Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping

Classification of foot–ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required; this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, sliding-window label overlapping of time-series wearable motion data in training dataset acquisition is proposed to accurately detect foot–ground contact phases, which are composed of 3 sub-phases as well as the swing phase, at a frequency of 100 Hz with a convolutional neural network (CNN) architecture. We not only succeeded in developing a real-time CNN model for learning and obtaining a test accuracy of 99.8% or higher, but also confirmed that its validation accuracy was close to 85%.

Download Full-text

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.10.ipas-180 ◽

2020 ◽

Vol 2020 (10) ◽

pp. 181-1-181-7

Author(s):

Takahiro Kudo ◽

Takanori Fujisawa ◽

Takuro Yamaguchi ◽

Masaaki Ikehara

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Architecture ◽

Large Scale ◽

Blind Deconvolution ◽

Training Dataset ◽

Image Deconvolution ◽

Classic Problem ◽

Key Points ◽

Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Download Full-text

Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

Scientific Reports ◽

10.1038/s41598-020-78129-0 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Young-Gon Kim ◽

Sungchul Kim ◽

Cristina Eunbee Cho ◽

In Hye Song ◽

Hee Jin Lee ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Frozen Section ◽

Medical Center ◽

External Validation ◽

Model Performance ◽

Classification Model ◽

Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Download Full-text

Development of in-house fully residual deep convolutional neural network-based segmentation software for the male pelvic CT

Radiation Oncology ◽

10.1186/s13014-021-01867-6 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Hideaki Hirashima ◽

Mitsuhiro Nakamura ◽

Pascal Baillehache ◽

Yusuke Fujimoto ◽

Shota Nakagawa ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Volumetric Modulated Arc Therapy ◽

Intensity Modulated Radiotherapy ◽

Deep Convolutional Neural Network ◽

Training Dataset ◽

Dice Similarity Coefficient ◽

Optimal Model ◽

Pelvic Region ◽

Segmentation Accuracy

Abstract Background This study aimed to (1) develop a fully residual deep convolutional neural network (CNN)-based segmentation software for computed tomography image segmentation of the male pelvic region and (2) demonstrate its efficiency in the male pelvic region. Methods A total of 470 prostate cancer patients who had undergone intensity-modulated radiotherapy or volumetric-modulated arc therapy were enrolled. Our model was based on FusionNet, a fully residual deep CNN developed to semantically segment biological images. To develop the CNN-based segmentation software, 450 patients were randomly selected and separated into the training, validation and testing groups (270, 90, and 90 patients, respectively). In Experiment 1, to determine the optimal model, we first assessed the segmentation accuracy according to the size of the training dataset (90, 180, and 270 patients). In Experiment 2, the effect of varying the number of training labels on segmentation accuracy was evaluated. After determining the optimal model, in Experiment 3, the developed software was used on the remaining 20 datasets to assess the segmentation accuracy. The volumetric dice similarity coefficient (DSC) and the 95th-percentile Hausdorff distance (95%HD) were calculated to evaluate the segmentation accuracy for each organ in Experiment 3. Results In Experiment 1, the median DSC for the prostate were 0.61 for dataset 1 (90 patients), 0.86 for dataset 2 (180 patients), and 0.86 for dataset 3 (270 patients), respectively. The median DSCs for all the organs increased significantly when the number of training cases increased from 90 to 180 but did not improve upon further increase from 180 to 270. The number of labels applied during training had a little effect on the DSCs in Experiment 2. The optimal model was built by 270 patients and four organs. In Experiment 3, the median of the DSC and the 95%HD values were 0.82 and 3.23 mm for prostate; 0.71 and 3.82 mm for seminal vesicles; 0.89 and 2.65 mm for the rectum; 0.95 and 4.18 mm for the bladder, respectively. Conclusions We have developed a CNN-based segmentation software for the male pelvic region and demonstrated that the CNN-based segmentation software is efficient for the male pelvic region.

Download Full-text

Automatic Handgun Detection with Deep Learning in Video Surveillance Images

Applied Sciences ◽

10.3390/app11136085 ◽

2021 ◽

Vol 11 (13) ◽

pp. 6085

Author(s):

Jesus Salido ◽

Vanesa Lomas ◽

Jesus Ruiz-Santaquiteria ◽

Oscar Deniz

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Video Surveillance ◽

Automatic Detection ◽

Public Spaces ◽

Detection Methods ◽

Training Dataset ◽

Average Precision ◽

Terrorist Acts

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.

Download Full-text

Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

Applied Sciences ◽

10.3390/app10062104 ◽

2020 ◽

Vol 10 (6) ◽

pp. 2104

Author(s):

Michał Tomaszewski ◽

Paweł Michalski ◽

Jakub Osuchowski

Keyword(s):

Neural Network ◽

Neural Networks ◽

Object Detection ◽

Convolutional Neural Network ◽

Deep Neural Networks ◽

Detection Efficiency ◽

Training Data ◽

Training Dataset ◽

Training Set ◽

Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

Download Full-text

Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study

BMC Medical Imaging ◽

10.1186/s12880-021-00710-4 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Pei Yang ◽

Yong Pi ◽

Tao He ◽

Jiangming Sun ◽

Jianan Wei ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Predictive Value ◽

Automatic Differentiation ◽

External Validation ◽

Deep Convolutional Neural Network ◽

Image Feature ◽

Training Dataset ◽

Internal Validation

Abstract Background 99mTc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop an artificial intelligence (AI) system to automatically classify the four patterns of thyroid scintigram. Methods We collected 3087 thyroid scintigrams from center 1 to construct the training dataset (n = 2468) and internal validating dataset (n = 619), and another 302 cases from center 2 as external validating datasets. Four pre-trained neural networks that included ResNet50, DenseNet169, InceptionV3, and InceptionResNetV2 were implemented to construct AI models. The models were trained separately with transfer learning. We evaluated each model’s performance with metrics as following: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), recall, precision, and F1-score. Results The overall accuracy of four pre-trained neural networks in classifying four common uptake patterns of thyroid scintigrams all exceeded 90%, and the InceptionV3 stands out from others. It reached the highest performance with an overall accuracy of 92.73% for internal validation and 87.75% for external validation, respectively. As for each category of thyroid scintigrams, the area under the receiver operator characteristic curve (AUC) was 0.986 for ‘diffusely increased,’ 0.997 for ‘diffusely decreased,’ 0.998 for ‘focal increased,’ and 0.945 for ‘heterogeneous uptake’ in internal validation, respectively. Accordingly, the corresponding performances also obtained an ideal result of 0.939, 1.000, 0.974, and 0.915 in external validation, respectively. Conclusions Deep convolutional neural network-based AI model represented considerable performance in the classification of thyroid scintigrams, which may help physicians improve the interpretation of thyroid scintigrams more consistently and efficiently.

Download Full-text

A Deep Learning-Based Approach for the Detection of Early Signs of Gingivitis in Orthodontic Patients Using Faster Region-Based Convolutional Neural Networks

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17228447 ◽

2020 ◽

Vol 17 (22) ◽

pp. 8447

Author(s):

Dima M. Alalharith ◽

Hajar M. Alharthi ◽

Wejdan M. Alghamdi ◽

Yasmine M. Alsenbel ◽

Nida Aslam ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Periodontal Disease ◽

Convolutional Neural Network ◽

Region Of Interest ◽

Training Dataset ◽

Detection Accuracy ◽

Detection Model ◽

Art Object ◽

Orthodontic Patients

Computer-based technologies play a central role in the dentistry field, as they present many methods for diagnosing and detecting various diseases, such as periodontitis. The current study aimed to develop and evaluate the state-of-the-art object detection and recognition techniques and deep learning algorithms for the automatic detection of periodontal disease in orthodontic patients using intraoral images. In this study, a total of 134 intraoral images were divided into a training dataset (n = 107 [80%]) and a test dataset (n = 27 [20%]). Two Faster Region-based Convolutional Neural Network (R-CNN) models using ResNet-50 Convolutional Neural Network (CNN) were developed. The first model detects the teeth to locate the region of interest (ROI), while the second model detects gingival inflammation. The detection accuracy, precision, recall, and mean average precision (mAP) were calculated to verify the significance of the proposed model. The teeth detection model achieved an accuracy, precision, recall, and mAP of 100 %, 100%, 51.85%, and 100%, respectively. The inflammation detection model achieved an accuracy, precision, recall, and mAP of 77.12%, 88.02%, 41.75%, and 68.19%, respectively. This study proved the viability of deep learning models for the detection and diagnosis of gingivitis in intraoral images. Hence, this highlights its potential usability in the field of dentistry and aiding in reducing the severity of periodontal disease globally through preemptive non-invasive diagnosis.

Download Full-text

Arrangements of Resting State Electroencephalography as the Input to Convolutional Neural Network for Biometric Identification

Computational Intelligence and Neuroscience ◽

10.1155/2019/7895924 ◽

2019 ◽

Vol 2019 ◽

pp. 1-10 ◽

Cited By ~ 3

Author(s):

Chi Qin Lai ◽

Haidi Ibrahim ◽

Mohd Zaid Abdullah ◽

Jafri Malin Abdullah ◽

Shahrel Azmin Suandi ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Resting State ◽

Biometric Identification ◽

Test Accuracy ◽

Sensitive Information ◽

The Matrix ◽

Eyes Open ◽

Important Field ◽

Amplitude Versus

Biometric is an important field that enables identification of an individual to access their sensitive information and asset. In recent years, electroencephalography- (EEG-) based biometrics have been popularly explored by researchers because EEG is able to distinct between two individuals. The literature reviews have shown that convolutional neural network (CNN) is one of the classification approaches that can avoid the complex stages of preprocessing, feature extraction, and feature selection. Therefore, CNN is suggested to be one of the efficient classifiers for biometric identification. Conventionally, input to CNN can be in image or matrix form. The objective of this paper is to explore the arrangement of EEG for CNN input to investigate the most suitable input arrangement of EEG towards the performance of EEG-based identification. EEG datasets that are used in this paper are resting state eyes open (REO) and resting state eyes close (REC) EEG. Six types of data arrangement are compared in this paper. They are matrix of amplitude versus time, matrix of energy versus time, matrix of amplitude versus time for rearranged channels, image of amplitude versus time, image of energy versus time, and image of amplitude versus time for rearranged channels. It was found that the matrix of amplitude versus time for each rearranged channels using the combination of REC and REO performed the best for biometric identification, achieving validation accuracy and test accuracy of 83.21% and 79.08%, respectively.

Download Full-text

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

Brain Sciences ◽

10.3390/brainsci10020084 ◽

2020 ◽

Vol 10 (2) ◽

pp. 84 ◽

Cited By ~ 6

Author(s):

Atif Mehmood ◽

Muazzam Maqsood ◽

Muzaffar Bashir ◽

Yang Shuyuan

Keyword(s):

Neural Network ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Convolutional Neural Network ◽

State Of The Art ◽

Early Stage ◽

The State ◽

Test Accuracy ◽

Learning Approaches

Alzheimer’s disease (AD) may cause damage to the memory cells permanently, which results in the form of dementia. The diagnosis of Alzheimer’s disease at an early stage is a problematic task for researchers. For this, machine learning and deep convolutional neural network (CNN) based approaches are readily available to solve various problems related to brain image data analysis. In clinical research, magnetic resonance imaging (MRI) is used to diagnose AD. For accurate classification of dementia stages, we need highly discriminative features obtained from MRI images. Recently advanced deep CNN-based models successfully proved their accuracy. However, due to a smaller number of image samples available in the datasets, there exist problems of over-fitting hindering the performance of deep learning approaches. In this research, we developed a Siamese convolutional neural network (SCNN) model inspired by VGG-16 (also called Oxford Net) to classify dementia stages. In our approach, we extend the insufficient and imbalanced data by using augmentation approaches. Experiments are performed on a publicly available dataset open access series of imaging studies (OASIS), by using the proposed approach, an excellent test accuracy of 99.05% is achieved for the classification of dementia stages. We compared our model with the state-of-the-art models and discovered that the proposed model outperformed the state-of-the-art models in terms of performance, efficiency, and accuracy.

Download Full-text

An Efficient and Lightweight Convolutional Neural Network for Remote Sensing Image Scene Classification

Sensors ◽

10.3390/s20071999 ◽

2020 ◽

Vol 20 (7) ◽

pp. 1999 ◽

Cited By ~ 6

Author(s):

Donghang Yu ◽

Qing Xu ◽

Haitao Guo ◽

Chuan Zhao ◽

Yuzhun Lin ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Convolutional Neural Network ◽

Visual Recognition ◽

Feature Fusion ◽

Remote Sensing Image ◽

Classification Performance ◽

Image Features ◽

Training Dataset ◽

Scene Classification

Classifying remote sensing images is vital for interpreting image content. Presently, remote sensing image scene classification methods using convolutional neural networks have drawbacks, including excessive parameters and heavy calculation costs. More efficient and lightweight CNNs have fewer parameters and calculations, but their classification performance is generally weaker. We propose a more efficient and lightweight convolutional neural network method to improve classification accuracy with a small training dataset. Inspired by fine-grained visual recognition, this study introduces a bilinear convolutional neural network model for scene classification. First, the lightweight convolutional neural network, MobileNetv2, is used to extract deep and abstract image features. Each feature is then transformed into two features with two different convolutional layers. The transformed features are subjected to Hadamard product operation to obtain an enhanced bilinear feature. Finally, the bilinear feature after pooling and normalization is used for classification. Experiments are performed on three widely used datasets: UC Merced, AID, and NWPU-RESISC45. Compared with other state-of-art methods, the proposed method has fewer parameters and calculations, while achieving higher accuracy. By including feature fusion with bilinear pooling, performance and accuracy for remote scene classification can greatly improve. This could be applied to any remote sensing image classification task.

Download Full-text