Imaging Performance Research Articles

Trends in resource utilization for new-onset psychosis hospitalizations at children's hospitals.

Children with new-onset psychosis often require hospitalization for medical evaluation. The goal of this study was to assess variations in the management of children with new-onset psychosis and characterize trends in resource utilization. The study included index hospitalizations for children ages 7-18 admitted to children's hospitals with a primary diagnosis of psychosis from 2011 to 2022 using the Pediatric Health Information System (PHIS) database. Children with a complex chronic condition were excluded. Resource utilization categories included medication, imaging, laboratory, and other clinical resources. Variability in resource utilization was assessed using covariance tests for random intercepts with generalized linear modes after adjusting for age, sex, payor, and severity. Trends in resource utilization were examined using generalized estimating equations adjusting for the same factors and accounting for hospital clustering. Our data set included 7126 new-onset psychosis hospitalizations from 37 children's hospitals. Teenage males and non-Hispanic Whites were most likely to be hospitalized. There was a significant variation in resource utilization across hospitals in all categories (p < .001). The most frequently utilized resources were antipsychotic medications (76%), serum chemistry (77%), toxicology labs (72%), and brain magnetic resonance imaging (22%). The most notable increases in utilization were in the performance of laboratory tests, brain imaging, anesthetic use, and intravenous immunoglobulin use. Study findings suggest that there has been a stable rate of hospitalization for children with new-onset psychosis, yet a significant variation in the medical evaluation exists. Significant increases and variations in resource utilization across all categories suggest an emerging need for robust evidence and consensus-based practice guidelines.

Abstract WP201: The Performance of Portable Low-field Magnetic resonance imaging in Acute Ischemic Stroke

Abstract WP201: The Performance of Portable Low-field Magnetic resonance imaging in Acute Ischemic Stroke

Abstract TP143: Improving CT imaging in Non-Fatal strangulation Domestic Violence Victims

Introduction: The incidence of domestic violence (DV) can vary from 2 to 4 million in a year. Domestic violence can be broad in definition and not limited to physical assault. The role of the medical provider in caring for these patients can be difficult; studies suggest that less than 10% of these cases are diagnosed correctly in the emergency room. In collaboration with Brooklyn District Attorney office, we examined and designed a quality improvement study to look at the performance of CT imaging in non-fatal strangulation DV in the emergency department from 8/1/2021 to 3/31/2024 of all NYC Health and Hospitals System (NYCHH). The timely identification of arterial dissection can potentially lead to a decrease risk of stroke. Methods: We developed a non-fatal strangulation pathway in the emergency department for DV patients. We examined the use of CT head and CTA head and neck. The utilization of CT was monitored every quartile. Cases were abstracted with diagnoses of DV and asphyxiation. Strategies were employed to encourage and improve the utilization of pathway. Results: In total, 2163 domestic violence cases were abstracted from electronic medical records. 63% (n=1363) female 5.2% (113) male 31.7% (n=687) did not select for sex (NOA) The percentage of CT performance during 8/1/2021 through 3/31/2024 was 5.5% (116/2163). Upon further evaluation, the percentage of female cases imaged was 5.5% (75/116); by contrast, male cases were imaged at 24.8% (28/116), and NOA 1.9% (13/116). The odds ratio of CT performances in noted cases was 4.5 [95% CI 2.8016-7.2381], 13.0946 [6.5861-26.0349], 2.9 [1.6024-5.277], Male to female cases, male to NOA, and Female to NOA, respectively. Discussion: The literature on domestic violence range in incidence from 2 million to 4 million in a year. The identification of stroke risk factors from a domestic violence incident is a novel approach and has not been fully elucidated. Non-fatal strangulation is known to decrease cerebral perfusion; the risk of developing an arterial dissection is known. Arterial dissection is an independent risk factor for ischemic stroke. In this study, we have observed a low utilization of imaging to rule out dissection; there is a suggestion of disparity among the sexes in diagnosis. Conclusion: The observation from this study involving all hospitals in the NYCHH system reveals a need to better educate and improve diagnosis of domestic violence. This can lead to prompt intervention and medical stabilization.

Blind-label subwavelength ultrasound imaging.

There is a long-existing trade-off between the imaging resolution and penetration depth in acoustic imaging caused by the diffraction limit. Most existing approaches addressing this trade-off require controlled "labels," i.e., metamaterials or contrast agents, to be deposited close to the objects and to either remain static or be tracked precisely during imaging. We propose a "blind-label" approach for acoustic subwavelength imaging. The blind labels are randomly distributed acoustic scatterers with deep-subwavelength sizes whose exact locations and trajectories are not necessary information in image reconstruction. The proposed method achieves the resolution of 0.24 wavelengths in ultrasound imaging experiments and 0.2 wavelengths in simulations, providing over 10 times improvement compared to the diffraction limit. We also elucidate the influence of scatterer size and concentration on imaging performance. The proposed "blind-label" approach relaxes the restrictions of existing acoustic subwavelength imaging technologies relying on controlled labels, therefore substantially improving the practicality of acoustic subwavelength imaging in biomedical ultrasound imaging, sonar, and nondestructive testing.

Development of next generation low-cost OCT towards improved point-of-care retinal imaging

Low-cost optical coherence tomography (OCT) has shown promise in increasing access to noninvasive retinal imaging at the point of care, especially in low-resource environments. A next-generation low-cost OCT system is presented which improves performance over previous versions by employing balanced detection, improved spectrometer falloff, and an increased A-line rate of 40 kHz. An algorithm is presented for image display that uses a histogram matching procedure to improve contrast-to-noise ratio (CNR). Imaging performance is benchmarked with CNR analysis of retinal OCT images, demonstrating a CNR of 2.01 ± 0.39 (p &lt; 0.0001) for macula images collected during a clinical trial, a significant improvement over previous low-cost OCT systems.

Development of a portable testing chamber to assess imaging performance of laparoscopes in low- and middle-income countries.

Laparoscopic surgery is generally unavailable in low- and middle-income countries (LMICs) due to the high cost of installation and lack of qualified personnel to maintain and repair equipment. We developed a low-cost, durable, reusable laparoscopic system, called the KeyScope laparoscope, for use in LMICs. To reliably build and service the KeyScope in LMICs, a portable testing chamber (PTC) is needed to assess image performance. A PTC was developed to characterize KeyScope laparoscope performance in LMICs. Images of standard resolution, color accuracy, distortion, and depth of field (DOF) targets were captured in both a standard optical bench setup (OBS) and the PTC. Measurements from the OBS and PTC were quantified and compared using standard software (ImageJ and Imatest). To further reduce cost, alternative paper imaging targets were identified and compared with standard glass targets. To improve usability, MATLAB applications (apps) were developed to automate image analysis and reduce cost. The PTC achieved similar results compared to the OBS for the image quality metrics, distortion and DOF. Further, the PTC presented similar results to the OBS for resolution at 4 to 7cm working distances and improved resolution at periphery working distances of 3 and 10cm. Color accuracy values were also improved in the PTC compared with those measured in the OBS. The low-cost resolution, color accuracy, and distortion targets resulted in similar image quality results to the standard image quality target. MATLAB apps produced similar results to Imatest and ImageJ software and decreased the time to complete image quality test analysis. The low-cost portable design of the PTC will facilitate the translation of the KeyScope by enabling accurate and fast characterization of laparoscopic imaging performance in LMICs.

Semi-supervised learning-based identification of the attachment between sludge and microparticles in wastewater treatment.

Monitoring the microparticle transfer process in wastewater treatment systems is crucial for improving treatment performance. Supervised deep learning methods show high performance to automatically detect particles, but they rely on vast amounts of labeled data for training. To overcome this issue, we proposed a semi-supervised learning (SSL) method based on the Simple framework for Contrastive Learning of visual Representations (SimCLR), to detect microparticles free from sludge and attached to sludge. First, we pre-trained a ResNet50 backbone by SimCLR, to extract features from much unlabeled data (1,000 images). Then, we constructed a Mask R-CNN architecture based on the pre-trained ResNet50, and fine-tuned it on a small quantity of labeled data (≈200 images with ≈600 annotated particles) in supervised learning fashion. We showcased its performance and practical applicability for microscopy images obtained from the water lab of TU Delft. The results demonstrate that the SSL methods obtain a significant improvement in mean average precision of up to 5% compared to the conventional supervised learning method, when a limited amount of labeled data is available (e.g., 91 labeled images). Furthermore, these methods improve the average precision for detecting attached particles by over 12%. With the detection results from the SSL methods, we measured the attachment efficiency of microparticles to sludge under varying mixed liquor suspended solids concentration and aeration intensity. The precise measurements demonstrate the effectiveness and practical applicability of the SSL method in facilitating long-term monitoring of particle transfer processes in biological wastewater treatment systems.

Three-dimensional diffractive acoustic tomography

Acoustically probing biological tissues with light or sound, photoacoustic and ultrasound imaging can provide anatomical, functional, and/or molecular information at depths far beyond the optical diffusion limit. However, most photoacoustic and ultrasound imaging systems rely on linear-array transducers with elevational focusing and are limited to two-dimensional imaging with anisotropic resolutions. Here, we present three-dimensional diffractive acoustic tomography (3D-DAT), which uses an off-the-shelf linear-array transducer with single-slit acoustic diffraction. Without jeopardizing its accessibility by general users, 3D-DAT has achieved simultaneous 3D photoacoustic and ultrasound imaging with optimal imaging performance in deep tissues, providing near-isotropic resolutions, high imaging speed, and a large field-of-view, as well as enhanced quantitative accuracy and detection sensitivity. Moreover, powered by the fast focal line volumetric reconstruction, 3D-DAT has achieved 50-fold faster reconstruction times than traditional photoacoustic imaging reconstruction. Using 3D-DAT on small animal models, we mapped the distribution of the biliverdin-binding serpin complex in glassfrogs, tracked gold nanoparticle accumulation in a mouse tumor model, imaged genetically-encoded photoswitchable tumors, and investigated polyfluoroalkyl substances exposure on developing embryos. With its enhanced imaging performance and high accessibility, 3D-DAT may find broad applications in fundamental life sciences and biomedical research.

Effect of tracer size distribution on magnetic particle imaging performance

Abstract Magnetic particle imaging (MPI) is a tracer-based tomographic imaging technique utilized in applications such as lung perfusion imaging, cancer diagnosis, stem cell tracking, etc. The goal of translating MPI to clinical use has prompted studies on further improving the spatial-temporal resolutions of MPI through various methods, including image reconstruction algorithm, scanning trajectory design, magnetic field profile design, and tracer design. Iron oxide magnetic nanoparticles (MNPs) are favored for MPI and magnetic resonance imaging (MRI) over other materials due to their high biocompatibility, low cost, and ease of preparation and surface modification. For core–shell MNPs, the tracers’ magnetic core size and non-magnetic coating layer characteristics can significantly affect MPI signals through dynamic magnetization relaxations. Most works to date have assumed an ensemble of MNP tracers with identical sizes, ignoring that artificially synthesized MNPs typically follow a log-normal size distribution, which can deviate theoretical results from experimental data. In this work, we first characterize the size distributions of four commercially available iron oxide MNP products and then model the collective magnetic responses of these MNPs for MPI applications. For an ensemble of MNP tracers with size standard deviations of σ, we applied a stochastic Langevin model to study the effect of size distribution on MPI imaging performance. Under an alternating magnetic field (AMF), i.e., the excitation field in MPI, we collected the time domain dynamic magnetizations (M-t curves), magnetization-field hysteresis loops (M-H curves), point-spread functions (PSFs), and higher harmonics from these MNP tracers. The intrinsic MPI spatial resolution, which is related to the full width at half maximum (FWHM) of the PSF profile, along with the higher harmonics, serve as metrics to provide insights into how the size distribution of MNP tracers affects MPI performance.

Condition assessment of bolted connections in steel structures using deep learning

Steel structure connections are prone to bolt loosening and subsequent loss of strength or stability if not inspected periodically. Use of noncontact sensing and artificial intelligence can substantially increase the safety and efficiency of these inspections; however, the existing defect detection models do not account for variability of defects in both missing and loosened bolt connections. Furthermore, the performance of available deep learning models can be substantially diminished due to the presence of background noise in images of real structures. Finding these defects could be even more difficult in highway steel structures due to the complex and continuously changing nature of background. Additionally, no datasets are available to properly use these models for defect detection. In this paper, Mask RCNN (MRCN), You Only Look Once (YOLO), and Faster RCNN (FRCNN) models were adapted for investigation. These models were trained and tuned on a unique dataset-developed by the Authors comprised of 1100 raw images with connection defects of laboratory-made and in-service structures. A series of image enhancement and augmentation techniques were used to superimpose bolt and nut defects on intact images of in-service ancillary structure and to increase the size in training dataset to 1500. After models achieved satisfactory performance in laboratory images, they were tested on field and lab data (including 200 images with defective bolt). Thermal images were used to develop an efficient way to mask image background in visual images. The result indicated that removing background decreased the false positive rate (FRP) around 65% between the investigated deep learning models on UAS image. Overall accuracy of these models estimated between where 90% and 93%when FRCNN and Mask RCN.

Feature-targeted deep learning framework for pulmonary tumorous Cone-beam CT (CBCT) enhancement with multi-task customized perceptual loss and feature-guided CycleGAN.

Thoracic Cone-beam computed tomography (CBCT) is routinely collected during image-guided radiation therapy (IGRT) to provide updated patient anatomy information for lung cancer treatments. However, CBCT images often suffer from streaking artifacts and noise caused by under-rate sampling projections and low-dose exposure, resulting in loss of lung anatomy which contains crucial pulmonary tumorous and functional information. While recent deep learning-based CBCT enhancement methods have shown promising results in suppressing artifacts, they have limited performance on preserving anatomical details containing crucial tumorous information due to lack of targeted guidance. To address this issue, we propose a novel feature-targeted deep learning framework which generates ultra-quality pulmonary imaging from CBCT of lung cancer patients via a multi-task customized feature-to-feature perceptual loss function and a feature-guided CycleGAN. The framework comprises two main components: a multi-task learning feature-selection network (MTFS-Net) for building up a customized feature-to-feature perceptual loss function (CFP-loss); and a feature-guided CycleGan network. Our experiments showed that the proposed framework can generate synthesized CT (sCT) images for the lung that achieved a high similarity to CT images, with an average SSIM index of 0.9747 and an average PSNR index of 38.5995 globally, and an average Pearman's coefficient of 0.8929 within the tumor region on multi-institutional datasets. The sCT images also achieved visually pleasing performance with effective artifacts suppression, noise reduction, and distinctive anatomical details preservation. Functional imaging tests further demonstrated the pulmonary texture correction performance of the sCT images, and the similarity of the functional imaging generated from sCT and CT images has reached an average DSC value of 0.9147, SCC value of 0.9615 and R value of 0.9661. Comparison experiments with pixel-to-pixel loss also showed that the proposed perceptual loss significantly enhances the performance of involved generative models. Our experiment results indicate that the proposed framework outperforms the state-of-the-art models for pulmonary CBCT enhancement. This framework holds great promise for generating high-quality pulmonary imaging from CBCT that is suitable for supporting further analysis of lung cancer treatment.

Breast ultrasound imaging systems performance evaluation using novel Contrast-Detail (C-D) and Anechoic-Target (A-T) phantoms.

C-D and A-T phantoms were imaged using a range of clinical breast ultrasound systems and imaging modes. A novel sensitive imaging performance metric, the Detectability Score (DS), was proposed which encompasses the Lesion Contrast to Noise Ratio (LCNR) weighted by the lesion depth and diameter. A geometry-based theoretical model comparing LCNR measured using spherical and cylindrical phantom anechoic/lesion targets was developed to investigate the influence of slice thickness on focal lesion detectability. LCNR and DS metrics derived from phantom image measurments were capable of differentiating the imaging performance of a range of ultrasound systems and advanced imaging modes, with the -2 dB contrast lesion targets offered as the most challenging to resolve. The geometry-based theoretical model, validated against phantom measurements, demonstrated the significant influence of slice thickness on focal lesion detectability, highlighting the need for increased availability of low contrast resolution spherical target phantoms for clinically realistic performance evaluation. The performance metrics coupled with the -1 dB contrast targets provide scope for evaluating future technological improvements in ultrasound systems. Given the high dependence of breast cancer care on high quality ultrasound imaging techniques, there is a need for evaluating imaging performance using clinically relevant test objects.

Automated cell annotation in multi-cell images using an improved CRF_ID algorithm.

Cell identification is an important yet difficult process in data analysis of biological images. Previously, we developed an automated cell identification method called CRF_ID and demonstrated its high performance in Caenorhabditis elegans whole-brain images (Chaudhary et al., 2021). However, because the method was optimized for whole-brain imaging, comparable performance could not be guaranteed for application in commonly used C. elegans multi-cell images that display a subpopulation of cells. Here, we present an advancement, CRF_ID 2.0, that expands the generalizability of the method to multi-cell imaging beyond whole-brain imaging. To illustrate the application of the advance, we show the characterization of CRF_ID 2.0 in multi-cell imaging and cell-specific gene expression analysis in C. elegans. This work demonstrates that high-accuracy automated cell annotation in multi-cell imaging can expedite cell identification and reduce its subjectivity in C. elegans and potentially other biological images of various origins.

What have we learnt from histology about the efficacy of coronary imaging modalities in assessing plaque composition?

Accurate evaluation of coronary artery pathology is essential for risk stratification and tailoring appropriate treatment. Intravascular imaging was introduced for this purpose 40 years ago enabling for the first time in vivo plaque characterization. Since then, several studies have evaluated the efficacy of the existing intravascular imaging modalities in assessing plaque pathology and composition and their potential in guiding intervention and predicting vulnerable plaques. Today it is known that intravascular imaging is an indispensable tool in percutaneous coronary intervention planning, but the existing modalities have a limited efficacy in predicting lesion vulnerability; a fact that should be attributed to their advantages and limitations in accurately assessing morpho-pathological features that are common in advanced atherosclerotic plaques. This review aims to provide a comprehensive evaluation of the performance of intravascular imaging in characterizing plaque phenotypes using histology as a reference standard; it summarizes the studies comparing the available invasive imaging techniques against histology, discusses the findings and limitations of these studies and highlights the potential of novel intravascular imaging approaches that were introduced for a more complete and comprehensive evaluation of plaque pathobiology.

Automated cell annotation in multi-cell images using an improved CRF_ID algorithm

Cell identification is an important yet difficult process in data analysis of biological images. Previously, we developed an automated cell identification method called CRF_ID and demonstrated its high performance in Caenorhabditis elegans whole-brain images (Chaudhary et al., 2021). However, because the method was optimized for whole-brain imaging, comparable performance could not be guaranteed for application in commonly used C. elegans multi-cell images that display a subpopulation of cells. Here, we present an advancement, CRF_ID 2.0, that expands the generalizability of the method to multi-cell imaging beyond whole-brain imaging. To illustrate the application of the advance, we show the characterization of CRF_ID 2.0 in multi-cell imaging and cell-specific gene expression analysis in C. elegans. This work demonstrates that high-accuracy automated cell annotation in multi-cell imaging can expedite cell identification and reduce its subjectivity in C. elegans and potentially other biological images of various origins.

Microsphere-assisted super-resolution polarized light microscopy for polarization-sensitive materials.

Polarization sensitivity is a fundamental phenomenon observed in nature, and its application is vital for advancing scientific discoveries. Here, we present a microsphere-assisted polarized light microscopy method that enables high-quality, label-free super-resolution imaging of polarization-sensitive materials. We investigated the imaging performance of this method using various samples, including colloidal crystals and grating structures. Both simulations and experiments were performed to explore the underlying physical mechanisms driving the enhancement in imaging quality. The results of this work have potential values for the fields of polarized light microscopy and super-resolution imaging.

Automated karyogram analysis for early detection of genetic and neurodegenerative disorders: a hybrid machine learning approach

Anomalous chromosomes are the cause of genetic diseases such as cancer, Alzheimer's, Parkinson's, epilepsy, and autism. Karyotype analysis is the standard procedure for diagnosing genetic disorders. Identifying anomalies is often costly, time-consuming, heavily reliant on expert interpretation, and requires considerable manual effort. Efforts are being made to automate karyogram analysis. However, the unavailability of large datasets, particularly those including samples with chromosomal abnormalities, presents a significant challenge. The development of automated models requires extensive labeled and incredibly abnormal data to accurately identify and analyze abnormalities, which are difficult to obtain in sufficient quantities. Although the deep learning-based architecture has yielded state-of-the-art performance in medical image anomaly detection, it cannot be generalized well because of the lack of anomalous datasets. This study introduces a novel hybrid approach that combines unsupervised and supervised learning techniques to overcome the challenges of limited labeled data and scalability in chromosomal analysis. An Autoencoder-based system is initially trained with unlabeled data to identify chromosome patterns. It is fine-tuned on labeled data, followed by a classification step using a Convolutional Neural Network (CNN). A unique dataset of 234,259 chromosome images, including the training, validation, and test sets, was used. Marking a significant achievement in the scale of chromosomal analysis. The proposed hybrid system accurately detects structural anomalies in individual chromosome images, achieving 99.3% accuracy in classifying normal and abnormal chromosomes. We also used a structural similarity index measure and template matching to identify the part of the abnormal chromosome that differed from the normal one. This automated model has the potential to significantly contribute to the early detection and diagnosis of chromosome-related disorders that affect both genetic health and neurological behavior.

Using light to image millimeter wave based on stacked meta-MEMS chip

A stacked metamaterial MEMS (meta-MEMS) chip is proposed, which can perfectly absorb electromagnetic waves, convert them into mechanical energy, drive movement of the optical micro-reflectors array, and detect millimeter waves. It is equivalent to using visible light to image a millimeter wave. The meta-MEMS adopts the design of upper and lower chip separation and then stacking to achieve the “dielectric-resonant-air-ground” structure, reduce the thickness of the metamaterial and MEMS structures, and improve the performance of millimeter wave imaging. For verification, we designed and prepared a 94 GHz meta-MEMS focal plane array chip, in which the sum of the thickness of the metamaterial and MEMS structures is only 1/2500 wavelength, the pixel size is less than 1/3 wavelength, but the absorption rate is as high as 99.8%. Moreover, a light readout module was constructed to test the millimeter wave imaging performance. The results show that the response speed can reach 144 Hz and the lens-less imaging resolution is 1.5 mm.

Number Recognition Through Color Distortion Using Convolutional Neural Networks

Machine learning applied to image-based number recognition has made significant strides in recent years. Recent use of Large Language Models (LLMs) in natural language search and generation of text have improved performance for general images, yet performance limitations still exist for data subsets related to color blindness. In this paper, we replicated the training of six distinct neural networks (MNIST, LeNet5, VGG16, AlexNet, and two AlexNet modifications) using deep learning techniques with the MNIST dataset and the Ishihara-Like MNIST dataset. While many prior works have dealt with MNIST, the Ishihara adaption addresses red-green combinations of color blindness, allowing for further research in color distortion. Through this research, we applied pre-processing to accentuate the effects of red-green and monochrome colorblindness and hyper-parameterized the existing architectures, ultimately achieving better overall performance than currently published in known works.

Comparative image quality and dosimetric performance of two generations of dedicated breast CT systems.

Dedicated breast computed tomography (bCT) systems offer detailed imaging for breast cancer diagnosis and treatment. As new bCT generations are developed, it is important to evaluate their imaging performance and dose efficiency to understand differences over previous models. To characterize the imaging performance and dose efficiency of a second-generation (GEN2) bCT system and compare them to those of a first-generation (GEN1) system. The imaging performance was evaluated through key metrics: modulation transfer function (MTF), noise power spectrum (NPS), and detective quantum efficiency (DQE) in the projection domain. In the image domain, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), and the visibility of calcifications were analyzed using a quality control (QC) phantom with masses and calcification clusters. Air kerma and tube output were measured and mean glandular dose (MGD) estimated for different phantom sizes for dosimetric characterization of the acquisition protocols set by the automatic exposure control (AEC). GEN2 outperformed GEN1 at higher spatial frequencies, with 57% of the MTF observed at 1cycles/mm compared to 43% for GEN1. For a 2mm diameter mass, GEN2 showed 60% higher CNR and 63% higher SNR. However, for larger masses, GEN1 outperformed GEN2, with CNR and SNR values higher by 12% to 44% and 14% to 43%, respectively. GEN2 also achieves higher DQE across the frequency spectrum, with 45% at 1 cycle/mm, compared to GEN1's 20%. Regarding calcifications in the QC phantom, the 320µm calcifications resulted in distinct full-width-at-half-maxima (FWHM±SD), with 897±58µm for GEN1 and 811±127µm for GEN2, with a p-value of 0.19. For 290µm calcifications, GEN1's FWHM was 866±129µm, while GEN2's was narrower at 665±57µm, with a p-valueof 0.01. The tube output was higher for GEN1 (45.2 mGy/mAs) compared to GEN2 (31.5 mGy/mAs). Additionally, GEN2 resulted in 8% lower MGD values compared to GEN1. While GEN1 offers better CNR and SNR for larger masses, GEN2 provides superior resolution for calcifications, better MTF, improved DQE, and lower MGD at AEC-determined settings.