Search

Objective. The generation of quantification maps and weighted images in synthetic MRI techniques is based on complex fitting equations. This process requires longer image generation times. The objective of this study is to evaluate the feasibility of deep learning method for fast reconstruction of synthetic MRI. Approach. A total of 44 healthy subjects were recruited and random divided into a training set (30 subjects) and a testing set (14 subjects). A multiple-dynamic, multiple-echo (MDME) sequence was used to acquire synthetic MRI images. Quantification maps (T1, T2, and proton density (PD) maps) and weighted (T1W, T2W, and T2W FLAIR) images were created with MAGiC software and then used as the ground truth images in the deep learning (DL) model. An improved multichannel U-Net structure network was trained to generate quantification maps and weighted images from raw synthetic MRI imaging data (8 module images). Quantitative evaluation was performed on quantification maps. Quantitative evaluation metrics, as well as qualitative evaluation were used in weighted image evaluation. Nonparametric Wilcoxon signed-rank tests were performed in this study. Main results. The results of quantitative evaluation show that the error between the generated quantification images and the reference images is small. For weighted images, no significant difference in overall image quality or signal-to-noise ratio was identified between DL images and synthetic images. Notably, the DL images achieved improved image contrast with T2W images, and fewer artifacts were present on DL images than synthetic images acquired by T2W FLAIR. Significance. The DL algorithm provides a promising method for image generation in synthetic MRI techniques, in which every step of the calculation can be optimized and faster, thereby simplifying the workflow of synthetic MRI techniques., (Creative Commons Attribution license.)

Abstract Fluid dynamics computations for tube-like geometries are crucial in biomedical evaluations of vascular and airways fluid dynamics. Physics-Informed Neural Networks (PINNs) have emerged as a promising alternative to traditional computational fluid dynamics (CFD) methods. However, vanilla PINNs often demand longer training times than conventional CFD methods for each specific flow scenario, limiting their widespread use. To address this, multi-case PINN approach has been proposed, where varied geometry cases are parameterized and pre-trained on the PINN. This allows for quick generation of flow results in unseen geometries. In this study, we compare three network architectures to optimize the multi-case PINN through experiments on a series of idealized 2D stenotic tube flows. The evaluated architectures include the ‘Mixed Network’, treating case parameters as additional dimensions in the vanilla PINN architecture; the “Hypernetwork”, incorporating case parameters into a side network that computes weights in the main PINN network; and the “Modes” network, where case parameters input into a side network contribute to the final output via an inner product, similar to DeepONet. Results confirm the viability of the multi-case parametric PINN approach, with the Modes network exhibiting superior performance in terms of accuracy, convergence efficiency, and computational speed. To further enhance the multi-case PINN, we explored two strategies. First, incorporating coordinate parameters relevant to tube geometry, such as distance to wall and centerline distance, as inputs to PINN, significantly enhanced accuracy and reduced computational burden. Second, the addition of extra loss terms, enforcing zero derivatives of existing physics constraints in the PINN (similar to gPINN), improved the performance of the Mixed Network and Hypernetwork, but not that of the Modes network. In conclusion, our work identified strategies crucial for future scaling up to 3D, wider geometry ranges, and additional flow conditions, ultimately aiming towards clinical utility.

Using a deep learning algorithm in the development of a computer-aided system for colon polyp detection is effective in reducing the miss rate. This study aimed to develop a system for colon polyp detection and classification. We used a data augmentation technique and conditional GAN to generate polyp images for YOLO training to improve the polyp detection ability. After testing the model five times, a model with 300 GANs (GAN 300) achieved the highest average precision (AP) of 54.60% for SSA and 75.41% for TA. These results were better than those of the data augmentation method, which showed AP of 53.56% for SSA and 72.55% for TA. The AP, mAP, and IoU for the 300 GAN model for the HP were 80.97%, 70.07%, and 57.24%, and the data increased in comparison with the data augmentation technique by 76.98%, 67.70%, and 55.26%, respectively. We also used Gaussian blurring to simulate the blurred images during colonoscopy and then applied DeblurGAN-v2 to deblur the images. Further, we trained the dataset using YOLO to classify polyps. After using DeblurGAN-v2, the mAP increased from 25.64% to 30.74%. This method effectively improved the accuracy of polyp detection and classification. [ABSTRACT FROM AUTHOR]

Detecting product adoption intentions on social media could yield significant value in a wide range of applications, such as personalized recommendations and targeted marketing. In the literature, no study has explored the detection of product adoption intentions on social media, and only a few relevant studies have focused on purchase intention detection for products in one or several categories. Focusing on a product category rather than a specific product is too coarse-grained for precise advertising. Additionally, existing studies primarily focus on using one type of text representation in target social media posts, ignoring the major yet unexplored potential of fusing different text representations. In this paper, we first formulate the problem of product adoption intention mining and demonstrate the necessity of studying this problem and its practical value. To detect a product adoption intention for an individual product, we propose a novel and general multiview deep learning model that simultaneously taps into the capability of multiview learning in leveraging different representations and deep learning in learning latent data representations using a flexible nonlinear transformation. Specifically, the proposed model leverages three different text representations from a multiview perspective and takes advantage of local and long-term word relations by integrating convolutional neural network (CNN) and long short-term memory (LSTM) modules. Extensive experiments on three Twitter datasets demonstrate the effectiveness of the proposed multiview deep learning model compared with the existing benchmark methods. This study also significantly contributes research insights to the literature about intention mining and provides business value to relevant stakeholders such as product providers. [ABSTRACT FROM AUTHOR]

The Mycogone perniciosa disease of Agaricus bisporus is highly contagious, with insignificant early symptoms and a long infestation period. Currently, there is a lack of a convenient and rapid means to detect the disease for early control. By using the transmission route of the disease, this paper focuses on M. perniciosa chlamydospore detection in contaminated soil. Microscopic hyperspectral images of M. perniciosa chlamydospore in contaminated soil were obtained to establish a detection model. Given a small target and a complex background, we proposed an improved spore detection model based on a faster regional convolutional neural network (Faster R-CNN). Furthermore, we combined the residual network Resnet50 and feature pyramid network (FPN) to extract thick spore target features at multiple scales. Meanwhile, we optimized the region proposal network (RPN) region proposal generation by adding two small scales to improve the performance of the detection model. The first three principal components (with 95% or more information) and RGB images were selected as model inputs, respectively, and the final average precision (AP) was 94.68% and 92.35%, respectively. This PC-based model also was compared to the VGG16 and Resnet50-based feature extraction networks of Faster R-CNN and Darknet53-based feature extraction network of the YOLOv3 model, and the AP was found to improve by 5.41%, 4.78%, and 6.34%, respectively. The results showed that micro-hyperspectral imaging combined with deep learning methods could accurately detect the chlamydospore in the soil, providing new methods and ideas for the early prevention and detection of M. perniciosa disease of A. bisporus. [Display omitted] • A new means of early warning of disease infection in A. bisporus cultivation. • Micro-hyperspectral imaging were combined with deep learning for target detection. • An improved spore detection model based on Faster-RCNN was proposed. • PCA images got from micro-hyperspectral images provide richer feature information. [ABSTRACT FROM AUTHOR]

People detection is commonly used in computer vision systems, particularly for video surveillance and passenger flow statistics. Unlike standard cameras, fisheye cameras offer a large field of view and reduce occlusions when mounted overhead. However, due to the orientation variation of people in fisheye images, head detection models suffer from severe distortion when applied to fisheye images captured by top-view fisheye cameras. This work develops an end-to-end head detection method named HD-YOLO against complex situations in top-view fisheye images. The radius-aware loss function is designed to make HD-YOLO adapt to the impact of fisheye distortion, and the channel attention module is added to the model. We have also created new fisheye-image datasets for evaluation. Experiments showed that HD-YOLO outperforms other baseline methods on public and self-built datasets. • The distortion of fisheye images decreases the detection performance of CNNs seriously. • The radius-aware loss makes detection models robust to the distortion of fisheye images. • The channel attention is effective for YOLO to detect in fisheye images. [ABSTRACT FROM AUTHOR]

The flavor and market value of loquats are substantially affected by their soluble solids content (SSC). This study explored the ability of hyperspectral imaging combined with multiple regression models to detect SSC of loquats using small sample size. In this study, one hundred and fifteen loquats were collected as samples, and regions of interest in the hyperspectral images of the samples were extracted. The spectral data processed through direct orthogonal signal correction (DOSC), the best among the five processing methods examined, was selected for the feature spectrum process. Successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), improved uninformative variable elimination algorithm (im UVE), and im UVE-SPA algorithms were used to extract feature spectra and establish partial least squares regression (PLSR), support vector machine regression (SVR), back-propagation neural network (BPNN), and customized convolutional neural network (CNN) models, respectively. The results demonstrated that the CNN model based on the 18 feature spectra extracted by CARS was the best (correlation coefficient of validation = 0.904, root mean square error of validation = 0.336 %, and residual predictive deviation = 2.339). Consequently, hyperspectral images with small sample size combined with appropriate regression models can be used for nondestructive detection of loquat brix. Furthermore, the wavelength feature extraction algorithm effectively improves the performance of CNN models with small sample sizes. This study can serve as a valuable reference for the nondestructive detection of fruit brix in other limited sample situations. [Display omitted] • Hyperspectral imaging can predict the SSC of loquat from small sample sizes. • The performance of customized CNN was the best in SSC prediction. • Feature selection algorithms could improve the performance of the CNN models. • Deep learning can also perform well in the regression problem. [ABSTRACT FROM AUTHOR]

• A lightweight tomato target detection algorithm based on YOLOv5 is proposed. • The improved model has a significantly higher detection speed on the CPU platform. • The model is deployed on smartphones using model quantization and an APP is developed to achieve local real-time detection of tomatoes. • The 16-bit quantized model performs the best and the detection speed meets the needs of real-time. The current deep-learning-based tomato target detection algorithm has many parameters; it has drawbacks of large computation, long time consumption, and reliance on high-computing-power devices such as graphics processing units (GPU). In this study, we propose a lightweight improved YOLOv5 (You Only Look Once) based algorithm to achieve real-time localization and ripeness detection of tomato fruits. Initially, this algorithm used a down-sampling convolutional layer instead of the original focus layer, reconstructing the backbone network of YOLOv5 using the bneck module of MobileNetV3. Then, it performs channel pruning for the neck layer to further reduce the model size and uses a genetic algorithm for hyperparameter optimization to improve detection accuracy. We evaluate the improved algorithm using a homemade tomato dataset. The experimental results demonstrated that the improved model number of parameters and floating point operations per second (FLOPs) were compressed by 78% and 84.15% compared to the original YOLOv5s, while the mAP reached 0.969. Meanwhile, the detection speed on the central processing unit (CPU) platform was 42.5 ms, which was 64.88% better. This study further utilized the Nihui convolutional neural network (NCNN) framework to quantize the improved model and developed an Android-based real-time tomato monitoring application (app). Experimental results demonstrated that the 16-bit quantized model achieved an average detection frame rate of 26.5 frames per second (fps) on the mobile side with lower arithmetic power, which was 268% better than the original YOLOv5s, and the model size was reduced by 51.1% while achieving a 93% true detection rate. [ABSTRACT FROM AUTHOR]