scholarly journals A novel cell segmentation method for developing embryos using machine learning

2018 ◽  
Author(s):  
Rikifumi Ota ◽  
Takahiro Ide ◽  
Tatsuo Michiue
Keyword(s):  
Machine Learning ◽  
Cell Shape ◽  
State Of The Art ◽  
Cell Segmentation ◽  
Segmentation Method ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Segmented Image ◽  
Novel Method ◽  
Better Than

AbstractCell segmentation is crucial in the study of morphogenesis in developing embryos, but it is limited in its accuracy. In this study we provide a novel method for cell segmentation using machine-learning, termed Cell Segmenter using Machine Learning (CSML). CSML performed better than state-of-the-art methods, such as RACE and watershed, in the segmentation of ectodermal cells in the Xenopus embryo. CSML required only one whole embryo image for training a Fully Convolutional Network classifier, and it took 20 seconds per each image to return a segmented image. To validate its accuracy, we compared it to other methods in assessing several indicators of cell shape. We also examined the generality by measuring its performance in segmenting independent images. Our data demonstrates the superiority of CSML, and we expect this application to significantly improve efficiency in cell shape studies.

GUESS: projecting machine learning scores to well-calibrated probability estimates for clinical decision-making

2018 ◽  
Vol 35 (14) ◽  
pp. 2458-2465 ◽  
Author(s):  
Johanna Schwarz ◽  
Dominik Heider
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
State Of The Art ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Calibration Method ◽  
Probability Estimates ◽  
Calibration Methods ◽  
Novel Method

Abstract Motivation Clinical decision support systems have been applied in numerous fields, ranging from cancer survival toward drug resistance prediction. Nevertheless, clinical decision support systems typically have a caveat: many of them are perceived as black-boxes by non-experts and, unfortunately, the obtained scores cannot usually be interpreted as class probability estimates. In probability-focused medical applications, it is not sufficient to perform well with regards to discrimination and, consequently, various calibration methods have been developed to enable probabilistic interpretation. The aims of this study were (i) to develop a tool for fast and comparative analysis of different calibration methods, (ii) to demonstrate their limitations for the use on clinical data and (iii) to introduce our novel method GUESS. Results We compared the performances of two different state-of-the-art calibration methods, namely histogram binning and Bayesian Binning in Quantiles, as well as our novel method GUESS on both, simulated and real-world datasets. GUESS demonstrated calibration performance comparable to the state-of-the-art methods and always retained accurate class discrimination. GUESS showed superior calibration performance in small datasets and therefore may be an optimal calibration method for typical clinical datasets. Moreover, we provide a framework (CalibratR) for R, which can be used to identify the most suitable calibration method for novel datasets in a timely and efficient manner. Using calibrated probability estimates instead of original classifier scores will contribute to the acceptance and dissemination of machine learning based classification models in cost-sensitive applications, such as clinical research. Availability and implementation GUESS as part of CalibratR can be downloaded at CRAN.

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.

ON THE QUASI-STATIONARY DISTRIBUTION OF SIS MODELS

2016 ◽  
Vol 30 (4) ◽  
pp. 622-639 ◽  
Author(s):  
Gaofeng Da ◽  
Maochao Xu ◽  
Shouhuai Xu
Keyword(s):  
Stationary Distribution ◽  
Upper Bound ◽  
Hazard Rate ◽  
State Of The Art ◽  
Upper Bounds ◽  
Hazard Rate Order ◽  
Reversed Hazard Rate ◽  
Novel Method ◽  
Better Than ◽  
Quasi Stationary Distribution

In this paper, we propose a novel method for constructing upper bounds of the quasi-stationary distribution of SIS processes. Using this method, we obtain an upper bound that is better than the state-of-the-art upper bound. Moreover, we prove that the fixed point map Φ [7] actually preserves the equilibrium reversed hazard rate order under a certain condition. This allows us to further improve the upper bound. Some numerical results are presented to illustrate the results.

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 TISNet-Enhanced Fully Convolutional Network with Encoder-Decoder Structure for Tongue Image Segmentation in Traditional Chinese Medicine

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Xiaodong Huang ◽  
Hui Zhang ◽  
Li Zhuo ◽  
Xiaoguang Li ◽  
Jing Zhang
Keyword(s):  
Image Segmentation ◽  
Receptive Field ◽  
Positional Information ◽  
Dice Similarity Coefficient ◽  
Segmentation Method ◽  
Feature Maps ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Segmentation Methods ◽  
Feature Pyramid

Extracting the tongue body accurately from a digital tongue image is a challenge for automated tongue diagnoses, as the blurred edge of the tongue body, interference of pathological details, and the huge difference in the size and shape of the tongue. In this study, an automated tongue image segmentation method using enhanced fully convolutional network with encoder-decoder structure was presented. In the frame of the proposed network, the deep residual network was adopted as an encoder to obtain dense feature maps, and a Receptive Field Block was assembled behind the encoder. Receptive Field Block can capture adequate global contextual prior because of its structure of the multibranch convolution layers with varying kernels. Moreover, the Feature Pyramid Network was used as a decoder to fuse multiscale feature maps for gathering sufficient positional information to recover the clear contour of the tongue body. The quantitative evaluation of the segmentation results of 300 tongue images from the SIPL-tongue dataset showed that the average Hausdorff Distance, average Symmetric Mean Absolute Surface Distance, average Dice Similarity Coefficient, average precision, average sensitivity, and average specificity were 11.2963, 3.4737, 97.26%, 95.66%, 98.97%, and 98.68%, respectively. The proposed method achieved the best performance compared with the other four deep-learning-based segmentation methods (including SegNet, FCN, PSPNet, and DeepLab v3+). There were also similar results on the HIT-tongue dataset. The experimental results demonstrated that the proposed method can achieve accurate tongue image segmentation and meet the practical requirements of automated tongue diagnoses.

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 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 Segmenting the Semi-Conductive Shielding Layer of Cable Slice Images Using the Convolutional Neural Network

Polymers ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 2085
Author(s):  
Wen Zhu ◽  
Fei Dong ◽  
Beiping Hou ◽  
Wesley Kenniard Takudzwa Gwatidzo ◽  
Le Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Essential Role ◽  
Structural Parameters ◽  
Receptive Fields ◽  
Structural Parameter ◽  
Pixel Classification ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Novel Method

Being an important part of aerial insulated cable, the semiconductive shielding layer is made of a typical polymer material and can improve the cable transmission effects; the structural parameters will affect the cable quality directly. Then, the image processing of the semiconductive layer plays an essential role in the structural parameter measurements. However, the semiconductive layer images are often disturbed by the cutting marks, which affect the measurements seriously. In this paper, a novel method based on the convolutional neural network is proposed for image segmentation. In our proposed strategy, a deep fully convolutional network with a skip connection algorithm is defined as the main framework. The inception structure and residual connection are employed to fuse features extracted from the receptive fields with different sizes. Finally, an improved weighted loss function and refined algorithm are utilized for pixel classification. Experimental results show that our proposed algorithm achieves better performance than the current algorithms.

Capped ℓ1-norm regularized least squares classification with label noise

2021 ◽  
pp. 1-13
Author(s):  
Zhi Yang ◽  
Haitao Gan ◽  
Xuan Li ◽  
Cong Wu
Keyword(s):  
Machine Learning ◽  
Least Squares ◽  
Supervised Learning ◽  
State Of The Art ◽  
Negative Influence ◽  
Optimization Approach ◽  
Classification Methods ◽  
Label Noise ◽  
Negative Effect ◽  
Novel Method

Since label noise can hurt the performance of supervised learning (SL), how to train a good classifier to deal with label noise is an emerging and meaningful topic in machine learning field. Although many related methods have been proposed and achieved promising performance, they have the following drawbacks: (1) they can lead to data waste and even performance degradation if the mislabeled instances are removed; and (2) the negative effect of the extremely mislabeled instances cannot be completely eliminated. To address these problems, we propose a novel method based on the capped ℓ1 norm and a graph-based regularizer to deal with label noise. In the proposed algorithm, we utilize the capped ℓ1 norm instead of the ℓ1 norm. The used norm can inherit the advantage of the ℓ1 norm, which is robust to label noise to some extent. Moreover, the capped ℓ1 norm can adaptively find extremely mislabeled instances and eliminate the corresponding negative influence. Additionally, the proposed algorithm makes full use of the mislabeled instances under the graph-based framework. It can avoid wasting collected instance information. The solution of our algorithm can be achieved through an iterative optimization approach. We report the experimental results on several UCI datasets that include both binary and multi-class problems. The results verified the effectiveness of the proposed algorithm in comparison to existing state-of-the-art classification methods.

scholarly journals A Semantic Segmentation Method for Buffer Layer Defect Detection in High Voltage Cable

2021 ◽  
Vol 233 ◽  
pp. 01032
Author(s):  
Zhang Jun ◽  
Duan Xiaoli ◽  
Xie Yi ◽  
Duan Jianjia ◽  
Huang Fuyong ◽  
...  
Keyword(s):  
Buffer Layer ◽  
High Voltage ◽  
Defect Detection ◽  
Semantic Segmentation ◽  
Segmentation Method ◽  
Convolutional Network ◽  
Test Set ◽  
Fully Convolutional Network ◽  
X Ray ◽  
Layer Defect

A semantic segmentation method based on the fully convolutional network is proposed to detect the buffer layer defect in high voltage cable automatically. One hundred seventy-seven high-resolution X-ray images of cables are collected. FCN-8s and VGG16 backbone are adopted. The results indicated that the FCN-8s achieves the mIoU to 0.67 on the test set, proving to be an efficient way to detect the buffer layer defects.

Sign in / Sign up

Export Citation Format

Share Document