Attention-guided duplex adversarial U-net for pancreatic segmentation from computed tomography images.

PURPOSE: Segmenting the organs from computed tomography (CT) images is crucial to early diagnosis and treatment. Pancreas segmentation is especially challenging because the pancreas has a small volume and a large variation in shape. METHODS: To mitigate this issue, an attention-guided duplex adversarial U-Net (ADAU-Net) for pancreas segmentation is proposed in this work. First, two adversarial networks are integrated into the baseline U-Net to ensure the obtained prediction maps resemble the ground truths. Then, attention blocks are applied to preserve much contextual information for segmentation. The implementation of the proposed ADAU-Net consists of two steps: 1) backbone segmentor selection scheme is introduced to select an optimal backbone segmentor from three two-dimensional segmentation model variants based on a conventional U-Net and 2) attention blocks are integrated into the backbone segmentor at several locations to enhance the interdependency among pixels for a better segmentation performance, and the optimal structure is selected as a final version. RESULTS: The experimental results on the National Institutes of Health Pancreas-CT dataset show that our proposed ADAU-Net outperforms the baseline segmentation network by 6.39% in dice similarity coefficient and obtains a competitive performance compared with the-state-of-art methods for pancreas segmentation. CONCLUSION: The ADAU-Net achieves satisfactory segmentation results on the public pancreas dataset, indicating that the proposed model can segment pancreas outlines from CT images accurately.

Enhanced Terahertz Phase Retrieval Imaging by Unequal Spaced Measurement.

Terahertz lensless phase retrieval imaging is a promising technique for non-destructive inspection applications. In the conventional multiple-plane phase retrieval method, the convergence speed due to wave propagations and measures with equal interval distance is slow and leads to stagnation. To address this drawback, we propose a nonlinear unequal spaced measurement scheme in which the interval space between adjacent measurement planes is gradually increasing, it can significantly increase the diversity of the intensity with a smaller number of required images. Both the simulation and experimental results demonstrate that our method enables quantitative phase and amplitude imaging with a faster speed and better image quality, while also being computationally efficient and robust to noise.

Multi-scale Selection and Multi-channel Fusion Model for Pancreas Segmentation Using Adversarial Deep Convolutional Nets.

Organ segmentation from existing imaging is vital to the medical image analysis and disease diagnosis. However, the boundary shapes and area sizes of the target region tend to be diverse and flexible. And the frequent applications of pooling operations in traditional segmentor result in the loss of spatial information which is advantageous to segmentation. All these issues pose challenges and difficulties for accurate organ segmentation from medical imaging, particularly for organs with small volumes and variable shapes such as the pancreas. To offset aforesaid information loss, we propose a deep convolutional neural network (DCNN) named multi-scale selection and multi-channel fusion segmentation model (MSC-DUnet) for pancreas segmentation. This proposed model contains three stages to collect detailed cues for accurate segmentation: (1) increasing the consistency between the distributions of the output probability maps from the segmentor and the original samples by involving the adversarial mechanism that can capture spatial distributions, (2) gathering global spatial features from several receptive fields via multi-scale field selection (MSFS), and (3) integrating multi-level features located in varying network positions through the multi-channel fusion module (MCFM). Experimental results on the NIH Pancreas-CT dataset show that our proposed MSC-DUnet obtains superior performance to the baseline network by achieving an improvement of 5.1% in index dice similarity coefficient (DSC), which adequately indicates that MSC-DUnet has great potential for pancreas segmentation.

Microwave photonic radar for distance and velocity measurement based on optical mixing and compressive sensing.

We propose a microwave photonic compressive sensing radar for distance and velocity measurement. First, a de-chirped signal that carries distance or velocity information is extracted between the transmitted and received signals in the proposed system. Then it is mixed with a pseudo-random bit sequence in the optical domain using a Mach-Zehnder modulator. After that, the de-chirped signal can be acquired by a photodetector and an analog-to-digital converter (ADC) at a sub-Nyquist sampling rate. Finally, a reconstruction algorithm can be used to recover the de-chirped signal. In our test, the bandwidth of ADC can be shortened from 2 GHz to 500 MHz, leading to a compression factor of four. A series of frequencies from 1.043 GHz to 1.875 GHz can be compressed with a 500-MHz ADC and recovered using a reconstruction algorithm. For a moving target, the Doppler frequency shift can be calculated, and the direction of the moving target can be distinguished. The maximum relative error of distance measurement is 0.21%. The maximum relative error of velocity measurement is 2.6%. The signal-to-noise ratio can be developed from ∼15dB to ∼30dB. This microwave photonic compressive sensing radar can achieve distance and velocity measurements using few samples. Also, it provides a large bandwidth of system operation and reduces data processing and storage pressure.

Accurate pancreas segmentation using multi-level pyramidal pooling residual U-Net with adversarial mechanism.

BACKGROUND: A novel multi-level pyramidal pooling residual U-Net with adversarial mechanism was proposed for organ segmentation from medical imaging, and was conducted on the challenging NIH Pancreas-CT dataset. METHODS: The 82 pancreatic contrast-enhanced abdominal CT volumes were split via four-fold cross validation to test the model performance. In order to achieve accurate segmentation, we firstly involved residual learning into an adversarial U-Net to achieve a better gradient information flow for improving segmentation performance. Then, we introduced a multi-level pyramidal pooling module (MLPP), where a novel pyramidal pooling was involved to gather contextual information for segmentation, then four groups of structures consisted of a different number of pyramidal pooling blocks were proposed to search for the structure with the optimal performance, and two types of pooling blocks were applied in the experimental section to further assess the robustness of MLPP for pancreas segmentation. For evaluation, Dice similarity coefficient (DSC) and recall were used as the metrics in this work. RESULTS: The proposed method preceded the baseline network 5.30% and 6.16% on metrics DSC and recall, and achieved competitive results compared with the-state-of-art methods. CONCLUSIONS: Our algorithm showed great segmentation performance even on the particularly challenging pancreas dataset, this indicates that the proposed model is a satisfactory and promising segmentor.

Ratiometric Fluorescent Detection of Intracellular Singlet Oxygen by Semiconducting Polymer Dots.

Singlet oxygen (1O2) plays important roles in many biological processes. However, it is very difficult to detect 1O2 in the intracellular environment because of its relatively low concentration and short lifetime. Here, we developed a ratiometric probe based on semiconducting polymer dots (Pdots) that can sensitively detect 1O2 in live cells. An organic dye, singlet oxygen sensor green (SOSG), was doped in polyfluorene Pdots, and excitation energy was efficiently transferred from the polymer to the SOSG dye. Accordingly, the Pdots showed constant blue fluorescence as a reference, and increased green fluorescence upon singlet oxygen generation. The ratiometric response of Pdots was examined in the intracellular environment by in situ 1O2 generation with a photosensitizer and light irradiation. Both spectroscopic measurements and confocal imaging were performed to monitor intracellular 1O2 generation during photodynamic therapy using the Pdot probe. Our results indicate that the SOSG-doped Pdots are promising for intracellular 1O2 detection.

Automatic Organ Segmentation for CT Scans Based on Super-Pixel and Convolutional Neural Networks.

Accurate segmentation of specific organ from computed tomography (CT) scans is a basic and crucial task for accurate diagnosis and treatment. To avoid time-consuming manual optimization and to help physicians distinguish diseases, an automatic organ segmentation framework is presented. The framework utilized convolution neural networks (CNN) to classify pixels. To reduce the redundant inputs, the simple linear iterative clustering (SLIC) of super-pixels and the support vector machine (SVM) classifier are introduced. To establish the perfect boundary of organs in one-pixel-level, the pixels need to be classified step-by-step. First, the SLIC is used to cut an image into grids and extract respective digital signatures. Next, the signature is classified by the SVM, and the rough edges are acquired. Finally, a precise boundary is obtained by the CNN, which is based on patches around each pixel-point. The framework is applied to abdominal CT scans of livers and high-resolution computed tomography (HRCT) scans of lungs. The experimental CT scans are derived from two public datasets (Sliver 07 and a Chinese local dataset). Experimental results show that the proposed method can precisely and efficiently detect the organs. This method consumes 38 s/slice for liver segmentation. The Dice coefficient of the liver segmentation results reaches to 97.43%. For lung segmentation, the Dice coefficient is 97.93%. This finding demonstrates that the proposed framework is a favorable method for lung segmentation of HRCT scans.

An Improved High-Sensitivity Airborne Transient Electromagnetic Sensor for Deep Penetration.

The investigation depth of transient electromagnetic sensors can be effectively increased by reducing the system noise, which is mainly composed of sensor internal noise, electromagnetic interference (EMI), and environmental noise, etc. A high-sensitivity airborne transient electromagnetic (AEM) sensor with low sensor internal noise and good shielding effectiveness is of great importance for deep penetration. In this article, the design and optimization of such an AEM sensor is described in detail. To reduce sensor internal noise, a noise model with both a damping resistor and a preamplifier is established and analyzed. The results indicate that a sensor with a large diameter, low resonant frequency, and low sampling rate will have lower sensor internal noise. To improve the electromagnetic compatibility of the sensor, an electromagnetic shielding model for a central-tapped coil is established and discussed in detail. Previous studies have shown that unclosed shields with multiple layers and center grounding can effectively suppress EMI and eddy currents. According to these studies, an improved differential AEM sensor is constructed with a diameter, resultant effective area, resonant frequency, and normalized equivalent input noise of 1.1 m, 114 m², 35.6 kHz, and 13.3 nV/m², respectively. The accuracy of the noise model and the shielding effectiveness of the sensor have been verified experimentally. The results show a good agreement between calculated and measured results for the sensor internal noise. Additionally, over 20 dB shielding effectiveness is achieved in a complex electromagnetic environment. All of these results show a great improvement in sensor internal noise and shielding effectiveness.

Generation and dynamics analysis of N-scrolls existence in new translation-type chaotic systems.

In this paper, we propose two kinds of translation type chaotic systems for creating 2 N + 1-and 2(N + 1)-scrolls chaotic attractors from a simple three-dimensional system, which are named the translation-2 chaotic system (a12a21 < 0) and the translation-3 chaotic system (a12a21 > 0). We also propose the successful design criterion for constructing 2 N + 1-and 2(N + 1)-scrolls, respectively. Then, the dynamics property of the translation-2 chaotic system is studied in detail. MATLAB simulation results show that very sophisticated dynamical behaviors and unique chaotic behaviors of the system. Finally, the definition and criterion of multi-scroll attractors for the translation-3 chaotic system is obtained. Three representative examples are shown in some classical chaotic systems that can be equally obtained via the set parameters of the translation type chaotic system. Furthermore, we show that the translation type chaotic systems have similar but topologically non-equivalent chaotic attractors, and they are the three-dimensional ordinary differential equations.

Generation of 2N + 1-scroll existence in new three-dimensional chaos systems.

We propose a systematic methodology for creating 2N + 1-scroll chaotic attractors from a simple three-dimensional system, which is named as the translation chaotic system. It satisfies the condition a12a21 = 0, while the Chua system satisfies a12a21 > 0. In this paper, we also propose a successful (an effective) design and an analytical approach for constructing 2N + 1-scrolls, the translation transformation principle. Also, the dynamics properties of the system are studied in detail. MATLAB simulation results show very sophisticated dynamical behaviors and unique chaotic behaviors of the system. It provides a new approach for 2N + 1-scroll attractors. Finally, to explore the potential use in technological applications, a novel block circuit diagram is also designed for the hardware implementation of 1-, 3-, 5-, and 7-scroll attractors via switching the switches. Translation chaotic system has the merit of convenience and high sensitivity to initial values, emerging potentials in future engineering chaos design.

Object reconstitution using pseudo-inverse for ghost imaging.

We propose a novel method for object reconstruction of ghost imaging based on Pseudo-Inverse, where the original objects are reconstructed by computing the pseudo-inverse of the matrix constituted by the row vectors of each speckle field. We conduct reconstructions for binary images and gray-scale images. With equal number of measurements, our method presents a satisfying performance on enhancing Peak Signal to Noise Ratio (PSNR) and reducing computing time. Being compared with the other existing methods, its PSNR distinctly exceeds that of the traditional Ghost Imaging (GI) and Differential Ghost Imaging (DGI). In comparison with the Compressive-sensing Ghost Imaging (CGI), the computing time is substantially shortened, and in regard to PSNR our method exceeds CGI on grayscale images and performs as well as CGI visually on binary images. The influence of both the detection noise and the accuracy of measurement matrix on PSNR are also presented.

Generation of Multi-Lobe Chua Corsage Memristor and Its Neural Oscillation.

The Chua corsage memristor (CCM) is considered as one of the candidates for the realization of biological neuron models due to its rich neuromorphic behaviors. In this paper, a universal model for m-lobe CCM memristor is proposed. Moreover, a novel small-signal equivalent circuit with one capacitor is derived based on the proposed model to determine the edge of chaos and obtain the zero-pole diagrams and analyze the frequency response and oscillation mechanism of the m-lobe CCM system, which are discussed in detail. In view of existence of the edge of chaos, the frequency response and the oscillation mechanism of the simplest oscillator is analysed using the proposed model. Finally, the proposed model has exhibited some essential neural oscillation, including the stable limit cycle, supercritical Hopf bifurcation, spiking and bursting oscillation. This study also reveals a previously undiscovered behavior of bursting oscillation in a CCM system.

A Minimally Interactive Method for Labeling Respiratory Phases in Free-Breathing Thoracic Dynamic MRI for Constructing 4D Images.

OBJECTIVE: Determination of end-expiration (EE) and end-inspiration (EI) time points in the respiratory cycle in free-breathing slice image acquisitions of the thorax is one key step needed for 4D image construction via dynamic magnetic resonance imaging. The purpose of this paper is to realize the automation of the labeling process. METHODS: The diaphragm is used as a surrogate for tracking respiratory motion and determining the state of breathing. Regions of interest (ROIs) containing the hemi-diaphragms are set by human interaction to compute the optical flow matrix between two adjacent 2D time slices. Subsequently, our approach examines the diaphragm speed and direction and by considering the change in the optical flow matrix, the EE or EI points are detected. RESULTS AND CONCLUSION: The labeling accuracy for the lateral aspect of the left lung and the lateral aspect of the right lung (0.63±0.71) is significantly lower (P < 0.05) than the accuracy for other positions (0.42±0.44), but the error in almost all scenarios is less than 1 time point. By comparing between automatic and manual labeling in 12 scenarios, we found out that 9 scenarios showed no significant difference (P > 0.05) between two methods. Overall, our method is found to be highly agreeable with manual labeling and greatly shortens the labeling time, requiring less than 8 minutes/ study compared to 4 hours/ study for manual labeling. SIGNIFICANCE: Our method achieves automatic labeling of EE and EI points without the need for use of patientinternal or external markers.

Dual adversarial convolutional networks with multilevel cues for pancreatic segmentation.

Accurate organ segmentation is a relatively challenging subject in medical imaging, especially for the pancreas, whose morphological characteristics are subtle but variable. In this paper, a novel dual adversarial convolutional network with multilevel cues (DACN-MC) is proposed to segment the pancreas in computerized tomography (CT). DACN-MC first involves a duplex adversarial network using a conventional model for biomedical image segmentation, which ensures the veracity of the predicted probability volumes and ultimately enhances the quality of the obtained maps. Specifically, one of the adversarial networks helps the predicted maps to resemble the ground truths by importing extra guidance into the original loss functions. The other adversarial network further judges whether the obtained maps are well segmented and improves the image quality once again. Then, a multilevel cue collection module (MCCM) is introduced to gather many useful details for pancreas segmentation. In other words, we collect several sets of material formed by features from different layers and pick out a group with optimal performance for use in the ultimate algorithm. The experimental results show that dual adversarial convolutional networks together with multilevel cue collection help our proposed algorithm to achieve competitive segmentation performance, based on the results of several evaluation indexes.

Automated measurement of hip-knee-ankle angle on the unilateral lower limb X-rays using deep learning.

Significant inherent extra-articular varus angulation is associated with abnormal postoperative hip-knee-ankle (HKA) angle. At present, HKA is manually measured by orthopedic surgeons and it increases the doctors' workload. To automatically determine HKA, a deep learning-based automated method for measuring HKA on the unilateral lower limb X-rays was developed and validated. This study retrospectively selected 398 double lower limbs X-rays during 2018 and 2020 from Jilin University Second Hospital. The images (n = 398) were cropped into unilateral lower limb images (n = 796). The deep neural network was used to segment the head of hip, the knee, and the ankle in the same image, respectively. Then, the mean square error of distance between each internal point of each organ and the organ's boundary was calculated. The point with the minimum mean square error was set as the central point of the organ. HKA was determined using the coordinates of three organs' central points according to the law of cosines. In a quantitative analysis, HKA was measured manually by three orthopedic surgeons with a high consistency (176.90 ° ± 12.18°, 176.95 ° ± 12.23°, 176.87 ° ± 12.25°) as evidenced by the Kandall's W of 0.999 (p < 0.001). Of note, the average measured HKA by them (176.90 ° ± 12.22°) served as the ground truth. The automatically measured HKA by the proposed method (176.41 ° ± 12.08°) was close to the ground truth, showing no significant difference. In addition, intraclass correlation coefficient (ICC) between them is 0.999 (p < 0.001). The average of difference between prediction and ground truth is 0.49°. The proposed method indicates a high feasibility and reliability in clinical practice.

Pancreas segmentation based on an adversarial model under two-tier constraints.

Pancreas segmentation is vital for the effective diagnosis and treatment of diabetic or pancreatic diseases. However, the irregular shape and strong variability of the pancreas in medical images pose significant challenges to accurate segmentation. In this paper, we propose a novel segmentation algorithm that imposes two-tier constraints on a conventional network through adversarial learning, namely UDCGAN. Specifically, we incorporate a dual adversarial training scheme in a conventional segmentation network, which further facilitates the probability maps from the segmentor to converge on the ground truth distributions owing to the effectiveness of generative adversarial networks (GANs) in capturing data distributions. This novel segmentation algorithm is equivalent to employing adversarial learning on a segmentation network that has been trained in an adversarial manner. Duplex intervention and guidance further refine the loss functions of the segmentor, thus effectively contributing to the preservation of details for segmentation. The segmentation results on the NIH Pancreas-CT dataset show that our proposed model achieves a competitive performance compared with other state-of-the-art methods.

Development and assessment of an individualized nomogram to predict colorectal cancer liver metastases.

BACKGROUND: This article aims to develop and assess the radiomics paradigm for predicting colorectal cancer liver metastasis (CRLM) from the primary tumor. METHODS: This retrospective study included 100 patients from the First Hospital of Jilin University from June 2017 to December 2017. The 100 patients comprised 50 patients with and 50 without CRLM. The maximum-level enhanced computed tomography (CT) image of primary cancer in the portal venous phase of each patient was selected as the original image data. To automatically implement radiomics-related paradigms, we developed a toolkit called Radiomics Intelligent Analysis Toolkit (RIAT). RESULTS: With RIAT, the model based on logistic regression (LR) using both the radiomics and clinical information signatures showed the maximum net benefit. The area under the curve (AUC) value was 0.90±0.02 (sensitivity =0.85±0.02, specificity =0.79±0.04) for the training set, 0.86±0.11 (sensitivity =0.85±0.09, specificity =0.75±0.19) for the verification set, 0.906 (95% CI, 0.840-0.971; sensitivity =0.81, specificity =0.84) for the cross-validation set, and 0.899 (95% CI, 0.761-1.000; sensitivity =0.78, specificity =0.91) for the test set. CONCLUSIONS: The radiomics nomogram-based LR with clinical risk and radiomics features allows for a more accurate classification of CRLM using CT images with RIAT.

Organic Transistor Nonvolatile Memory with Three-Level Information Storage and Optical Detection Functions.

By the current processing technology, it is a challenge to obtain ultrahigh-density information storage in the conventional binary floating-gate-based organic field-effect transistor (FG-OFET) nonvolatile memories (NVMs). To develop a multilevel memory in one cell is a feasible solution. In this work, we demonstrate FG-OFET NVMs with an integrated polymer floating-gate/tunneling (I-FG/T) layer consisting of poly(9,9-dioctylfluorene-co-benzothiadiazole) (F8BT) and polystyrene. The photoelectric effect of organic/polymer semiconductors is used to improve the controllability of the polarity and the number of the charges stored in the floating-gate. The FG-OFET NVMs integrate light sensitivity and nonvolatile information storage functions. By selecting suitable optical and electrical programming/erasing conditions, three-level information storage states, corresponding to electron storage, approximate neutrality, and hole storage in the floating-gate, are achieved and freely switched to each other. The memory mechanism and the dependence of the memory performances on the F8BT contents in I-FG/T layers are investigated. As a result, good memory performances, with mobility larger than 1.0 cm2 V-1 s-1, reliable three-level switching endurance over 100 cycles, and stable three-level retention capability over 20 000 s, are achieved in our memory. Furthermore, an imaging system with a nonvolatile information storage function is demonstrated in a 16 × 5 array of FG-OFET NVMs.

Accurate colorectal tumor segmentation for CT scans based on the label assignment generative adversarial network.

PURPOSE: Colorectal tumor segmentation is an important step in the analysis and diagnosis of colorectal cancer. This task is a time consuming one since it is often performed manually by radiologists. This paper presents an automatic postprocessing module to refine the segmentation of deep networks. The label assignment generative adversarial network (LAGAN) is improved from the generative adversarial network (GAN) and assigns labels to the outputs of deep networks. We apply the LAGAN to segment colorectal tumors in computed tomography (CT) scans and explore the performances of different combinations of deep networks. MATERIAL AND METHODS: A total of 223 patients with colorectal cancer (CRC) are enrolled in the study. The CT scans of the colorectal tumors are first segmented by FCN32 and Unet separately, which output probabilistic maps. Then, the probabilistic maps are labeled by the LAGAN and finally, the binary segmentation results are obtained. The LAGAN consists of a generating model and a discriminating model. The generating model utilizes the probabilistic maps from deep networks to imitate the distribution of the ground truths, and the discriminating model attempts to distinguish generations and ground truths. Through competitive training, the generating model of the LAGAN can realize label assignments for the probabilistic maps. RESULTS: The LAGAN increases the DSC of FCN32 from 81.83% ± 0.35% to 90.82% ± 0.36%. In the Unet-based segmentation, the LAGAN increases the DSC from 86.67% ± 0.70% to 91.54% ± 0.53%. It takes approximately 10 ms to refine a single CT slice. CONCLUSIONS: The results demonstrate that the LAGAN is a robust and flexible module, which can be used to refine the segmentation of diverse deep networks. Compared with other networks, the LAGAN can achieve desirable segmented accuracy for colorectal tumors.

Automated and accurate quantification of subcutaneous and visceral adipose tissue from magnetic resonance imaging based on machine learning.

Accurate measuring of subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) is vital for the research of many diseases. The localization and quantification of SAT and VAT by computed tomography (CT) expose patients to harmful ionizing radiation. Magnetic resonance imaging (MRI) is a safe and painless test. The aim of this paper is to explore a practical method for the segmentation of SAT and VAT based on the iterative decomposition of water and fat with echo asymmetry and least square estimation­iron quantification (IDEAL-IQ) technology and machine learning. The approach involves two main steps. First, a deep network is designed to segment the inner and outer boundaries of SAT in fat images and the peritoneal cavity contour in water images. Second, after mapping the peritoneal cavity contour onto the fat images, the assumption-free K-means++ with a Markov chain Monte Carlo (AFK-MC2) clustering method is used to obtain the VAT content. An MRI data set from 75 subjects is utilized to construct and evaluate the new strategy. The Dice coefficients for the SAT and VAT content obtained from the proposed method and the manual measurements performed by experts are 0.96 and 0.97, respectively. The experimental results indicate that the proposed method and the manual measurements exhibit high reliability.