Medical Image Diagnosis Research Articles

Privacy-Preserving Convolutional Bi-LSTM Network for Robust Analysis of Encrypted Time-Series Medical Images

Deep learning (DL) algorithms can improve healthcare applications. DL has improved medical imaging diagnosis, therapy, and illness management. The use of deep learning algorithms on sensitive medical images presents privacy and data security problems. Improving medical imaging while protecting patient anonymity is difficult. Thus, privacy-preserving approaches for deep learning model training and inference are gaining popularity. These picture sequences are analyzed using state-of-the-art computer aided detection/diagnosis techniques (CAD). Algorithms that upload medical photos to servers pose privacy issues. This article presents a convolutional Bi-LSTM network to assess completely homomorphic-encrypted (HE) time-series medical images. From secret image sequences, convolutional blocks learn to extract selective spatial features and Bi-LSTM-based analytical sequence layers learn to encode time data. A weighted unit and sequence voting layer uses geographical with varying weights to boost efficiency and reduce incorrect diagnoses. Two rigid benchmarks—the CheXpert, and the BreaKHis public datasets—illustrate the framework’s efficacy. The technique outperforms numerous rival methods with an accuracy above 0.99 for both datasets. These results demonstrate that the proposed outline can extract visual representations and sequential dynamics from encrypted medical picture sequences, protecting privacy while attaining good medical image analysis performance.

Automatic intracranial abnormality detection and localization in head CT scans by learning from free-text reports

Deep learning has yielded promising results for medical image diagnosis but relies heavily on manual image annotations, which are expensive to acquire. We present Cross-DL, a cross-modality learning framework for intracranial abnormality detection and localization in head computed tomography (CT) scans by learning from free-text imaging reports. Cross-DL has a discretizer that automatically extracts discrete labels of abnormality types and locations from reports, which are utilized to train an image analyzer by a dynamic multi-instance learning approach. Benefiting from the low annotation cost and a consequent large-scale training set of 28,472 CT scans, Cross-DL achieves accurate performance, with an average area under the receiver operating characteristic curve (AUROC) of 0.956 (95% confidence interval: 0.952-0.959) in detecting 4 abnormality types in 17 regions while accurately localizing abnormalities at the voxel level. An intracranial hemorrhage classification experiment on the external dataset CQ500 achieves an AUROC of 0.928 (0.905-0.951). The model can also help review prioritization.

Medical image retrieval via nearest neighbor search on pre-trained image features

Nearest neighbor search, also known as NNS, is a technique used to locate the points in a high-dimensional space closest to a given query point. This technique has multiple applications in medicine, such as searching large medical imaging databases, disease classification, and diagnosis. However, when the number of points is significantly large, the brute-force approach for finding the nearest neighbor becomes computationally infeasible. Therefore, various approaches have been developed to make the search faster and more efficient to support the applications. With a focus on medical imaging, this paper proposes DenseLinkSearch (DLS), an effective and efficient algorithm that searches and retrieves the relevant images from heterogeneous sources of medical images. Towards this, given a medical database, the proposed algorithm builds an index that consists of pre-computed links of each point in the database. The search algorithm utilizes the index to efficiently traverse the database in search of the nearest neighbor. We also explore the role of medical image feature representation in content-based medical image retrieval tasks. We propose a Transformer-based feature representation technique that outperformed the existing pre-trained Transformer-based approaches on benchmark medical image retrieval datasets. We extensively tested the proposed NNS approach and compared the performance with state-of-the-art NNS approaches on benchmark datasets and our created medical image datasets. The proposed approach outperformed the existing approaches in terms of retrieving accurate neighbors and retrieval speed. In comparison to the existing approximate NNS approaches, our proposed DLS approach outperformed them in terms of lower average time per query and ≥99% R@10 on 11 out of 13 benchmark datasets. We also found that the proposed medical feature representation approach is better for representing medical images compared to the existing pre-trained image models. The proposed feature extraction strategy obtained an improvement of 9.37%, 7.0%, and 13.33% in terms of P@5, P@10, and P@20, respectively, in comparison to the best-performing pre-trained image model. The source code and datasets of our experiments are available at https://github.com/deepaknlp/DLS.

Adversarial Attack and Defense in Breast Cancer Deep Learning Systems.

Deep-learning-assisted medical diagnosis has brought revolutionary innovations to medicine. Breast cancer is a great threat to women's health, and deep-learning-assisted diagnosis of breast cancer pathology images can save manpower and improve diagnostic accuracy. However, researchers have found that deep learning systems based on natural images are vulnerable to attacks that can lead to errors in recognition and classification, raising security concerns about deep systems based on medical images. We used the adversarial attack algorithm FGSM to reveal that breast cancer deep learning systems are vulnerable to attacks and thus misclassify breast cancer pathology images. To address this problem, we built a deep learning system for breast cancer pathology image recognition with better defense performance. Accurate diagnosis of medical images is related to the health status of patients. Therefore, it is very important and meaningful to improve the security and reliability of medical deep learning systems before they are actually deployed.

Spatial attention-based residual network for human burn identification and classification

Diagnosing burns in humans has become critical, as early identification can save lives. The manual process of burn diagnosis is time-consuming and complex, even for experienced doctors. Machine learning (ML) and deep convolutional neural network (CNN) models have emerged as the standard for medical image diagnosis. The ML-based approach typically requires handcrafted features for training, which may result in suboptimal performance. Conversely, DL-based methods automatically extract features, but designing a robust model is challenging. Additionally, shallow DL methods lack long-range feature dependency, decreasing efficiency in various applications. We implemented several deep CNN models, ResNeXt, VGG16, and AlexNet, for human burn diagnosis. The results obtained from these models were found to be less reliable since shallow deep CNN models need improved attention modules to preserve the feature dependencies. Therefore, in the proposed study, the feature map is divided into several categories, and the channel dependencies between any two channel mappings within a given class are highlighted. A spatial attention map is built by considering the links between features and their locations. Our attention-based model BuRnGANeXt50 kernel and convolutional layers are also optimized for human burn diagnosis. The earlier study classified the burn based on depth of graft and non-graft. We first classified the burn based on the degree. Subsequently, it is classified into graft and non-graft. Furthermore, the proposed model performance is evaluated on Burns_BIP_US_database. The sensitivity of the BuRnGANeXt50 is 97.22% and 99.14%, respectively, for classifying burns based on degree and depth. This model may be used for quick screening of burn patients and can be executed in the cloud or on a local machine. The code of the proposed method can be accessed at https://github.com/dhirujis02/Journal.git for the sake of reproducibility.

Classification of Medical Image Notes for Image Labeling by Using MinBERT

The lack of labeled image data poses a serious challenge to the application of artificial intelligence (AI) in medical image diagnosis. Medical image notes contain valuable patient information that could be used to label images for machine learning tasks. However, most image note texts are unstructured with heterogeneity and short-paragraph characters, which fail traditional keyword-based techniques. We utilized a deep learning approach to recover missing labels for medical image notes automatically by using a combination of deep word embedding and deep neural network classifiers. Bidirectional encoder representations from transformers trained on medical image notes corpus (MinBERT) were proposed. We applied the proposed techniques to two typical classification tasks: Medical image type identification and clinical diagnosis identification. The two methods significantly outperformed baseline methods and presented high accuracies of 99.56% and 99.72% in image type identification and of 94.56% and 92.45% in clinical diagnosis identification. Visualization analysis further indicated that word embedding could efficiently capture semantic similarities and regularities across diverse expressions. Results indicated that our proposed framework could accurately recover the missing label information of medical images through the automatic extraction of electronic medical record information. Hence, it could serve as a powerful tool for exploring useful training data in various medical AI applications.

Neuromorphic applications in medicine.

In recent years, there has been a growing demand for miniaturization, low power consumption, quick treatments, and non-invasive clinical strategies in the healthcare industry. To meet these demands, healthcare professionals are seeking new technological paradigms that can improve diagnostic accuracy while ensuring patient compliance. Neuromorphic engineering, which uses neural models in hardware and software to replicate brain-like behaviors, can help usher in a new era of medicine by delivering low power, low latency, small footprint, and high bandwidth solutions. This paper provides an overview of recent neuromorphic advancements in medicine, including medical imaging and cancer diagnosis, processing of biosignals for diagnosis, and biomedical interfaces, such as motor, cognitive, and perception prostheses. For each section, we provide examples of how brain-inspired models can successfully compete with conventional artificial intelligence algorithms, demonstrating the potential of neuromorphic engineering to meet demands and improve patient outcomes. Lastly, we discuss current struggles in fitting neuromorphic hardware with non-neuromorphic technologies and propose potential solutions for future bottlenecks in hardware compatibility.

A multi-scale 3-stacked-layer coned U-net framework for tumor segmentation in whole slide images

The contribution of deep learning in medical image diagnosis has gained extensive interest due to its excellent performance. Furthermore, the interest has also grown in digital pathology since it is considered the golden standard for tumor detection and diagnosis in digital Whole Slide Images (WSIs). This paper proposes an end-to-end cone-shaped encoder-decoder framework called a Multi-scale 3-stacked-Layer coned U-Net (Ms3LcU-Net) framework. It boosts performance by using many enhancements and integrating techniques such as blended mutual attention, dilated fusion, edge enhancement, and atrous pooling. Furthermore, the morphological post-processing and test time augmentation techniques are used in Ms3LcU-Net to refine and smooth the generated segmentations. The experimental results from a quantitative perspective using multiple evaluation metrics and from a qualitative viewpoint by visualizing the generated segmentation predictions conducted on the public PAIP 2019 and DigestPath datasets demonstrated the effectiveness and competitiveness of the proposed model for tumor segmentation in WSIs. The proposed framework yielded an average clipped Jaccard Index value of 0.7211 on the validation set of the PAIP 2019 dataset. In contrast, the DigestPath dataset achieved an average dice coefficient and F1-score of 0.833 and 0.897, respectively. The code will be available publicly upon acceptance of the paper at https://github.com/Heba-AbdeNabi/Ms3LcU-Net-.

A Proposed Deep-Learning-Based Framework for Medical Image Communication, Storage and Diagnosis

A Proposed Deep-Learning-Based Framework for Medical Image Communication, Storage and Diagnosis

Reconstruction and completion of high-resolution 3D cardiac shapes using anisotropic CMRI segmentations and continuous implicit neural representations

Since the onset of computer-aided diagnosis in medical imaging, voxel-based segmentation has emerged as the primary methodology for automatic analysis of left ventricle (LV) function and morphology in cardiac magnetic resonance images (CMRI). In standard clinical practice, simultaneous multi-slice 2D cine short-axis MR imaging is performed under multiple breath-holds resulting in highly anisotropic 3D images. Furthermore, sparse-view CMRI often lacks whole heart coverage caused by large slice thickness and often suffers from inter-slice misalignment induced by respiratory motion. Therefore, these volumes only provide limited information about the true 3D cardiac anatomy which may hamper highly accurate assessment of functional and anatomical abnormalities. To address this, we propose a method that learns a continuous implicit function representing 3D LV shapes by training an auto-decoder. For training, high-resolution segmentations from cardiac CT angiography are used. The ability of our approach to reconstruct and complete high-resolution shapes from manually or automatically obtained sparse-view cardiac shape information is evaluated by using paired high- and low-resolution CMRI LV segmentations. The results show that the reconstructed LV shapes have an unconstrained subvoxel resolution and appear smooth and plausible in through-plane direction. Furthermore, Bland-Altman analysis reveals that reconstructed high-resolution ventricle volumes are closer to the corresponding reference volumes than reference low-resolution volumes with bias of [limits of agreement] −3.51 [−18.87, 11.85] mL, and 12.96 [−10.01, 35.92] mL respectively. Finally, the results demonstrate that the proposed approach allows recovering missing shape information and can indirectly correct for limited motion-induced artifacts.

ChatGPT in Radiology: The Advantages and Limitations of Artificial Intelligence for Medical Imaging Diagnosis.

This review article provides an overview of using artificial intelligence (AI) in radiology. It discusses the advantages and limitations of ChatGPT, a large language model, for medical imaging diagnosis. ChatGPT has shown great promise in improving the accuracy and efficiency of radiological diagnoses by reducing interpretation variability and errors and improving workflow efficiency. However, there are also limitations, including the need for high-quality training data, ethical considerations, and further research and development to improve its performance and usability. Despite these challenges, ChatGPT has the potential to significantly impact radiology and medical imaging diagnosis. The review article highlights the need for continued research and development, coupled with ethical and regulatory considerations, to ensure that ChatGPT is used to its full potential in improving radiological diagnoses and patient care.

Revolutionizing pediatric neuroimaging: the era of CT, MRI, and beyond.

To review the evolution of cross-sectional imaging in pediatric neuroradiology from early developments to current advancements and future directions. Information was obtained through a PubMed literature search as well as referenced online resources and personal experience from radiologists currently practicing pediatric neuroimaging and those who experienced the era of nascent cross-sectional imaging. The advent of computed tomography (CT) and magnetic resonance imaging (MRI) in the 1970s and 1980s brought about a revolutionary shift in the field of medical imaging, neurosurgical and neurological diagnosis. These cross-sectional imaging techniques ushered in a new era by enabling the visualization of soft tissue structures within the brain and spine. Advancements in these imaging modalities have continued at a remarkable pace, now providing not only high high-resolution and 3-dimensional anatomical imaging, but also functional assessment. With each stride forward, CT and MRI have provided clinicians with invaluable insights, improving the accuracy and precision of diagnoses, facilitating the identification of optimal surgical targets, and guiding the selection of appropriate treatment strategies. This article traces the origins and early developments of CT and MRI, chronicling their journey from pioneering technologies to their current indispensable status in clinical applications and exciting possibilities that lie ahead in the realm of medical imaging and neurologic diagnosis.

The Detection of COVID-19 in Chest X-rays Using Ensemble CNN Techniques

Advances in the field of image classification using convolutional neural networks (CNNs) have greatly improved the accuracy of medical image diagnosis by radiologists. Numerous research groups have applied CNN methods to diagnose respiratory illnesses from chest X-rays and have extended this work to prove the feasibility of rapidly diagnosing COVID-19 with high degrees of accuracy. One issue in previous research has been the use of datasets containing only a few hundred images of chest X-rays containing COVID-19, causing CNNs to overfit the image data. This leads to lower accuracy when the model attempts to classify new images, as would be clinically expected. In this work, we present a model trained on the COVID-QU-Ex dataset containing 33,920 chest X-ray images, with an equal share of COVID-19, Non-COVID pneumonia, and Normal images. The model is an ensemble of pre-trained CNNs (ResNet50, VGG19, and VGG16) and GLCM textural features. The model achieved a 98.34% binary classification accuracy (COVID-19/no COVID-19) on a test dataset of 6581 chest X-rays and 94.68% for distinguishing between COVID-19, Non-COVID pneumonia, and normal chest X-rays. The results also demonstrate that a higher 98.82% three-class test accuracy can be achieved using the model if the training dataset only contains a few thousand images. However, the generalizability of the model suffers due to the smaller dataset size. This study highlights the benefits of both ensemble CNN techniques and larger dataset sizes for medical image classification performance.

Widespread presentation of brown tumors mimicking multiple myeloma

Brown tumors or osteitis fibrosa cystica has become a rare presentation of primary hyperparathyroidism in up-to-date clinical practice. Here, we describe a case of longstanding untreated hyperparathyroidism presenting itself with brown tumors in a 65-year-old patient. During the diagnostic work-up of this patient, bone SPECT/CT and 18F-FDG-PET/CT revealed multiple widespread osteolytic lesions. Differentiating from other bone tumors such as multiple myeloma is challenging. In this case, the final diagnosis was made by integrating the medical history, biochemical diagnosis of primary hyperparathyroidism, pathological findings and medical imaging.

Artificial Intelligence in Human Medicine

This editorial reflects on the emergence of artificial intelligence and how it is applied in the field of health. AI is a technology that mimics the functioning of the human brain and uses algorithms, machine learning, pattern recognition and cognitive computing to process large amounts of data and extract useful insights. AI can improve health and well-being of people in various areas of medicine, such as medical image analysis, diagnosis, treatment, genetics, pregnancy and smart prosthetics. These applications can help medical professionals make better clinical decisions, accelerate research and development of new drugs, personalize patient care and reduce costs and human errors. AI can also empower users to access relevant information about their health and actively participate in their care. However, AI also poses ethical, legal and social challenges that must be addressed with responsibility and transparency.

2D Perovskite Mn2+ -Doped Cs2 CdBr2 Cl2 Scintillator for Low-Dose High-Resolution X-ray Imaging.

High-performance X-ray scintillators with low detection limits and high light yield are of great importance and are a challenge for low-dose X-ray imaging in medical diagnosis and industrial detection. In this work, the synthesis of a new 2D perovskite, Cs2 CdBr2 Cl2 , via hydrothermal reaction is reported. By doping Mn2+ into the perovskite, a yellow emission located at 593nm is obtained, and the photoluminescence quantum yield (PLQY) of Cs2 CdBr2 Cl2 :5%Mn2+ perovskite reaches the highest value of 98.52%. The near-unity PLQY and negligible self-absorption of Cs2 CdBr2 Cl2 :5%Mn2+ enable excellent X-ray scintillation performance with a high light yield of 64 950 photons MeV-1 and low detection limit of 17.82 nGyair s-1 . Moreover, combining Cs2 CdBr2 Cl2 :5%Mn2+ with poly(dimethylsiloxane) to fabricate a flexible scintillator screen achieves low-dose X-ray imaging with a high resolution of 12.3 line pairs (lp) mm-1 . The results suggest that Cs2 CdBr2 Cl2 :5%Mn2+ is a promising candidate for low-dose and high-resolution X-ray imaging. The study presents a new approach to designing high-performance scintillators through metal-ion doping.

Generation of Musculoskeletal Ultrasound Images with Diffusion Models

The recent advances in deep learning have revolutionised computer-aided diagnosis in medical imaging. However, deep learning approaches to unveil their full potential require significant amounts of data, which can be a challenging task in some scientific fields, such as musculoskeletal ultrasound imaging, in which data privacy and security reasons can lead to important limitations in the acquisition and the distribution process of patients’ data. For this reason, different generative methods have been introduced to significantly reduce the required amount of real data by generating synthetic images, almost indistinguishable from the real ones. In this study, the power of the diffusion models is incorporated for the generation of realistic data from a small set of musculoskeletal ultrasound images in four different muscles. Afterwards, the similarity of the generated and real images is assessed with different types of qualitative and quantitative metrics that correspond well with human judgement. In particular, the histograms of pixel intensities of the two sets of images have demonstrated that the two distributions are statistically similar. Additionally, the well-established LPIPS, SSIM, FID, and PSNR metrics have been used to quantify the similarity of these sets of images. The two sets of images have achieved extremely high similarity scores in all these metrics. Subsequently, high-level features are extracted from the two types of images and visualized in a two-dimensional space for inspection of their structure and to identify patterns. From this representation, the two sets of images are hard to distinguish. Finally, we perform a series of experiments to assess the impact of the generated data for training a highly efficient Attention-UNet for the important clinical application of muscle thickness measurement. Our results depict that the synthetic data play a significant role in the model’s final performance and can lead to the improvement of the deep learning systems in musculoskeletal ultrasound.

Secure Convolution Neural Network Inference Based on Homomorphic Encryption

Today, the rapid development of deep learning has spread across all walks of life, and it can be seen in various fields such as image classification, automatic driving, and medical imaging diagnosis. Convolution Neural Networks (CNNs) are also widely used by the public as tools for deep learning. In real life, if local customers implement large-scale model inference first, they need to upload local data to the cloud, which will cause problems such as data leakage and privacy disclosure. To solve this problem, we propose a framework using homomorphic encryption technology. Our framework has made improvements to the batch operation and reduced the complexity of layer connection. In addition, we provide a new perspective to deal with the impact of the noise caused by the homomorphic encryption scheme on the accuracy during the inference. In our scheme, users preprocess the images locally and then send them to the cloud for encrypted inference without worrying about privacy leakage during the inference process. Experiments show that our proposed scheme is safe and efficient, which provides a safe solution for users who cannot process data locally.

A four-wall virtual reality visualization of patient-specific anatomy: Creating full user immersive experience from computed tomography scans

Virtual reality is the future of medical imaging diagnosis. Previous studies have introduced virtual reality rendering of anatomical models while others have mentioned processes to extract 3D models from Computed Tomography (CT) images. In this study, we provide a detailed workflow to transforming patient-specific two-dimensional (2D) CT dicom format imaging files to three-dimensional (3D) immersive, dynamic and interactive anatomical assembly models while incorporating them into a four-wall virtual reality environment system. Our study implemented 3D CAD and virtual reality capacities through software and engineering design tools to transform 2D medical images into interactive 3D models in our system. In doing so, the user was able to gain a sense of depth, scale, and dimensionality while immersed in the environment and while implementing interactive tools to investigate patient- specific hip-femur dynamics. At the same time, users were able to identify key anatomical landmarks in the patients’ hip joints. Applications of the VR system to the medical field and orthopedics, in particular, were discussed.

CTMLP: Can MLPs replace CNNs or transformers for COVID-19 diagnosis?

BackgroundConvolutional Neural Networks (CNNs) and the hybrid models of CNNs and Vision Transformers (VITs) are the recent mainstream methods for COVID-19 medical image diagnosis. However, pure CNNs lack global modeling ability, and the hybrid models of CNNs and VITs have problems such as large parameters and computational complexity. These models are difficult to be used effectively for medical diagnosis in just-in-time applications. MethodsTherefore, a lightweight medical diagnosis network CTMLP based on convolutions and multi-layer perceptrons (MLPs) is proposed for the diagnosis of COVID-19. The previous self-supervised algorithms are based on CNNs and VITs, and the effectiveness of such algorithms for MLPs is not yet known. At the same time, due to the lack of ImageNet-scale datasets in the medical image domain for model pre-training. So, a pre-training scheme TL-DeCo based on transfer learning and self-supervised learning was constructed. In addition, TL-DeCo is too tedious and resource-consuming to build a new model each time. Therefore, a guided self-supervised pre-training scheme was constructed for the new lightweight model pre-training. ResultsThe proposed CTMLP achieves an accuracy of 97.51%, an f1-score of 97.43%, and a recall of 98.91% without pre-training, even with only 48% of the number of ResNet50 parameters. Furthermore, the proposed guided self-supervised learning scheme can improve the baseline of simple self-supervised learning by 1%–1.27%. ConclusionThe final results show that the proposed CTMLP can replace CNNs or Transformers for a more efficient diagnosis of COVID-19. In addition, the additional pre-training framework was developed to make it more promising in clinical practice.