Automatic segmentation of brain tumors from medical images is important for clinical assessment and treatment planning of brain tumors. Recent years have seen an increasing use of convolutional ...neural networks (CNNs) for this task, but most of them use either 2D networks with relatively low memory requirement while ignoring 3D context, or 3D networks exploiting 3D features while with large memory consumption. In addition, existing methods rarely provide uncertainty information associated with the segmentation result. We propose a cascade of CNNs to segment brain tumors with hierarchical subregions from multi-modal Magnetic Resonance images (MRI), and introduce a 2.5D network that is a trade-off between memory consumption, model complexity and receptive field. In addition, we employ test-time augmentation to achieve improved segmentation accuracy, which also provides voxel-wise and structure-wise uncertainty information of the segmentation result. Experiments with BraTS 2017 dataset showed that our cascaded framework with 2.5D CNNs was one of the top performing methods (second-rank) for the BraTS challenge. We also validated our method with BraTS 2018 dataset and found that test-time augmentation improves brain tumor segmentation accuracy and that the resulting uncertainty information can indicate potential mis-segmentations and help to improve segmentation accuracy.
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic ...segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.
Blue thermally activated delayed fluorescence (TADF) emitters that can simultaneously achieve high efficiency in doped and nondoped organic light‐emitting diodes (OLEDs) are rarely reported. Reported ...here is a strategy using a tri‐spiral donor for such versatile blue TADF emitters. Impressively, by simply extending the nonconjugated fragment and molecular length, aggregation‐caused emission quenching (ACQ) can be greatly alleviated to achieve as high as a 90 % horizontal orientation dipole ratio and external quantum efficiencies (EQEs) of up to 33.3 % in doped and 20.0 % in nondoped sky‐blue TADF‐OLEDs. More fascinatingly, a high‐efficiency purely organic white OLED with an outstanding EQE of up to 22.8 % was also achieved by employing TspiroS‐TRZ as a blue emitter and an assistant host. This compound is the first blue TADF emitter that can simultaneously achieve high electroluminescence (EL) efficiency in doped, nondoped sky‐blue, and white TADF‐OLEDs.
TADF, Tada! By using a tri‐spiral donor, the thermally activated delayed fluorescence (TADF) emitter TspiroS‐TRZ can achieve a 90 % horizontal orientation dipole ratio and greatly alleviate aggregation‐caused emission quenching (ACQ). The emitter demonstrates state‐of‐the‐art external quantum efficiencies (EQEs) of 33.3, 20.0, and 22.8 % in purely organic doped, nondoped sky‐blue, and white TADF‐OLEDs, respectively. HTAU=hole transporting adjusting unit, OLED=organic light‐emitting diode.
The status-legitimacy hypothesis proposes that people with lower socioeconomic status (SES) are more likely to justify the social system than those with higher SES. However, empirical studies found ...inconsistent findings. In the present research, we argue that at least part of the confusion stems from the possibility that objective and subjective SES are differently related to system justification. On one hand, subjective SES is more related to status maintenance motivation and may increase system justification. On the other hand, objective SES is more related to access to information about the social reality, which may increase criticism about the system and lead to lower system justification. These hypotheses were supported by evidence from five studies (total N = 26,134) involving both adult and adolescent samples in China. We recommend that future research on status-related issues needs to distinguish the potential divergent roles of objective and subjective SES.
•A method to infer voxel-level correspondence from higher-level anatomical labels.•Efficient and fully-automated registration for MR and ultrasound prostate images.•Validation experiments with 108 ...pairs of labelled interventional patient images.•Open-source implementation.
One of the fundamental challenges in supervised learning for multimodal image registration is the lack of ground-truth for voxel-level spatial correspondence. This work describes a method to infer voxel-level transformation from higher-level correspondence information contained in anatomical labels. We argue that such labels are more reliable and practical to obtain for reference sets of image pairs than voxel-level correspondence. Typical anatomical labels of interest may include solid organs, vessels, ducts, structure boundaries and other subject-specific ad hoc landmarks. The proposed end-to-end convolutional neural network approach aims to predict displacement fields to align multiple labelled corresponding structures for individual image pairs during the training, while only unlabelled image pairs are used as the network input for inference. We highlight the versatility of the proposed strategy, for training, utilising diverse types of anatomical labels, which need not to be identifiable over all training image pairs. At inference, the resulting 3D deformable image registration algorithm runs in real-time and is fully-automated without requiring any anatomical labels or initialisation. Several network architecture variants are compared for registering T2-weighted magnetic resonance images and 3D transrectal ultrasound images from prostate cancer patients. A median target registration error of 3.6 mm on landmark centroids and a median Dice of 0.87 on prostate glands are achieved from cross-validation experiments, in which 108 pairs of multimodal images from 76 patients were tested with high-quality anatomical labels.
Display omitted
We present a novel method to segment instances of glandular structures from colon histopathology images. We use a structure learning approach which represents local spatial configurations of class ...labels, capturing structural information normally ignored by sliding-window methods. This allows us to reveal different spatial structures of pixel labels (e.g., locations between adjacent glands, or far from glands), and to identify correctly neighboring glandular structures as separate instances. Exemplars of label structures are obtained via clustering and used to train support vector machine classifiers. The label structures predicted are then combined and post-processed to obtain segmentation maps. We combine hand-crafted, multi-scale image features with features computed by a deep convolutional network trained to map images to segmentation maps. We evaluate the proposed method on the public domain GlaS data set, which allows extensive comparisons with recent, alternative methods. Using the GlaS contest protocol, our method achieves the overall best performance.
High-resolution volume reconstruction from multiple motion-corrupted stacks of 2D slices plays an increasing role for fetal brain Magnetic Resonance Imaging (MRI) studies. Currently existing ...reconstruction methods are time-consuming and often require user interactions to localize and extract the brain from several stacks of 2D slices. We propose a fully automatic framework for fetal brain reconstruction that consists of four stages: 1) fetal brain localization based on a coarse segmentation by a Convolutional Neural Network (CNN), 2) fine segmentation by another CNN trained with a multi-scale loss function, 3) novel, single-parameter outlier-robust super-resolution reconstruction, and 4) fast and automatic high-resolution visualization in standard anatomical space suitable for pathological brains. We validated our framework with images from fetuses with normal brains and with variable degrees of ventriculomegaly associated with open spina bifida, a congenital malformation affecting also the brain. Experiments show that each step of our proposed pipeline outperforms state-of-the-art methods in both segmentation and reconstruction comparisons including expert-reader quality assessments. The reconstruction results of our proposed method compare favorably with those obtained by manual, labor-intensive brain segmentation, which unlocks the potential use of automatic fetal brain reconstruction studies in clinical practice.
Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare ...systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from research to clinical practice. This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.
As the main driver of innovation, enterprises can effectively promote the level of social innovation. This paper incorporates digital inclusive finance into the research framework of innovation in ...Small and Medium-sized enterprises, and investigates the impact of digital inclusive finance on the innovation ability of Small and Medium-sized enterprises through theoretical and empirical analyses. The theoretical analysis finds that digital inclusive finance can compensate for the “long-tail effect” in the financing process and help enterprises obtain financing loans. In terms of empirical analysis, this paper has conducted empirical tests by selecting the innovation data of Chinese A-share listed companies from 2010 to 2021, and the results show that: (1) Digital inclusive finance still has a facilitating effect on the technological innovation capability of Small and Medium-sized enterprises after the robustness test. (2)The mechanism evaluation finds that the digital inclusive finance segmentation indicators, i.e., the depth of use, the breadth of coverage and the degree of digitalization, are also important ways to enhance the technological innovation capability of Small and Medium-sized enterprises. (3)The innovative introduction of financial mismatch variables reveals that the financial mismatch problem in the financial market has a suppressive effect on the technological innovation capability of Small and Medium-sized enterprises. (4)Further analysis of the mediation effect of digital inclusive finance reveals that digital inclusive finance can effectively correct the financial mismatch problem in the traditional financial model and promote the technological innovation capability of Small and Medium-sized enterprises. This paper enriches the analysis of the economic effects of digital inclusive finance, while providing Chinese empirical support for digital inclusive finance to promote the innovation ability of Small and Medium-sized enterprises.
•This paper attempts to examine whether the financial mismatch problem that exists in the traditional financial industry has an impact on enterprises innovation by analyzing it.•Combining macro-finance perspectives with micro-individuals, we study the impact of digital development of finance on enterprises innovation.•Based on the analysis of the impact of digital inclusive finance on firms' innovation capacity, we analyze whether there is a mediating effect of financial mismatch.