From E-Commerce to the Metaverse: A Neuroscientific Analysis of Digital Consumer Behavior.

The growing interest in consumer behavior in the digital environment is leading scholars and companies to focus on consumer behavior and choices on digital platforms, such as the metaverse. On this immersive digital shopping platform, consumer neuroscience provides an optimal opportunity to explore consumers' emotions and cognitions. In this study, neuroscience techniques (EEG, SC, BVP) were used to compare emotional and cognitive aspects of shopping between metaverse and traditional e-commerce platforms. Participants were asked to purchase the same product once on a metaverse platform (Second Life, SL) and once via an e-commerce website (EC). After each task, questionnaires were administered to measure perceived enjoyment, informativeness, ease of use, cognitive effort, and flow. Statistical analyses were conducted to examine differences between SL and EC at the neurophysiological and self-report levels, as well as between different stages of the purchase process. The results show that SL elicits greater cognitive engagement than EC, but it is also more mentally demanding, with a higher workload and more memorization, and fails to elicit a strong positive emotional response, leading to a poorer shopping experience. These findings provide insights not only for digital-related consumer research but also for companies to improve their metaverse shopping experience. Before investing in the platform or creating a digital retail space, companies should thoroughly analyze it, focusing on how to enhance users' cognition and emotions, ultimately promoting a better consumer experience. Despite its limitations, this pilot study sheds light on the emotional and cognitive aspects of metaverse shopping and suggests potential for further research with a consumer neuroscience approach in the metaverse field.

Understanding mechanisms of generalization following locomotor adaptation.

Our nervous system has the remarkable ability to adapt our gait to accommodate changes in our body or surroundings. However, our adapted walking patterns often generalize only partially (or not at all) between different contexts. Here, we sought to understand how the nervous system generalizes adapted gait patterns from one context to another. Through a series of split-belt treadmill walking experiments, we evaluated different mechanistic hypotheses to explain the partial generalization of adapted gait patterns from split-belt treadmill to overground walking. In support of the credit assignment hypothesis, our experiments revealed the central finding that adaptation involves recalibration of two distinct forward models. Recalibration of the first model generalizes to overground walking, suggesting that the model represents the general movement dynamics of our body. On the other hand, recalibration of the second model does not generalize to overground walking, suggesting the model represents dynamics specific to treadmill walking. These findings reveal that there is a predefined portion of forward model recalibration that generalizes across context, leading to overall partial generalization of walking adaptation.

Explainable Precision Medicine in Breast MRI: A Combined Radiomics and Deep Learning Approach for the Classification of Contrast Agent Uptake.

In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. In accordance with the Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility of such an assessment to inter-reader variability highlights the urgent need for a standardized classification algorithm. In this retrospective study, the first post-contrast subtraction images for 27 healthy female subjects were included. The BPE was classified slice-wise by two expert radiologists. The extraction of radiomic features from segmented BPE was followed by dataset splitting and dimensionality reduction. The latent representations were then utilized as inputs to a deep neural network classifying BPE into BI-RADS classes. The network's predictions were elucidated at the radiomic feature level with Shapley values. The deep neural network achieved a BPE classification accuracy of 84 ± 2% (p-value < 0.00001). Most of the misclassifications involved adjacent classes. Different radiomic features were decisive for the prediction of each BPE class underlying the complexity of the decision boundaries. A highly precise and explainable pipeline for BPE classification was achieved without user- or algorithm-dependent radiomic feature selection.

Automatic Detection of Post-Operative Clips in Mammography Using a U-Net Convolutional Neural Network.

BACKGROUND: After breast conserving surgery (BCS), surgical clips indicate the tumor bed and, thereby, the most probable area for tumor relapse. The aim of this study was to investigate whether a U-Net-based deep convolutional neural network (dCNN) may be used to detect surgical clips in follow-up mammograms after BCS. METHODS: 884 mammograms and 517 tomosynthetic images depicting surgical clips and calcifications were manually segmented and classified. A U-Net-based segmentation network was trained with 922 images and validated with 394 images. An external test dataset consisting of 39 images was annotated by two radiologists with up to 7 years of experience in breast imaging. The network's performance was compared to that of human readers using accuracy and interrater agreement (Cohen's Kappa). RESULTS: The overall classification accuracy on the validation set after 45 epochs ranged between 88.2% and 92.6%, indicating that the model's performance is comparable to the decisions of a human reader. In 17.4% of cases, calcifications have been misclassified as post-operative clips. The interrater reliability of the model compared to the radiologists showed substantial agreement (κreader1 = 0.72, κreader2 = 0.78) while the readers compared to each other revealed a Cohen's Kappa of 0.84, thus showing near-perfect agreement. CONCLUSIONS: With this study, we show that surgery clips can adequately be identified by an AI technique. A potential application of the proposed technique is patient triage as well as the automatic exclusion of post-operative cases from PGMI (Perfect, Good, Moderate, Inadequate) evaluation, thus improving the quality management workflow.

The impact of physical activity on promoter-specific methylation of genes involved in the redox-status and disease progression: A longitudinal study on post-surgery female breast cancer patients undergoing medical treatment.

Most anticancer treatments act on oxidative-stress pathways by producing reactive oxygen species (ROS) to kill cancer cells, commonly resulting in consequential drug-induced systemic cytotoxicity. Physical activity (PA) has arisen as an integrative cancer therapy, having positive health effects, including in redox-homeostasis. Here, we investigated the impact of an online supervised PA program on promoter-specific DNA methylation, and corresponding gene expression/activity, in 3 antioxidants- (SOD1, SOD2, and CAT) and 3 breast cancer (BC)-related genes (BRCA1, L3MBTL1 and RASSF1A) in a population-based sample of women diagnosed with primary BC, undergoing medical treatment. We further examined mechanisms involved in methylating and demethylating pathways, predicted biological pathways and interactions of exercise-modulated molecules, and the functional relevance of modulated antioxidant markers on parameters related to aerobic capacity/endurance, physical fatigue and quality of life (QoL). PA maintained levels of SOD activity in blood plasma, and at the cellular level significantly increased SOD2 mRNA (≈+77 %), contrary to their depletion due to medical treatment. This change was inversely correlated with DNA methylation in SOD2 promoter (≈-20 %). Similarly, we found a significant effect of PA only on L3MBTL1 promoter methylation (≈-25 %), which was inversely correlated with its mRNA (≈+43 %). Finally, PA increased TET1 mRNA levels (≈+15 %) and decreased expression of DNMT3B mRNA (≈-28 %). Our results suggest that PA-modulated DNA methylation affects several signalling pathways/biological activities involved in the cellular oxidative stress response, chromatin organization/regulation, antioxidant activity and DNA/protein binding. These changes may positively impact clinical outcomes and improve the response to cancer treatment in post-surgery BC patients.

Generalizable attention U-Net for segmentation of fibroglandular tissue and background parenchymal enhancement in breast DCE-MRI.

OBJECTIVES: Development of automated segmentation models enabling standardized volumetric quantification of fibroglandular tissue (FGT) from native volumes and background parenchymal enhancement (BPE) from subtraction volumes of dynamic contrast-enhanced breast MRI. Subsequent assessment of the developed models in the context of FGT and BPE Breast Imaging Reporting and Data System (BI-RADS)-compliant classification. METHODS: For the training and validation of attention U-Net models, data coming from a single 3.0-T scanner was used. For testing, additional data from 1.5-T scanner and data acquired in a different institution with a 3.0-T scanner was utilized. The developed models were used to quantify the amount of FGT and BPE in 80 DCE-MRI examinations, and a correlation between these volumetric measures and the classes assigned by radiologists was performed. RESULTS: To assess the model performance using application-relevant metrics, the correlation between the volumes of breast, FGT, and BPE calculated from ground truth masks and predicted masks was checked. Pearson correlation coefficients ranging from 0.963 ± 0.004 to 0.999 ± 0.001 were achieved. The Spearman correlation coefficient for the quantitative and qualitative assessment, i.e., classification by radiologist, of FGT amounted to 0.70 (p < 0.0001), whereas BPE amounted to 0.37 (p = 0.0006). CONCLUSIONS: Generalizable algorithms for FGT and BPE segmentation were developed and tested. Our results suggest that when assessing FGT, it is sufficient to use volumetric measures alone. However, for the evaluation of BPE, additional models considering voxels' intensity distribution and morphology are required. CRITICAL RELEVANCE STATEMENT: A standardized assessment of FGT density can rely on volumetric measures, whereas in the case of BPE, the volumetric measures constitute, along with voxels' intensity distribution and morphology, an important factor. KEY POINTS: • Our work contributes to the standardization of FGT and BPE assessment. • Attention U-Net can reliably segment intricately shaped FGT and BPE structures. • The developed models were robust to domain shift.

Automatic learning mechanisms for flexible human locomotion.

Movement flexibility and automaticity are necessary to successfully navigate different environments. When encountering difficult terrains such as a muddy trail, we can change how we step almost immediately so that we can continue walking. This flexibility comes at a cost since we initially must pay deliberate attention to how we are moving. Gradually, after a few minutes on the trail, stepping becomes automatic so that we do not need to think about our movements. Canonical theory indicates that different adaptive motor learning mechanisms confer these essential properties to movement: explicit control confers flexibility, while forward model recalibration confers automaticity. Here we uncover a distinct mechanism of treadmill walking adaptation - an automatic stimulus-response mapping - that confers both properties to movement. The mechanism is flexible as it learns stepping patterns that can be rapidly changed to suit a range of treadmill configurations. It is also automatic as it can operate without deliberate control or explicit awareness by the participants. Our findings reveal a tandem architecture of forward model recalibration and automatic stimulus-response mapping mechanisms for walking, reconciling different findings of motor adaptation and perceptual realignment.

Neuroselling: applying neuroscience to selling for a new business perspective. An analysis on teleshopping advertising.

This paper presents an innovative research project that aims to study the emotional factors influencing decision-making elicited by infomercials, a powerful sales technique that uses emotional communication to engage viewers, capture attention, and build trust. Using cutting-edge consumer neuroscience techniques, this study focuses on the identification of the variables that most impact the Call-to-Action and Purchase Intention. Forty participants were selected and divided into two groups, with each group exposed to one of two infomercials (condition A = male seller; condition B = female seller). EEG signals were recorded as well as Eye-tracking data. After the viewing, participants completed a self-report questionnaire. Results show that seller characteristics such as Performance and Trustworthiness, as well as Neurophysiological variables such as Approach-Withdrawal Index, Willingness to Pay, Attention and Engagement, significantly impact the final Call-to-Action, Purchase Intention, and infomercial Likeability responses. Moreover, eye-tracking data revealed that the more time is spent observing crucial areas of the infomercial, the more it will increase our Willingness to Pay and our interest and willingness to approach the infomercial and product. These findings highlight the importance of considering both the Seller attributes and the consumers' Neurophysiological responses to understand and predict their behaviors in response to marketing stimuli since they all seem to play a crucial role in shaping consumers' attitudes and purchase intentions. Overall, the study is a significant pilot in the new field of neuroselling, shedding light on crucial emotional aspects of the seller/buyer relationship and providing valuable insights for researchers and marketers.

Endocrine Disruptors in Food, Estrobolome and Breast Cancer.

The microbiota is now recognized as one of the major players in human health and diseases, including cancer. Regarding breast cancer (BC), a clear link between microbiota and oncogenesis still needs to be confirmed. Yet, part of the bacterial gene mass inside the gut, constituting the so called "estrobolome", influences sexual hormonal balance and, since the increased exposure to estrogens is associated with an increased risk, may impact on the onset, progression, and treatment of hormonal dependent cancers (which account for more than 70% of all BCs). The hormonal dependent BCs are also affected by environmental and dietary endocrine disruptors and phytoestrogens which interact with microbiota in a bidirectional way: on the one side disruptors can alter the composition and functions of the estrobolome, ad on the other the gut microbiota influences the metabolism of endocrine active food components. This review highlights the current evidence about the complex interplay between endocrine disruptors, phytoestrogens, microbiome, and BC, within the frames of a new "oncobiotic" perspective.

Detection of microcalcifications in photon-counting dedicated breast-CT using a deep convolutional neural network: Proof of principle.

OBJECTIVE: In this study, we investigate the feasibility of a deep Convolutional Neural Network (dCNN), trained with mammographic images, to detect and classify microcalcifications (MC) in breast-CT (BCT) images. METHODS: This retrospective single-center study was approved by the local ethics committee. 3518 icons generated from 319 mammograms were classified into three classes: "no MC" (1121), "probably benign MC" (1332), and "suspicious MC" (1065). A dCNN was trained (70% of data), validated (20%), and tested on a "real-world" dataset (10%). The diagnostic performance of the dCNN was tested on a subset of 60 icons, generated from 30 mammograms and 30 breast-CT images, and compared to human reading. ROC analysis was used to calculate diagnostic performance. Moreover, colored probability maps for representative BCT images were calculated using a sliding-window approach. RESULTS: The dCNN reached an accuracy of 98.8% on the "real-world" dataset. The accuracy on the subset of 60 icons was 100% for mammographic images, 60% for "no MC", 80% for "probably benign MC" and 100% for "suspicious MC". Intra-class correlation between the dCNN and the readers was almost perfect (0.85). Kappa values between the two readers (0.93) and the dCNN were almost perfect (reader 1: 0.85 and reader 2: 0.82). The sliding-window approach successfully detected suspicious MC with high image quality. The diagnostic performance of the dCNN to classify benign and suspicious MC was excellent with an AUC of 93.8% (95% CI 87, 4%-100%). CONCLUSION: Deep convolutional networks can be used to detect and classify benign and suspicious MC in breast-CT images.

Systematic analysis of changes in radiomics features during dynamic breast-MRI: Evaluation of specific biomarkers.

OBJECTIVES: In this retrospective, single-center study we investigate the changes of radiomics features during dynamic breast-MRI for healthy tissue compared to benign and malignant lesions. METHODS: 60 patients underwent breast-MRI using a dynamic 3D gradient-echo sequence. Changes of 34 texture features (TF) in 30 benign and 30 malignant lesions were calculated for 5 dynamic datasets and corresponding 4 subtraction datasets. Statistical analysis was performed with ANOVA, and systematic changes in features were described by linear and polynomial regression models. RESULTS: ANOVA revealed significant differences (p < 0.05) between normal tissue and lesions in 13 TF, compared to 9 TF between benign and malignant lesions. Most TF showed significant differences in early dynamic and subtraction datasets. TF associated with homogeneity were suitable to discriminate between healthy parenchyma and lesions, whereas run-length features were more suitable to discriminate between benign and malignant lesions. Run length nonuniformity (RLN) was the only feature able to distinguish between all three classes with an AUC of 88.3%. Characteristic changes were observed with a systematic increase or decrease for most TF with mostly polynomial behavior. Slopes showed earlier peaks in malignant lesions, compared to benign lesions. Mean values for the coefficient of determination were higher during subtraction sequences, compared to dynamic sequences (benign: 0.98 vs 0. 72; malignant: 0.94 vs 0.74). CONCLUSIONS: TF of breast lesions follow characteristic patterns during dynamic breast-MRI, distinguishing benign from malignant lesions. Early dynamic and subtraction datasets are particularly suitable for texture analysis in breast-MRI. Features associated with tissue homogeneity seem to be indicative of benign lesions.

Screening for Physical Activity Levels in Non-Metastatic Breast Cancer Patients Undergoing Surgery: An Observational Study.

BACKGROUND: Physical activity (PA) can play a role in lowering the risk of breast cancer (BC), but also in reducing perioperative complications and treatments related side effects, improving the quality of life and decreasing mortality in BC survivors. PA and nutritional screening are not offered to patients after cancer diagnosis as standard of care, even in high quality breast units. METHODS: From February 2019 to March 2020, we performed a preoperative physical and nutritional screening in 504 consecutive BC patients waiting for surgery. The screening included an IPAQ questionnaire to evaluate the level of physical activity; nutritional screening with measurement of anthropometric parameters (weight, height, waist and hips circumference, BMI, and waist hip ratio) and evaluation of body composition using Bioelectrical Impedance Analysis (BIA). RESULTS: The majority of patients in our series resulted physically inactive: clustering the IPAQ scores, 47% of patients proved to be physically inactive (MET score <700), 34% moderately active (MET score 700-2520), and only 19% physically active (MET score > 2520). In addition, approximately half of the patients (49.01%) resulted overweight or obese, and more than half (55.2%) had a percentage of fatty tissue over the recommended cut off for adult women. CONCLUSIONS: Our data confirm that assessment of PA levels should become part of the standard preoperative evaluation of BC patients and behavioral interventions should be offered to them, in order to pre-habilitate for surgery and improve outcomes. IPAQ Questionnaire and body composition analysis could be quick and easy screening tools in order to identify which patients may need more support in being active during and after anticancer treatments.

Apple Polyphenol Diet Extends Lifespan, Slows down Mitotic Rate and Reduces Morphometric Parameters in Drosophila Melanogaster: A Comparison between Three Different Apple Cultivars.

Plant-derived polyphenols exhibit beneficial effects on physiological and pathological processes, including cancer and neurodegenerative disorders, mainly because of their antioxidant activity. Apples are highly enriched in these compounds, mainly in their peel. The Tuscia Red (TR) apple variety exhibits the peculiar characteristic of depositing high quantities of polyphenols in the pulp, the edible part of the fruit. Since polyphenols, as any natural product, cannot be considered a panacea per se, in this paper, we propose to assess the biological effects of TR flesh extracts, in comparison with two commercial varieties, in a model system, the insect Drosophila melanogaster, largely recognized as a reliable system to test the in vivo effects of natural and synthetic compounds. We performed a comparative, qualitative and quantitative analysis of the polyphenol compositions of the three cultivars and found that TR flesh shows the highest content of polyphenols, and markedly, anthocyanins. Then, we focused on their effects on a panel of physiological, morphometrical, cellular and behavioral phenotypes in wild-type D. melanogaster. We found that all the apple polyphenol extracts showed dose-dependent effects on most of the phenotypes we considered. Remarkably, all the varieties induced a strong relenting of the cell division rate.

Sensing red blood cell nano-mechanics: Toward a novel blood biomarker for Alzheimer's disease.

Red blood cells (RBCs) are characterized by a remarkable elasticity, which allows them to undergo very large deformation when passing through small vessels and capillaries. This extreme deformability is altered in various clinical conditions, suggesting that the analysis of red blood cell (RBC) mechanics has potential applications in the search for non-invasive and cost-effective blood biomarkers. Here, we provide a comparative study of the mechanical response of RBCs in patients with Alzheimer's disease (AD) and healthy subjects. For this purpose, RBC viscoelastic response was investigated using atomic force microscopy (AFM) in the force spectroscopy mode. Two types of analyses were performed: (i) a conventional analysis of AFM force-distance (FD) curves, which allowed us to retrieve the apparent Young's modulus, E; and (ii) a more in-depth analysis of time-dependent relaxation curves in the framework of the standard linear solid (SLS) model, which allowed us to estimate cell viscosity and elasticity, independently. Our data demonstrate that, while conventional analysis of AFM FD curves fails in distinguishing the two groups, the mechanical parameters obtained with the SLS model show a very good classification ability. The diagnostic performance of mechanical parameters was assessed using receiving operator characteristic (ROC) curves, showing very large areas under the curves (AUC) for selected biomarkers (AUC > 0.9). Taken all together, the data presented here demonstrate that RBC mechanics are significantly altered in AD, also highlighting the key role played by viscous forces. These RBC abnormalities in AD, which include both a modified elasticity and viscosity, could be considered a potential source of plasmatic biomarkers in the field of liquid biopsy to be used in combination with more established indicators of the pathology.

BI-RADS-Based Classification of Mammographic Soft Tissue Opacities Using a Deep Convolutional Neural Network.

The aim of this study was to investigate the potential of a machine learning algorithm to classify breast cancer solely by the presence of soft tissue opacities in mammograms, independent of other morphological features, using a deep convolutional neural network (dCNN). Soft tissue opacities were classified based on their radiological appearance using the ACR BI-RADS atlas. We included 1744 mammograms from 438 patients to create 7242 icons by manual labeling. The icons were sorted into three categories: "no opacities" (BI-RADS 1), "probably benign opacities" (BI-RADS 2/3) and "suspicious opacities" (BI-RADS 4/5). A dCNN was trained (70% of data), validated (20%) and finally tested (10%). A sliding window approach was applied to create colored probability maps for visual impression. Diagnostic performance of the dCNN was compared to human readout by experienced radiologists on a "real-world" dataset. The accuracies of the models on the test dataset ranged between 73.8% and 89.8%. Compared to human readout, our dCNN achieved a higher specificity (100%, 95% CI: 85.4-100%; reader 1: 86.2%, 95% CI: 67.4-95.5%; reader 2: 79.3%, 95% CI: 59.7-91.3%), and the sensitivity (84.0%, 95% CI: 63.9-95.5%) was lower than that of human readers (reader 1:88.0%, 95% CI: 67.4-95.4%; reader 2:88.0%, 95% CI: 67.7-96.8%). In conclusion, a dCNN can be used for the automatic detection as well as the standardized and observer-independent classification of soft tissue opacities in mammograms independent of the presence of microcalcifications. Human decision making in accordance with the BI-RADS classification can be mimicked by artificial intelligence.

Radiomics in photon-counting dedicated breast CT: potential of texture analysis for breast density classification.

BACKGROUND: We investigated whether features derived from texture analysis (TA) can distinguish breast density (BD) in spiral photon-counting breast computed tomography (PC-BCT). METHODS: In this retrospective single-centre study, we analysed 10,000 images from 400 PC-BCT examinations of 200 patients. Images were categorised into four-level density scale (a-d) using Breast Imaging Reporting and Data System (BI-RADS)-like criteria. After manual definition of representative regions of interest, 19 texture features (TFs) were calculated to analyse the voxel grey-level distribution in the included image area. ANOVA, cluster analysis, and multinomial logistic regression statistics were used. A human readout then was performed on a subset of 60 images to evaluate the reliability of the proposed feature set. RESULTS: Of the 19 TFs, 4 first-order features and 7 second-order features showed significant correlation with BD and were selected for further analysis. Multinomial logistic regression revealed an overall accuracy of 80% for BD assessment. The majority of TFs systematically increased or decreased with BD. Skewness (rho -0.81), as a first-order feature, and grey-level nonuniformity (GLN, -0.59), as a second-order feature, showed the strongest correlation with BD, independently of other TFs. Mean skewness and GLN decreased linearly from density a to d. Run-length nonuniformity (RLN), as a second-order feature, showed moderate correlation with BD, but resulted in redundant being correlated with GLN. All other TFs showed only weak correlation with BD (range -0.49 to 0.49, p < 0.001) and were neglected. CONCLUSION: TA of PC-BCT images might be a useful approach to assess BD and may serve as an observer-independent tool.

Detecting Abnormal Axillary Lymph Nodes on Mammograms Using a Deep Convolutional Neural Network.

The purpose of this study was to determine the feasibility of a deep convolutional neural network (dCNN) to accurately detect abnormal axillary lymph nodes on mammograms. In this retrospective study, 107 mammographic images in mediolateral oblique projection from 74 patients were labeled to three classes: (1) "breast tissue", (2) "benign lymph nodes", and (3) "suspicious lymph nodes". Following data preprocessing, a dCNN model was trained and validated with 5385 images. Subsequently, the trained dCNN was tested on a "real-world" dataset and the performance compared to human readers. For visualization, colored probability maps of the classification were calculated using a sliding window approach. The accuracy was 98% for the training and 99% for the validation set. Confusion matrices of the "real-world" dataset for the three classes with radiological reports as ground truth yielded an accuracy of 98.51% for breast tissue, 98.63% for benign lymph nodes, and 95.96% for suspicious lymph nodes. Intraclass correlation of the dCNN and the readers was excellent (0.98), and Kappa values were nearly perfect (0.93-0.97). The colormaps successfully detected abnormal lymph nodes with excellent image quality. In this proof-of-principle study in a small patient cohort from a single institution, we found that deep convolutional networks can be trained with high accuracy and reliability to detect abnormal axillary lymph nodes on mammograms.

Quantitative 23 Na-MRI of the intervertebral disk at 3 T.

Monitoring the tissue sodium content (TSC) in the intervertebral disk geometry noninvasively by MRI is a sensitive measure to estimate changes in the proteoglycan content of the intervertebral disk, which is a biomarker of degenerative disk disease (DDD) and of lumbar back pain (LBP). However, application of quantitative sodium concentration measurements in 23 Na-MRI is highly challenging due to the lower in vivo concentrations and smaller gyromagnetic ratio, ultimately yielding much smaller signal relative to 1 H-MRI. Moreover, imaging the intervertebral disk geometry imposes higher demands, mainly because the necessary RF volume coils produce highly inhomogeneous transmit field patterns. For an accurate absolute quantification of TSC in the intervertebral disks, the B1 field variations have to be mitigated. In this study, we report for the first time quantitative sodium concentration in the intervertebral disks at clinical field strengths (3 T) by deploying 23 Na-MRI in healthy human subjects. The sodium B1 maps were calculated by using the double-angle method and a double-tuned (1 H/23 Na) transceive chest coil, and the individual effects of the variation in the B1 field patterns in tissue sodium quantification were calculated. Phantom measurements were conducted to evaluate the quality of the Na-weighted images and B1 mapping. Depending on the disk position, the sodium concentration was calculated as 161.6 mmol/L-347 mmol/L, and the mean sodium concentration of the intervertebral disks varies between 254.6 ± 54 mmol/L and 290.1 ± 39 mmol/L. A smoothing effect of the B1 correction on the sodium concentration maps was observed, such that the standard deviation of the mean sodium concentration was significantly reduced with B1 mitigation. The results of this work provide an improved integration of quantitative 23 Na-MRI into clinical studies in intervertebral disks such as degenerative disk disease and establish alternative scoring schemes to existing morphological scoring such as the Pfirrmann score.

Fully automatic classification of automated breast ultrasound (ABUS) imaging according to BI-RADS using a deep convolutional neural network.

PURPOSE: The aim of this study was to develop and test a post-processing technique for detection and classification of lesions according to the BI-RADS atlas in automated breast ultrasound (ABUS) based on deep convolutional neural networks (dCNNs). METHODS AND MATERIALS: In this retrospective study, 645 ABUS datasets from 113 patients were included; 55 patients had lesions classified as high malignancy probability. Lesions were categorized in BI-RADS 2 (no suspicion of malignancy), BI-RADS 3 (probability of malignancy < 3%), and BI-RADS 4/5 (probability of malignancy > 3%). A deep convolutional neural network was trained after data augmentation with images of lesions and normal breast tissue, and a sliding-window approach for lesion detection was implemented. The algorithm was applied to a test dataset containing 128 images and performance was compared with readings of 2 experienced radiologists. RESULTS: Results of calculations performed on single images showed accuracy of 79.7% and AUC of 0.91 [95% CI: 0.85-0.96] in categorization according to BI-RADS. Moderate agreement between dCNN and ground truth has been achieved (κ: 0.57 [95% CI: 0.50-0.64]) what is comparable with human readers. Analysis of whole dataset improved categorization accuracy to 90.9% and AUC of 0.91 [95% CI: 0.77-1.00], while achieving almost perfect agreement with ground truth (κ: 0.82 [95% CI: 0.69-0.95]), performing on par with human readers. Furthermore, the object localization technique allowed the detection of lesion position slice-wise. CONCLUSIONS: Our results show that a dCNN can be trained to detect and distinguish lesions in ABUS according to the BI-RADS classification with similar accuracy as experienced radiologists. KEY POINTS: • A deep convolutional neural network (dCNN) was trained for classification of ABUS lesions according to the BI-RADS atlas. • A sliding-window approach allows accurate automatic detection and classification of lesions in ABUS examinations.