scholarly journals Accurate brain age prediction with lightweight deep neural networks

2019 ◽  
Author(s):  
Han Peng ◽  
Weikang Gong ◽  
Christian F. Beckmann ◽  
Andrea Vedaldi ◽  
Stephen M. Smith
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Uk Biobank ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Prediction Bias ◽  
Dataset Size ◽  
Art Performance ◽  
Brain Age ◽  
Age Prediction

AbstractDeep learning has huge potential for accurate disease prediction with neuroimaging data, but the prediction performance is often limited by training-dataset size and computing memory requirements. To address this, we propose a deep convolutional neural network model, Simple Fully Convolutional Network (SFCN), for accurate prediction of brain age using T1-weighted structural MRI data. Compared with other popular deep network architectures, SFCN has fewer parameters, so is more compatible with small dataset size and 3D volume data. The network architecture was combined with several techniques for boosting performance, including data augmentation, pre-training, model regularization, model ensemble and prediction bias correction. We compared our overall SFCN approach with several widely-used machine learning models. It achieved state-of-the-art performance in UK Biobank data (N = 14,503), with mean absolute error (MAE) = 2.14y in brain age prediction and 99.5% in sex classification. SFCN also won (both parts of) the 2019 Predictive Analysis Challenge for brain age prediction, involving 79 competing teams (N = 2,638, MAE = 2.90y). We describe here the details of our approach, and its optimisation and validation. Our approach can easily be generalised to other tasks using different image modalities, and is released on GitHub.HighlightsA lightweight deep learning model, Simple Fully Convolutional Network (SFCN), is presented, achieving state-of-the-art brain age prediction and sex classification performance in UK Biobank MRI brain imaging data.Even with limited number of training subjects (e.g., 50), SFCN performs better than widely-used regression models.A semi-multimodal ensemble strategy is proposed and achieved first place in the PAC 2019 brain age prediction challenge.Linear regression can remove brain age prediction bias (even on unlabelled data) while maintaining state-of-the-art performance.

scholarly journals PyConvU-Net: a lightweight and multiscale network for biomedical image segmentation

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Changyong Li ◽  
Yongxian Fan ◽  
Xiaodong Cai
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
State Of The Art ◽  
Experimental Results ◽  
Actual Situation ◽  
Controlled Experiments ◽  
Biomedical Image ◽  
Segmentation Methods ◽  
Art Performance

Abstract Background With the development of deep learning (DL), more and more methods based on deep learning are proposed and achieve state-of-the-art performance in biomedical image segmentation. However, these methods are usually complex and require the support of powerful computing resources. According to the actual situation, it is impractical that we use huge computing resources in clinical situations. Thus, it is significant to develop accurate DL based biomedical image segmentation methods which depend on resources-constraint computing. Results A lightweight and multiscale network called PyConvU-Net is proposed to potentially work with low-resources computing. Through strictly controlled experiments, PyConvU-Net predictions have a good performance on three biomedical image segmentation tasks with the fewest parameters. Conclusions Our experimental results preliminarily demonstrate the potential of proposed PyConvU-Net in biomedical image segmentation with resources-constraint computing.

scholarly journals Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

2018 ◽  
Vol 10 (11) ◽  
pp. 1827 ◽  
Author(s):  
Ahram Song ◽  
Jaewan Choi ◽  
Youkyung Han ◽  
Yongil Kim
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Spatial Information ◽  
Short Term Memory ◽  
Hyperspectral Images ◽  
Convolutional Network ◽  
Ground Truth Data ◽  
Fully Convolutional Network ◽  
Training Samples ◽  
Multi Temporal

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

scholarly journals Fully Convolutional Network for Consistent Voxel-Wise Correspondence

2020 ◽  
Vol 34 (07) ◽  
pp. 12935-12942 ◽  
Author(s):  
Yungeng Zhang ◽  
Yuru Pei ◽  
Yuke Guo ◽  
Gengyu Ma ◽  
Tianmin Xu ◽  
...  
Keyword(s):  
Vector Fields ◽  
State Of The Art ◽  
Displacement Vector ◽  
Cone Beam Ct ◽  
Deformable Registration ◽  
Cone Beam ◽  
Nonlinear Mapping ◽  
Convolutional Network ◽  
Mapping Functions ◽  
Fully Convolutional Network

In this paper, we propose a fully convolutional network-based dense map from voxels to invertible pair of displacement vector fields regarding a template grid for the consistent voxel-wise correspondence. We parameterize the volumetric mapping using a convolutional network and train it in an unsupervised way by leveraging the spatial transformer to minimize the gap between the warped volumetric image and the template grid. Instead of learning the unidirectional map, we learn the nonlinear mapping functions for both forward and backward transformations. We introduce the combinational inverse constraints for the volumetric one-to-one maps, where the pairwise and triple constraints are utilized to learn the cycle-consistent correspondence maps between volumes. Experiments on both synthetic and clinically captured volumetric cone-beam CT (CBCT) images show that the proposed framework is effective and competitive against state-of-the-art deformable registration techniques.

scholarly journals FMnet: Iris Segmentation and Recognition by Using Fully and Multi-Scale CNN for Biometric Security

2019 ◽  
Vol 9 (10) ◽  
pp. 2042 ◽  
Author(s):  
Rachida Tobji ◽  
Wu Di ◽  
Naeem Ayoub
Keyword(s):  
Neural Networks ◽  
Iris Recognition ◽  
State Of The Art ◽  
Features Extraction ◽  
Iris Segmentation ◽  
Recognition Method ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Multi Scale ◽  
Biometric Security

In Deep Learning, recent works show that neural networks have a high potential in the field of biometric security. The advantage of using this type of architecture, in addition to being robust, is that the network learns the characteristic vectors by creating intelligent filters in an automatic way, grace to the layers of convolution. In this paper, we propose an algorithm “FMnet” for iris recognition by using Fully Convolutional Network (FCN) and Multi-scale Convolutional Neural Network (MCNN). By taking into considerations the property of Convolutional Neural Networks to learn and work at different resolutions, our proposed iris recognition method overcomes the existing issues in the classical methods which only use handcrafted features extraction, by performing features extraction and classification together. Our proposed algorithm shows better classification results as compared to the other state-of-the-art iris recognition approaches.

scholarly journals Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing

2019 ◽  
Vol 33 ◽  
pp. 3598-3605 ◽  
Author(s):  
Ryosuke Furuta ◽  
Naoto Inoue ◽  
Toshihiko Yamasaki
Keyword(s):  
Image Processing ◽  
Reinforcement Learning ◽  
State Of The Art ◽  
Great Success ◽  
Local Color ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Effective Learning ◽  
Pixel Value ◽  
Problem Setting

This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of deep RL for image processing are still limited. Therefore, we extend deep RL to pixelRL for various image processing applications. In pixelRL, each pixel has an agent, and the agent changes the pixel value by taking an action. We also propose an effective learning method for pixelRL that significantly improves the performance by considering not only the future states of the own pixel but also those of the neighbor pixels. The proposed method can be applied to some image processing tasks that require pixel-wise manipulations, where deep RL has never been applied.We apply the proposed method to three image processing tasks: image denoising, image restoration, and local color enhancement. Our experimental results demonstrate that the proposed method achieves comparable or better performance, compared with the state-of-the-art methods based on supervised learning.

scholarly journals Exploitation of deep learning in the automatic detection of cracks on paved roads

GEOMATICA ◽  
2019 ◽  
Vol 73 (2) ◽  
pp. 29-44
Author(s):  
Won Mo Jung ◽  
Faizaan Naveed ◽  
Baoxin Hu ◽  
Jianguo Wang ◽  
Ningyuan Li
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Ground Truth ◽  
Learning Networks ◽  
Test Image ◽  
Convolutional Network ◽  
Image Patches ◽  
Severity Levels ◽  
First Time ◽  
Different Levels

With the advance of deep learning networks, their applications in the assessment of pavement conditions are gaining more attention. A convolutional neural network (CNN) is the most commonly used network in image classification. In terms of pavement assessment, most existing CNNs are designed to only distinguish between cracks and non-cracks. Few networks classify cracks in different levels of severity. Information on the severity of pavement cracks is critical for pavement repair services. In this study, the state-of-the-art CNN used in the detection of pavement cracks was improved to localize the cracks and identify their distress levels based on three categories (low, medium, and high). In addition, a fully convolutional network (FCN) was, for the first time, utilized in the detection of pavement cracks. These designed architectures were validated using the data acquired on four highways in Ontario, Canada, and compared with the ground truth that was provided by the Ministry of Transportation of Ontario (MTO). The results showed that with the improved CNN, the prediction precision on a series of test image patches were 72.9%, 73.9%, and 73.1% for cracks with the severity levels of low, medium, and high, respectively. The precision for the FCN was tested on whole pavement images, resulting in 62.8%, 63.3%, and 66.4%, respectively, for cracks with the severity levels of low, medium, and high. It is worth mentioning that the ground truth contained some uncertainties, which partially contributed to the relatively low precision.

scholarly journals Biomedical Concept Recognition Using Deep Neural Sequence Models

2019 ◽  
Author(s):  
Negacy D. Hailu ◽  
Michael Bada ◽  
Asmelash Teka Hadgu ◽  
Lawrence E. Hunter
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Conditional Random Field ◽  
Concept Recognition ◽  
Performance Improvements ◽  
Art Performance

AbstractBackgroundthe automated identification of mentions of ontological concepts in natural language texts is a central task in biomedical information extraction. Despite more than a decade of effort, performance in this task remains below the level necessary for many applications.Resultsrecently, applications of deep learning in natural language processing have demonstrated striking improvements over previously state-of-the-art performance in many related natural language processing tasks. Here we demonstrate similarly striking performance improvements in recognizing biomedical ontology concepts in full text journal articles using deep learning techniques originally developed for machine translation. For example, our best performing system improves the performance of the previous state-of-the-art in recognizing terms in the Gene Ontology Biological Process hierarchy, from a previous best F1 score of 0.40 to an F1 of 0.70, nearly halving the error rate. Nearly all other ontologies show similar performance improvements.ConclusionsA two-stage concept recognition system, which is a conditional random field model for span detection followed by a deep neural sequence model for normalization, improves the state-of-the-art performance for biomedical concept recognition. Treating the biomedical concept normalization task as a sequence-to-sequence mapping task similar to neural machine translation improves performance.

scholarly journals Investigasi Pengaruh Skema Stride dan Step Training untuk Deteksi Jari Pada Region-based Fully Convolutional Network (R-FCN) dalam Teknologi Augmented Reality

2021 ◽  
Vol 12 (2) ◽  
pp. 138
Author(s):  
Hashfi Fadhillah ◽  
Suryo Adhi Wibowo ◽  
Rita Purnamasari
Keyword(s):  
Deep Learning ◽  
Augmented Reality ◽  
Virtual World ◽  
Training Data ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Connected Network ◽  
Learning Region ◽  
Centroid Point ◽  
Fully Connected

Abstract  Combining the real world with the virtual world and then modeling it in 3D is an effort carried on Augmented Reality (AR) technology. Using fingers for computer operations on multi-devices makes the system more interactive. Marker-based AR is one type of AR that uses markers in its detection. This study designed the AR system by detecting fingertips as markers. This system is designed using the Region-based Deep Fully Convolutional Network (R-FCN) deep learning method. This method develops detection results obtained from the Fully Connected Network (FCN). Detection results will be integrated with a computer pointer for basic operations. This study uses a predetermined step scheme to get the best IoU parameters, precision and accuracy. The scheme in this study uses a step scheme, namely: 25K, 50K and 75K step. High precision creates centroid point changes that are not too far away. High accuracy can improve AR performance under conditions of rapid movement and improper finger conditions. The system design uses a dataset in the form of an index finger image with a configuration of 10,800 training data and 3,600 test data. The model will be tested on each scheme using video at different distances, locations and times. This study produced the best results on the 25K step scheme with IoU of 69%, precision of 5.56 and accuracy of 96%.Keyword: Augmented Reality, Region-based Convolutional Network, Fully Convolutional Network, Pointer, Step training Abstrak Menggabungkan dunia nyata dengan dunia virtual lalu memodelkannya bentuk 3D merupakan upaya yang diusung pada teknologi Augmented Reality (AR). Menggunakan jari untuk operasi komputer pada multi-device membuat sistem yang lebih interaktif. Marker-based AR merupakan salah satu jenis AR yang menggunakan marker dalam deteksinya. Penelitian ini merancang sistem AR dengan mendeteksi ujung jari sebagai marker. Sistem ini dirancang menggunakan metode deep learning Region-based Fully Convolutional Network (R-FCN). Metode ini mengembangkan hasil deteksi yang didapat dari Fully Connected Network (FCN). Hasil deteksi akan diintegrasikan dengan pointer komputer untuk operasi dasar. Penelitian ini menggunakan skema step training yang telah ditentukan untuk mendapatkan parameter IoU, presisi dan akurasi yang terbaik. Skema pada penelitian ini menggunakan skema step yaitu: 25K, 50K dan 75K step. Presisi tinggi menciptakan perubahan titik centroid yang tidak terlalu jauh. Akurasi  yang tinggi dapat meningkatkan kinerja AR dalam kondisi pergerakan yang cepat dan kondisi jari yang tidak tepat. Perancangan sistem menggunakan dataset berupa citra jari telunjuk dengan konfigurasi 10.800 data latih dan 3.600 data uji. Model akan diuji pada tiap skema dilakukan menggunakan video pada jarak, lokasi dan waktu yang berbeda. Penelitian ini menghasilkan hasil terbaik pada skema step 25K dengan IoU sebesar 69%, presisi sebesar 5,56 dan akurasi sebesar 96%.Kata kunci: Augmented Reality, Region-based Convolutional Network, Fully Convolutional Network, Pointer, Step training 

scholarly journals Real-time Arabic scene text detection using fully convolutional neural networks

2021 ◽  
Vol 11 (2) ◽  
pp. 1634
Author(s):  
Rajae Moumen ◽  
Raddouane Chiheb ◽  
Rdouan Faizi
Keyword(s):  
Real Time ◽  
Data Augmentation ◽  
State Of The Art ◽  
Arabic Language ◽  
Text Detection ◽  
The State ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Scene Text Detection ◽  
Scene Text

The aim of this research is to propose a fully convolutional approach to address the problem of real-time scene text detection for Arabic language. Text detection is performed using a two-steps multi-scale approach. The first step uses light-weighted fully convolutional network: TextBlockDetector FCN, an adaptation of VGG-16 to eliminate non-textual elements, localize wide scale text and give text scale estimation. The second step determines narrow scale range of text using fully convolutional network for maximum performance. To evaluate the system, we confront the results of the framework to the results obtained with single VGG-16 fully deployed for text detection in one-shot; in addition to previous results in the state-of-the-art. For training and testing, we initiate a dataset of 575 images manually processed along with data augmentation to enrich training process. The system scores a precision of 0.651 vs 0.64 in the state-of-the-art and a FPS of 24.3 vs 31.7 for a VGG-16 fully deployed.

scholarly journals Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping

2016 ◽  
Author(s):  
Michael P. Pound ◽  
Alexandra J. Burgess ◽  
Michael H. Wilson ◽  
Jonathan A. Atkinson ◽  
Marcus Griffiths ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Analysis ◽  
Paradigm Shift ◽  
State Of The Art ◽  
Plant Phenotyping ◽  
Learning Approaches ◽  
Challenging Problem ◽  
Feature Identification ◽  
Art Performance

AbstractDeep learning is an emerging field that promises unparalleled results on many data analysis problems. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping, and demonstrate state-of-the-art results for root and shoot feature identification and localisation. We predict a paradigm shift in image-based phenotyping thanks to deep learning approaches.

Sign in / Sign up

Export Citation Format

Share Document