG-16) has a 96 percent and 96 percent accuracy for both training and testing photos respectively.

Technology Innovation: Detection of Counterfeit Region in an Image

With availability of advanced photo editing tools today, digital images can be tampered with malicious intention at ease. The image tampering can create various ill effects like false disease diagnosis of medical images, defaming people, hiding evidences, creating false claims etc. Since images are being increasingly used as the most creditable information for inferring various conclusion and judgments in many application scenarios, it is necessary to ensure the authenticity of the image and detect any counterfeit regions in the image. Nowadays tampering can be done in sophisticated manner without leaving any trace and it becomes difficult to detect with naked eye. In this work, we survey the state of art existing works on detection of counterfeit or tampered regions in the images. The survey is done to identify the challenges in existing counterfeit detection techniques.

Accuracy of Automated Computer-Aided Diagnosis for Stroke Imaging: A Critical Evaluation of Current Evidence.

There is increasing interest in computer applications, using artificial intelligence methodologies, to perform health care tasks previously performed by humans, particularly in medical imaging for diagnosis. In stroke, there are now commercial artificial intelligence software for use with computed tomography or MR imaging to identify acute ischemic brain tissue pathology, arterial obstruction on computed tomography angiography or as hyperattenuated arteries on computed tomography, brain hemorrhage, or size of perfusion defects. A rapid, accurate diagnosis may aid treatment decisions for individual patients and could improve outcome if it leads to effective and safe treatment; or conversely, to disaster if a delayed or incorrect diagnosis results in inappropriate treatment. Despite this potential clinical impact, diagnostic tools including artificial intelligence methods are not subjected to the same clinical evaluation standards as are mandatory for drugs. Here, we provide an evidence-based review of the pros and cons of commercially available automated methods for medical imaging diagnosis, including those based on artificial intelligence, to diagnose acute brain pathology on computed tomography or magnetic resonance imaging in patients with stroke.

A review of intelligent medical imaging diagnosis for the COVID-19 infection

Due to the unavailability of specific vaccines or drugs to treat COVID-19 infection, the world has witnessed a rise in the human mortality rate. Currently, real time RT-PCR technique is widely accepted to detect the presence of the virus, but it is time consuming and has a high rate of eliciting false positives/negatives results. This has opened research avenues to identify substitute strategies to diagnose the infection. Related works in this direction have shown promising results when RT-PCR diagnosis is complemented with Chest imaging results. Finally integrating intelligence and automating diagnostic systems can improve the speed and efficiency of the diagnosis process which is extremely essential in the present scenario. This paper reviews the use of CT scan, Chest X-ray, lung ultrasound images for COVID-19 diagnosis, discusses the automation of chest image analysis using machine learning and deep learning models, elucidates the achievements, challenges, and future directions in this domain.

Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression

Although for many diseases there is a progressive diagnosis scale, automatic analysis of grade-based medical images is quite often addressed as a binary classification problem, missing the finer distinction and intrinsic relation between the different possible stages or grades. Ordinal regression (or classification) considers the order of the values of the categorical labels and thus takes into account the order of grading scales used to assess the severity of different medical conditions. This paper presents a quantum-inspired deep probabilistic learning ordinal regression model for medical image diagnosis that takes advantage of the representational power of deep learning and the intrinsic ordinal information of disease stages. The method is evaluated on two different medical image analysis tasks: prostate cancer diagnosis and diabetic retinopathy grade estimation on eye fundus images. The experimental results show that the proposed method not only improves the diagnosis performance on the two tasks but also the interpretability of the results by quantifying the uncertainty of the predictions in comparison to conventional deep classification and regression architectures. The code and datasets are available at https://github.com/stoledoc/DQOR.

Medical Image Segmentation Algorithm for Three-Dimensional Multimodal Using Deep Reinforcement Learning and Big Data Analytics.

To avoid the problems of relative overlap and low signal-to-noise ratio (SNR) of segmented three-dimensional (3D) multimodal medical images, which limit the effect of medical image diagnosis, a 3D multimodal medical image segmentation algorithm using reinforcement learning and big data analytics is proposed. Bayesian maximum a posteriori estimation method and improved wavelet threshold function are used to design wavelet shrinkage algorithm to remove high-frequency signal component noise in wavelet domain. The low-frequency signal component is processed by bilateral filtering and the inverse wavelet transform is used to denoise the 3D multimodal medical image. An end-to-end DRD U-Net model based on deep reinforcement learning is constructed. The feature extraction capacity of denoised image segmentation is increased by changing the convolution layer in the traditional reinforcement learning model to the residual module and introducing the multiscale context feature extraction module. The 3D multimodal medical image segmentation is done using the reward and punishment mechanism in the deep learning reinforcement algorithm. In order to verify the effectiveness of 3D multimodal medical image segmentation algorithm, the LIDC-IDRI data set, the SCR data set, and the DeepLesion data set are selected as the experimental data set of this article. The results demonstrate that the algorithm's segmentation effect is effective. When the number of iterations is increased to 250, the structural similarity reaches 98%, the SNR is always maintained between 55 and 60 dB, the training loss is modest, relative overlap and accuracy all exceed 95%, and the overall segmentation performance is superior. Readers will understand how deep reinforcement learning and big data analytics test the effectiveness of 3D multimodal medical image segmentation algorithm.

Improving local SNR of a single-channel 54.6 mT MRI system using additional LC-resonator

Very-low field magnetic resonance imaging (VLF-MRI, B0 < 0.1T) has an essential application in medical imaging diagnosis because of its light weight and low cost. For single-channel RF coil VLF-MRI system, a planar spiral LC-resonator placed on the surface of samples was designed to improve the local SNR. First, an equivalent circuit model was established to evaluate the boosting effects on radiofrequency (RF) magnetic field and SNR. Second, the relationship between the resonant capacitance and the transmission coefficient was deduced according to the circuit model, and the appropriate resonant capacitance was obtained. Then, the influence of the diameter and the number of turns of the LC-resonator on the SNR is considered, and the structure of the LC-resonator was optimized to maximize the SNR. Finally, a phantom MRI experiment was carried out with our home-built 54.6 mT MRI system to compare the SNR of the experiment with the calculation, the SNR enhancement trend of the two was consistent. Additional experiments were conducted using orange and chicken leg to demonstrate the SNR enhancement abilities of the LC-resonator. The enhancement of SNR reached up to 1.8-fold and 2.2-fold depending on the distance between the sample and LC-resonator. For comparison, we conducted imaging experiments on surface receiving coil with the same parameters, and the results show that the SNR of the LC resonator is comparable to that of the surface coil. The reported LC-resonator provide a low-cost local enhancement method for VLF-MRI.

Detection and Classification of Brain Tumors From MRI Images Using a Deep Convolutional Neural Network Approach

Brain tumor is a severe cancer disease caused by uncontrollable and abnormal partitioning of cells. Timely disease detection and treatment plans lead to the increased life expectancy of patients. Automated detection and classification of brain tumor are a more challenging process which is based on the clinician’s knowledge and experience. For this fact, one of the most practical and important techniques is to use deep learning. Recent progress in the fields of deep learning has helped the clinician’s in medical imaging for medical diagnosis of brain tumor. In this paper, we present a comparison of Deep Convolutional Neural Network models for automatically binary classification query MRI images dataset with the goal of taking precision tools to health professionals based on fined recent versions of DenseNet, Xception, NASNet-A, and VGGNet. The experiments were conducted using an MRI open dataset of 3,762 images. Other performance measures used in the study are the area under precision, recall, and specificity.

Faster-RCNN based intelligent detection and localization of dental caries

The use of AI (artificial intelligence) for auxiliary diagnosis of medical images is a current development trend, where the automatic recognition of lesion location is a key problem in AI-assisted diagnosis of medical images. In the past, most of the studies on AI-assisted diagnosis of dental caries based on X-ray image primarily focused on the classification of abnormalities rather than the detection and localization of dental caries, which is not conducive to expanding the clinical application of this technique. Accordingly, in this work, an AI-assisted diagnosis method is developed that employs Faster-RCNN to predict the number and locations of caries lesions based on periapical films. To support the application of this diagnosis method, an open Web platform for detection of dental caries is constructed in the following way: First, clinical samples acquired by professional doctors are collected and labeled to build the sample space and label space. Then, a caries detection model is built through training and testing on samples. Finally, the contents of Web platform are set up, the layout is configured through HTML/CSS programming, and the model is deployed on Alibaba cloud server using the Flask framework. After the diagnosis platform is put into operation, doctors and patients can upload the medical images to be tested onto the website of platform, where test results can be obtained. These test results can help doctors diagnose the diseases with higher efficiency and precision.

Removal of Specular Reflection Using Angle Adjustment of Linear Polarized Filter in Medical Imaging Diagnosis.

The biggest problem in imaging medicine is the occurrence of light reflection in the imaging process for lesion diagnosis. The formation of light reflection obscures the diagnostic field of the lesion and interferes with the correct diagnosis of the observer. The existing method has the inconvenience of performing a diagnosis in a state in which light reflection is suppressed by adjusting the direction angle of the camera. This paper proposes a method for rotating a linear polarization filter to remove light reflection in a diagnostic imaging camera. Vertical polarization and horizontal polarization are controlled through the rotation of the filter, and the polarization is adjusted to horizontal polarization. The rotation angle of the filter for horizontal polarization control will be 90°, and the vertical and horizontal polarization waves induce a 90° difference from each other. In this study, light reflection can be effectively removed during the imaging process, and light reflection removal can secure the field of view of the lesion. The removal of light reflection can help the observer’s accurate diagnosis, and these results are expected to be highly reliable and commercialized for direct application in the field of diagnostic medicine.

Effective of Modern Techniques on Content-Based Medical Image Retrieval: A Survey

The advancement in medical imaging has resulted in a rapid and large increase in medical images inside repositories. These medical images contain very important information that can be used in many things, including diagnosing diseases. This implies that a precise, efficient way of indexing and retrieving biomedical images is necessary to obtain medical images from such repositories in real-time. CBMIR, therefore, played an important part, where the CBMIR’s area is very important in the field of image processing and involves low-level feature extraction and similarity measures for the comparison of medical images such as color histograms, edges, texture, shape. The majority of the methods already in use in CBMIR enhance the retrieval of a medical image and diseases diagnosis by reducing the issue of the semantic gap between low visual and high semantic levels. Also, secure access to the medical image of diverse cases, which are often kept on a network and are susceptible to malicious attacks is considered an important target for all medical practitioners. So, most CBMIRs try to cover this target for the purpose of privacy preservation. So, in this survey, the most advanced (CBMIR) frameworks that were used to reduce the issue of semantic gaps, high dimensionality feature maps were covered, disease diagnosis, and medical image security. Furthermore, the different publicly and standard databases used in measuring the performance of these frameworks also were covered.

BreastScreening-AI: Evaluating medical intelligent agents for human-AI interactions

In this paper, we developed BreastScreening-AI within two scenarios for the classification of multimodal beast images: (1) Clinician-Only; and (2) Clinician-AI. The novelty relies on the introduction of a deep learning method into a real clinical workflow for medical imaging diagnosis. We attempt to address three high-level goals in the two above scenarios. Concretely, how clinicians: i) accept and interact with these systems, revealing whether are explanations and functionalities required; ii) are receptive to the introduction of AI-assisted systems, by providing benefits from mitigating the clinical error; and iii) are affected by the AI assistance. We conduct an extensive evaluation embracing the following experimental stages: (a) patient selection with different severities, (b) qualitative and quantitative analysis for the chosen patients under the two different scenarios. We address the high-level goals through a real-world case study of 45 clinicians from nine institutions. We compare the diagnostic and observe the superiority of the Clinician-AI scenario, as we obtained a decrease of 27% for False-Positives and 4% for False-Negatives. Through an extensive experimental study, we conclude that the proposed design techniques positively impact the expectations and perceptive satisfaction of 91% clinicians, while decreasing the time-to-diagnose by 3 min per patient.

Medical image diagnosis of prostate tumor based on PSP-Net+VGG16 deep learning network

Background and objectiveProstate cancer is the most common cancer of the male reproductive system. With the development of medical imaging technology, magnetic resonance images (MRI) have been used in the diagnosis and treatment of prostate cancer because of its clarity and non-invasiveness. Prostate MRI segmentation and diagnosis experience problems such as low tissue boundary contrast. The traditional segmentation method of manually drawing the contour boundary of the tissue cannot meet the clinical real-time requirements. How to quickly and accurately segment the prostate tumor has become an important research topic. MethodsThis paper proposes a prostate tumor diagnosis based on the deep learning network PSP-Net+VGG16. The deep convolutional neural network segmentation method based on the PSP-Net constructs a atrous convolution residual structure model extraction network. First, the three-dimensional prostate MRI is converted to two-dimensional image slices, and then the slice input of the two-dimensional image is trained based on the PSP-Net neural network; and the VGG16 network is used to analyze the region of interest and classify prostate cancer and normal prostate. ResultsAccording to the experimental results, the segmentation method based on the deep learning network PSP-Net is used to identify the data set samples. The segmentation accuracy is close to the Dice similarity coefficient and Hausdorff distance, and even exceeds the traditional prostate image segmentation method. The Dice index reached 91.3%, and the technique is superior in speed of processing. The predicted tumor markers are very close to the actual markers manually by clinicians; the classification accuracy and recognition rates of prostate MRI based on VGG16 are as high as 87.95% and 87.33%, and the accuracy rate and recall rate of the network model are relatively balanced. The area under curve index is also higher than other models, with good generalization ability. ConclusionExperiments show that prostate cancer diagnosis based on the deep learning network PSP-Net+VGG16 is superior in accuracy and processing time compared to other algorithms, and can be well applied to clinical prostate tumor diagnosis.

A coronary artery CTA segmentation approach based on deep learning.

Presence of plaque and coronary artery stenosis are the main causes of coronary heart disease. Detection of plaque and coronary artery segmentation have become the first choice in detecting coronary artery disease. The purpose of this study is to investigate a new method for plaque detection and automatic segmentation and diagnosis of coronary arteries and to test its feasibility of applying to clinical medical image diagnosis. A multi-model fusion coronary CT angiography (CTA) vessel segmentation method is proposed based on deep learning. The method includes three network layer models namely, an original 3-dimensional full convolutional network (3D FCN) and two networks that embed the attention gating (AG) model in the original 3D FCN. Then, the prediction results of the three networks are merged by using the majority voting algorithm and thus the final prediction result of the networks is obtained. In the post-processing stage, the level set function is used to further iteratively optimize the results of network fusion prediction. The JI (Jaccard index) and DSC (Dice similarity coefficient) scores are calculated to evaluate accuracy of blood vessel segmentations. Applying to a CTA dataset of 20 patients, accuracy of coronary blood vessel segmentation using FCN, FCN-AG1, FCN-AG2 network and the fusion method are tested. The average values of JI and DSC of using the first three networks are (0.7962, 0.8843), (0.8154, 0.8966) and (0.8119, 0.8936), respectively. When using new fusion method, average JI and DSC of segmentation results increase to (0.8214, 0.9005), which are better than the best result of using FCN, FCN-AG1 and FCN-AG2 model independently.

Medical image super‐resolution using correlation filter interleaved progressive convolution network (CFIPC)

In medical image diagnosis, performance is affected because of degradation in image resolution, imaging equipment and imaging parameters. Currently, deep learning has gained much attention from researchers due to its capability to maintain perceptual quality after reconstruction. Therefore, this letter is motivated by the advantages of deep learning and proposes a novel model termed as the correlation filter interleaved progressive convolution network (CFIPC). In this letter, dilated convolution interleaved with a correlation filter expands the receptive field without any pixel information losses. The result analysis was performed on DRIVE, CHASEB1, MRI, ultrasound and histopathological dataset medical datasets at 2x/4x/8x/16x upscaling factors and achieved the highest PSNR/SSIM value of 50.54/0.9986 at a 2x upscaling factor on the histopathological dataset.

Generative Adversarial Networks in Medical Image augmentation: A review

ObjectWith the development of deep learning, the number of training samples for medical image-based diagnosis and treatment models is increasing. Generative Adversarial Networks (GANs) have attracted attention in medical image processing due to their excellent image generation capabilities and have been widely used in data augmentation. In this paper, a comprehensive and systematic review and analysis of medical image augmentation work are carried out, and its research status and development prospects are reviewed. MethodThis paper reviews 105 medical image augmentation related papers, which mainly collected by ELSEVIER, IEEE Xplore, and Springer from 2018 to 2021. We counted these papers according to the parts of the organs corresponding to the images, and sorted out the medical image datasets that appeared in them, the loss function in model training, and the quantitative evaluation metrics of image augmentation. At the same time, we briefly introduce the literature collected in three journals and three conferences that have received attention in medical image processing. ResultFirst, we summarize the advantages of various augmentation models, loss functions, and evaluation metrics. Researchers can use this information as a reference when designing augmentation tasks. Second, we explore the relationship between augmented models and the amount of the training set, and tease out the role that augmented models may play when the quality of the training set is limited. Third, the statistical number of papers shows that the development momentum of this research field remains strong. Furthermore, we discuss the existing limitations of this type of model and suggest possible research directions. ConclusionWe discuss GAN-based medical image augmentation work in detail. This method effectively alleviates the challenge of limited training samples for medical image diagnosis and treatment models. It is hoped that this review will benefit researchers interested in this field.