Image Volume Research Articles

Performing Automated, High-Speed Photometry on Occulting, Small Outer Solar System Bodies

Monitoring stellar occultations provides a powerful means to measure the shapes and sizes of small Solar System bodies, but produces large quantities of image data which can be laborious to analyse. An automated Python-based software, occ_find, was written for performing high-speed aperture photometry on spool files packed with large volumes of images from the 1.54m Danish Telescope. occ_find processed 11 spool files at a maximum rate of around 4–6 minutes per spool file, without image reduction. From these files, 3 occultation events were detected. The measured chord lengths are consistent with prior size measurements of these small bodies.

Gossamer: Scaling Image Processing and Reconstruction to Whole Brains.

Neuronal reconstruction-a process that transforms image volumes into 3D geometries and skeletons of cells- bottlenecks the study of brain function, connectomics and pathology. Domain scientists need exact and complete segmentations to study subtle topological differences. Existing methods are diskbound, dense-access, coupled, single-threaded, algorithmically unscalable and require manual cropping of small windows and proofreading of skeletons due to low topological accuracy. Designing a data-intensive parallel solution suited to a neurons' shape, topology and far-ranging connectivity is particularly challenging due to I/O and load-balance, yet by abstracting these vision tasks into strategically ordered specializations of search, we progressively lower memory by 4 orders of magnitude. This enables 1 mouse brain to be fully processed in-memory on a single server, at 67× the scale with 870× less memory while having 78% higher automated yield than APP2, the previous state of the art in performant reconstruction.

RhIL-7-hyFc, a long-acting interleukin-7, improves efficacy of CAR-T cell therapy in solid tumors

BackgroundChimeric antigen receptor T-cell (CAR-T) therapy has achieved remarkable remission in patients with B-cell malignancies. However, its efficacy in treating solid tumors remains limited. Here, we investigated a combination therapy...

Spectrum of Cognitive Biases in Diagnostic Radiology.

Cognitive biases are systematic thought processes involving the use of a filter of personal experiences and preferences arising from the tendency of the human brain to simplify information processing, especially when taking in vast amounts of data such as from imaging studies. These biases encompass a wide spectrum of thought processes and frequently overlap in their concepts, with multiple biases usually in operation when interpretive and perceptual errors occur in radiology. The authors review the gamut of cognitive biases that occur in radiology. These biases are organized according to their expected stage of occurrence while the radiologist reads and interprets an imaging study. In addition, the authors propose several additional cognitive biases that have not yet, to their knowledge, been defined in the radiologic literature but are applicable to diagnostic radiology. Case examples are used to illustrate potential biases and their impact, with emergency radiology serving as the clinical paradigm, given the associated high imaging volumes, wide diversity of imaging examinations, and rapid pace, which can further increase a radiologist's reliance on biases and heuristics. Potential strategies to recognize and overcome one's personal biases at each stage of image interpretation are also discussed. Awareness of such biases and their unintended effects on imaging interpretations and patient outcomes may help make radiologists cognizant of their own biases that can result in diagnostic errors. Identification of cognitive bias in departmental and systematic quality improvement practices may represent another tool to prevent diagnostic errors in radiology. ©RSNA, 2024 See the invited commentary by Larson in this issue.

Multidimensional Analysis of the Adult Human Heart in Health and Disease Using Hierarchical Phase-Contrast Tomography.

Background Current clinical imaging modalities such as CT and MRI provide resolution adequate to diagnose cardiovascular diseases but cannot depict detailed structural features in the heart across length scales. Hierarchical phase-contrast tomography (HiP-CT) uses fourth-generation synchrotron sources with improved x-ray brilliance and high energies to provide micron-resolution imaging of intact adult organs with unprecedented detail. Purpose To evaluate the capability of HiP-CT to depict the macro- to microanatomy of structurally normal and abnormal adult human hearts ex vivo. Materials and Methods Between February 2021 and September 2023, two adult human donor hearts were obtained, fixed in formalin, and prepared using a mixture of crushed agar in a 70% ethanol solution. One heart was from a 63-year-old White male without known cardiac disease, and the other was from an 87-year-old White female with a history of multiple known cardiovascular pathologies including ischemic heart disease, hypertension, and atrial fibrillation. Nondestructive ex vivo imaging of these hearts without exogenous contrast agent was performed using HiP-CT at the European Synchrotron Radiation Facility. Results HiP-CT demonstrated the capacity for high-spatial-resolution, multiscale cardiac imaging ex vivo, revealing histologic-level detail of the myocardium, valves, coronary arteries, and cardiac conduction system across length scales. Virtual sectioning of the cardiac conduction system provided information on fatty infiltration, vascular supply, and pathways between the cardiac nodes and adjacent structures. HiP-CT achieved resolutions ranging from gross (isotropic voxels of approximately 20 µm) to microscopic (approximately 6.4-µm voxel size) to cellular (approximately 2.3-µm voxel size) in scale. The potential for quantitative assessment of features in health and disease was demonstrated. Conclusion HiP-CT provided high-spatial-resolution, three-dimensional images of structurally normal and diseased ex vivo adult human hearts. Whole-heart image volumes were obtained with isotropic voxels of approximately 20 µm, and local regions of interest were obtained with resolution down to 2.3-6.4 µm without the need for sectioning, destructive techniques, or exogenous contrast agents. Published under a CC BY 4.0 license Supplemental material is available for this article. See also the editorial by Bluemke and Pourmorteza in this issue.

Dual Volume Image Fusion Technique for Anatomical Evaluation of Cavernous Sinus Dural Arteriovenous Fistula: Usefulness for Transvenous Target Segment Embolization

In this preliminary study, we investigated the value of fusion techniques by flat detector computed tomography based dual volume rotational angiography (DVRA) for the evaluation of the anatomical relationship of cavernous sinus dural arteriovenous fistula (CSDAVF) and assessed the possibility of transvenous target segment embolization. Twenty-six patients with CSDAVF supplied by multiple feeders underwent DVRA for each feeding large vessel separately. We assessed the anatomical relationship of feeders, fistula points, and venous drainage with three dual volume image fusion techniques. Transvenous embolization was targeted to the segment of fistulous point for preserving those not involved and reducing coil mass effect. Dual vessel multi-planar reconstruction fusion technique could show which segment of the cavernous sinus supplied by feeding arteries. In the dual vessel volume rendering fusion technique, the association between feeding arteries, fistula points, and draining veins of 2 different vessels could be accurately identified in 3 dimensions. In addition, we could visualize the exact anatomical relationship between the components of CSDAVF and skull anatomy with the single vessel fusion technique. Based on various fusion images, target segment embolization was successfully performed in 8 patients. In this group, we achieved complete or near complete occlusion without complications, including cranial nerve palsy. Detailed anatomical information including accurate fistula point, specific feeding arteries, and draining veins could be obtained with various dual volume image fusion techniques. In addition, the target segment embolization of CSDAVF could be possible with understanding of the precise CSDAVF architectures.

Quantitative analysis of malignant brain tumor on MRI images

Longitudinal relaxation time (T1)- weighted, Transverse relaxation time (T2)- weighted and flair Magetic Resonance Imaging (MRI) sequences are used for the study of high grade malignant brain tumors and their surrounding edemas. This study aimed to examine the characteristic of MRI on malignant brain tumor and to evaluate the benefits of Flair and T2 (Transverse relaxation time) -weighted over the T1(Longitudinal relaxation time) -weighted sequence. A total of 25 patients of malignant brain tumors were selected for analysis including 16 women aged 1 to 75 (mean age, 38.31 years) and 9 men aged 1 to 75 (mean age, 19.5 years). All patients had the T1- weighted, T2- weighted and Flair MRI sequences. A Region based segmentation of MATLAB software was performed on each type of tumor and 3D volume was calculated by spheroid volume tool of MATLAB. For all the patients tumor volume was calculated in cubic millimeter and compared with other sequences.The Flair and T2- weighted images volumes were significantly larger than the T1 – weighted image volume. There was also statistical difference of volume occurred in MRI sequences. T2- weighted and Flair MRI sequences showed 100% more volume than T1- weighted in the age group between 51 to 75 years. Similarly, both T2-weighted and Flair MRI sequence showed 61% volume more than T1-weighted in the age groups betrwen 26 to 75 years. Our findings suggest that the volume produced by these techniques are distinct and not interchangeable. Flair and T2-weighted images proved efficient for the measurement of abnormal tissues and CSF fluid in the brain. On the other hand T1-weighted images efficiently locate the tumor in fat and white matter of the brain.

Adaptive image processing embedding to make the ecological tasks of deep learning more robust on camera traps images

Camera traps serve as a valuable tool for wildlife monitoring, generating a vast collection of images for ecologists to conduct ecological investigations, such as species identification and population estimation. However, the sheer volume of images poses a challenge, and the integration of deep learning into automated ecological investigation tasks remains complex, particularly when dealing with low-quality images in long-term monitoring programs. Existing approaches often struggle to strike a balance between image enhancement and deep learning for ecological tasks, thereby overlooking crucial information contained within low-quality images. This research introduces a pioneering adaptive image processing module (AIP) that seamlessly incorporates image processing into camera trap ecological tasks, elevating the performance of wildlife monitoring activities. Specifically, a differentiable image processing (DIP) module is presented to enhance low-quality images, with its parameters predicted by a Non-local based parameter predictor (NLPP). Additionally, an end-to-end approach based on hybrid data containing both original and synthetic data is proposed, encompassing adaptive image processing methods and downstream tasks for camera traps, adaptable to various scenarios. This approach effectively reduces the manual labor and time required for professional image processing. When applied to real-world camera trap images and synthetic image datasets, our method achieves an accuracy of 92.26% and 86.65% in classifying wildlife, respectively, demonstrating its robustness. By outperforming alternative methods under harsh conditions, the application of the adaptive image processing module instills greater confidence in deep learning applications within complex environments.

Synthetic hematocrit from virtual non-contrast images for myocardial extracellular volume evaluation with photon-counting detector CT.

To assess the accuracy of a synthetic hematocrit derived from virtual non-contrast (VNC) and virtual non-iodine images (VNI) for myocardial extracellular volume (ECV) computation with photon-counting detector computed tomography (PCD-CT). Consecutive patients undergoing PCD-CT including a coronary CT angiography (CCTA) and a late enhancement (LE) scan and having a blood hematocrit were retrospectively included. In the first 75 patients (derivation cohort), CCTA and LE scans were reconstructed as VNI at 60, 70, and 80 keV and as VNC with quantum iterative reconstruction (QIR) strengths 2, 3, and 4. Blood pool attenuation (BPmean) was correlated to blood hematocrit. In the next 50 patients (validation cohort), synthetic hematocrit was calculated using BPmean. Myocardial ECV was computed using the synthetic hematocrit and compared with the ECV using the blood hematocrit as a reference. In the derivation cohort (49 men, mean age 79 ± 8 years), a correlation between BPmean and blood hematocrit ranged from poor for VNI of CCTA at 80 keV, QIR2 (R2 = 0.12) to moderate for VNI of LE at 60 keV, QIR4; 70 keV, QIR3 and 4; and VNC of LE, QIR3 and 4 (all, R2 = 0.58). In the validation cohort (29 men, age 75 ± 14 years), synthetic hematocrit was calculated from VNC of the LE scan, QIR3. Median ECV was 26.9% (interquartile range (IQR), 25.5%, 28.8%) using the blood hematocrit and 26.8% (IQR, 25.4%, 29.7%) using synthetic hematocrit (VNC, QIR3; mean difference, -0.2%; limits of agreement, -2.4%, 2.0%; p = 0.33). Synthetic hematocrit calculated from VNC images enables an accurate computation of myocardial ECV with PCD-CT. Virtual non-contrast images from cardiac late enhancement scans with photon-counting detector CT allow the calculation of a synthetic hematocrit, which enables accurate computation of myocardial extracellular volume. Blood hematocrit is mandatory for conventional myocardial extracellular volume computation. Synthetic hematocrit can be calculated from virtual non-iodine and non-contrast photon-counting detector CT images. Synthetic hematocrit from virtual non-contrast images enables computation of the myocardial extracellular volume.

A SAR Ship Detection Method Based on Adversarial Training.

SAR (synthetic aperture radar) ship detection is a hot topic due to the breadth of its application. However, limited by the volume of the SAR image, the generalization ability of the detector is low, which makes it difficult to adapt to new scenes. Although many data augmentation methods-for example, clipping, pasting, and mixing-are used, the accuracy is improved little. In order to solve this problem, the adversarial training is used for data generation in this paper. Perturbation is added to the SAR image to generate new samples for training, and it can make the detector learn more abundant features and promote the robustness of the detector. By separating batch normalization between clean samples and disturbed images, the performance degradation on clean samples is avoided. By simultaneously perturbing and selecting large losses of classification and location, it can keep the detector adaptable to more confrontational samples. The optimization efficiency and results are improved through K-step average perturbation and one-step gradient descent. The experiments on different detectors show that the proposed method achieves 8%, 10%, and 17% AP (Average Precision) improvement on the SSDD, SAR-Ship-Dataset, and AIR-SARShip, compared to the traditional data augmentation methods.

Serial block-face scanning electron microscopy of adherent cells on thin plastic substrate

Abstract Serial block-face (SBF) scanning electron microscopy (SEM) is used for imaging the entire internal ultrastructure of cells, tissue samples or small organisms. Here, we present a workflow for SBF SEM of adherent cells, such as Giardia parasites and HeLa cells, attached to the surface of a plastic culture dish, which preserves the interface between cells and plastic substrate. Cells were embedded in situ on their substrate using silicone microwells and were mounted for cross-sectioning which allowed SBF imaging of large volumes and many cells. A standard sample preparation and embedding protocol for thin section electron microscopy provided already sufficient resolution and image quality to visualize larger structures. To improve resolution and image quality of SBF imaging, we stepwise tested modifications of the protocol, such as the moderate increase of the heavy metal content of the sample. Modifications of the embedding by either the reduction of the resin layer (minimal embedding) or the addition of silver colloid to the resin were evaluated at high and low vacuum imaging conditions. The optimized sample preparation protocol is very similar to the standard preparation protocol for thin section electron microscopy, so that the samples can also be used for this application. The protocol applies a higher concentration of osmium tetroxide, a higher temperature for heavy metal incubation and an additional lead en bloc staining. In summary, the presented workflow provides a generic and adaptable solution for studying adherent cells by SBF SEM.

CAS3D: 3D quantitative morphometry on Second Harmonic Generation image volumes from single skeletal muscle fibers

The CAS3D image processing method intuitively applies a combination of Fourier space and real space 3D analysis algorithms to volumetric images of single skeletal muscle fiber Myosin II Second Harmonic Generation (SHG) XYZ image data. Our developed tool automatically quantifies the myofibrillar orientation in muscle samples by determining the cosine angle sum of intensity gradients in 3D (CAS3D) while determining the mean sarcomere length (SL) and sample orientation. The expected CAS3D values could be reproduced from ideal artificial data sets. Applied random noise in artificial images lowers the detected CAS3D value, and for noise levels below 20%, the correlation can be approximated by a linear function with a slope of −0.006 CAS3D/noise%. The deviations in SL and orientation detection were determined on ideal and noisy artificial data sets and were statistically indistinguishable from 0 (null hypothesis t-test P > 0.1). The software was applied to a previously published data set of single skeletal muscle fiber volumetric SHG image data from a rat intensive care unit (ICU) model of ventilator-induced diaphragm dysfunction (VIDD) with treatment regimens involving the small anti-inflammatory molecules BGP-15, vamorolone, or prednisolone. Our method reliably reproduced the results of the previous work and improved the standard deviation of the cosine angle sum detection in all sample groups from a mean of 0.03 to 0.008. This improvement is achieved by applying analysis algorithms to the whole volumetric images in 3D in contrast to the previously common method of slice-wise XY analysis.

Multi-FusNet: fusion mapping of features for fine-grained image retrieval networks.

As the diversity and volume of images continue to grow, the demand for efficient fine-grained image retrieval has surged across numerous fields. However, the current deep learning-based approaches to fine-grained image retrieval often concentrate solely on the top-layer features, neglecting the relevant information carried in the middle layer, even though these information contains more fine-grained identification content. Moreover, these methods typically employ a uniform weighting strategy during hash code mapping, risking the loss of critical region mapping-an irreversible detriment to fine-grained retrieval tasks. To address the above problems, we propose a novel method for fine-grained image retrieval that leverage feature fusion and hash mapping techniques. Our approach harnesses a multi-level feature cascade, emphasizing not just top-layer but also intermediate-layer image features, and integrates a feature fusion module at each level to enhance the extraction of discriminative information. In addition, we introduce an agent self-attention architecture, marking its first application in this context, which steers the model to prioritize on long-range features, further avoiding the loss of critical regions of the mapping. Finally, our proposed model significantly outperforms existing state-of-the-art, improving the retrieval accuracy by an average of 40% for the 12-bit dataset, 22% for the 24-bit dataset, 16% for the 32-bit dataset, and 11% for the 48-bit dataset across five publicly available fine-grained datasets. We also validate the generalization ability and performance stability of our proposed method by another five datasets and statistical significance tests. Our code can be downloaded from https://github.com/BJFU-CS2012/MuiltNet.git.

Pediatric diffuse intrinsic pontine glioma radiotherapy response prediction: MRI morphology and T2 intensity-based quantitative analyses.

An easy-to-implement MRI model for predicting partial response (PR) postradiotherapy for diffuse intrinsic pontine glioma (DIPG) is lacking. Utilizing quantitative T2 signal intensity and introducing a visual evaluation method based on T2 signal intensity heterogeneity, and compared MRI radiomic models for predicting radiotherapy response in pediatric patients with DIPG. We retrospectively included patients with brainstem gliomas aged ≤ 18 years admitted between July 2011 and March 2023. Applying Response Assessment in Pediatric Neuro-Oncology criteria, we categorized patients into PR and non-PR groups. For qualitative analysis, tumor heterogeneity vision was classified into four grades based on T2-weighted images. Quantitative analysis included the relative T2 signal intensity ratio (rT2SR), extra pons volume ratio, and tumor ring-enhancement volume. Radiomic features were extracted from T2-weighted and T1-enhanced images of volumes of interest. Univariate analysis was used to identify independent variables related to PR. Multivariate logistic regression was performed using significant variables (p < 0.05) from univariate analysis. Of 140 patients (training n = 109, and test n = 31), 64 (45.7%) achieved PR. The AUC of the predictive model with extrapontine volume ratio, rT2SRmax-min (rT2SRdif), and grade was 0.89. The AUCs of the T2-weighted and T1WI-enhanced models with radiomic signatures were 0.84 and 0.81, respectively. For the 31 DIPG test sets, the AUCs were 0.91, 0.83, and 0.81, for the models incorporating the quantitative features, radiomic model (T2-weighted images, and T1W1-enhanced images), respectively. Combining T2-weighted quantification with qualitative and extrapontine volume ratios reliably predicted pediatric DIPG radiotherapy response. Combining T2-weighted quantification with qualitative and extrapontine volume ratios can accurately predict diffuse intrinsic pontine glioma (DIPG) radiotherapy response, which may facilitate personalized treatment and prognostic assessment for patients with DIPG. Early identification is crucial for radiotherapy response and risk stratification in diffuse intrinsic pontine glioma. The model using tumor heterogeneity and quantitative T2 signal metrics achieved an AUC of 0.91. Using a combination of parameters can effectively predict radiotherapy response in this population.

Explainable prediction model for the human papillomavirus status in patients with oropharyngeal squamous cell carcinoma using CNN on CT images

Several studies have emphasised how positive and negative human papillomavirus (HPV+ and HPV−, respectively) oropharyngeal squamous cell carcinoma (OPSCC) has distinct molecular profiles, tumor characteristics, and disease outcomes. Different radiomics-based prediction models have been proposed, by also using innovative techniques such as Convolutional Neural Networks (CNNs). Although some of these models reached encouraging predictive performances, there evidence explaining the role of radiomic features in achieving a specific outcome is scarce. In this paper, we propose some preliminary results related to an explainable CNN-based model to predict HPV status in OPSCC patients. We extracted the Gross Tumor Volume (GTV) of pre-treatment CT images related to 499 patients (356 HPV+ and 143 HPV−) included into the OPC-Radiomics public dataset to train an end-to-end Inception-V3 CNN architecture. We also collected a multicentric dataset consisting of 92 patients (43 HPV+ , 49 HPV−), which was employed as an independent test set. Finally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) technique to highlight the most informative areas with respect to the predicted outcome. The proposed model reached an AUC value of 73.50% on the independent test. As a result of the Grad-CAM algorithm, the most informative areas related to the correctly classified HPV+ patients were located into the intratumoral area. Conversely, the most important areas referred to the tumor edges. Finally, since the proposed model provided additional information with respect to the accuracy of the classification given by the visualization of the areas of greatest interest for predictive purposes for each case examined, it could contribute to increase confidence in using computer-based predictive models in the actual clinical practice.

FDG-PET/CT-based respiration-gated lung segmentation and quantification of lung inflammation in COPD patients

Objective and results descriptionThe study objective was to investigate the potential of quantitative measures of pulmonary inflammation by [18 F]Fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) as a surrogate marker of inflammation in COPD. Patients treated with anti-inflammatory Liraglutide were compared to placebo and correlated with inflammatory markers. 27 COPD-patients (14 receiving Liraglutide treatment and 13 receiving placebo) underwent 4D-respiratory-gated FDG-PET/CT before and after treatment. Two raters independently segmented the lungs from CT images and measured activity in whole lung, mean standard uptake values (SUVmean) corrected for lean-body-mass in the phase-matched PET images of the whole segmented lung volume, and total lesion glycolysis (TLG; SUVmean multiplied by volume). Inter-rater reliability was analyzed with Bland-Altman analysis and correlation plots. We found no differences in metabolic activity in the lungs between the two groups as a surrogate of pulmonary inflammation, and no changes in inflammation markers. The purpose of the research and brief summary of main findings. The degree of and changes in pulmonary inflammation in chronic obstructive pulmonary disease (COPD) may be difficult to ascertain. Measuring metabolic activity as a surrogate marker of inflammation by FDG-PET/CT may be useful, but data on its use in COPD including reproducibility is still limited, especially with respiration-gated technique, which should improve quantification in the lungs. We assessed several quantitative measures of metabolic activity and correlated them with inflammation markers, and we assessed reproducibility of the methods. We found no differences in metabolic activity between the two groups (before and after 40 weeks treatment with Liraglutide vs. placebo). Bland-Altman analysis showed good agreement between the two raters.Trial registrationThe study was conducted between February 2018 and March 2020 at the Department of Pulmonary Diseases at Hospital South West Jutland and Lillebaelt Hospital, Denmark, and registered from March 2018 at clinicaltrials.gov with trial registration number NCT03466021.

Exploiting 2D-SDMCHM and matching embedding driven by flag-shaped hexagon prediction for visually meaningful medical image cryptosystem

With the proliferation of advanced medical technologies and smart wearable devices, a considerable volume of patient data and medical images is being generated and stored, leading to an escalating concern over patient privacy violations and manipulation. Therefore, safeguarding the secrecy and integrity of medical images is paramount for preserving patient privacy and ensuring accurate medical diagnostics. To tackle this challenge, this paper introduces a novel approach, the Visually Meaningful Medical Image Cryptosystem (VMMIC), leveraging a 2-Dimensional Sinusoidal Discrete Memristor Coupled Hyperchaotic Map (2D-SDMCHM) to protect the privacy of medical images. The innovation of this study is primarily reflected in three aspects: Firstly, a novel Discrete Memristor (DM) model is proposed, upon which a new 2D-SDMCHM is constructed. Comparative analysis showcases its superior chaos robustness, as evidenced by evaluations through bifurcation diagrams, phase trajectories, Lyapunov exponents, and Shannon entropy. Secondly, we introduce a measurement matrix optimization algorithm based on Optimal Matrix Arrangement (OMA) for Compressive Sensing (CS), aimed at minimizing the coherence of the measurement matrix, thereby enhancing reconstruction accuracy. Lastly, a Matching Embedding Method Driven by Flag-Shaped Hexagon Prediction (MEMFHP) is introduced to ensure lossless concealment of confidential information. Experimental findings and comparative evaluations affirm the VMMIC's capability to meet high standards of reconstruction quality, steganography, and efficiency in handling medical images, while also demonstrating robustness against various attacks. Consequently, the proposed VMMIC holds significant promise for practical implementation in engineering applications.

IMG-08. SYNTHESIZING MISSING MRI SEQUENCES IN PEDIATRIC BRAIN TUMORS USING GENERATIVE ADVERSARIAL NETWORKS; TOWARDS IMPROVED VOLUMETRIC TUMOR ASSESSMENT

Abstract BACKGROUND Standard MRI sequences, such as pre- and post-contrast T1w, T2w, and FLAIR images, are essential for optimizing segmentation of tumor subregions and evaluating treatment responses in pediatric brain tumors (PBTs). However, MRI sets are often incomplete due to imaging artifacts or inconsistent acquisition protocols across various centers. Generative Adversarial Networks (GANs) have been effectively utilized to generate missing MRI sequences for adult brain tumors. This study applies image-to-image translation models using GANs to synthesize missing FLAIR images from T2w images in PBTs. METHODS This retrospective study developed two GAN models, pix2pix in both 2D and 3D, trained and validated on T2w and FLAIR image pairs from 79 and 19 patients, respectively, with pediatric-type diffuse high-grade gliomas (diffuse midline glioma (DMG) including diffuse intrinsic pontine glioma (DIPG)), collected from the Children’s Brain Tumor Network (CBTN). The 2D pix2pix model processes each T2w MRI volume slice-by-slice, generating corresponding FLAIR slices to reconstruct the complete image volume. The 3D pix2pix model allows translation of 3D FLAIR volumes directly from T2w volumes without the need for individual slice processing and reconstruction. The quality of the generated FLAIR volumes was evaluated using Structural Similarity Index (SSI; best closer to 1) and Mean Squared Error (MSE; best near 0) on the validation set. RESULTS The 2D and 3D models achieved robust performance with median SSI, MSE of 0.88, 0.004, and 0.92, 0.002, respectively. CONCLUSIONS The GAN models developed in this study effectively generate missing FLAIR MRI volumes from corresponding T2w images in PBTs. The 3D model, outperforming 2D, speeds the overall processing pipeline by eliminating volume slicing and reconstruction. Future work includes assessing the impact of these synthesized images on the accuracy of our pretrained autosegmentation models in differentiating tumor subregions and measuring tumor volumes in longitudinal MRIs.

Privacy-preserving geo-tagged image search in edge–cloud computing for IoT

The Internet of Things (IoT) generates a significant volume of geo-tagged images via surveillance sensors in edge–cloud computing environments. Image search is essential to facilitate information sharing, data analysis, and strategic decision-making. However, outsourced images are typically encrypted for privacy protection, posing a challenge in simultaneously searching for visual and geographical relevance on encrypted images. To address this, this paper proposes an edge intelligence empowered privacy-preserving top-k geo-tagged image search scheme for IoT in edge–cloud computing. The scheme presents a novel single-to-multi searchable encryption method for geo-tagged images that enables multiple users to perform secure nearest neighbor queries on a data source. Additionally, an extended anchor-based position determination method and an inner product-based distance calculation method are designed to enable geo-tagged image similarity calculation on ciphertext. Finally, a secure pruning method is introduced to improve query performance. Experiments are conducted to verify the performance of the scheme in terms of high efficiency and accuracy of the search.

Instance-level medical image classification for text-based retrieval in a medical data integration center

A medical data integration center integrates a large volume of medical images from clinical departments, including X-rays, CT scans, and MRI scans. Ideally, all images should be indexed appropriately with standard clinical terms. However, some images have incorrect or missing annotations, which creates challenges in searching and integrating data centrally. To address this issue, accurate and meaningful descriptors are needed for indexing fields, enabling users to efficiently search for desired images and integrate them with international standards.This paper aims to provide concise annotation for missing or incorrectly indexed fields, incorporating essential instance-level information such as radiology modalities (e.g., X-rays), anatomical regions (e.g., chest), and body orientations (e.g., lateral) using a Deep Learning classification model - ResNet50. To demonstrate the capabilities of our algorithm in generating annotations for indexing fields, we conducted three experiments using two open-source datasets, the ROCO dataset, and the IRMA dataset, along with a custom dataset featuring SNOMED CT labels. While the outcomes of these experiments are satisfactory (Precision of >75%) for less critical tasks and serve as a valuable testing ground for image retrieval, they also underscore the need for further exploration of potential challenges. This essay elaborates on the identified issues and presents well-founded recommendations for refining and advancing our proposed approach.