Representative Images Research Articles

Cross-layer importance evaluation for neural network pruning

Filter pruning has achieved remarkable success in reducing memory consumption and speeding up inference for convolutional neural networks (CNNs). Some prior works, such as heuristic methods, attempted to search for suitable sparse structures during the pruning process, which may be expensive and time-consuming. In this paper, an efficient cross-layer importance evaluation (CIE) method is proposed to automatically calculate proportional relationships among convolutional layers. Firstly, every layer is pruned separately by grid sampling way to obtain the accuracy of the model for all sampling points. And then, contribution matrices are built to describe the importance of each layer to model accuracy. Finally, the binary search algorithm is used to search the optimal sparse structure under a target pruned value. Extensive experiments on multiple representative image classification tasks demonstrate that proposed method acquires better compression performance under a little time cost compared to existing pruning algorithms. For instance, it reduces more than 50% FLOPs with only a small loss of 0.93% and 0.43% in the top-1 and top-5 accuracy for ResNet50, respectively. At the cost of only 0.24% accuracy loss, the pruned VGG19 model parameters are successfully compressed by 27.23× and the throughput has increased by 2.46×. On the whole, CIE has an excellent effect on the deployment and application of the CNNs model in edge device in terms of efficiency and accuracy.

SymTC: A symbiotic Transformer-CNN net for instance segmentation of lumbar spine MRI

Intervertebral disc disease, a prevalent ailment, frequently leads to intermittent or persistent low back pain, and diagnosing and assessing of this disease rely on accurate measurement of vertebral bone and intervertebral disc geometries from lumbar MR images. Deep neural network (DNN) models may assist clinicians with more efficient image segmentation of individual instances (discs and vertebrae) of the lumbar spine in an automated way, which is termed as instance image segmentation. In this work, we proposed SymTC, an innovative lumbar spine MR image segmentation model that combines the strengths of Transformer and Convolutional Neural Network (CNN). Specifically, we designed a parallel dual-path architecture to merge CNN layers and Transformer layers, and we integrated a novel position embedding into the self-attention module of Transformer, enhancing the utilization of positional information for more accurate segmentation. To further improve model performance, we introduced a new data synthesis technique to create synthetic yet realistic MR image dataset, named SSMSpine, which is made publicly available. We evaluated our SymTC and the other 16 representative image segmentation models on our private in-house dataset and public SSMSpine dataset, using two metrics, Dice Similarity Coefficient and the 95th percentile Hausdorff Distance. The results indicate that SymTC surpasses the other 16 methods, achieving the highest dice score of 96.169 % for segmenting vertebral bones and intervertebral discs on the SSMSpine dataset. The SymTC code and SSMSpine dataset are publicly available at https://github.com/jiasongchen/SymTC.

SSAL-Net: Semi-supervised network integrating self-supervised adversarial learning for diagnosing subtypes of pulmonary nodules

Accurately diagnosing the subtype of pulmonary nodules is a crucial step in screening patients with early-stage lung cancer. However, most of existing researches can only diagnose benign and malignant pulmonary nodules but cannot give detailed subtypes. Besides, although convolutional neural networks (CNNs) have been widely used in the intelligent diagnosis of benign and malignant pulmonary nodules, it is difficult to further improve the diagnostic accuracy due to the small number of samples. In this paper, a semi-supervised network integrating self-supervised adversarial learning (SSAL-Net) suitable for small sample classification problem is proposed to diagnose adenocarcinoma, squamous cell carcinoma, inflammation, and other benign types of pulmonary nodules. SSAL-Net is mainly composed of a self-supervised classification network (SSC-Net), an unsupervised adversarial reconstruction network (UAR-Net) and a supervised classification network (SC-Net), where SSC-Net and UAR-Net share an encoder to provide representative image features to SC-Net. SSAL-Net takes three different forms of pulmonary nodule data generated based on prior knowledge as input, and enables end-to-end collaborative training through SSC-Net, UAR-Net and SC-Net performing their respective tasks. The experimental results show that SSAL-Net can identify adenocarcinoma, squamous cell carcinoma, inflammation and other benign types of pulmonary nodules with an average accuracy of 89.29% on our self-constructed lung CT image dataset, and can identify malignant pulmonary nodules with an average accuracy of 94.67% on the publicly available LIDC-IDRI dataset, obtaining the state-of-the-art results.

NetDiffus: Network traffic generation by diffusion models through time-series imaging

While Machine-Learning based network data analytics are now commonplace for many networking solutions, nonetheless, limited access to appropriate networking data has been an enduring challenge for many networking problems. Causes for lack of such data include complexity of data gathering, commercial sensitivity, as well as privacy and regulatory constraints. To overcome these challenges, we present a Diffusion-Model (DM) based end-to-end framework, NetDiffus, for synthetic network traffic generation which is one of the emerging topics in networking and computing system. NetDiffus first converts one-dimensional time-series network traffic into two-dimensional images, and then synthesizes representative images for the original data. We demonstrate that NetDiffus outperforms the state-of-the-art traffic generation methods based on Generative Adversarial Networks (GANs) by providing 66.4% increase in the fidelity of the generated data and an 18.1% increase in downstream machine learning tasks. We evaluate NetDiffus on seven diverse traffic traces and show that utilizing synthetic data significantly improves several downstream ML tasks including traffic fingerprinting, anomaly detection and traffic classification. The code has been included at https://github.com/Nirhoshan/NetDiffus.

ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts.

The development of next-generation tissue-engineered medical devices such as tissue-engineered vascular grafts (TEVGs) is a leading trend in translational medicine. Microscopic examination is an indispensable part of animal experimentation, and histopathological analysis of regenerated tissue is crucial for assessing the outcomes of implanted medical devices. However, the objective quantification of regenerated tissues can be challenging due to their unusual and complex architecture. To address these challenges, research and development of advanced ML-driven tools for performing adequate histological analysis appears to be an extremely promising direction. We compiled a dataset of 104 representative whole slide images (WSIs) of TEVGs which were collected after a 6-month implantation into the sheep carotid artery. The histological examination aimed to analyze the patterns of vascular tissue regeneration in TEVGs in situ. Having performed an automated slicing of these WSIs by the Entropy Masker algorithm, we filtered and then manually annotated 1,401 patches to identify 9 histological features: arteriole lumen, arteriole media, arteriole adventitia, venule lumen, venule wall, capillary lumen, capillary wall, immune cells, and nerve trunks. To segment and quantify these features, we rigorously tuned and evaluated the performance of six deep learning models (U-Net, LinkNet, FPN, PSPNet, DeepLabV3, and MA-Net). After rigorous hyperparameter optimization, all six deep learning models achieved mean Dice Similarity Coefficients (DSC) exceeding 0.823. Notably, FPN and PSPNet exhibited the fastest convergence rates. MA-Net stood out with the highest mean DSC of 0.875, demonstrating superior performance in arteriole segmentation. DeepLabV3 performed well in segmenting venous and capillary structures, while FPN exhibited proficiency in identifying immune cells and nerve trunks. An ensemble of these three models attained an average DSC of 0.889, surpassing their individual performances. This study showcases the potential of ML-driven segmentation in the analysis of histological images of tissue-engineered vascular grafts. Through the creation of a unique dataset and the optimization of deep neural network hyperparameters, we developed and validated an ensemble model, establishing an effective tool for detecting key histological features essential for understanding vascular tissue regeneration. These advances herald a significant improvement in ML-assisted workflows for tissue engineering research and development.

Zinner syndrome: a radiological journey through a little known condition.

Zinner syndrome is a rare congenital urological entity, secondary to an alteration in embryogenesis between 4th and 13th weeks of gestation, specifically because of abnormalities in the development of the distal mesonephric duct. It is characterized by the triad of unilateral renal agenesis, cystic dilatation of the ipsilateral seminal vesicle and ipsilateral ejaculatory duct obstruction. The aim of this article is to provide the reader with all the necessary information to be able to suspect the presence of this syndrome, reviewing its physiopathology, clinical manifestations and the imaging techniques that enable its diagnosis, emphasizing those radiological findings by MRI that should lead us to think about it. This work is illustrated with representative radiological images of cases belonging to our institution, including patients with different variants of Zinner syndrome. We also include an overview of the embryology of the male urogenital system, to remember the role of the mesonephric duct and the ureteral bud in the formation of the different urogenital structures, as well as a differential diagnosis that allows us to differentiate seminal vesicle cysts from other pelvic cystic lesions.

Research on color and texture characteristics and visual perception of custom wardrobe finishes

In recent years, the custom wardrobe market has been steadily developing. While meeting the functional needs of users, it is gradually shifting towards aesthetic preferences. Rapidly grasping users’ preferences for the appearance of custom wardrobes is a key focus of current research. This study collected a large number of decorative surface images of custom wardrobes and objectively analyzed the design features based on color moments and Tamura texture feature data in computer image analysis methods. K-means cluster analysis was performed on the feature data. Collected images of the points closest to the cluster centers were further screened to select representative finish images, and finally a questionnaire survey was conducted at Nanjing Forestry University, with the help of semantic differential method and factor analysis. The characteristics of the samples were comprehensively summarized to infer design elements. The study found that warm-toned, medium-low saturation, and medium brightness surfaces were preferred by the panel. Different colors, contrasts, saturations, brightness, element features, and arrangements have significantly different effects on visual perception. These conclusions can provide a reference for subsequent custom wardrobe design.

Evaluation of postoperative complications of hypospadias using high-frequency ultrasound imaging

PurposeVarious complications following hypospadias surgery present distinct manifestations when examined with ultrasound. Utilizing high-frequency ultrasound, clinicians can promptly identify these complications and initiate appropriate treatment. The aim of this study is to catalogue the ultrasonographic presentations of various postoperative complications following hypospadias surgery, thereby providing a reference for ultrasonographic diagnosis.MethodsUltrasonic images of post-hypospadias surgery from October 1, 2015, to June 30, 2023, recorded at the Plastic Surgery Hospital of the Chinese Academy of Medical Sciences, serve as the basis for this investigation. Drawing on patient clinical diagnoses, this study compiles and selects representative ultrasound images of diverse complications.ResultsThe study encompassed a total of 121 subjects; 26 demonstrated urethral stricture on ultrasonic images, two presented local urethral dilation, six showed intraurethral hair-like structures, 17 revealed intraurethral septum, two exhibited intraurethral fold, one had urethral calculus, one displayed urethral calcification, 12 indicated intraurethral urine accumulation, and two showed urethral diverticulum.ConclusionUltrasound examination is helpful for postoperative diagnosis following hypospadias, detecting complications such as urethral stricture, urethral hair growth, and urethral diverticulum, which can help doctors choose appropriate clinical treatment strategies.

Generation of pore-space images using improved pyramid Wasserstein generative adversarial networks

High-resolution three-dimensional X-ray microscopy can be used to image the pore space of materials. Machine learning algorithms can generate a statistical ensemble of representative images of arbitrary sizes for rock characterization, modeling, and analysis. However, current methods struggle to capture features at different spatial scales observed in many complex rocks which have a wide range of pore size. We use the Improved Pyramid Wasserstein Generative Adversarial Network (IPWGAN) to automatically reproduce multi-scale features in segmented three-dimensional images of porous materials, enabling the reliable generation of large-scale representations of complex porous media. A Laplacian pyramid generator is introduced, which creates pore-space features across a hierarchy of spatial scales. Feature statistics mixing regularization enhances the discriminator’s ability to distinguish between real and generated images by mixing their feature statistics, thereby indirectly enhancing the generator’s ability to capture and reproduce multi-scale pore-space features, leading to increased diversity and realism in the generated images. The method has been tested on five sandstone and carbonate samples. The generated images, which can be of any size – including cm-scale ten-billion-cell images – demonstrate the power of the approach. These images have two-point correlation functions, porosity, permeability, Euler characteristic, curvature, and specific surface area closer to those of the training datasets than existing machine learning techniques. The generated images accurately capture geometric and flow properties, demonstrating a considerable improvement over previously published studies using generative adversarial networks. For instance, the mean relative error in the calculated absolute permeability between the Berea sandstone images generated by IPWGAN and the corresponding real rock images can be reduced by 79%. The work allows representative models of a wide range of porous media to be generated, offering potential benefits in carbon dioxide sequestration, underground hydrogen storage, and enhanced oil recovery.

Intelligent emotion recognition in product design using multimodal physiological signals and machine learning

Identifying emotional responses in products is essential for product design and user research. Traditional methods, such as interviews and surveys, for gathering product experience data are time-consuming and resource-intensive, and often fail to capture users’ genuine emotional intentions. This article introduces an intelligent method for accurately identifying user-product emotions using multimodal physiological signals and machine learning techniques. The study involves designing experiments with 63 representative product images, and collecting various physiological signals (eye movement, electrodermal activity, and pulse). Using the K-means algorithm, we establish efficacy-arousal assessment labels to create a product emotion dataset. Preprocessing methods, including time–frequency analysis and wavelet transformation, ensure high-quality signal analysis data. By extracting temporal, frequency, and time–frequency features from multimodal physiological signals, the Relief algorithm determines the optimal feature combination. Finally, the study evaluates the performance of five machine learning classifiers, with results indicating an 81.31% recognition accuracy for the proposed product emotion recognition framework. This framework proves effective for objectively analyzing user emotions in product experiences.

Deep learning models for interpretation of point of care ultrasound in military working dogs.

Military working dogs (MWDs) are essential for military operations in a wide range of missions. With this pivotal role, MWDs can become casualties requiring specialized veterinary care that may not always be available far forward on the battlefield. Some injuries such as pneumothorax, hemothorax, or abdominal hemorrhage can be diagnosed using point of care ultrasound (POCUS) such as the Global FAST® exam. This presents a unique opportunity for artificial intelligence (AI) to aid in the interpretation of ultrasound images. In this article, deep learning classification neural networks were developed for POCUS assessment in MWDs. Images were collected in five MWDs under general anesthesia or deep sedation for all scan points in the Global FAST® exam. For representative injuries, a cadaver model was used from which positive and negative injury images were captured. A total of 327 ultrasound clips were captured and split across scan points for training three different AI network architectures: MobileNetV2, DarkNet-19, and ShrapML. Gradient class activation mapping (GradCAM) overlays were generated for representative images to better explain AI predictions. Performance of AI models reached over 82% accuracy for all scan points. The model with the highest performance was trained with the MobileNetV2 network for the cystocolic scan point achieving 99.8% accuracy. Across all trained networks the diaphragmatic hepatorenal scan point had the best overall performance. However, GradCAM overlays showed that the models with highest accuracy, like MobileNetV2, were not always identifying relevant features. Conversely, the GradCAM heatmaps for ShrapML show general agreement with regions most indicative of fluid accumulation. Overall, the AI models developed can automate POCUS predictions in MWDs. Preliminarily, ShrapML had the strongest performance and prediction rate paired with accurately tracking fluid accumulation sites, making it the most suitable option for eventual real-time deployment with ultrasound systems. Further integration of this technology with imaging technologies will expand use of POCUS-based triage of MWDs.

Comparison between PA and PWI/TFM Techniques for Non-Destructive Testing of Carbon Steel Weld

The Total Focusing Method (TFM) technique is an advanced Non-Destructive Testing (NDT) Ultrasonic Testing (UT) technique well known for its representative images of high resolution. It was firstly developed together with Full Matrix Capture (FMC) acquisition which can be substituted later by Plane Wave Imaging (PWI) acquisition for its improved acquisition speed and gain reserve without lowering the image quality. For these advantages, the PWI/TFM technique is tending to be more and more widely implemented. This article presents some results of the related study on PWI/TFM technique. Starting by PWI/TFM reconstruction principles, mainly on the influences of beam steering settings and corresponding inspection coverage in predefined Region of Interest (ROI), it focuses on the comparison on the indication amplitudes of planar discontinuities between classical Phased Array (PA) technique and PWI/TFM technique.

Airway and Voice Outcomes After Thyroarytenoid Myomectomy for Bilateral Vocal Fold Immobility.

Type 4 posterior glottic stenosis and bilateral vocal fold paralysis are clinically challenging causes of bilateral vocal fold immobility (BVFI) that result in glottic airway obstruction. Established procedures for BVFI typically worsen dysphonia. We hypothesize the use of thyroarytenoid myomectomy (TAM) in the setting of BVFI will improve dyspnea with decreased detriment to voice. Eleven unilateral TAM procedures were performed between April 2021 and June 2023 at a single institution. Pre- and postoperative patient reported outcomes were compared. Representative images of maximal glottic opening were analyzed in ImageJ to calculate ipsilateral bowing index (BI), total BI, maximum glottic surface area (MGSA), and maximum opening angle (MOA). Statistical comparisons were performed with paired t-tests when normality was confirmed with Shapiro-Wilk test and otherwise with Wilcoxon signed-rank tests, with threshold for significance of α = 0.05. Interrater reliability for objective glottal measures was compared with intraclass correlation coefficient (ICC). Dyspnea Index improved from mean (standard error) of 24.1 (3.8) to 9.1 (3.3), p = 0.004. Voice Handicap Index-10 improved from 20.0 (4) to 10.3 (3.8), p = 0.011. Glottal Function Index improved from 9.6 (1.4) to 6.3 (1.3), p = 0.017. There was no significant difference in ipsilateral BI, total BI, MOA, and median MGSA. There was good to excellent ICCs for all comparisons (0.83-0.95). TAM demonstrated significant improvement in symptoms from BVFI while not significantly altering glottal structure. These data suggest TAM improves dyspnea in patients with BVFI without significantly impairing voice. 4 Laryngoscope, 134:4307-4312, 2024.

#2607 Generation of a tissue resident macrophage depleted reporter rat to examine cardiovascular homeostasis and kidney disease

Abstract Cardiovascular disease (CVD) and chronic kidney disease (CKD) are currently the 1st and 10th leading cause of global mortality, respectively. By 2050, CKD is predicted to be the 5th leading cause, with most of those individuals dying of CVD. Recent single cell RNA sequencing data has highlighted the plasticity of macrophage populations in both renal and cardiovascular injury and repair. Many of these subpopulations of macrophages remain uncharacterized. We have generated the Red FIRE rat, which is a cross between the Csf1r-mApple reporter rat and the super-enhancer FIRE knockout rat. The Csf1r-mApple reporter rat introduces a fluorescent signal to cells of the monocyte-macrophage lineage and the KO of FIRE (fms-intronic regulatory element), while the FIRE rat has fms-intronic regulatory element (FIRE), which is the superenhancer in the Csf1r locus knocked out, resulting in depletion of tissue resident macrophages. These red FIRE rats will allow us to visualize all Csf1r expressing cells (macrophages) and in the FIRE rats deplete populations of tissue resident macrophages (TRM) (including those in the kidney and heart). This will enable us to visualize and study TRM populations in homeostasis and injury. We hypothesise that the red FIRE rats will show a more severe phenotype in injury and have altered vascular function (local and systemic). Male and female (8–10-week-old) rats underwent a 6- or 12-week 5/6 subtotal nephrectomy (5/6 STNx) in groups of 4-8. Baseline, midpoint and endpoint urine and serum were collected for analysis, as well as blood pressure measurements and echocardiograms to monitor kidney and heart health/decline. At the end of the experiment, kidneys and the heart were collected for flow cytometry, immunofluorescence, RT-qPCR, and histological staining. The thoracic aorta, mesentery, and common renal arteries were collected for functional analysis using isometric (wire)myography. The knockout of the FIRE super enhancer resulted in depletion of kidney TRMs (Fig. 1) as visualised by immunofluorescent staining of both wild type and macrophage-depleted (red FIRE) rat tissue. Figure 1A shows the composite image and individual stains; DAPI, IBa1 (pan macrophage marker), and Csf1r-mApple (tissue resident macrophages) on a naïve heart. Representative composite images also compare STNx hearts (Fig. 1B) and kidneys (Fig. 1C) in both wild type and macrophage-depleted rats. This allowed for comparison of these rats in both injury and homeostasis. Figure 1: Immunofluorescent staining of the uninjured heart of a FIRE wild type (WT), mApple positive rat (A), the injured kidney (B) and heart (C) of mApple positive, FIRE wild type (Control) or mApple positive, FIRE knock out (FIRE) rats post 12-week 5/6 subtotal nephrectomy (5/6 STNx). DAPI: nuclei, IBa1: all macrophages, csf1r (mApple): tissue resident macrophages. Representative imagining, figure made using FIJI. Our preliminary data suggests previously undescribed roles for tissue-resident macrophages in rats i.e. ion handling, vascular homeostasis and roles in CKD and repair. These results could help reveal new specific druggable targets that could be exploited for treatments which could halt progression of disease and thus reduce end stage renal failure patient numbers, healthcare costs and premature CVD-related deaths.

Cytotoxic effect of silver nanoparticles biosynthesized from Hirudo medicinalis saliva on HepG2 cells

Primary hepatocellular carcinoma is a devastating type of liver cancer. Silver nanoparticles (AgNPs) have been assessed for a variety of purposes, including being tested as an anticancer agent. The aim of this study was to assess the cytotoxicity of AgNPs that were biosynthesized from leech saliva on HepG2 cells, through the undertaking of a simple MTT assay. HepG2 cells were obtained from the cell bank of the Pasteur Institute of Iran. In this study, AgNP-treated HepG2 cells were cultured at a density of 104 cells per well, and 100 μL of MTT at a concentration of 0.5 mg/mL were added to each well; the treated cells were then let to incubate for 4 h. Subsequently, a plate reader device operating at a wavelength of 570 nm was used in order to determine the concentration of the chemical dissolved in isopropanol. Representative images of the cells show remarkable changes in their morphology at AgNP concentrations of 25 and 50 μg/mL. At 48 h, the nanoparticle’s IC50 value was 50 μg/mL. Our study shows that leech salivary extract-derived AgNPs are cytotoxic to HepG2 cells.

Improving image quality of sparse-view lung tumor CT images with U-Net

BackgroundWe aimed to improve the image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determine the best tradeoff between number of views, IQ, and diagnostic confidence.MethodsCT images from 41 subjects aged 62.8 ± 10.6 years (mean ± standard deviation, 23 men), 34 with lung metastasis, 7 healthy, were retrospectively selected (2016–2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used.ResultsThe 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images.ConclusionsProjection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level.Relevance statementOur reader study demonstrates the benefit of U-Net postprocessing for regular CT screenings of patients with lung metastasis to increase the IQ and diagnostic confidence while reducing the dose.Key points• Sparse-projection-view streak artifacts reduce the quality and usability of sparse-view CT images.• U-Net-based postprocessing removes sparse-view artifacts while maintaining diagnostically accurate IQ.• Postprocessed sparse-view CTs drastically increase radiologists’ confidence in diagnosing lung metastasis.Graphical

Abstract PO1-06-07: EMSY enhances cancer stem cell self-renewal and tumorigenesis by reshaping methionine metabolism in triple-negative breast cancer

Abstract PO1-06-07: EMSY enhances cancer stem cell self-renewal and tumorigenesis by reshaping methionine metabolism in triple-negative breast cancer

Response Evaluation Criteria in Gastrointestinal and Abdominal Cancers: Which to Use and How to Measure.

As the management of gastrointestinal malignancy has evolved, tumor response assessment has expanded from size-based assessments to those that include tumor enhancement, in addition to functional data such as those derived from PET and diffusion-weighted imaging. Accurate interpretation of tumor response therefore requires knowledge of imaging modalities used in gastrointestinal malignancy, anticancer therapies, and tumor biology. Targeted therapies such as immunotherapy pose additional considerations due to unique imaging response patterns and drug toxicity; as a consequence, immunotherapy response criteria have been developed. Some gastrointestinal malignancies require assessment with tumor-specific criteria when assessing response, often to guide clinical management (such as watchful waiting in rectal cancer or suitability for surgery in pancreatic cancer). Moreover, anatomic measurements can underestimate therapeutic response when applied to molecular-targeted therapies or locoregional therapies in hypervascular malignancies such as hepatocellular carcinoma. In these cases, responding tumors may exhibit morphologic changes including cystic degeneration, necrosis, and hemorrhage, often without significant reduction in size. Awareness of pitfalls when interpreting gastrointestinal tumor response is required to correctly interpret response assessment imaging and guide appropriate oncologic management. Data-driven image analyses such as radiomics have been investigated in a variety of gastrointestinal tumors, such as identifying those more likely to respond to therapy or recur, with the aim of delivering precision medicine. Multimedia-enhanced radiology reports can facilitate communication of gastrointestinal tumor response by automatically embedding response categories, key data, and representative images. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Abstract 1142: Effect Of Chronic E-cigarette Nicotine Exposure On A Mouse Model Of Hind-limb Ischemia

Background: The rise of e-cigarette use in the United States has been rapid, yet its impact on peripheral artery disease (PAD) remains largely unexplored. This study investigates the relationship between e-cigarette use and PAD using a mouse ischemic hindlimb model. Method: Mice aged 6-8 weeks were divided into four groups. Three groups inhaled e-cigarette vapor continuously for 14, 20, or 28 days prior, and for 28 days after hindlimb ischemia (HLI) surgery, using an InExpose system (Figure 1). A control group was exposed to room air (RA) before and after HLI. Laser-Doppler perfusion imaging tracked hindlimb blood flow, and functional deficits were assessed using the modified ischemia scale. Figure 1: Methodology Results: Blood perfusion in the ischemic hindlimb of the e-cigarette groups (EC-14, EC-20, EC-28) was significantly lower than the non-vaping group at 21 days post-surgery. In the EC-14 group, perfusion improved after 10 days of vaping cessation (Figure 2). Additionally, there was a reduction in platelet and leukocyte counts in the e-cigarette groups compared to RA, with no difference in red blood cells. Necrosis and claw damage were observed in EC-20 and EC-28 groups but not in non-vaping mice. Figure 2: Representative images of perfusion recovery measured by LDPI. Conclusion: Chronic e-cigarette nicotine exposure impairs blood flow recovery and causes necrosis in mice with hind limb ischemia, potentially due to perturbed angiogenesis and arteriogenesis. This study highlights the detrimental effects of e-cigarette nicotine on vascular health.

Drug-induced mucosal alterations observed during esophagogastroduodenoscopy.

Several features of drug-induced mucosal alterations have been observed in the upper gastrointestinal tract, i.e., the esophagus, stomach, and duodenum. These include pill-induced esophagitis, desquamative esophagitis, worsening of gastroesophageal reflux, chemotherapy-induced esophagitis, proton pump inhibitor-induced gastric mucosal changes, medication-induced gastric erosions and ulcers, pseudomelanosis of the stomach, olmesartan-related gastric mucosal inflammation, lanthanum deposition in the stomach, zinc acetate hydrate tablet-induced gastric ulcer, immune-related adverse event gastritis, olmesartan-asso-ciated sprue-like enteropathy, pseudomelanosis of the duodenum, and lanthanum deposition in the duodenum. For endoscopists, acquiring accurate knowledge regarding these diverse drug-induced mucosal alterations is crucial not only for the correct diagnosis of these lesions but also for differential diag-nosis of other conditions. This minireview aims to provide essential information on drug-induced mucosal alterations observed on esophagogastroduodenoscopy, along with representative endoscopic images.