Testing biasedness of self-reported microbusiness innovation in the annual business survey.

This study tests for potential bias in self-reported innovation due to the inclusion of a research and development (R&D) module that only microbusinesses (less than 10 employees) receive in the Annual Business Survey (ABS). Previous research found that respondents to combined innovation/R&D surveys reported innovation at lower rates than respondents to innovation-only surveys. A regression discontinuity design is used to test whether microbusinesses, which constitute a significant portion of U.S. firms with employees, are less likely to report innovation compared to other small businesses. In the vicinity of the 10-employee threshold, the study does not detect statistically significant biases for new-to-market and new-to-business product innovation. Statistical power analysis confirms the nonexistence of biases with a high power. Comparing the survey design of ABS to earlier combined innovation/R&D surveys provides valuable insights for the proposed integration of multiple Federal surveys into a single enterprise platform survey. The findings also have important implications for the accuracy and reliability of innovation data used as an input to policymaking and business development strategies in the United States.

Synthesis-based imaging-differentiation representation learning for multi-sequence 3D/4D MRI.

Multi-sequence MRIs can be necessary for reliable diagnosis in clinical practice due to the complimentary information within sequences. However, redundant information exists across sequences, which interferes with mining efficient representations by learning-based models. To handle various clinical scenarios, we propose a sequence-to-sequence generation framework (Seq2Seq) for imaging-differentiation representation learning. In this study, not only do we propose arbitrary 3D/4D sequence generation within one model to generate any specified target sequence, but also we are able to rank the importance of each sequence based on a new metric estimating the difficulty of a sequence being generated. Furthermore, we also exploit the generation inability of the model to extract regions that contain unique information for each sequence. We conduct extensive experiments using three datasets including a toy dataset of 20,000 simulated subjects, a brain MRI dataset of 1251 subjects, and a breast MRI dataset of 2101 subjects, to demonstrate that (1) top-ranking sequences can be used to replace complete sequences with non-inferior performance; (2) combining MRI with our imaging-differentiation map leads to better performance in clinical tasks such as glioblastoma MGMT promoter methylation status prediction and breast cancer pathological complete response status prediction. Our code is available at https://github.com/fiy2W/mri_seq2seq.

Longitudinal Prediction of Postnatal Brain Magnetic Resonance Images via a Metamorphic Generative Adversarial Network.

Missing scans are inevitable in longitudinal studies due to either subject dropouts or failed scans. In this paper, we propose a deep learning framework to predict missing scans from acquired scans, catering to longitudinal infant studies. Prediction of infant brain MRI is challenging owing to the rapid contrast and structural changes particularly during the first year of life. We introduce a trustworthy metamorphic generative adversarial network (MGAN) for translating infant brain MRI from one time-point to another. MGAN has three key features: (i) Image translation leveraging spatial and frequency information for detail-preserving mapping; (ii) Quality-guided learning strategy that focuses attention on challenging regions. (iii) Multi-scale hybrid loss function that improves translation of image contents. Experimental results indicate that MGAN outperforms existing GANs by accurately predicting both tissue contrasts and anatomical details.

RadioLOGIC, a healthcare model for processing electronic health records and decision-making in breast disease.

Digital health data used in diagnostics, patient care, and oncology research continue to accumulate exponentially. Most medical information, and particularly radiology results, are stored in free-text format, and the potential of these data remains untapped. In this study, a radiological repomics-driven model incorporating medical token cognition (RadioLOGIC) is proposed to extract repomics (report omics) features from unstructured electronic health records and to assess human health and predict pathological outcome via transfer learning. The average accuracy and F1-weighted score for the extraction of repomics features using RadioLOGIC are 0.934 and 0.934, respectively, and 0.906 and 0.903 for the prediction of breast imaging-reporting and data system scores. The areas under the receiver operating characteristic curve for the prediction of pathological outcome without and with transfer learning are 0.912 and 0.945, respectively. RadioLOGIC outperforms cohort models in the capability to extract features and also reveals promise for checking clinical diagnoses directly from electronic health records.

Relationship between Σ3 Boundaries, Dislocation Slip, and Plasticity in Pure Nickel.

This study investigated the relationship between the Σ3 boundaries, dislocation slip, and plasticity in pure nickel wires after grain boundary (GB) modification. Both quasi in situ tensile tests and simulations were employed. During plastic deformation, twins surrounded by Σ3 boundaries may exhibit a good deformation coordination. With an increase in strain, the slip systems corresponding to the maximum Schmid factor and the actual activated slip systems remain unchanged. Even sub-grains can maintain the dominant slip system of their origin matrix grains. Slip systems with slip planes (111) and (1-1-1) are the most active. Moreover, random boundaries have strong hindering effects on dislocations, and the nearby stress accumulates continuously with an increase in strain. In contrast, Σ3 boundaries demonstrate weak blocking effects and can release the nearby stress due to their unique interfacial structures, which is favorable for improving plasticity. They are more penetrable for dislocations or may react with the piled dislocations. In addition, some Σ3 boundaries can improve their geometrical compatibility factor with an increase in the strain, which enhances the deformation coordination of the grains. The research results provide a better understanding of the plasticizing mechanism for face-centered cubic (fcc) materials after grain boundary modification.

Predicting breast cancer types on and beyond molecular level in a multi-modal fashion.

Accurately determining the molecular subtypes of breast cancer is important for the prognosis of breast cancer patients and can guide treatment selection. In this study, we develop a deep learning-based model for predicting the molecular subtypes of breast cancer directly from the diagnostic mammography and ultrasound images. Multi-modal deep learning with intra- and inter-modality attention modules (MDL-IIA) is proposed to extract important relations between mammography and ultrasound for this task. MDL-IIA leads to the best diagnostic performance compared to other cohort models in predicting 4-category molecular subtypes with Matthews correlation coefficient (MCC) of 0.837 (95% confidence interval [CI]: 0.803, 0.870). The MDL-IIA model can also discriminate between Luminal and Non-Luminal disease with an area under the receiver operating characteristic curve of 0.929 (95% CI: 0.903, 0.951). These results significantly outperform clinicians' predictions based on radiographic imaging. Beyond molecular-level test, based on gene-level ground truth, our method can bypass the inherent uncertainty from immunohistochemistry test. This work thus provides a noninvasive method to predict the molecular subtypes of breast cancer, potentially guiding treatment selection for breast cancer patients and providing decision support for clinicians.

Four-Dimensional Machine Learning Radiomics for the Pretreatment Assessment of Breast Cancer Pathologic Complete Response to Neoadjuvant Chemotherapy in Dynamic Contrast-Enhanced MRI.

BACKGROUND: Breast cancer response to neoadjuvant chemotherapy (NAC) is typically evaluated through the assessment of tumor size reduction after a few cycles of NAC. In case of treatment ineffectiveness, this results in the patient suffering potentially severe secondary effects without achieving any actual benefit. PURPOSE: To identify patients achieving pathologic complete response (pCR) after NAC by spatio-temporal radiomic analysis of dynamic contrast-enhanced (DCE) MRI images acquired before treatment. STUDY TYPE: Single-center, retrospective. POPULATION: A total of 251 DCE-MRI pretreatment images of breast cancer patients. FIELD STRENGTH/SEQUENCE: 1.5 T/3 T, T1-weighted DCE-MRI. ASSESSMENT: Tumor and peritumoral regions were segmented, and 348 radiomic features that quantify texture temporal variation, enhancement kinetics heterogeneity, and morphology were extracted. Based on subsets of features identified through forward selection, machine learning (ML) logistic regression models were trained separately with all images and stratifying on cancer molecular subtype and validated with leave-one-out cross-validation. STATISTICAL TESTS: Feature significance was assessed using the Mann-Whitney U-test. Significance of the area under the receiver operating characteristics (ROC) curve (AUC) of the ML models was assessed using the associated 95% confidence interval (CI). Significance threshold was set to 0.05, adjusted with Bonferroni correction. RESULTS: Nine features related to texture temporal variation and enhancement kinetics heterogeneity were significant in the discrimination of cases achieving pCR vs. non-pCR. The ML models achieved significant AUC of 0.707 (all cancers, n = 251, 59 pCR), 0.824 (luminal A, n = 107, 14 pCR), 0.823 (luminal B, n = 47, 15 pCR), 0.844 (HER2 enriched, n = 25, 11 pCR), 0.803 (triple negative, n = 72, 19 pCR). DATA CONCLUSIONS: Differences in imaging phenotypes were found between complete and noncomplete responders. Furthermore, ML models trained per cancer subtype achieved high performance in classifying pCR vs. non-pCR cases. They may, therefore, have potential to help stratify patients according to the level of response predicted before treatment, pending further validation with larger prospective cohorts. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 4.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

Albumin-templated manganese carbonate nanoparticles for precise magnetic resonance imaging of acute myocardial infarction.

Myocardial infarction (MI) is a major cause of death worldwide. Early and precise diagnosis of myocardial viability after MI is extremely important for effective treatment and prognosis evaluation. Herein, we developed the BSA-templated manganese carbonate (MnCO3@BSA) nanoparticles as an MR imaging contrast agent for accurate detection of the infarcted regions. The chemophysical features, targeting capability toward the infarct, and biocompatibility were evaluated. The nanoparticles showed superior chemical stability. In vitro study suggested that the MnCO3@BSA nanoparticles do not enter normal cardiomyocytes. MR imaging indicated that the MnCO3@BSA with a high longitudinal (r1) relaxivity of 5.84 mM-1s-1 at physiological condition specifically accumulated into the infarcted regions of myocardial ischemia/reperfusion (I/R) mice. In addition, the MnCO3@BSA nanoparticles exhibited low cytotoxicity to cardiomyocytes, no damage to organs and good hemocompatibility. Thereby, the MnCO3@BSA nanoparticles manifested great potential as an extracellular contrast agent of MR imaging for sensitive and specific detection of the infarcted regions during acute myocardial I/R injury.

Modified effects of air pollutants on the relationship between temperature variability and hand, foot, and mouth disease in Zibo City, China.

Hand, foot, and mouth disease (HFMD) poses a great disease burden in China. However, there are few studies on the relationship between temperature variability (TV) and HFMD. Moreover, whether air pollutions have modified effects on this relationship is still unknown. Therefore, this study aims to explore the modified effects of air pollutants on TV-HFMD association in Zibo City, China. Daily data of HFMD cases, meteorological factors, and air pollutants from 2015 to 2019 were collected for Zibo City. TV was estimated by calculating standard deviation of minimum and maximum temperatures over the exposure days. We used generalized additive model to estimate the association between TV and HFMD. The modified effects of air pollutants were assessed by comparing the estimated TV-HFMD associations between different air stratums. We found that TV increased the risk of HFMD. The effect was strongest at TV03 (4 days of exposure), when the incidence of HFMD increased by 3.6% [95% CI: 1.3-5.9%] for every 1℃ increases in TV. Males, children aged 0-4 years, were more sensitive to TV. We found that sulfur dioxide (SO2) enhanced TV's effects on all considered exposure days, while ozone (O3) reduced TV's effects on some exposure days in whole concerned population. However, we did not detect significant effect modification by particulate matter less than 10 microns in aerodynamic diameter (PM10). These findings are of significance in developing policies and public health practices to reduce the risks of HFMD by integrating changes in temperatures and air pollutants.

GAN-based disentanglement learning for chest X-ray rib suppression.

Clinical evidence has shown that rib-suppressed chest X-rays (CXRs) can improve the reliability of pulmonary disease diagnosis. However, previous approaches on generating rib-suppressed CXR face challenges in preserving details and eliminating rib residues. We hereby propose a GAN-based disentanglement learning framework called Rib Suppression GAN, or RSGAN, to perform rib suppression by utilizing the anatomical knowledge embedded in unpaired computed tomography (CT) images. In this approach, we employ a residual map to characterize the intensity difference between CXR and the corresponding rib-suppressed result. To predict the residual map in CXR domain, we disentangle the image into structure- and contrast-specific features and transfer the rib structural priors from digitally reconstructed radiographs (DRRs) computed by CT. Furthermore, we employ additional adaptive loss to suppress rib residue and preserve more details. We conduct extensive experiments based on 1673 CT volumes, and four benchmarking CXR datasets, totaling over 120K images, to demonstrate that (i) our proposed RSGAN achieves superior image quality compared to the state-of-the-art rib suppression methods; (ii) combining CXR with our rib-suppressed result leads to better performance in lung disease classification and tuberculosis area detection.

Semi-supervised segmentation of lesion from breast ultrasound images with attentional generative adversarial network.

BACKGROUND AND OBJECTIVE: Automatic segmentation of breast lesion from ultrasound images is a crucial module for the computer aided diagnostic systems in clinical practice. Large-scale breast ultrasound (BUS) images remain unannotated and need to be effectively explored to improve the segmentation quality. To address this, a semi-supervised segmentation network is proposed based on generative adversarial networks (GAN). METHODS: In this paper, a semi-supervised learning model, denoted as BUS-GAN, consisting of a segmentation base network-BUS-S and an evaluation base network-BUS-E, is proposed. The BUS-S network can densely extract multi-scale features in order to accommodate the individual variance of breast lesion, thereby enhancing the robustness of segmentation. Besides, the BUS-E network adopts a dual-attentive-fusion block having two independent spatial attention paths on the predicted segmentation map and leverages the corresponding original image to distill geometrical-level and intensity-level information, respectively, so that to enlarge the difference between lesion region and background, thus improving the discriminative ability of the BUS-E network. Then, through adversarial training, the BUS-GAN model can achieve higher segmentation quality because the BUS-E network guides the BUS-S network to generate more accurate segmentation maps with more similar distribution as ground truth. RESULTS: The counterpart semi-supervised segmentation methods and the proposed BUS-GAN model were trained with 2000 in-house images, including 100 annotated images and 1900 unannotated images, and tested on two different sites, including 800 in-house images and 163 public images. The results validate that the proposed BUS-GAN model can achieve higher segmentation accuracy on both the in-house testing dataset and the public dataset than state-of-the-art semi-supervised segmentation methods. CONCLUSIONS: The developed BUS-GAN model can effectively utilize the unannotated breast ultrasound images to improve the segmentation quality. In the future, the proposed segmentation method can be a potential module for the automatic breast ultrasound diagnose system, thus relieving the burden of a tedious image annotation process and alleviating the subjective influence of physicians' experiences in clinical practice. Our code will be made available on https://github.com/fiy2W/BUS-GAN.

Two-stage CNNs for computerized BI-RADS categorization in breast ultrasound images.

BACKGROUND: Quantizing the Breast Imaging Reporting and Data System (BI-RADS) criteria into different categories with the single ultrasound modality has always been a challenge. To achieve this, we proposed a two-stage grading system to automatically evaluate breast tumors from ultrasound images into five categories based on convolutional neural networks (CNNs). METHODS: This new developed automatic grading system was consisted of two stages, including the tumor identification and the tumor grading. The constructed network for tumor identification, denoted as ROI-CNN, can identify the region contained the tumor from the original breast ultrasound images. The following tumor categorization network, denoted as G-CNN, can generate effective features for differentiating the identified regions of interest (ROIs) into five categories: Category "3", Category "4A", Category "4B", Category "4C", and Category "5". Particularly, to promote the predictions identified by the ROI-CNN better tailor to the tumor, refinement procedure based on Level-set was leveraged as a joint between the stage and grading stage. RESULTS: We tested the proposed two-stage grading system against 2238 cases with breast tumors in ultrasound images. With the accuracy as an indicator, our automatic computerized evaluation for grading breast tumors exhibited a performance comparable to that of subjective categories determined by physicians. Experimental results show that our two-stage framework can achieve the accuracy of 0.998 on Category "3", 0.940 on Category "4A", 0.734 on Category "4B", 0.922 on Category "4C", and 0.876 on Category "5". CONCLUSION: The proposed scheme can extract effective features from the breast ultrasound images for the final classification of breast tumors by decoupling the identification features and classification features with different CNNs. Besides, the proposed scheme can extend the diagnosing of breast tumors in ultrasound images to five sub-categories according to BI-RADS rather than merely distinguishing the breast tumor malignant from benign.

[Magnitude image-guided phase unwrapping algorithm of susceptibility weighted images].

To better use the phase information to compensate the influence of blood flow, the phase unwrapping problem in susceptibility weighted imaging (SWI) is studied in this paper. In order to improve the accuracy of unwrapping, this paper proposes a magnitude image-guided phase unwrapping algorithm of SWI. The basic idea is as follows: (1) reduce the influence of noise by improving the rotational invariant non-local principal component analysis method (PRI-NL-PCA); (2) extract the corresponding solid region in the phase image to avoid the influence of the background noise on the phase unwrapping method; (3) use the phase compensation method to constrain the phase image reconstructed by the K-space. Finally, the reliability of the unwrapping method is evaluated by using four kinds of statistics as quantification index: the number, mean (M), variance (Var), and positive percentage (Pos) and negative percentage (Neg) of phasic error points. By comparing the simulated data with 226 sets of true head SWI data, the results show that the proposed algorithm has high accuracy compared with the classical branch cut method and the least squares method.