Standard Imaging Research Articles

Researching on insulator defect recognition based on context cluster CenterNet++

The existing UAV inspection images are faced with many challenges for insulator defect recognition. A new multi-resolution Context Cluster CenterNet++ model is proposed. First, this paper proposes the Context Cluster method to solve the problem of low recognition accuracy caused by non-uniform distribution of targets. The cluster region is used to identify and predict the location of the target, and the improved loss function is used to modify the cluster center. Secondly, this paper uses deformable convolution operator (DCNv2) combined with path aggregation network (PAN) to carry out deformable convolution operation on the image, and accurately predicts the regression box and key point triplet (KP), so as to improve the accurate positioning of the target position of any shape and any scale. The sensitivity of the model to target scale change and deformation is reduced, and the recognition accuracy of the model is improved. Then, Bhattacharyya distance is used to calculate the triplet prediction loss of key points and the target center point offset loss, so as to significantly improve the positioning accuracy of the same target in different frames. Finally, experiments are carried out on the MS-COCO dataset and the National Grid standardized UAV inspection insulator image dataset. Our code is at https://github.com/mengbonannan88/CC-CenterNet.

Exploring 3D Modeling for Enhanced Visualization and Analysis of Pediatric Pelvic Ring Fractures: A Pilot Study

Introduction Pediatric pelvic fractures are high energy injuries that present substantial treatment challenges due to their propensity for plastic deformation, complex fracture patterns, and lack of consensus on surgical indications. There is potential for negative long-term outcomes in patients with residual deformity, but our understanding of acceptable alignment is limited. Plain radiographs and computed tomography (CT) are frequently employed for pre- and post-operative assessment of injury patterns, but are limited to two-dimensional analysis. Three dimensional (3D) modeling offers an opportunity for improved assessment of pelvic anatomy. Methods Two pediatric patients who sustained unstable pelvic ring injuries requiring operative fixation, with both pre- and post-operative CT scans, were identified from an existing IRB-approved trauma database. Utilizing 3D Slicer, 3D segmentations were rendered from DICOM data and specific landmarks were identified to calculate deformity pre- and post-operatively including displacement at the sacroiliac (SI) joints, pubic symphysis, and iliac crest. A modified Keshishyan deformity index was also calculated. Mesh overlay was performed using Autodesk Maya in x, y and z planes to provide visual representation of post-operative changes. Results 3D renderings successfully illustrated complex pelvic fractures in a 9 year old female and 12 year old. Measurements made on 3D models showed similar improvements in diastasis and symmetry to measurements made in standard 2D imaging, but with generally smaller magnitudes. Graphic overlap allow for sophisticated representation of improvement in deformity. Measurements on plain radiographs and 2D CT differed from 3D measurements by anywhere from 0.1 mm to 6.7 mm. Conclusion This proof-of-concept pilot study demonstrates that 3D renderings enhance the ability to measure displacement and deformity in pediatric pelvic trauma for both pre-operative planning and post-operative evaluation. Future applications of this technology include evaluation of pelvic deformity remodeling after trauma in both operative and non-operatively treated pediatric patients.

Hematuria in the ER patient: optimizing detection of upper tract urothelial - A pictorial essay.

Upper tract urothelial carcinoma (UTUC) is a rare and challenging subset of the more frequently encountered urothelial carcinomas (UCs), comprising roughly 5-7% of all UCs and less than 10% of all renal tumors. Hematuria is a common presenting symptom in the emergency setting, often prompting imaging to rule out serious etiologies, with UTUC especially posing as a diagnostic challenge. These UTUC lesions of the kidney and ureter are often small, mimicking other pathologies, and are more aggressive than typical UC of the bladder, emphasizing the importance of timely and accurate diagnosis. Multidetector computed tomography urography (CTU) is the standard imaging modality for diagnosis, tumor staging, and surgical planning. Various postprocessing techniques like multiplanar reconstructions, maximal intensity projection (MIP) images, and 3D volumetric rendering technique (VRT) are crucial for accurate detection. In addition, 3D cinematic rendering (CR) is a novel technique that employs advanced illumination models, producing images with realistic shadows and increased surface detail, outperforming traditional VRT. We willreview the distinctive imaging features between UTUC and infiltrating mimicking lesions on CTU in patients who presented with hematuria, in conjunction with advanced postprocessing techniques,ultimately improving diagnostic confidence and preoperative planning in the emergency context.

Computed Tomography Angiography Indications in the Follow-Up of Kawasaki Disease Patients

Kawasaki disease (KD), or mucocutaneous lymph node syndrome, is a vasculitis that primarily affects young children and results in coronary artery abnormalities. Echocardiography is the standard imaging modality for monitoring KD patients; however, this method does not detect some coronary artery anomalies. This case report demonstrates the significance of computed tomography (CT) angiography in identifying previously undiagnosed coronary abnormalities in a KD patient. We herein describe a 7-year-old male who presented with symptoms consistent with KD and was treated subsequently with intravenous immune globulin (IVIG). Follow-up echocardiography showed no significant coronary artery abnormalities. Three years later, the patient presented with flu-like symptoms, and an ECG revealed anterolateral ischemic changes. Echocardiography showed normal coronary arteries. Nonetheless, a CT angiogram was performed due to the ischemic changes on ECG, and it identified a myocardial bridge in the left anterior descending artery, which had not been detected by echocardiography or ECG. This case report emphasizes the importance of considering CT angiography as an adjunct imaging modality in the evaluation and follow-up of KD patients, particularly when echocardiographic findings are inconclusive or when clinical presentation raises concerns for potential coronary artery abnormalities. Further research is needed to establish evidence-based guidelines for the optimal timing and clinical indications for CT angiography in KD patients.

Unlocking ultra-deep wide-field imaging with sidereal visibility averaging

abstract Producing ultra-deep high-angular-resolution images with current and next-generation radio interferometers introduces significant computational challenges. In particular, the imaging is so demanding that processing large datasets, accumulated over hundreds of hours on the same pointing, is likely infeasible in the current data reduction schemes. In this paper, we revisit a solution to this problem that was considered in the past but is not being used in modern software: sidereal visibility averaging (SVA). This technique combines individual observations taken at different sidereal days into one much smaller dataset by averaging visibilities at similar baseline coordinates. We present our method and validated it using four separate 8-hour observations of the ELAIS-N1 deep field, taken with the International LOw Frequency ARray (LOFAR) Telescope (ILT) at 140 MHz. Additionally, we assessed the accuracy constraints imposed by Earth's orbital motion relative to the observed pointing when combining multiple datasets. We find, with four observations, data volume reductions of a factor of 1.8 and computational time improvements of a factor of 1.6 compared to standard imaging. These factors will increase when more observations are combined with SVA. For instance, with 3000 hours of LOFAR data aimed at achieving sensitivities of the order of μJy beam^-1 at sub-arcsecond resolutions, we estimate data volume reductions of up to a factor of 169 and a 14-fold decrease in computing time using our current algorithm. This advancement for imaging large deep interferometric datasets will benefit current generation instruments, such as LOFAR, and upcoming instruments such as the Square Kilometre Array (SKA), provided the calibrated visibility data of the individual observations are retained. abstract

Shape-matching-based fracture reduction aid concept exemplified on the proximal humerus-a pilot study.

Optimizing fracture reduction quality is key to achieve successful osteosynthesis, especially for epimetaphyseal regions such as the proximal humerus (PH), but can be challenging, partly due to the lack of a clear endpoint. We aimed to develop the prototype for a novel intraoperative C-arm-based aid to facilitate true anatomical reduction of fractures of the PH. The proposed method designates the reduced endpoint position of fragments by superimposing the outer boundary of the premorbid bone shape on intraoperative C-arm images, taking the mirrored intact contralateral PH from the preoperative CT scan as a surrogate. The accuracy of the algorithm was tested on 60 synthetic C-arm images created from the preoperative CT images of 20 complex PH fracture cases (Dataset A) and on 12 real C-arm images of a prefractured human anatomical specimen (Dataset B). The predicted outer boundary shape was compared with the known exact solution by (1) a calculated matching error and (2) two experienced shoulder trauma surgeons. A prediction accuracy of 88% (with 73% 'good') was achieved according to the calculation method and an 87% accuracy (68% 'good') by surgeon assessment in Dataset A. Accuracy was 100% by both assessments for Dataset B. By seamlessly integrating into the standard perioperative workflow and imaging, the intuitive shape-matching-based aid, once developed as a medical device, has the potential to optimize the accuracy of the reduction of PH fractures while reducing the number of X-rays and surgery time. Further studies are required to demonstrate the applicability and efficacy of this method in optimizing fracture reduction quality.

The Impact of Weighting Factors on Dual-Energy Computed Tomography Image Quality in Non-Contrast Head Examinations: Phantom and Patient Study

Background: This study aims to evaluate the impact of various weighting factors (WFs) on the quality of weighted average (WA) dual-energy computed tomography (DECT) non-contrast brain images and to determine the optimal WF value. Because they simulate standard CT images, 0.4-WA reconstructions are routinely used. Methods: In the initial phase of the research, quantitative and qualitative analyses of WA DECT images of an anthropomorphic head phantom, utilizing WFs ranging from 0 to 1 in 0.1 increments, were conducted. Based on the phantom study findings, WFs of 0.4, 0.6, and 0.8 were chosen for patient analyses, which were identically carried out on 85 patients who underwent non-contrast head DECT. Three radiologists performed subjective phantom and patient analyses. Results: Quantitative phantom image analysis revealed the best gray-to-white matter contrast-to-noise ratio (CNR) at the highest WFs and minimal noise artifacts at the lowest WF values. However, the WA reconstructions were deemed non-diagnostic by all three readers. Two readers found 0.6-WA patient reconstructions significantly superior to 0.4-WA images (p < 0.001), while reader 1 found them to be equally good (p = 0.871). All readers agreed that 0.8-WA images exhibited the lowest image quality. Conclusions: In conclusion, 0.6-WA reconstructions demonstrated superior image quality over 0.4-WA and are recommended for routine non-contrast brain DECT.

The textures of sarcoidosis: quantifying lung disease through variograms

Objective. Sarcoidosis is a granulomatous disease affecting the lungs in over 90% of patients. Qualitative assessment of chest CT by radiologists is standard clinical practice and reliable quantification of disease from CT would support ongoing efforts to identify sarcoidosis phenotypes. Standard imaging feature engineering techniques such as radiomics suffer from extreme sensitivity to image acquisition and processing, potentially impeding generalizability of research to clinical populations. In this work, we instead investigate approaches to engineering variogram-based features with the intent to identify a robust, generalizable pipeline for image quantification in the study of sarcoidosis.Approach. For a cohort of more than 300 individuals with sarcoidosis, we investigated 24 feature engineering pipelines differing by decisions for image registration to a template lung, empirical and model variogram estimation methods, and feature harmonization for CT scanner model, and subsequently 48 sets of phenotypes produced through unsupervised clustering. We then assessed sensitivity of engineered features, phenotypes produced through unsupervised clustering, and sarcoidosis disease signal strength to pipeline.Main results. We found that variogram features had low to mild association with scanner model and associations were reduced by image registration. For each feature type, features were also typically robust to all pipeline decisions except image registration. Strength of disease signal as measured by association with pulmonary function testing and some radiologist visual assessments was strong (optimistic AUC ≈ 0.9,p≪0.0001in models for architectural distortion, conglomerate mass, fibrotic abnormality, and traction bronchiectasis) and fairly consistent across engineering approaches regardless of registration and harmonization for CT scanner.Significance. Variogram-based features appear to be a suitable approach to image quantification in support of generalizable research in pulmonary sarcoidosis.

Shaping the structural dynamics of motor learning through cueing during sleep.

Enhancing the retention of recent memory traces through sleep reactivation is possible via Targeted Memory Reactivation (TMR), involving cueing learned material during post-training sleep. Evidence indicates detectable short-term microstructural changes in the brain within an hour after motor sequence learning, and post-training sleep is believed to contribute to the consolidation of these motor memories, potentially leading to enduring microstructural changes. In this study, we explored how TMR during post-training sleep affects performance gains and delayed microstructural remodeling, using both standard Diffusion Tensor Imaging (DTI) and advanced Neurite Orientation Dispersion & Density Imaging (NODDI). Sixty healthy young adults participated in a five-day protocol, undergoing five Diffusion-Weighted Imaging (DWI) sessions, pre- and post-two motor sequence training sessions, and after a post-training night of either regular sleep (RS) or TMR. Results demonstrated rapid skill acquisition on Day 1, followed by performance stabilization on Day 2, and improvement on Day 5, in both RS and TMR groups. (Re)training induced widespread microstructural changes in motor-related areas, initially involving the hippocampus, followed by a delayed engagement of the caudate nucleus. Mean Diffusivity (MD) changes were accompanied by increased Neurite Density Index (NDI) in the putamen, suggesting increased neurite density, while Free Water Fraction (FWF) reduction indicated glial reorganization. TMR-related structural differences emerged in the dorsolateral prefrontal cortex (DLPFC) on Day 2 and the right cuneus on Day 5, suggesting unique sleep TMR-related neural reorganization patterns. Persistence of practice-related structural changes, although moderated over time, suggest a lasting neural network reorganization, partially mediated by sleep TMR.

Unsupervised clustering of intraventricular hemodynamic forces for the phenotyping of left-ventricular function in non-ischemic left ventricular cardiomyopathy.

Cardiac magnetic resonance (CMR) is essential for diagnosing cardiomyopathy, serving as the gold standard for assessing heart chamber volumes and tissue characterization. Hemodynamic forces (HDF) analysis, a novel approach using standard cine CMR images, estimates energy exchange between the left ventricular (LV) wall and blood. While prior research has focused on peak or mean longitudinal HDF values, this study aims to investigate whether unsupervised clustering of HDF curves can identify clinically significant patterns and stratify cardiovascular risk in non-ischemic LV cardiomyopathy (NILVC). A retrospective cohort of 279 patients with NILVC who underwent cardiac CMR at Vall d'Hebron University Hospital (Barcelona) was examined. Unsupervised clustering of longitudinal and transversal HDF curves was performed using Dynamic Time Warping for dissimilarity measurement and the Partitioning Around Medoids algorithm. Outcomes were defined as a composite of cardiovascular mortality, heart failure hospitalization, and ventricular arrhythmias. Median age was 65[57.0;74.0] years, with 27.2% females and 35.5% showing late gadolinium enhancement (LGE). Unsupervised clustering identified three distinct clusters, delineating risk groups with worsening LA and LV function, indicating a stepwise increase in cardiovascular risk profile. Over a median follow-up of 40 months, 60 patients experienced the composite outcome. After adjusting for LGE, LVEF and LV size, clusters 2 and 3 demonstrated a significantly higher risk of adverse events (both p<0.05) compared to cluster 1. Analyzing both longitudinal and transversal HDF throughout the cardiac cycle enables the identification of distinct phenotypes with prognostic value beyond ejection fraction and LGE in NILVC patients.

Comparison of diagnostic performance for pulmonary nodule detection between free-breathing spiral ultrashort echo time and free-breathing radial volumetric interpolated breath-hold examination

ObjectiveThis study aims to evaluate the efficacy of two free-breathing magnetic resonance imaging (MRI) sequences—spiral ultrashort echo time (spiral UTE) and radial volumetric interpolated breath-hold examination (radial VIBE).MethodsPatients were prospectively enrolled between February 2021 and September 2022. All participants underwent both 3T MRI scanning, utilizing the radial VIBE sequence and spiral UTE sequence, as well as standard chest CT imaging. The CT and MRI examinations were conducted within a 7-day interval. Two radiologists assessed the image quality using a visual 5-point ordinal Likert scale, and pulmonary nodules identified on MRI were evaluated through comparison with CT as the reference standard.ResultsA total of 52 patients participated in this study, during which 82 pulmonary nodules were detected via CT imaging. The image quality scores for depicting pulmonary vasculature and airways using the spiral UTE sequence (4.61 ± 0.63; 4.76 ± 0.48) were significantly higher than those for the radial VIBE sequence (4.27 ± 0.87; 4.14 ± 0.82) (P < 0.05). However, for nodules smaller than 6 mm, the detection rate for the spiral UTE sequence (82.61%) was notably higher than that of the radial VIBE sequence (39.13%) (P < 0.05). Additionally, the detection rate for ground-glass nodules was higher with the spiral UTE sequence (75.00%) compared to the radial VIBE sequence (17.86%) (P < 0.05). The Pearson correlation coefficient (r) between radial VIBE and CT was 0.99 (P < 0.001), and the Pearson correlation coefficient (r) between spiral UTE and CT was also 0.99 (P < 0.001).ConclusionThe spiral UTE sequence demonstrates superior capability in visualizing ground glass nodules, blood vessels, and airways. In cases where patients present with ground glass nodules, the spiral UTE sequence is the preferred choice. Conversely, when the nodules are solid or partially solid, it is advisable to opt for radial VIBE sequences that are time-efficient and exhibit fewer artifacts.

Baseline trichoscopic values for afro-textured hair in indigenous South Africans show lower density and unique features.

Afro-textured hair exhibits distinct physicochemical properties with possible variations in measurable hair parameters. Standardized documentation of trichoscopic norms of afro-textured hair in indigenous Africans is notably lacking. A cross-sectional study involving 122 South Africans of both genders of African ancestry (mean age 20.9 ± 3.3 years) with natural afro-textured hair was performed to establish trichoscopic norms. Standard images, one overview, and five microimages (one 20× and four 50× magnifications) were captured with the FotoFinder Medicam1000V2 videodermoscope. Hair density (HD; N/cm2); hair shaft thickness (HST; μm); the proportion of thin, mid, and thick hairs (%); cumulative hair thickness (mm/cm2); and follicular units (FU; N/cm2) were assessed. The average HD was 139.1 ± 33.88 hairs/cm2 with significant variations across different scalp areas. The average hair thickness was 62.59 ± 8.45 μm with the frontal scalp showing the greatest HST, the proportion of thick hairs, cumulative hair thickness, and FU densities; the temporal had the greatest proportion of thin hairs, whereas the occipital showed the highest proportion of triple hair FU. Male participants exhibited significantly greater average hair thickness, more thick hairs, and more double and triple FU, whereas females had higher cumulative hair thickness density, more thin and intermediate hairs, and more single follicular units. Baseline trichoscopic values for natural afro-textured hair in indigenous South Africans reveal lower hair densities, variations in shaft diameters, and follicular unit patterns compared to other racial groups. Significant gender-based differences are evident in some of the measured parameters. Tailored reference values are essential for accurate clinical evaluations and hair transplant planning.

Conjunctival Bulbar Redness Extraction Pipeline for High-Resolution Ocular Surface Photography.

To extract conjunctival bulbar redness from standardized high-resolution ocular surface photographs of a novel imaging system by implementing an image analysis pipeline. Data from two trials (healthy; outgoing ophthalmic clinic) were collected, processed, and used to train a machine learning model for ocular surface segmentation. Various regions of interest were defined to globally and locally extract a redness biomarker based on color intensity. The image-based redness scores were correlated to clinical gradings (Efron) for validation. The model to determine the regions of interest was verified for a segmentation performance, yielding mean intersections over union of 0.9639 (iris) and 0.9731 (ocular surface). All trial data were analyzed and a digital grading scale for the novel imaging system was established. Photographs and redness scores from visits weeks apart showed good feasibility and reproducibility. For scores within the same session, a mean coefficient of variation of 4.09% was observed. A moderate positive Spearman correlation (0.599) was found with clinical grading. The proposed conjunctival bulbar redness extraction pipeline demonstrates that by using standardized imaging, a segmentation model and image-based redness scores' external eye photography can be classified and evaluated. Therefore, it shows the potential to provide eye care professionals with an objective tool to grade ocular redness and facilitate clinical decision-making in a high-throughput manner. To empower clinicians and researchers with a high-throughput workflow by standardized imaging combined with an analysis tool based on artificial intelligence to objectively determine an image-based redness score.

Risk factors and predictive models in the progression from MCI to Alzheimer's disease.

The conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD) is related to various factors. The causal relationships among these factors remain unclear. This study aims to investigate pathways of the progression by using causal analysis and build a predictive model with high accuracy. 162 MCI patients were recruited from the Alzheimer's Disease Neuroimaging Initiative database. 68 patients progressed to AD. 94 patients did not convert to AD. We captured standard T1-weighted images, processed them for feature extraction, and selected relevant features using mRMR and LASSO to calculate cortical and nuclear scores. The computational causal structure discovery and regression analyses were adopted to analyze the intricate relationships among APOE ε4 alleles, P-tau, Aβ1-42, cortical and nuclear scores. The individualized prediction nomogram was constructed. Our results indicated that APOE ε4 alleles was the promoter that caused MCI to transform into AD. Three independent pathways were identified, including P-tau, Aβ1-42, and cortical atrophy. P-tau was the cause of nuclear atrophy. The APOE ε4 alleles, P-tau, Aβ1-42, cortical and nuclear scores all had good predictive value for the MCI conversion. The predictive accuracy of the combined model was the highest, with an AUC of 0.918 in the training cohort and 0.908 in the testing cohort. A multi-predictor nomogram was established. Our study elucidated the initiating factors and three independent pathways involved in the conversion of MCI to AD. The predictive value of each factor was clarified and a multi-predictor nomogram was established with high accuracy.

A Randomized Non‐overlapping Encryption Scheme for Enhanced Image Security in Internet of Things (IoT) Applications

ABSTRACTThe rapid proliferation of Internet of Things (IoT) devices has underscored the critical need to safeguard the data they store and transmit. Among various data types, digital images often carry highly sensitive information, making their protection against breaches essential. This study introduces a novel image encryption algorithm specifically designed to bolster the security of images in resource‐constrained IoT ecosystems. Leveraging the randomness of a 5D multi‐wing hyperchaotic map, the proposed method employs pairs of non‐overlapping rectangles to induce confusion by swapping the pixels they encompass. Repeated iterations of this operation achieve significant confusion effects, enhancing encryption strength. To validate the robustness of the proposed algorithm, standard benchmark images were utilized, and rigorous security metrics —including information entropy, correlation coefficient, histogram uniformity, and resistance to differential attacks —were analyzed. Results demonstrate that the algorithm not only ensures strong protection against unauthorized access but also maintains low computational complexity, making it ideal for IoT applications. This research provides a foundational step toward ensuring the confidentiality and integrity of visual data in an increasingly interconnected digital world.

Self-interactive learning: Fusion and evolution of multi-scale histomorphology features for molecular traits prediction in computational pathology.

Predicting disease-related molecular traits from histomorphology brings great opportunities for precision medicine. Despite the rich information present in histopathological images, extracting fine-grained molecular features from standard whole slide images (WSI) is non-trivial. The task is further complicated by the lack of annotations for subtyping and contextual histomorphological features that might span multiple scales. This work proposes a novel multiple-instance learning (MIL) framework capable of WSI-based cancer morpho-molecular subtyping by fusion of different-scale features. Our method, debuting as Inter-MIL, follows a weakly-supervised scheme. It enables the training of the patch-level encoder for WSI in a task-aware optimisation procedure, a step normally not modelled in most existing MIL-based WSI analysis frameworks. We demonstrate that optimising the patch-level encoder is crucial to achieving high-quality fine-grained and tissue-level subtyping results and offers a significant improvement over task-agnostic encoders. Our approach deploys a pseudo-label propagation strategy to update the patch encoder iteratively, allowing discriminative subtype features to be learned. This mechanism also empowers extracting fine-grained attention within image tiles (the small patches), a task largely ignored in most existing weakly supervised-based frameworks. With Inter-MIL, we carried out four challenging cancer molecular subtyping tasks in the context of ovarian, colorectal, lung, and breast cancer. Extensive evaluation results show that Inter-MIL is a robust framework for cancer morpho-molecular subtyping with superior performance compared to several recently proposed methods, in small dataset scenarios where the number of available training slides is less than 100. The iterative optimisation mechanism of Inter-MIL significantly improves the quality of the image features learned by the patch embedded and generally directs the attention map to areas that better align with experts' interpretation, leading to the identification of more reliable histopathology biomarkers. Moreover, an external validation cohort is used to verify the robustness of Inter-MIL on molecular trait prediction.

2025 Update Consensus of 99mTc-Pyrophosphate Scintigraphy in the Transthyretin Cardiac Amyloidosis from the Taiwan Society of Cardiology and the Society of Nuclear Medicine of the Republic of China.

This 2025 updated consensus outlines the diagnostic strategy for transthyretin amyloid cardiomyopathy (ATTR-CM). Given that ATTR-CM is a significant contributor to heart failure, this article emphasizes the importance of making an early and precise diagnosis, particularly as new therapeutic options become available. Highlighting the critical importance of an early and accurate diagnosis, particularly in light of emerging therapeutic modalities, this consensus underscores the central role of 99mTc-pyrophosphate (PYP) scintigraphy as a non-invasive diagnostic tool. The consensus calls for the adoption of standardized imaging protocols and interpretation criteria to ensure consistency and reliability across diverse clinical settings. The integration of qualitative and quantitative imaging techniques within a structured diagnostic framework places particular focus on the use of single-photon emission computed tomography/computed tomography (SPECT/CT) imaging to enhance diagnostic precision by minimizing blood pool activity and eliminating overlapping interference. Three-hour imaging is considered to be critical for accurate evaluations and to reduce false-positive findings, and it is recommended for its superior diagnostic accuracy. Moreover, quantitative assessments are also considered to be essential for evaluating myocardial amyloid deposition. This updated consensus provides comprehensive guidelines for clinicians, with the aim of optimizing patient outcomes through precise diagnosis and effective management of ATTR-CM. The consensus concludes by advocating for continued research and refinement of imaging methodologies, particularly to enhance the clinical applicability of 99mTc-PYP scintigraphy and other future developments in nuclear molecular imaging.

Accuracy of Abbreviated Breast MRI in Diagnosing Breast Cancer in Women with Dense Breasts Compared with Standard Imaging Modalities

Abstract Background: Breast density is an independent risk factor for breast cancer and affects the sensitivity of mammography screening. Therefore, new breast imaging approaches could benefit women with increased breast density in early cancer detection and diagnosis. Objectives: To assess the diagnostic performance of abbreviated breast MRI compared with mammography and other imaging modalities in screening and diagnosing breast cancer among Saudi women with dense breast tissue. Methods: A retrospective diagnostic study was conducted using anonymized medical images and histopathology information from 55 women, aged ≥30 years, who had dense breasts (Breast Imaging and Reporting Data System [BI-RADS] breast density categories C and D) and an abnormal mammogram. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated for mammography, digital breast tomosynthesis (DBT), synthetic mammography (SM) derived from DBT, ultrasound, and abbreviated breast MRI (ABMRI). Results: A total of 19 women had pathology-proven breast cancer. Among all methods, ABMRI showed the highest sensitivity (94.7%) and specificity (58.3%), while mammography showed the lowest (84.2% and 44.4%, respectively). AUC for ABMRI was higher than all the methods including mammography (0.751 vs. 0.643; P &lt; 0.05). Conclusion: ABMRI appears to be more accurate in cancer diagnosis than mammography and other modalities for women with dense breast tissue. Further research is advised on a larger sample of Saudi women to confirm the benefit of ABMRI in breast cancer screening and diagnosis for women with increased breast density.

Inferring 3D finger bone shapes from 2D images – a detailed analysis of shape accuracy

ABSTRACT 3D visualisation and modelling of anatomical structures of the human body play a significant role in diagnosis, computer-aided surgery, surgical planning, and patient follow-up. However, 2D X-ray images are often used in clinical routine. We propose and validate a method for reconstructing 3D shapes from 2D X-ray scans. This method comprises automatic segmentation and labelling, automated construction of 3D statistical shape models (SSM), and automatic fitting of the SSM to standard 2D X-ray images. This workflow is applied to finger bone shape reconstruction and validated for each finger bone using a set of five synthetic reference configurations and 34 CT/X-ray data pairs. We reached submillimetre accuracy for 91.59% of the synthetic data, while 79.65% of the clinical cases show surface errors below 2 mm. Thus, applying the proposed method can add valuable 3D information where 3D imaging is not indicated. Moreover, 3D imaging can be avoided if the 2D-3D reconstruction accuracy is sufficient.

Advancing real-time echocardiographic diagnosis with a hybrid deep learning model

This research focuses on developing a novel hybrid deep learning architecture designed for real-time analysis of ultrasound heart images. The object of the study is the diagnostic accuracy and efficiency in detecting heart pathologies such as atrial septal defect (ASD) and aortic stenosis (AS) from ultrasound data. The problem is the insufficient accuracy and generalizability of existing models in real-time cardiac image analysis, which limits their practical clinical application. To solve this, the convolutional neural networks (CNNs), combining local feature extraction was integrated with global contextual understanding of cardiac structures. Additionally, a YOLOv7 for precise segmentation and detection was utilized. The results demonstrate that the hybrid model achieves an overall diagnostic accuracy of 92 % for ASD detection and 90 % for AS detection, representing a 7 % improvement over the standard YOLOv7 model. These improvements are attributed to the hybrid architecture's ability to simultaneously capture fine-grained anatomical details and broader structural relationships, enhancing the detection of subtle cardiac anomalies. The findings suggest that combination of CNNs enhances pattern recognition and contextual analysis, leading to better detection of cardiac anomalies. The key features contributing to solving the problem include the hybrid architecture's ability to capture detailed local features and broader structural context simultaneously. In practical terms, the model can be applied in clinical settings that require real-time cardiac assessment using standard medical imaging equipment. Its computational efficiency and high accuracy make it suitable even in resource-constrained environments, reducing analysis time for clinicians, supporting personalized treatment plans, and potentially improving patient outcomes in cardiology