scholarly journals FCN Based Approach for the Automatic Segmentation of Bone Surfaces in Ultrasound Images

10.29007/bncb ◽  
2018 ◽  
Author(s):  
Mateo Villa ◽  
Guillaume Dardenne ◽  
Maged Nasan ◽  
Hoel Letissier ◽  
Chafiaa Hamitouche ◽  
...  
Keyword(s):  
State Of The Art ◽  
Imaging Modality ◽  
Automatic Segmentation ◽  
Ultrasound Images ◽  
Manual Segmentation ◽  
Bone Segmentation ◽  
Bone Morphology ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Phase Symmetry

In CAOS, ultrasound imaging has been proposed as a solution for obtaining the specific bone morphology of the patient, avoiding limitations of existing technologies. However, this imaging modality presents different drawbacks that make difficult the automatic bone segmentation. A new algorithm, based on Fully Convolutional Networks (FCN), is proposed. The aim of this paper is to compare and validate this method with (1) a manual segmentation that was performed by three independent experts, and (2) a state of the art method called Confidence in Phase Symmetry (CPS). The FCN based approach outperforms the CPS algorithm and the RMSE is close to the manual segmentation variability.

scholarly journals Encoding Time Series as Multi-Scale Signed Recurrence Plots for Classification Using Fully Convolutional Networks

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 3818
Author(s):  
Ye Zhang ◽  
Yi Hou ◽  
Shilin Zhou ◽  
Kewei Ouyang
Keyword(s):  
Time Series ◽  
State Of The Art ◽  
Recurrence Plot ◽  
The State ◽  
Recurrence Plots ◽  
Convolutional Networks ◽  
Multi Scale ◽  
Fully Convolutional Networks ◽  
Benchmark Datasets ◽  
Visualization Evaluation

Recent advances in time series classification (TSC) have exploited deep neural networks (DNN) to improve the performance. One promising approach encodes time series as recurrence plot (RP) images for the sake of leveraging the state-of-the-art DNN to achieve accuracy. Such an approach has been shown to achieve impressive results, raising the interest of the community in it. However, it remains unsolved how to handle not only the variability in the distinctive region scale and the length of sequences but also the tendency confusion problem. In this paper, we tackle the problem using Multi-scale Signed Recurrence Plots (MS-RP), an improvement of RP, and propose a novel method based on MS-RP images and Fully Convolutional Networks (FCN) for TSC. This method first introduces phase space dimension and time delay embedding of RP to produce multi-scale RP images; then, with the use of asymmetrical structure, constructed RP images can represent very long sequences (>700 points). Next, MS-RP images are obtained by multiplying designed sign masks in order to remove the tendency confusion. Finally, FCN is trained with MS-RP images to perform classification. Experimental results on 45 benchmark datasets demonstrate that our method improves the state-of-the-art in terms of classification accuracy and visualization evaluation.

scholarly journals Context-guided fully convolutional networks for joint craniomaxillofacial bone segmentation and landmark digitization

2020 ◽  
Vol 60 ◽  
pp. 101621 ◽  
Author(s):  
Jun Zhang ◽  
Mingxia Liu ◽  
Li Wang ◽  
Si Chen ◽  
Peng Yuan ◽  
...  
Keyword(s):  
Bone Segmentation ◽  
Convolutional Networks ◽  
Fully Convolutional Networks

scholarly journals A Novel Object-Based Deep Learning Framework for Semantic Segmentation of Very High-Resolution Remote Sensing Data: Comparison with Convolutional and Fully Convolutional Networks

2019 ◽  
Vol 11 (6) ◽  
pp. 684 ◽  
Author(s):  
Maria Papadomanolaki ◽  
Maria Vakalopoulou ◽  
Konstantinos Karantzalos
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Novel Object ◽  
Convolutional Networks ◽  
Learning Framework ◽  
Fully Convolutional Networks ◽  
Object Based ◽  
Deep Networks ◽  
Very High

Deep learning architectures have received much attention in recent years demonstrating state-of-the-art performance in several segmentation, classification and other computer vision tasks. Most of these deep networks are based on either convolutional or fully convolutional architectures. In this paper, we propose a novel object-based deep-learning framework for semantic segmentation in very high-resolution satellite data. In particular, we exploit object-based priors integrated into a fully convolutional neural network by incorporating an anisotropic diffusion data preprocessing step and an additional loss term during the training process. Under this constrained framework, the goal is to enforce pixels that belong to the same object to be classified at the same semantic category. We compared thoroughly the novel object-based framework with the currently dominating convolutional and fully convolutional deep networks. In particular, numerous experiments were conducted on the publicly available ISPRS WGII/4 benchmark datasets, namely Vaihingen and Potsdam, for validation and inter-comparison based on a variety of metrics. Quantitatively, experimental results indicate that, overall, the proposed object-based framework slightly outperformed the current state-of-the-art fully convolutional networks by more than 1% in terms of overall accuracy, while intersection over union results are improved for all semantic categories. Qualitatively, man-made classes with more strict geometry such as buildings were the ones that benefit most from our method, especially along object boundaries, highlighting the great potential of the developed approach.

scholarly journals Image-Based Plant Disease Identification by Deep Learning Meta-Architectures

Plants ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1451
Author(s):  
Muhammad Hammad Saleem ◽  
Sapna Khanchi ◽  
Johan Potgieter ◽  
Khalid Mahmood Arif
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
State Of The Art ◽  
Mean Average Precision ◽  
Single Shot ◽  
Average Precision ◽  
Crop Monitoring ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Agricultural Applications

The identification of plant disease is an imperative part of crop monitoring systems. Computer vision and deep learning (DL) techniques have been proven to be state-of-the-art to address various agricultural problems. This research performed the complex tasks of localization and classification of the disease in plant leaves. In this regard, three DL meta-architectures including the Single Shot MultiBox Detector (SSD), Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Networks (RFCN) were applied by using the TensorFlow object detection framework. All the DL models were trained/tested on a controlled environment dataset to recognize the disease in plant species. Moreover, an improvement in the mean average precision of the best-obtained deep learning architecture was attempted through different state-of-the-art deep learning optimizers. The SSD model trained with an Adam optimizer exhibited the highest mean average precision (mAP) of 73.07%. The successful identification of 26 different types of defected and 12 types of healthy leaves in a single framework proved the novelty of the work. In the future, the proposed detection methodology can also be adopted for other agricultural applications. Moreover, the generated weights can be reused for future real-time detection of plant disease in a controlled/uncontrolled environment.

scholarly journals Shadow Peak: Accurate Real-time Bone Segmentation for Ultrasound and Developmental Dysplasia of the Hip

10.29007/w172 ◽  
2019 ◽  
Author(s):  
Prashant Pandey ◽  
Niamul Quader ◽  
Kishore Mulpuri ◽  
Pierre Guy ◽  
Rafeef Garbi ◽  
...  
Keyword(s):  
Pediatric Patients ◽  
State Of The Art ◽  
Developmental Dysplasia ◽  
Feature Analysis ◽  
Intensity Analysis ◽  
Bone Segmentation ◽  
Complex Image ◽  
Computationally Expensive ◽  
Phase Symmetry ◽  
Dysplasia Of The Hip

Confidence-weighted structured phase symmetry (CSPS) is a state-of-the-art bone seg- mentation technique for ultrasound (US), which has been recently proposed for automatic diagnosis for developmental dysplasia of the hip (DDH). However, CSPS relies on complex image phase feature analysis which is computationally expensive, and in our preliminary tests we have found it to be sometimes inaccurate. We evaluate a simpler alternative segmentation technique which we previously published, called Shadow Peak (SP), which uses intensity analysis to perform fast and accurate US bone segmentation. On average, SP segmentation ran 15 times faster for 2D US images, when tested on 15 hip images of pediatric patients. Furthermore, SP improves the segmentation F-score to 94%, compared to 72% when using CSPS segmentation.

Sign in / Sign up

Export Citation Format

Share Document