METAPHOR: Metabolic evaluation through phasor-based hyperspectral imaging and organelle recognition for mouse blastocysts and oocytes.

Only 30% of embryos from in vitro fertilized oocytes successfully implant and develop to term, leading to repeated transfer cycles. To reduce time-to-pregnancy and stress for patients, there is a need for a diagnostic tool to better select embryos and oocytes based on their physiology. The current standard employs brightfield imaging, which provides limited physiological information. Here, we introduce METAPHOR: Metabolic Evaluation through Phasor-based Hyperspectral Imaging and Organelle Recognition. This non-invasive, label-free imaging method combines two-photon illumination and AI to deliver the metabolic profile of embryos and oocytes based on intrinsic autofluorescence signals. We used it to classify i) mouse blastocysts cultured under standard conditions or with depletion of selected metabolites (glucose, pyruvate, lactate); and ii) oocytes from young and old mouse females, or in vitro-aged oocytes. The imaging process was safe for blastocysts and oocytes. The METAPHOR classification of control vs. metabolites-depleted embryos reached an area under the ROC curve (AUC) of 93.7%, compared to 51% achieved for human grading using brightfield imaging. The binary classification of young vs. old/in vitro-aged oocytes and their blastulation prediction using METAPHOR reached an AUC of 96.2% and 82.2%, respectively. Finally, organelle recognition and segmentation based on the flavin adenine dinucleotide signal revealed that quantification of mitochondria size and distribution can be used as a biomarker to classify oocytes and embryos. The performance and safety of the method highlight the accuracy of noninvasive metabolic imaging as a complementary approach to evaluate oocytes and embryos based on their physiology.

Advanced Image Stitching Method for Dual-Sensor Inspection.

Efficient image stitching plays a vital role in the Non-Destructive Evaluation (NDE) of infrastructures. An essential challenge in the NDE of infrastructures is precisely visualizing defects within large structures. The existing literature predominantly relies on high-resolution close-distance images to detect surface or subsurface defects. While the automatic detection of all defect types represents a significant advancement, understanding the location and continuity of defects is imperative. It is worth noting that some defects may be too small to capture from a considerable distance. Consequently, multiple image sequences are captured and processed using image stitching techniques. Additionally, visible and infrared data fusion strategies prove essential for acquiring comprehensive information to detect defects across vast structures. Hence, there is a need for an effective image stitching method appropriate for infrared and visible images of structures and industrial assets, facilitating enhanced visualization and automated inspection for structural maintenance. This paper proposes an advanced image stitching method appropriate for dual-sensor inspections. The proposed image stitching technique employs self-supervised feature detection to enhance the quality and quantity of feature detection. Subsequently, a graph neural network is employed for robust feature matching. Ultimately, the proposed method results in image stitching that effectively eliminates perspective distortion in both infrared and visible images, a prerequisite for subsequent multi-modal fusion strategies. Our results substantially enhance the visualization capabilities for infrastructure inspection. Comparative analysis with popular state-of-the-art methods confirms the effectiveness of the proposed approach.

Robust Multi-Modal Image Registration for Image Fusion Enhancement in Infrastructure Inspection.

Efficient multi-modal image fusion plays an important role in the non-destructive evaluation (NDE) of infrastructures, where an essential challenge is the precise visualizing of defects. While automatic defect detection represents a significant advancement, the determination of the precise location of both surface and subsurface defects simultaneously is crucial. Hence, visible and infrared data fusion strategies are essential for acquiring comprehensive and complementary information to detect defects across vast structures. This paper proposes an infrared and visible image registration method based on Euclidean evaluation together with a trade-off between key-point threshold and non-maximum suppression. Moreover, we employ a multi-modal fusion strategy to investigate the robustness of our image registration results.

Association between tissue loss type and amputation risk among Medicare patients with concomitant diabetes and peripheral arterial disease.

OBJECTIVE: Prior studies have described risk factors associated with amputation in patients with concomitant diabetes and peripheral arterial disease (DM/PAD). However, the association between the severity and extent of tissue loss type and amputation risk remains less well-described. We aimed to quantify the role of different tissue loss types in amputation risk among patients with DM/PAD, in the context of demographic, preventive, and socioeconomic factors. METHODS: Applying International Classification of Diseases (ICD)-9 and ICD-10 codes to Medicare claims data (2007-2019), we identified all patients with continuous fee-for-service Medicare coverage diagnosed with DM/PAD. Eight tissue loss categories were established using ICD-9 and ICD-10 diagnosis codes, ranging from lymphadenitis (least severe) to gangrene (most severe). We created a Cox proportional hazards model to quantify associations between tissue loss type and 1- and 5-year amputation risk, adjusting for age, race/ethnicity, sex, rurality, income, comorbidities, and preventive factors. Regional variation in DM/PAD rates and risk-adjusted amputation rates was examined at the hospital referral region level. RESULTS: We identified 12,257,174 patients with DM/PAD (48% male, 76% White, 10% prior myocardial infarction, 30% chronic kidney disease). Although 2.2 million patients (18%) had some form of tissue loss, 10.0 million patients (82%) did not. The 1-year crude amputation rate (major and minor) was 6.4% in patients with tissue loss, and 0.4% in patients without tissue loss. Among patients with tissue loss, the 1-year any amputation rate varied from 0.89% for patients with lymphadenitis to 26% for patients with gangrene. The 1-year amputation risk varied from two-fold for patients with lymphadenitis (adjusted hazard ratio, 1.96; 95% confidence interval, 1.43-2.69) to 29-fold for patients with gangrene (adjusted hazard ratio, 28.7; 95% confidence interval, 28.1-29.3), compared with patients without tissue loss. No other demographic variable including age, sex, race, or region incurred a hazard ratio for 1- or 5-year amputation risk higher than the least severe tissue loss category. Results were similar across minor and major amputation, and 1- and 5-year amputation outcomes. At a regional level, higher DM/PAD rates were inversely correlated with risk-adjusted 5-year amputation rates (R2 = 0.43). CONCLUSIONS: Among 12 million patients with DM/PAD, the most significant predictor of amputation was the presence and extent of tissue loss, with an association greater in effect size than any other factor studied. Tissue loss could be used in awareness campaigns as a simple marker of high-risk patients. Patients with any type of tissue loss require expedited wound care, revascularization as appropriate, and infection management to avoid amputation. Establishing systems of care to provide these interventions in regions with high amputation rates may prove beneficial for these populations.

Isatuximab, Bortezomib, Lenalidomide, and Dexamethasone for Multiple Myeloma.

BACKGROUND: Bortezomib, lenalidomide, and dexamethasone (VRd) is a preferred first-line treatment option for patients with newly diagnosed multiple myeloma. Whether the addition of the anti-CD38 monoclonal antibody isatuximab to the VRd regimen would reduce the risk of disease progression or death among patients ineligible to undergo transplantation is unclear. METHODS: In an international, open-label, phase 3 trial, we randomly assigned, in a 3:2 ratio, patients 18 to 80 years of age with newly diagnosed multiple myeloma who were ineligible to undergo transplantation to receive either isatuximab plus VRd or VRd alone. The primary efficacy end point was progression-free survival. Key secondary end points included a complete response or better and minimal residual disease (MRD)-negative status in patients with a complete response. RESULTS: A total of 446 patients underwent randomization. At a median follow-up of 59.7 months, the estimated progression-free survival at 60 months was 63.2% in the isatuximab-VRd group, as compared with 45.2% in the VRd group (hazard ratio for disease progression or death, 0.60; 98.5% confidence interval, 0.41 to 0.88; P<0.001). The percentage of patients with a complete response or better was significantly higher in the isatuximab-VRd group than in the VRd group (74.7% vs. 64.1%, P = 0.01), as was the percentage of patients with MRD-negative status and a complete response (55.5% vs. 40.9%, P = 0.003). No new safety signals were observed with the isatuximab-VRd regimen. The incidence of serious adverse events during treatment and the incidence of adverse events leading to discontinuation were similar in the two groups. CONCLUSIONS: Isatuximab-VRd was more effective than VRd as initial therapy in patients 18 to 80 years of age with newly diagnosed multiple myeloma who were ineligible to undergo transplantation. (Funded by Sanofi and a Cancer Center Support Grant; IMROZ ClinicalTrials.gov number, NCT03319667.).

Inter-Rater Reliability for the Amputation Endpoint in the National Vascular Quality Initiative.

BACKGROUND: National quality reporting efforts after revascularization for peripheral artery disease (PAD) are ongoing. Validation of endpoints are necessary in national quality registries. OBJECTIVES: This study sought to examine the interrater reliability for the endpoint of major amputation at 1 year in the Vascular Quality Initiative (VQI) registry and the Medicare-linked Vascular Quality Initiative registry (VQI-VISION) against electronic health record (EHR) review. METHODS: Surgical or endovascular revascularization procedures between January 1, 2010, and December 31, 2017, in the VQI registry and VQI-VISION for 2 academic health systems were queried. Major amputation data were abstracted by trained data collectors for the VQI and derived from Current Procedural Terminology codes for VQI-VISION. Cases underwent protocolized adjudication for the endpoint of major amputation by EHR review. Paired tests were used to evaluate the sensitivity and specificity. Spearman's ρ and Cohen's κ were used to evaluate interrater reliability. RESULTS: Amputation endpoints for 1,936 revascularizations were examined. Compared with major amputation data in EHR review, the sensitivity for the VQI registry was 35.9% and the specificity was 99.4% (ρ = 0.53; κ = 0.48). For VQI-VISION, sensitivity was 67.7% and specificity was 98.9% (ρ = 0.75; κ = 0.74). For any amputation in VQI data, sensitivity was 35.3% and specificity was 99.3% (ρ = 0.53; κ = 0.46), and for VQI-VISION, they were 71.6% and 97.7%, respectively (ρ = 0.75; κ = 0.74). CONCLUSIONS: Almost two-thirds of the amputations in the VQI registry and one-third of amputations in VQI-VISION were missing at 1 year compared against adjudicated EHR review. In preparing for national reporting systems for major amputation tracking, data collection system reform is needed.

A Retrospective Analysis of Surgical Acuity & Procedure Volume Before & During the COVID-19 Pandemic.

INTRODUCTION: In March 2020, the American College of Surgeons recommended postponing elective procedures amid the COVID-19 pandemic. We used Medicare claims to analyze changes in surgical and interventional procedure volumes from 2016 to 2021. METHODS: We studied 37 common surgical and interventional procedures using 5% Medicare claims files from January 1, 2016, through December 31, 2021. Procedures were classified according to American College of Surgeons guidelines as low, intermediate, or high acuity, and counts were analyzed per calendar year quarter (Q1-Q4), with stratification by sex and race/ethnicity. RESULTS: We observed 1,840,577 procedures and identified two periods of marked decline. In Q2 2020, overall procedure counts decreased by 32.2%, with larger declines in low (41.1%) and intermediate (30.8%) acuity procedures. High acuity procedures declined the least (18.2%). Overall volumes increased afterward but never returned to baseline. Another marked decline occurred in Q4 2021, with all acuity levels having declined to a similar extent (40.1%, 44.2%, and 46.9% for low, intermediate, and high acuity, respectively). High and intermediate acuity procedures declined more in Q4 2021 than Q2 2020 (P = 0.002). Similar patterns were observed across sex and race/ethnicity strata. CONCLUSIONS: Two major procedural volume declines occurred between 2020 and 2022 during the COVID-19 pandemic in the United States. High acuity (life or limb threatening) procedures were least affected in the first decline (Q2 2020) but not spared in second decline (Q4 2021). Future efforts should prioritize preserving high-acuity access during times of stress.

Automatic Deep Learning-Based Pipeline for Automatic Delineation and Measurement of Fetal Brain Structures in Routine Mid-Trimester Ultrasound Images.

INTRODUCTION: The aim of this study was to develop a pipeline using state-of-the-art deep learning methods to automatically delineate and measure several of the most important brain structures in fetal brain ultrasound (US) images. METHODS: The dataset was composed of 5,331 images of the fetal brain acquired during the routine mid-trimester US scan. Our proposed pipeline automatically performs the following three steps: brain plane classification (transventricular, transthalamic, or transcerebellar plane); brain structures delineation (9 different structures); and automatic measurement (from the structure delineations). The methods were trained on a subset of 4,331 images and each step was evaluated on the remaining 1,000 images. RESULTS: Plane classification reached 98.6% average class accuracy. Brain structure delineation obtained an average pixel accuracy higher than 96% and a Jaccard index higher than 70%. Automatic measurements get an absolute error below 3.5% for the four standard head biometries (head circumference, biparietal diameter, occipitofrontal diameter, and cephalic index), 9% for transcerebellar diameter, 12% for cavum septi pellucidi ratio, and 26% for Sylvian fissure operculization degree. CONCLUSIONS: The proposed pipeline shows the potential of deep learning methods to delineate fetal head and brain structures and obtain automatic measures of each anatomical standard plane acquired during routine fetal US examination.

Trends of Concomitant Diabetes and Peripheral Artery Disease and Lower Extremity Amputation in US Medicare Patients, 2007 to 2019.

BACKGROUND: Previous studies demonstrate geographic and racial/ethnic variation in diagnosis and complications of diabetes and peripheral artery disease (PAD). However, recent trends for patients diagnosed with both PAD and diabetes are lacking. We assessed the period prevalence of concurrent diabetes and PAD across the United States from 2007 to 2019 and regional and racial/ethnic variation in amputations among Medicare patients. METHODS: Using Medicare claims from 2007 to 2019, we identified patients with both diabetes and PAD. We calculated period prevalence of concomitant diabetes and PAD and incident cases of diabetes and PAD for every year. Patients were followed to identify amputations, and results were stratified by race/ethnicity and hospital referral region. RESULTS: 9 410 785 patients with diabetes and PAD were identified (mean age, 72.8 [SD, 10.94] years; 58.6% women, 74.7% White, 13.2% Black, 7.3% Hispanic, 2.8% Asian/API, and 0.6% Native American). Period prevalence of diabetes and PAD was 23 per 1000 beneficiaries. We observed a 33% relative decrease in annual new diagnoses throughout the study. All racial/ethnic groups experienced a similar decline in new diagnoses. Black and Hispanic patients had on average a 50% greater rate of disease compared with White patients. One- and 5-year amputation rates remained stable at ≈1.5% and 3%, respectively. Native American, Black, and Hispanic patients were at greater risk of amputation compared with White patients at 1- and 5-year time points (5-year rate ratio range, 1.22-3.17). Across US regions, we observed differential amputation rates, with an inverse relationship between the prevalence of concomitant diabetes and PAD and overall amputation rates. CONCLUSIONS: Significant regional and racial/ethnic variation exists in the incidence of concomitant diabetes and PAD among Medicare patients. Black patients in areas with the lowest rates of PAD and diabetes are at disproportionally higher risk for amputation. Furthermore, areas with higher prevalence of PAD and diabetes have the lowest rates of amputation.

Noninvasive prediction models of intra-amniotic infection in women with preterm labor.

BACKGROUND: Among women with preterm labor, those with intra-amniotic infection present the highest risk of early delivery and the most adverse outcomes. The identification of intra-amniotic infection requires amniocentesis, perceived as too invasive by women and physicians. Noninvasive methods for identifying intra-amniotic infection and/or early delivery are crucial to focus early efforts on high-risk preterm labor women while avoiding unnecessary interventions in low-risk preterm labor women. OBJECTIVE: This study modeled the best performing models, integrating biochemical data with clinical and ultrasound information to predict a composite outcome of intra-amniotic infection and/or spontaneous delivery within 7 days. STUDY DESIGN: From 2015 to 2020, data from a cohort of women, who underwent amniocentesis to rule in or rule out intra-amniotic infection or inflammation, admitted with a diagnosis of preterm labor at <34 weeks of gestation at the Hospital Clinic and Hospital Sant Joan de Déu, Barcelona, Spain, were used. At admission, transvaginal ultrasound was performed, and maternal blood and vaginal samples were collected. Using high-dimensional biology, vaginal proteins (using multiplex immunoassay), amino acids (using high-performance liquid chromatography), and bacteria (using 16S ribosomal RNA gene amplicon sequencing) were explored to predict the composite outcome. We selected ultrasound, maternal blood, and vaginal predictors that could be tested with rapid diagnostic techniques and developed prediction models employing machine learning that was applied in a validation cohort. RESULTS: A cohort of 288 women with preterm labor at <34 weeks of gestation, of which 103 (35%) had a composite outcome of intra-amniotic infection and/or spontaneous delivery within 7 days, were included in this study. The sample was divided into derivation (n=116) and validation (n=172) cohorts. Of note, 4 prediction models were proposed, including ultrasound transvaginal cervical length, maternal C-reactive protein, vaginal interleukin 6 (using an automated immunoanalyzer), vaginal pH (using a pH meter), vaginal lactic acid (using a reflectometer), and vaginal Lactobacillus genus (using quantitative polymerase chain reaction), with areas under the receiving operating characteristic curve ranging from 82.2% (95% confidence interval, ±3.1%) to 85.2% (95% confidence interval, ±3.1%), sensitivities ranging from 76.1% to 85.9%, and specificities ranging from 75.2% to 85.1%. CONCLUSION: The study results have provided proof of principle of how noninvasive methods suitable for point-of-care systems can select high-risk cases among women with preterm labor and might substantially aid in clinical management and outcomes while improving the use of resources and patient experience.

Automated Impact Damage Detection Technique for Composites Based on Thermographic Image Processing and Machine Learning Classification.

Composite materials are one of the primary structural components in most current transportation applications, such as the aerospace industry. Composite material diagnostics is a promising area in the fight against structural damage in aircraft and spaceships. Detection and diagnostic technologies often provide analysts with a valuable and rapid mechanism to monitor the health and safety of composite materials. Although many attempts have been made to develop damage detection techniques and make operations more efficient, there is still a need to develop/improve existing methods. Pulsed thermography (PT) technology was used in this study to obtain healthy and defective data sets from custom-designed composite samples having similar dimensions but different thicknesses (1.6 and 3.8). Ten carbon fibre-reinforced plastic (CFRP) panels were tested. The samples were subjected to impact damage of various energy levels, ranging from 4 to 12 J. Two different methods have been applied to detect and classify the damage to the composite structures. The first applied method is the statistical analysis, where seven different statistical criteria have been calculated. The final results have proved the possibility of detecting the damaged area in most cases. However, for a more accurate detection technique, a machine learning method was applied to thermal images; specifically, the Cube Support Vector Machine (SVM) algorithm was selected. The prediction accuracy of the proposed classification models was calculated within a confusion matrix based on the dataset patterns representing the healthy and defective areas. The classification results ranged from 78.7% to 93.5%, and these promising results are paving the way to develop an automated model to efficiently evaluate the damage to composite materials based on the non-distractive testing (NDT) technique.

Deriving International Classification of Diseases, 9th and 10th revision, codes for identifying and following up patients with diabetic lower extremity ulcers.

Objective: Administrative claims data offer a rich data source for clinical research. However, its application to the study of diabetic lower extremity ulceration is lacking. Our objective was to create a widely applicable framework by which investigators might derive and refine the International Classification of Diseases, 9th and 10th revision (ICD-9 and ICD-10, respectively) codes for use in identifying diabetic, lower extremity ulceration. Methods: We created a seven-step process to derive and refine the ICD-9 and ICD-10 coding lists to identify diabetic lower extremity ulcers. This process begins by defining the research question and the initial identification of a list of ICD-9 and ICD-10 codes to define the exposures or outcomes of interest. These codes are then applied to claims data, and the rates of clinical events are examined for consistency with prior research and changes across the ICD-9 to ICD-10 transition. The ICD-9 and ICD-10 codes are then cross referenced with each other to further refine the lists. Results: Using this method, we started with 8 ICD-9 and 43 ICD-10 codes used to identify lower extremity ulcers in patients with known diabetes and peripheral arterial disease and examined the association of ulceration with lower extremity amputation. After refinement, we had 45 ICD-9 codes and 304 ICD-10 codes. We then grouped the codes into eight clinical exposure groups and examined the rates of amputation as a rudimentary test of validity. We found that the rate of lower extremity amputation correlated with the severity of lower extremity ulceration. Conclusions: We identified 45 ICD-9 and 304 ICD-10 ulcer codes, which identified patients at risk of amputation from diabetes and peripheral artery disease. Although further validation at the medical record level is required, these codes can be used for claims-based risk stratification for long-term outcomes assessment in the treatment of patients at risk of limb loss.

Lipid biosynthesis enzyme Agpat5 in AgRP-neurons is required for insulin-induced hypoglycemia sensing and glucagon secretion.

The counterregulatory response to hypoglycemia that restores normal blood glucose levels is an essential physiological function. It is initiated, in large part, by incompletely characterized brain hypoglycemia sensing neurons that trigger the secretion of counterregulatory hormones, in particular glucagon, to stimulate hepatic glucose production. In a genetic screen of recombinant inbred BXD mice we previously identified Agpat5 as a candidate regulator of hypoglycemia-induced glucagon secretion. Here, using genetic mouse models, we demonstrate that Agpat5 expressed in agouti-related peptide neurons is required for their activation by hypoglycemia, for hypoglycemia-induced vagal nerve activity, and glucagon secretion. We find that inactivation of Agpat5 leads to increased fatty acid oxidation and ATP production and that suppressing Cpt1a-dependent fatty acid import into mitochondria restores hypoglycemia sensing. Collectively, our data show that AgRP neurons are involved in the control of glucagon secretion and that Agpat5, by partitioning fatty acyl-CoAs away from mitochondrial fatty acid oxidation and ATP generation, ensures that the fall in intracellular ATP, which triggers neuronal firing, faithfully reflects changes in glycemia.

Prediction of Neonatal Respiratory Morbidity Assessed by Quantitative Ultrasound Lung Texture Analysis in Twin Pregnancies.

The objective of this study was to evaluate the performance of quantitative ultrasound of fetal lung texture analysis in predicting neonatal respiratory morbidity (NRM) in twin pregnancies. This was an ambispective study involving consecutive cases. Eligible cases included twin pregnancies between 27.0 and 38.6 weeks of gestation, for which an ultrasound image of the fetal thorax was obtained within 48 h of delivery. Images were analyzed using quantusFLM® version 3.0. The primary outcome of this study was neonatal respiratory morbidity, defined as the occurrence of either transient tachypnea of the newborn or respiratory distress syndrome. The performance of quantusFLM® in predicting NRM was analyzed by matching quantitative ultrasound analysis and clinical outcomes. This study included 166 images. Neonatal respiratory morbidity occurred in 12.7% of cases, and it was predicted by quantusFLM® analysis with an overall sensitivity of 42.9%, specificity of 95.9%, positive predictive value of 60%, and negative predictive value of 92.1%. The accuracy was 89.2%, with a positive likelihood ratio of 10.4, and a negative likelihood ratio of 0.6. The results of this study demonstrate the good prediction capability of NRM in twin pregnancies using a non-invasive lung texture analysis software. The test showed an overall good performance with high specificity, negative predictive value, and accuracy.

Experimental Study and FEM Simulations for Detection of Rebars in Concrete Slabs by Coplanar Capacitive Sensing Technique.

In the present study, a relatively novel non-destructive testing (NDT) method called the coplanar capacitive sensing technique was applied in order to detect different sizes of rebars in a reinforced concrete (RC) structure. This technique effectively detects changes in the dielectric properties during scanning in various sections of concrete with and without rebars. Numerical simulations were carried out by three-dimensional (3D) finite element modelling (FEM) in COMSOL Multiphysics software to analyse the impact of the presence of rebars on the electric field generated by the coplanar capacitive probe. In addition, the effect of the presence of a surface defect on the rebar embedded in the concrete slab was demonstrated by the same software for the first time. Experiments were performed on a concrete slab containing rebars, and were compared with FEM results. The results showed that there is a good qualitative agreement between the numerical simulations and experimental results.

Quantitative ultrasound image analysis of axillary lymph nodes to differentiate malignancy from reactive benign changes due to COVID-19 vaccination.

PURPOSE: The aim of this study is to assess the potential of quantitative image analysis and machine learning techniques to differentiate between malignant lymph nodes and benign lymph nodes affected by reactive changes due to COVID-19 vaccination. METHOD: In this institutional review board-approved retrospective study, we improved our previously published artificial intelligence model, by retraining it with newly collected images and testing its performance on images containing benign lymph nodes affected by COVID-19 vaccination. All the images were acquired and selected by specialized breast-imaging radiologists and the nature of each node (benign or malignant) was assessed through a strict clinical protocol using ultrasound-guided biopsies. RESULTS: A total of 180 new images from 154 different patients were recruited: 71 images (10 cases and 61 controls) were used to retrain the old model and 109 images (36 cases and 73 controls) were used to evaluate its performance. The achieved accuracy of the proposed method was 92.7% with 77.8% sensitivity and 100% specificity at the optimal cut-off point. In comparison, the visual node inspection made by radiologists from ultrasound images reached 69.7% accuracy with 41.7% sensitivity and 83.6% specificity. CONCLUSIONS: The results obtained in this study show the potential of the proposed techniques to differentiate between malignant lymph nodes and benign nodes affected by reactive changes due to COVID-19 vaccination. These techniques could be useful to non-invasively diagnose lymph node status in patients with suspicious reactive nodes, although larger multicenter studies are needed to confirm and validate the results.

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging.

Automated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images-437 benign, 210, malignant, and 133 normal-were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1-84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.

Concordance of the risk of neonatal respiratory morbidity assessed by quantitative ultrasound lung texture analysis in fetuses of twin pregnancies.

To evaluate the concordance of the risk of neonatal respiratory morbidity (NRM) assessed by quantitative ultrasound lung texture analysis (QuantusFLM) between twin fetuses of the same pregnancy. Prospective study conducted in twin pregnancies. Fetal ultrasound lung images were obtained at 26.0-38.6 weeks of gestation. Categorical (high or low) and continuous results of the risk of NRM were compared between twins. Fetal ultrasound lung images from 131 pairs (262 images) of twins were included. The images were classified into three gestational age ranges: Group 1 (26.0-29.6 weeks, 78 images, 39 pairs [29.8%]); Group 2 (30.0-33.6 weeks, 98 images, 49 pairs [37.4%]) and Group 3 (34.0-38.6 weeks, 86 images, 43 pairs [32.8%]). Concordance was good in Groups 1 and 3 and moderate in Group 2. In Groups 2 and 3 at least one fetus presented high-risk results in 26.5% and 11.6% of twin pairs, respectively. Only gestational age < 32 weeks, gestational diabetes mellitus, and spontaneous conception were associated with a high risk of NRM in Group 2. There was good concordance of the risk of NRM between twins < 30.0 weeks and > 34.0 weeks. From 30.0 to 33.6 weeks 26.5% of the twin pairs had discordant results, with moderate concordance of the risk of NRM.

Erratum: An advanced workflow for single-particle imaging with the limited data at an X-ray free-electron laser. Corrigendum.

[This corrects the article DOI: 10.1107/S2052252520012798.].

Unsupervised learning approaches to characterizing heterogeneous samples using X-ray single-particle imaging.

One of the outstanding analytical problems in X-ray single-particle imaging (SPI) is the classification of structural heterogeneity, which is especially difficult given the low signal-to-noise ratios of individual patterns and the fact that even identical objects can yield patterns that vary greatly when orientation is taken into consideration. Proposed here are two methods which explicitly account for this orientation-induced variation and can robustly determine the structural landscape of a sample ensemble. The first, termed common-line principal component analysis (PCA), provides a rough classification which is essentially parameter free and can be run automatically on any SPI dataset. The second method, utilizing variation auto-encoders (VAEs), can generate 3D structures of the objects at any point in the structural landscape. Both these methods are implemented in combination with the noise-tolerant expand-maximize-compress (EMC) algorithm and its utility is demonstrated by applying it to an experimental dataset from gold nanoparticles with only a few thousand photons per pattern. Both discrete structural classes and continuous deformations are recovered. These developments diverge from previous approaches of extracting reproducible subsets of patterns from a dataset and open up the possibility of moving beyond the study of homogeneous sample sets to addressing open questions on topics such as nanocrystal growth and dynamics, as well as phase transitions which have not been externally triggered.