Segmentation Evaluation of Gutenberg's Bible Pages by Ground-Truth and Synthetic Images

2014 ◽  
Author(s):  
Ederson Marcos Sgarbi ◽  
Wellington Aparecido Della Mura ◽  
Jacques Facon ◽  
Daniela de Freitas Guilhermino Trindade ◽  
Victor Ronchi Garcia
Keyword(s):  
Ground Truth ◽  
Segmentation Evaluation ◽  
Synthetic Images

scholarly journals Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

Algorithms ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 212
Author(s):  
Youssef Skandarani ◽  
Pierre-Marc Jodoin ◽  
Alain Lalande
Keyword(s):  
Deep Learning ◽  
Cardiac Mri ◽  
Expert Knowledge ◽  
Medical Image Analysis ◽  
Ground Truth ◽  
Cine Mri ◽  
Data Sets ◽  
Mri Segmentation ◽  
Segmentation Evaluation ◽  
Ground Truth Data

Deep learning methods are the de facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application, which, like many others, requires a large number of annotated data so that a trained network can generalize well. Unfortunately, the process of having a large number of manually curated images by medical experts is both slow and utterly expensive. In this paper, we set out to explore whether expert knowledge is a strict requirement for the creation of annotated data sets on which machine learning can successfully be trained. To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with different loss functions on expert and non-expert ground truth for cardiac cine–MRI segmentation. Evaluation was done with classic segmentation metrics (Dice index and Hausdorff distance) as well as clinical measurements, such as the ventricular ejection fractions and the myocardial mass. The results reveal that generalization performances of a segmentation neural network trained on non-expert ground truth data is, to all practical purposes, as good as that trained on expert ground truth data, particularly when the non-expert receives a decent level of training, highlighting an opportunity for the efficient and cost-effective creation of annotations for cardiac data sets.

scholarly journals Segmentation of Multi-Tumor from PET/CT Images

2019 ◽  
Vol 8 (12S2) ◽  
pp. 170-176
Keyword(s):  
Automatic Segmentation ◽  
Mean Shift ◽  
Ground Truth ◽  
Histogram Equalization ◽  
Ct Images ◽  
Svm Classifier ◽  
Segmentation Evaluation ◽  
Multiple Tumor ◽  
Mean Shift Clustering ◽  
Pet Ct

The aim of the project is to develop a methodology for automatic segmentation of multiple tumor from PET/CT images. Image pre-processing methods such as Contrast Limited Adaptive Histogram Equalization (CLAHE), image sharpening and Wiener filtering were performed to remove the artifacts due to contrast variations and noise. The image was segmented using K-means, Threshold segmentation, watershed segmentation, FCM clustering Segmentation, Mean shift Clustering Segmentation, Graph Cut Segmentation. Evaluation was made for the segmentation against the Ground Truth. Various Features was selected and extracted. Classification was made using SVM classifier and KNN classifier to classify the tumor as benign or malignant. The proposed method was carried out using PET/CT images of lung cancer patients and implemented using MATLAB.

A Learning-Based Framework for Supervised and Unsupervised Image Segmentation Evaluation

2014 ◽  
Vol 14 (03) ◽  
pp. 1450014 ◽  
Author(s):  
Jian Lin ◽  
Bo Peng ◽  
Tianrui Li
Keyword(s):  
Image Segmentation ◽  
Ground Truth ◽  
Evaluation Framework ◽  
Segmentation Evaluation ◽  
Machine Learning Methods ◽  
Effectiveness Measure ◽  
Human Evaluation ◽  
Segmentation Quality ◽  
Image Segmentation Evaluation ◽  
Unsupervised Image Segmentation

Image segmentation is a fundamental task in automatic image analysis. However, there is still no generally accepted effectiveness measure which is suitable for evaluating the segmentation quality in every application. In this paper, we propose an evaluation framework which benefits from multiple stand-alone measures. To this end, different segmentation evaluation measures are chosen to evaluate segmentation separately, and the results are effectively combined using machine learning methods. We train and implement this framework in our brand-new segmentation dataset which contains images of different contents with segmentation ground truth and Weizmann segmentation database (WSD). In addition, we provide human evaluation of image segmentation pairs to benchmark the evaluation results of the measures. Experimental results show a better performance than the stand-alone methods.

Anatomy segmentation evaluation with sparse ground truth data

2020 ◽  
Author(s):  
Jieyu Li ◽  
Jayaram K. Udupa ◽  
Yubing Tong ◽  
Lisheng Wang ◽  
Drew A. Torigian
Keyword(s):  
Ground Truth ◽  
Segmentation Evaluation ◽  
Ground Truth Data

Segmentation evaluation with sparse ground truth data: Simulating true segmentations as perfect/imperfect as those generated by humans

2021 ◽  
Vol 69 ◽  
pp. 101980
Author(s):  
Jieyu Li ◽  
Jayaram K. Udupa ◽  
Yubing Tong ◽  
Lisheng Wang ◽  
Drew A. Torigian
Keyword(s):  
Ground Truth ◽  
Segmentation Evaluation ◽  
Ground Truth Data

scholarly journals Automatic monitoring of steel strip positioning error based on semantic segmentation

2020 ◽  
Vol 110 (11-12) ◽  
pp. 2847-2860
Author(s):  
Aline de Faria Lemos ◽  
Leonardo Adolpho Rodrigues da Silva ◽  
Balázs Vince Nagy
Keyword(s):  
Steel Strip ◽  
Mechanical Vibration ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Automatic Monitoring ◽  
Positioning Error ◽  
Segmentation Evaluation ◽  
Positioning Errors ◽  
Steel Strips ◽  
Position Correction

Abstract The misalignment of steel strips in relation to the roller table centerline still is an impairment for the rolling mill production lines. Nowadays, the strip position correction remains largely in the purview of human analysis, in which the strip steering is traditionally a semi-manual operation. Automating the alignment process could reduce the maintenance costs, damage to the plant, and prevent material losses. The first step into the automatization is to determine the strip position and its referred error. This study presents a method that employs semantic segmentation based on convolution neural networks to estimate steel strips positioning error from images of the process. Additionally, the system mitigates the influences of mechanical vibration on the images. The system performance was assessed by standard semantic segmentation evaluation metrics and in comparison with the dataset ground truth. The results showed that 97% of the estimated positioning errors are within a 2-pixel margin. The method demonstrated to be a robust real-time solution as the networks were trained from a set of low-resolution images acquired in a complex environment.

scholarly journals Emulated retinal image capture (ERICA) to test, train and validate processing of retinal images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Laura K. Young ◽  
Hannah E. Smithson
Keyword(s):  
Adaptive Optics ◽  
Retinal Image ◽  
Imaging System ◽  
Ground Truth ◽  
Learning Approaches ◽  
Image Capture ◽  
Ground Truth Data ◽  
Cone Mosaic ◽  
Synthetic Images

AbstractHigh resolution retinal imaging systems, such as adaptive optics scanning laser ophthalmoscopes (AOSLO), are increasingly being used for clinical research and fundamental studies in neuroscience. These systems offer unprecedented spatial and temporal resolution of retinal structures in vivo. However, a major challenge is the development of robust and automated methods for processing and analysing these images. We present ERICA (Emulated Retinal Image CApture), a simulation tool that generates realistic synthetic images of the human cone mosaic, mimicking images that would be captured by an AOSLO, with specified image quality and with corresponding ground-truth data. The simulation includes a self-organising mosaic of photoreceptors, the eye movements an observer might make during image capture, and data capture through a real system incorporating diffraction, residual optical aberrations and noise. The retinal photoreceptor mosaics generated by ERICA have a similar packing geometry to human retina, as determined by expert labelling of AOSLO images of real eyes. In the current implementation ERICA outputs convincingly realistic en face images of the cone photoreceptor mosaic but extensions to other imaging modalities and structures are also discussed. These images and associated ground-truth data can be used to develop, test and validate image processing and analysis algorithms or to train and validate machine learning approaches. The use of synthetic images has the advantage that neither access to an imaging system, nor to human participants is necessary for development.

Sign in / Sign up

Export Citation Format

Share Document