Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor ...prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data.
In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients' prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet's performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research.
PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet .
Inkjet printing, the deposition of microfluidic droplets on a specified area, has gained increasing attention from both academia and industry for its versatility and scalability for mass production. ...Inkjet printing productivity depends on the number of nozzles used in a multijet process. However, droplet jetting conditions can vary for each nozzle due to multiple factors, such as the surface wetting condition of the nozzle, properties of the ink, and variances in the manufacturing of the nozzle head. For these reasons, droplet jetting conditions must be continuously monitored and evaluated by skillful engineers. The present study presents a deep-learning-based method to identify the droplet jetting status of a single-jet printing process. A convolutional neural network (CNN)-based on the MobileNetV2 model was employed with optimized hyperparameters to classify the inkjet frames containing images captured with a CCD camera. By accumulating the classified class data in order by frame time, the jetting conditions could be evaluated with high accuracy. The method was also successfully demonstrated with a multijet process, with a test time of less than a second per image.
The quantum dot light‐emitting diode (QLED) represents one of the strongest display technologies and has unique advantages like a shallow emission spectrum and superior performance based on the ...cumulative studies of state‐of‐the‐art quantum dot (QD) synthesis and interfacial engineering. However, research on managing the device's light extraction has been lacking compared to the conventional LED field. Moreover, relevant studies on top‐emitting QLEDs (TE‐QLEDs) have been severely lacking compared to bottom‐emitting QLEDs (BE‐QLEDs). This paper demonstrates a novel light extraction structure called the randomly disassembled nanostructure (RaDiNa). The RaDiNa is formed by detaching polydimethylsiloxane (PDMS) film from a ZnO nanorod (ZnO NR) layer and laying it on top of the TE‐QLED. The RaDiNa‐attached TE‐QLED shows significantly widened angular‐dependent electroluminescence (EL) intensities over the pristine TE‐QLED, confirming the effective light extraction capability of the RaDiNa layer. Consequently, the optimized RaDiNa‐attached TE‐QLED achieves enhanced external quantum efficiency (EQE) over the reference device by 60%. For systematic analyses, current–voltage–luminance (J–V–L) characteristics are investigated using scanning electron microscopy (SEM) and optical simulation based on COMSOL Multiphysics. It is believed that this study's results provide essential information for the commercialization of TE‐QLEDs.
A simple and unique light extraction structure for top‐emitting quantum dot light‐emitting diodes (QLEDs) named RaDiNa is proposed. Based on the molded irregular holes on PDMS by ZnO nanorods, the narrow viewing angle of top‐emitting QLED is widened, which results in an external quantum efficiency increase of 60%.
A 48 WL stacked 256-Gb V-NAND flash memory with a 3 b MLC technology is presented. Several vertical scale-down effects such as deteriorated WL loading and variations are discussed. To enhance ...performance, reverse read scheme and variable-pulse scheme are presented to cope with nonuniform WL characteristics. For improved performance, dual state machine architecture is proposed to achieve optimal timing for BL and WL, respectively. Also, to maintain robust IO driver strength against PVT variations, an embedded ZQ calibration technique with temperature compensation is introduced. The chip, fabricated in a third generation of V-NAND technology, achieved a density of 2.6 Gb/mm 2 with 53.2 MB/s of program throughput.
For synthetic aperture radar (SAR) imaging, the compressive sensing (CS) coupled with total variation (TV)-based algorithm is known as an effective focusing technique using under-sampled dataset. ...However, the performance of the CS-TV method can be degraded by drawbacks of TV in terms of noise sensitivity and computational efficiency. In this paper, a novel approach to CS-SAR imaging is proposed based on improved Tikhonov regularization (ITR) coupled with an adaptive strategy using iterative reweighted matrix to solve the CS reconstruction problem of SAR images with sparsity. The proposed method can provide different degrees of performance of SAR autofocus with changes to the value of certain parameters of ITR. The proposed scheme outperforms conventional CS-based methods with respect to image quality, noise robustness, and computational complexity of the algorithm owing to the additional sensitivity of the proposed objective function. From the simulation results, we verify that the proposed autofocus method is highly efficient in forming SAR images from non-uniformly under-sampled dataset in terms of both image quality and computational efficiency.
Background
This study developed a triple-negative breast cancer (TNBC) surrogate subtype classification that represents TNBC subtypes based on the Vanderbilt subtype classification.
Methods
Patients ...who underwent primary curative surgery for TNBC were included. Representative FFPE blocks were used for gene expression analysis and tissue microarray construction for immunohistochemical (IHC) staining. The Vanderbilt subtypes were re-classified into four groups: basal-like (BL), mesenchymal-like (M), immunomodulatory (IM) and luminal androgen receptor (LAR) subtype. Classification and regression tree (CART) modeling was applied to develop a surrogate subtype classification.
Results
A total of 145 patients were included. The study cohort was allocated to the Vanderbilt 4 subtypes as LAR (
n
= 22, 15.2%), IM (
n
= 32, 22.1%), M (
n
= 38, 26.2%), BL (
n
= 25, 17.2%) and unclassified (
n
= 28, 19.3%). After excluding nine (6.2%) patients due to poor IHC staining quality, CART modeling was performed. TNBC surrogate subtypes were defined as follows: LAR subtype, androgen receptor Allred score 8; IM subtype, LAR-negative with a tumor-infiltrating lymphocyte (TIL) score > 70%; M subtype, LAR-negative with a TIL score < 20%; BL subtype, LAR-negative with a TIL score 20–70% and diffuse, strong p16 staining. The study cohort was classified by the surrogate subtypes as LAR (
n
= 26, 17.9%), IM (
n
= 21, 14.5%), M (
n
= 44, 30.3%), BL1 (
n
= 27, 18.6%) and unclassified (
n
= 18, 12.4%). Surrogate subtypes predicted TNBC Vanderbilt 4 subtypes with an accuracy of 0.708.
Conclusion
We have developed a TNBC surrogate subtype classification that correlates with the Vanderbilt subtype. It is a practical and accessible diagnostic test that can be easily applied in clinical practice.
Ground moving target imaging (GMTIm) is considered one of the most important applications of synthetic aperture radar (SAR). Phase modulation from a moving target's higher-order movements severely ...degrades the focusing quality of SAR images, because the conventional SAR-GMTIm algorithm assumes a constant target velocity in high-resolution GMTIm with single channel SAR. To solve this problem, a novel SAR-GMTIm algorithm in the compressive sensing (CS) framework is proposed to obtain high-resolution SAR images with highly focused responses and accurate relocation. After taking direct action on data in the defocused region of interest (ROI) from the entire image scene, CS theory is used to decompose an SAR-GMTIm signal into a set of the polynomial basis functions to remove the various phase errors related to higherorder movements. A modified orthogonal matching pursuit (MOMP)-type basis function-searching scheme is adopted to determine the motion parameter and reconstruct the sensing dictionary matrix. We can generate a refocused image of SAR-GMTIm from the complete SAR-GMTIm signal recovered using the proposed method. Finally, simulated and real measured SAR data are used to validate the effectiveness and superiority of the proposed method for SAR-GMTIm.
Synthetic aperture radar (SAR) image registration is a process of geometrically aligning two or more remote sensing images, acquired at different times, from different viewpoints or from different ...sensors. To solve the problem that determines which transformation provides the most accurate match between two images, we propose a novel Tsallis entropy-based approach combined with a sequential search strategy to significantly reduce the computational complexity compared to the existing methods, while retaining excellent SAR registration performance. The Tsallis entropy can be considered as a kind of general version of similarity metric, depending on the order of Tsallis entropy. Thus, we use Tsallis entropy as a cost function to measure the degree of the focus of an average intensity projection profile of SAR image. The global optimum of the similarity metric should be reached if the reference and sensed images are correctly registered. The proposed method consists of coarse and fine registration steps, and each step is divided into two parts: range and azimuth domain processing. From the experimental results, we verify that the proposed method outperforms conventional methods in terms of computational complexity of the algorithm owing to the sensitivity of the cost function and efficiency of sequential search strategy.
Crystalline or amorphous metal oxides are widely used in various optoelectronic devices as key components, such as transparent conductive electrodes, dielectrics or semiconducting active layers for ...thin‐film transistor (TFT) backplanes in large‐area displays, photovoltaics, and light‐emitting diodes. Although crystalline inorganic materials demonstrate outstanding optoelectronic performance, owing to their wide bandgaps, large conductivities, and high carrier mobilities, their inherent brittleness makes them vulnerable to mechanical stress, thereby limiting the use of metal‐oxide films in emerging flexible electronic applications. In this study, stress‐diffusive organic–inorganic hybrid superlattice nanostructures are developed to overcome the mechanical limitation of crystalline oxides and to provide high mechanical stability to metal‐oxide semiconductors. In particular, hybrid transparent superlattice electrodes based on crystalline indium–tin oxide exhibit high electrical conductivities of up to 555 S cm–1 (resistance variation < 3%) and effectively reduce the mechanical stress on the inorganic layer (up to 10 000 bending cycles with a radius of 1 mm). Furthermore, to ensure the viability of the hybrid superlattice flexible electronics, all solution‐processed superlattice crystalline indium–gallium‐oxide TFTs are implemented on a thin (≈5 µm) polyimide substrate, providing highly robust and excellent electrical performance (average mobility of 7.6 cm2 V–1 s–1).
A facile, high‐throughput, solution‐processed industrial standard metal‐oxide material is fabricated for flexible optoelectronic devices. The huge demand for flexible electronic devices needs a new class of materials. Instead of spending time on not well‐studied materials, the solution‐processed hybrid superlattice with industrial standard metal‐oxide and organic materials can be successfully applied in flexible electronic devices.
In this paper, we propose a novel cross-range scaling technique to estimate the rotational velocity (RV) of a maneuvering target. The proposed method includes three steps. First, a feature from ...accelerated segment test (FAST) is applied to two sequential inverse synthetic aperture radar (ISAR) images to find the locations of their robust feature points. Second, the rotation angle (RA) is estimated using two major axes, which are obtained using a principal component analysis (PCA) of the two feature data sets scaled by a candidate RV. Third, an RV search operation based on the measured RA is carried out via the bisection algorithm, which optimizes a newly devised cost function. Compared with the conventional method, the proposed method has two main advantages: 1) it requires no information about the rotation center of a target, and 2) it can efficiently generate a well-scaled ISAR image within a very short time. Finally, the results of experiments using point scatterers and real flying aircraft are provided to demonstrate the validity of the proposed method.