scholarly journals Semantic segmentation of gonio-photographs via adaptive ROI localisation and uncertainty estimation

2021 ◽  
Vol 6 (1) ◽  
pp. e000898
Author(s):  
Andrea Peroni ◽  
Anna Paviotti ◽  
Mauro Campigotto ◽  
Luis Abegão Pinto ◽  
Carlo Alberto Cutolo ◽  
...  
Keyword(s):  
Region Of Interest ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Uncertainty Estimation ◽  
Depth Of Field ◽  
Clinical Settings ◽  
Proposed Model ◽  
Validation Experiment ◽  
Segmentation Accuracy ◽  
Ground Truth Image

ObjectiveTo develop and test a deep learning (DL) model for semantic segmentation of anatomical layers of the anterior chamber angle (ACA) in digital gonio-photographs.Methods and analysisWe used a pilot dataset of 274 ACA sector images, annotated by expert ophthalmologists to delineate five anatomical layers: iris root, ciliary body band, scleral spur, trabecular meshwork and cornea. Narrow depth-of-field and peripheral vignetting prevented clinicians from annotating part of each image with sufficient confidence, introducing a degree of subjectivity and features correlation in the ground truth. To overcome these limitations, we present a DL model, designed and trained to perform two tasks simultaneously: (1) maximise the segmentation accuracy within the annotated region of each frame and (2) identify a region of interest (ROI) based on local image informativeness. Moreover, our calibrated model provides results interpretability returning pixel-wise classification uncertainty through Monte Carlo dropout.ResultsThe model was trained and validated in a 5-fold cross-validation experiment on ~90% of available data, achieving ~91% average segmentation accuracy within the annotated part of each ground truth image of the hold-out test set. An appropriate ROI was successfully identified in all test frames. The uncertainty estimation module located correctly inaccuracies and errors of segmentation outputs.ConclusionThe proposed model improves the only previously published work on gonio-photographs segmentation and may be a valid support for the automatic processing of these images to evaluate local tissue morphology. Uncertainty estimation is expected to facilitate acceptance of this system in clinical settings.

scholarly journals Diversity-Generated Image Inpainting with Style Extraction

2019 ◽  
Author(s):  
Weiwei Cai ◽  
Zhanguo Wei
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Image Inpainting ◽  
Ground Truth ◽  
Generative Model ◽  
Input Noise ◽  
Latent Vector ◽  
Proposed Model ◽  
Ground Truth Image

The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. This type of method generally attempts to generate one single "optimal" inpainting result, ignoring many other plausible results. However, considering the uncertainty of the inpainting task, one sole result can hardly be regarded as a desired regeneration of the missing area. In view of this weakness, which is related to the design of the previous algorithms, we propose a novel deep generative model equipped with a brand new style extractor which can extract the style noise (a latent vector) from the ground truth image. Once obtained, the extracted style noise and the ground truth image are both input into the generator. We also craft a consistency loss that guides the generated image to approximate the ground truth. Meanwhile, the same extractor captures the style noise from the generated image, which is forced to approach the input noise according to the consistency loss. After iterations, our generator is able to learn the styles corresponding to multiple sets of noise. The proposed model can generate a (sufficiently large) number of inpainting results consistent with the context semantics of the image. Moreover, we check the effectiveness of our model on three databases, i.e., CelebA, Agricultural Disease, and MauFlex. Compared to state-of-the-art inpainting methods, this model is able to offer desirable inpainting results with both a better quality and higher diversity. The code and model will be made available on https://github.com/vivitsai/SEGAN.

scholarly journals Mathematical Modelling of Ground Truth Image for 3D Microscopic Objects Using Cascade of Convolutional Neural Networks Optimized with Parameters’ Combinations Generators

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 416
Author(s):  
Omar Bilalovic ◽  
Zikrija Avdagic ◽  
Samir Omanovic ◽  
Ingmar Besic ◽  
Vedad Letic ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Segmentation ◽  
Mathematical Modelling ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Ground Truth ◽  
3D Images ◽  
Segmentation Accuracy ◽  
Augmentation Techniques ◽  
Ground Truth Image

Mathematical modelling to compute ground truth from 3D images is an area of research that can strongly benefit from machine learning methods. Deep neural networks (DNNs) are state-of-the-art methods design for solving these kinds of difficulties. Convolutional neural networks (CNNs), as one class of DNNs, can overcome special requirements of quantitative analysis especially when image segmentation is needed. This article presents a system that uses a cascade of CNNs with symmetric blocks of layers in chain, dedicated to 3D image segmentation from microscopic images of 3D nuclei. The system is designed through eight experiments that differ in following aspects: number of training slices and 3D samples for training, usage of pre-trained CNNs and number of slices and 3D samples for validation. CNNs parameters are optimized using linear, brute force, and random combinatorics, followed by voter and median operations. Data augmentation techniques such as reflection, translation and rotation are used in order to produce sufficient training set for CNNs. Optimal CNN parameters are reached by defining 11 standard and two proposed metrics. Finally, benchmarking demonstrates that CNNs improve segmentation accuracy, reliability and increased annotation accuracy, confirming the relevance of CNNs to generate high-throughput mathematical ground truth 3D images.

scholarly journals Deep Neural Network-Based Semantic Segmentation of Microvascular Decompression Images

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1167
Author(s):  
Ruifeng Bai ◽  
Shan Jiang ◽  
Haijiang Sun ◽  
Yifan Yang ◽  
Guiju Li
Keyword(s):  
Semantic Segmentation ◽  
Fine Tuning ◽  
Cerebral Vessel ◽  
Current State ◽  
Proposed Model ◽  
Segmentation Accuracy ◽  
Spatial Pyramid Pooling ◽  
Boundary Information ◽  
True Color ◽  
Good Research

Image semantic segmentation has been applied more and more widely in the fields of satellite remote sensing, medical treatment, intelligent transportation, and virtual reality. However, in the medical field, the study of cerebral vessel and cranial nerve segmentation based on true-color medical images is in urgent need and has good research and development prospects. We have extended the current state-of-the-art semantic-segmentation network DeepLabv3+ and used it as the basic framework. First, the feature distillation block (FDB) was introduced into the encoder structure to refine the extracted features. In addition, the atrous spatial pyramid pooling (ASPP) module was added to the decoder structure to enhance the retention of feature and boundary information. The proposed model was trained by fine tuning and optimizing the relevant parameters. Experimental results show that the encoder structure has better performance in feature refinement processing, improving target boundary segmentation precision, and retaining more feature information. Our method has a segmentation accuracy of 75.73%, which is 3% better than DeepLabv3+.

scholarly journals Semantic Segmentation of HeLa Cells: An Objective Comparison between one Traditional Algorithm and Three Deep-Learning Architectures

2020 ◽  
Author(s):  
Cefa Karabağ ◽  
Martin L. Jones ◽  
Christopher J. Peddie ◽  
Anne E. Weston ◽  
Lucy M. Collinson ◽  
...  
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Superior Performance ◽  
Processing Algorithm ◽  
Image Processing Algorithm ◽  
Segmentation Accuracy ◽  
Traditional Algorithm ◽  
Learning Architectures

AbstractIn this work, images of a HeLa cancer cell were semantically segmented with one traditional image-processing algorithm and three deep learning architectures: VGG16, ResNet18 and Inception-ResNet-v2. Three hundred slices, each 2000 × 2000 pixels, of a HeLa Cell were acquired with Serial Block Face Scanning Electron Microscopy. The deep learning architectures were pre-trained with ImageNet and then fine-tuned with transfer learning. The image-processing algorithm followed a pipeline of several traditional steps like edge detection, dilation and morphological operators. The algorithms were compared by measuring pixel-based segmentation accuracy and Jaccard index against a labelled ground truth. The results indicated a superior performance of the traditional algorithm (Accuracy = 99%, Jaccard = 93%) over the deep learning architectures: VGG16 (93%, 90%), ResNet18 (94%, 88%), Inception-ResNet-v2 (94%, 89%).

scholarly journals Automatic Detection of Pediatric Craniofacial Deformities using Convolutional Neural Networks

2020 ◽  
Vol 6 (3) ◽  
pp. 338-340
Author(s):  
Wattendorf Sonja ◽  
Tabatabaei Seyed Amir Hossein ◽  
Fischer Patrick ◽  
Hans-Peter Hans-Peter ◽  
Martina Wilbrand ◽  
...  
Keyword(s):  
Neural Network ◽  
Mobile Application ◽  
Therapy Monitoring ◽  
Semantic Segmentation ◽  
Learning Technologies ◽  
Skull Shape ◽  
Proposed Model ◽  
Segmentation Accuracy ◽  
Abnormal Head ◽  
Modern Machine

AbstractThe geometric shape of our skull is very important, not only from an esthetic perspective, but also from medical viewpoint. However, the lack of designated medical experts and wrong positioning is leading to an increasing number of abnormal head shapes in newborns and infants. To make screening and therapy monitoring for these abnormal shapes easier, we develop a mobile application to automatically detect and quantify such shapes. By making use of modern machine learning technologies like deep learning and transfer learning, we have developed a convolutional neural network for semantic segmentation of bird’s-eye view images of child heads. Using this approach, we have been able to achieve a segmentation accuracy of approximately 99 %, while having sensitivity and specificity of above 98 %. Given these promising results, we will use this basis to calculate medical parameters to quantify the skull shape. In addition, we will integrate the proposed model into a mobile application for further validation and usage in a real-world scenario.

Model and Method for Contributor’s Quality Assessment in Community Image Tagging Systems

2018 ◽  
pp. 45-51
Author(s):  
A. V. Ponomarev
Keyword(s):  
Large Scale ◽  
Wide Spectrum ◽  
Preference Relation ◽  
Pairwise Comparison ◽  
Ground Truth ◽  
Comparison Method ◽  
Characteristic Matrix ◽  
Image Tagging ◽  
Proposed Model

Introduction: Large-scale human-computer systems involving people of various skills and motivation into the information processing process are currently used in a wide spectrum of applications. An acute problem in such systems is assessing the expected quality of each contributor; for example, in order to penalize incompetent or inaccurate ones and to promote diligent ones.Purpose: To develop a method of assessing the expected contributor’s quality in community tagging systems. This method should only use generally unreliable and incomplete information provided by contributors (with ground truth tags unknown).Results:A mathematical model is proposed for community image tagging (including the model of a contributor), along with a method of assessing the expected contributor’s quality. The method is based on comparing tag sets provided by different contributors for the same images, being a modification of pairwise comparison method with preference relation replaced by a special domination characteristic. Expected contributors’ quality is evaluated as a positive eigenvector of a pairwise domination characteristic matrix. Community tagging simulation has confirmed that the proposed method allows you to adequately estimate the expected quality of community tagging system contributors (provided that the contributors' behavior fits the proposed model).Practical relevance: The obtained results can be used in the development of systems based on coordinated efforts of community (primarily, community tagging systems). 

Baby steps in the path of modifying the role of cardiologists for interpreting EKG for AMI

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Mehta ◽  
S Niklitschek ◽  
F Fernandez ◽  
C Villagran ◽  
J Avila ◽  
...  
Keyword(s):  
Human Resources ◽  
Ground Truth ◽  
Cost Effective ◽  
Clinical Settings ◽  
Dense Layer ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Original Dataset ◽  
Low Pass ◽  
Normal Branch

Abstract Background EKG interpretation is slowly transitioning to a physician-free, Artificial Intelligence (AI)-driven endeavor. Our continued efforts to innovate follow a carefully laid stepwise approach, as follows: 1) Create an AI algorithm that accurately identifies STEMI against non-STEMI using a 12-lead EKG; 2) Challenging said algorithm by including different EKG diagnosis to the previous experiment, and now 3) To further validate the accuracy and reliability of our algorithm while also improving performance in a prehospital and hospital settings. Purpose To provide an accurate, reliable, and cost-effective tool for STEMI detection with the potential to redirect human resources into other clinically relevant tasks and save the need for human resources. Methods Database: EKG records obtained from Latin America Telemedicine Infarct Network (Mexico, Colombia, Argentina, and Brazil) from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10-seconds length with sampling frequency of 500 [Hz], including the following balanced classes: unconfirmed and angiographically confirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding the ones included in other classes). The label of each record was manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: The first and last 250 samples were discarded as they may contain a standardization pulse. An order 5 digital low pass filter with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: The determined classes were STEMI (STEMI in different locations of the myocardium – anterior, inferior and lateral); Not-STEMI (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training & Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10; respectively. The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. Additional testing was performed with a subset of the original dataset of angiographically confirmed STEMI. Results See Figure Attached – Preliminary STEMI Dataset Accuracy: 96.4%; Sensitivity: 95.3%; Specificity: 97.4% – Confirmed STEMI Dataset: Accuracy: 97.6%; Sensitivity: 98.1%; Specificity: 97.2%. Conclusions Our results remain consistent with our previous experience. By further increasing the amount and complexity of the data, the performance of the model improves. Future implementations of this technology in clinical settings look promising, not only in performing swift screening and diagnostic steps but also partaking in complex STEMI management triage. Funding Acknowledgement Type of funding source: None

scholarly journals A stacked dense denoising–segmentation network for undersampled tomograms and knowledge transfer using synthetic tomograms

2021 ◽  
Vol 32 (3) ◽  
Author(s):  
Dimitrios Bellos ◽  
Mark Basham ◽  
Tony Pridmore ◽  
Andrew P. French
Keyword(s):  
Time Series ◽  
Knowledge Transfer ◽  
Semantic Segmentation ◽  
Real World Data ◽  
Transfer Scheme ◽  
X Ray ◽  
Segmentation Accuracy ◽  
X Ray Computed ◽  
Temporal Events ◽  
Time Critical

AbstractOver recent years, many approaches have been proposed for the denoising or semantic segmentation of X-ray computed tomography (CT) scans. In most cases, high-quality CT reconstructions are used; however, such reconstructions are not always available. When the X-ray exposure time has to be limited, undersampled tomograms (in terms of their component projections) are attained. This low number of projections offers low-quality reconstructions that are difficult to segment. Here, we consider CT time-series (i.e. 4D data), where the limited time for capturing fast-occurring temporal events results in the time-series tomograms being necessarily undersampled. Fortunately, in these collections, it is common practice to obtain representative highly sampled tomograms before or after the time-critical portion of the experiment. In this paper, we propose an end-to-end network that can learn to denoise and segment the time-series’ undersampled CTs, by training with the earlier highly sampled representative CTs. Our single network can offer two desired outputs while only training once, with the denoised output improving the accuracy of the final segmentation. Our method is able to outperform state-of-the-art methods in the task of semantic segmentation and offer comparable results in regard to denoising. Additionally, we propose a knowledge transfer scheme using synthetic tomograms. This not only allows accurate segmentation and denoising using less real-world data, but also increases segmentation accuracy. Finally, we make our datasets, as well as the code, publicly available.

Voice And Stream: Perceptual And Computational Modeling Of Voice Separation

2008 ◽  
Vol 26 (1) ◽  
pp. 75-94 ◽  
Author(s):  
Emilios Cambouropoulos
Keyword(s):  
Computational Modeling ◽  
Specific Problem ◽  
Cognitive Task ◽  
Ground Truth ◽  
Musical Score ◽  
Auditory Stream ◽  
Multiple Voices ◽  
Proposed Model ◽  
Single Voice ◽  
Small Dataset

LISTENERS ARE THOUGHT TO BE CAPABLE of perceiving multiple voices in music. This paper presents different views of what 'voice' means and how the problem of voice separation can be systematically described, with a view to understanding the problem better and developing a systematic description of the cognitive task of segregating voices in music. Well-established perceptual principles of auditory streaming are examined and then tailored to the more specific problem of voice separation in timbrally undifferentiated music. Adopting a perceptual view of musical voice, a computational prototype is developed that splits a musical score (symbolic musical data) into different voices. A single 'voice' may consist of one or more synchronous notes that are perceived as belonging to the same auditory stream. The proposed model is tested against a small dataset that acts as ground truth. The results support the theoretical viewpoint adopted in the paper.

Sign in / Sign up

Export Citation Format

Share Document