A unified framework for simultaneous assessment of accuracy, between-, and within-reader variability of image segmentations

2020 ◽  
Vol 29 (11) ◽  
pp. 3135-3152
Author(s):  
Andrew E Ghattas ◽  
Reinhard R Beichel ◽  
Brian J Smith
Keyword(s):  
Manual Segmentation ◽  
Unified Framework ◽  
Modeling Framework ◽  
Pet Ct ◽  
Segmentation Methods ◽  
Wide Range ◽  
Segmentation Algorithms ◽  
Segmentation Approach ◽  
Ct Data ◽  
Method Accuracy

Medical imaging is utilized in a wide range of clinical applications. To enable a detailed quantitative analysis, medical images must often be segmented to label (delineate) structures of interest; for example, a tumor. Frequently, manual segmentation is utilized in clinical practice (e.g., in radiation oncology) to define such structures of interest. However, it can be quite time consuming and subject to substantial between-, and within-reader variability. A more reproducible, less variable, and more time efficient segmentation approach is likely to improve medical treatment. This potential has spurred the development of segmentation algorithms which harness computational power. Segmentation algorithms’ widespread use is limited due to difficulty in quantifying their performance relative to manual segmentation, which itself is subject to variation. This paper presents a statistical model which simultaneously estimates segmentation method accuracy, and between- and within-reader variability. The model is simultaneously fit for multiple segmentation methods within a unified Bayesian framework. The Bayesian model is compared to other methods used in literature via a simulation study, and application to head and neck cancer PET/CT data. The modeling framework is flexible and can be employed in numerous comparison applications. Several alternate applications are discussed in the paper.

scholarly journals A NOVEL IMAGE SEGMENTATION APPROACH BASED ON NEUTROSOPHIC SET AND IMPROVED FUZZY C-MEANS ALGORITHM

2011 ◽  
Vol 07 (01) ◽  
pp. 155-171 ◽  
Author(s):  
H. D. CHENG ◽  
YANHUI GUO ◽  
YINGTAO ZHANG
Keyword(s):  
Image Segmentation ◽  
Point Of View ◽  
Neutrosophic Set ◽  
Convergence Criterion ◽  
Complex Objects ◽  
Fuzzy C Means ◽  
Segmentation Methods ◽  
Segmentation Algorithms ◽  
Segmentation Approach ◽  
Fuzzy C Means Algorithm

Image segmentation is an important component in image processing, pattern recognition and computer vision. Many segmentation algorithms have been proposed. However, segmentation methods for both noisy and noise-free images have not been studied in much detail. Neutrosophic set (NS), a part of neutrosophy theory, studies the origin, nature, and scope of neutralities, as well as their interaction with different ideational spectra. However, neutrosophic set needs to be specified and clarified from a technical point of view for a given application or field to demonstrate its usefulness. In this paper, we apply neutrosophic set and define some operations. Neutrosphic set is integrated with an improved fuzzy c-means method and employed for image segmentation. A new operation, α-mean operation, is proposed to reduce the set indeterminacy. An improved fuzzy c-means (IFCM) is proposed based on neutrosophic set. The computation of membership and the convergence criterion of clustering are redefined accordingly. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can segment images accurately and effectively. Especially, it can segment the clean images and the images having different gray levels and complex objects, which is the most difficult task for image segmentation.

scholarly journals Clinically feasible semi-automatic workflows for measuring metabolically active tumour volume in metastatic melanoma

2020 ◽  
Author(s):  
Joyce van Sluis ◽  
Ellen C. de Heer ◽  
Mayke Boellaard ◽  
Mathilde Jalving ◽  
Adrienne H. Brouwers ◽  
...  
Keyword(s):  
Overall Survival ◽  
Metastatic Melanoma ◽  
Pet Imaging ◽  
Fdg Pet ◽  
Tumour Volume ◽  
Imaging Biomarker ◽  
Manual Segmentation ◽  
Pet Ct ◽  
Segmentation Methods ◽  
Automatic Methods

Abstract Purpose Metabolically active tumour volume (MATV) is a potential quantitative positron emission tomography (PET) imaging biomarker in melanoma. Accumulating data indicate that low MATV may predict increased chance of response to immunotherapy and overall survival. However, metastatic melanoma can present with numerous (small) tumour lesions, making manual tumour segmentation time-consuming. The aim of this study was to evaluate multiple semi-automatic segmentation workflows to determine reliability and reproducibility of MATV measurements in patients with metastatic melanoma. Methods An existing cohort of 64 adult patients with histologically proven metastatic melanoma was used in this study. 18F-FDG PET/CT diagnostic baseline images were acquired using a European Association of Nuclear Medicine (EANM) Research Limited–accredited Siemens Biograph mCT PET/CT system (Siemens Healthineers, Knoxville, USA). PET data were analysed using manual, gradient-based segmentation and five different semi-automatic methods: three direct PET image–derived delineations (41MAX, A50P and SUV40) and two based on a majority-vote approach (MV2 and MV3), without and with (suffix ‘+’) manual lesion addition. Correlation between the different segmentation methods and their respective associations with overall survival was assessed. Results Correlation between the MATVs derived by the manual segmentation and semi-automated tumour segmentations ranged from R2 = 0.41 for A50P to R2 = 0.85 for SUV40+ and MV2+, respectively. Manual MATV segmentation did not differ significantly from the semi-automatic methods SUV40 (∆MATV mean ± SD 0.08 ± 0.60 mL, P = 0.303), SUV40+ (∆MATV − 0.10 ± 0.51 mL, P = 0.126), MV2+ (∆MATV − 0.09 ± 0.62 mL, P = 0.252) and MV3+ (∆MATV − 0.03 ± 0.55 mL, P = 0.615). Log-rank tests showed statistically significant overall survival differences between above and below median MATV patients for all segmentation methods with areas under the ROC curves of 0.806 for manual segmentation and between 0.756 [41MAX] and 0.807 [MV3+] for semi-automatic segmentations. Conclusions Simple and fast semi-automated FDG PET segmentation workflows yield accurate and reproducible MATV measurements that correlate well with manual segmentation in metastatic melanoma. The most readily applicable and user-friendly SUV40 method allows feasible MATV measurement in prospective multicentre studies required for validation of this potential PET imaging biomarker for clinical use.

scholarly journals Impact of segmentation and discretization on radiomic features in 68Ga-DOTA-TOC PET/CT images of neuroendocrine tumor

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Virginia Liberini ◽  
Bruno De Santi ◽  
Osvaldo Rampado ◽  
Elena Gallio ◽  
Beatrice Dionisi ◽  
...  
Keyword(s):  
Correlation Coefficients ◽  
Ct Images ◽  
Mean Value ◽  
Biological Information ◽  
Dice Similarity Coefficient ◽  
Manual Segmentation ◽  
Pet Ct ◽  
Segmentation Methods ◽  
Edge Based ◽  
The Impact

Abstract Objective To identify the impact of segmentation methods and intensity discretization on radiomic features (RFs) extraction from 68Ga-DOTA-TOC PET images in patients with neuroendocrine tumors. Methods Forty-nine patients were retrospectively analyzed. Tumor contouring was performed manually by four different operators and with a semi-automatic edge-based segmentation (SAEB) algorithm. Three SUVmax fixed thresholds (20, 30, 40%) were applied. Fifty-one RFs were extracted applying two different intensity rescale factors for gray-level discretization: one absolute (AR60 = SUV from 0 to 60) and one relative (RR = min-max of the VOI SUV). Dice similarity coefficient (DSC) was calculated to quantify segmentation agreement between different segmentation methods. The impact of segmentation and discretization on RFs was assessed by intra-class correlation coefficients (ICC) and the coefficient of variance (COVL). The RFs’ correlation with volume and SUVmax was analyzed by calculating Pearson’s correlation coefficients. Results DSC mean value was 0.75 ± 0.11 (0.45–0.92) between SAEB and operators and 0.78 ± 0.09 (0.36–0.97), among the four manual segmentations. The study showed high robustness (ICC > 0.9): (a) in 64.7% of RFs for segmentation methods using AR60, improved by applying SUVmax threshold of 40% (86.5%); (b) in 50.9% of RFs for different SUVmax thresholds using AR60; and (c) in 37% of RFs for discretization settings using different segmentation methods. Several RFs were not correlated with volume and SUVmax. Conclusions RFs robustness to manual segmentation resulted higher in NET 68Ga-DOTA-TOC images compared to 18F-FDG PET/CT images. Forty percent SUVmax thresholds yield superior RFs stability among operators, however leading to a possible loss of biological information. SAEB segmentation appears to be an optimal alternative to manual segmentation, but further validations are needed. Finally, discretization settings highly impacted on RFs robustness and should always be stated.

scholarly journals Deformable Models for Segmentation Based on Local Analysis

2017 ◽  
Vol 2017 ◽  
pp. 1-13 ◽  
Author(s):  
Jimena Olveres ◽  
Erik Carbajal-Degante ◽  
Boris Escalante-Ramírez ◽  
Enrique Vallejo ◽  
Carla María García-Moreno
Keyword(s):  
Local Binary Patterns ◽  
Distance Measures ◽  
Local Analysis ◽  
Hermite Transform ◽  
Active Shape Models ◽  
Shape Models ◽  
Segmentation Methods ◽  
Segmentation Algorithms ◽  
Image Modality ◽  
New Algorithms

Segmentation tasks in medical imaging represent an exhaustive challenge for scientists since the image acquisition nature yields issues that hamper the correct reconstruction and visualization processes. Depending on the specific image modality, we have to consider limitations such as the presence of noise, vanished edges, or high intensity differences, known, in most cases, as inhomogeneities. New algorithms in segmentation are required to provide a better performance. This paper presents a new unified approach to improve traditional segmentation methods as Active Shape Models and Chan-Vese model based on level set. The approach introduces a combination of local analysis implementations with classic segmentation algorithms that incorporates local texture information given by the Hermite transform and Local Binary Patterns. The mixture of both region-based methods and local descriptors highlights relevant regions by considering extra information which is helpful to delimit structures. We performed segmentation experiments on 2D images including midbrain in Magnetic Resonance Imaging and heart’s left ventricle endocardium in Computed Tomography. Quantitative evaluation was obtained with Dice coefficient and Hausdorff distance measures. Results display a substantial advantage over the original methods when we include our characterization schemes. We propose further research validation on different organ structures with promising results.

Revisiting the K-nn algorithm for obstetric image segmentation

2021 ◽  
pp. 1-13
Author(s):  
P. Salgado ◽  
T.-P. Azevedo Perdicoúlis
Keyword(s):  
Magnetic Resonance Image ◽  
Medical Image ◽  
Clustering Algorithm ◽  
Ultrasound Image ◽  
Well Being ◽  
Health Conditions ◽  
Medical Applications ◽  
Training Set ◽  
Segmentation Methods ◽  
Segmentation Algorithms

Medical image techniques are used to examine and determine the well-being of the foetus during pregnancy. Digital image processing (DIP) is essential to extract valuable information embedded in most biomedical signals. After, intelligent segmentation methods, based on classifier algorithms, must be applied to identify structures and relevant features from previous data. The success of both is essential for helping doctors to identify adverse health conditions from the medical images. To obtain easy and reliable DIP methods for foetus images in real-time, at different gestational ages, aware pre-processing needs to be applied to the images. Thence, some data features are extracted that are meant to be used as input to the segmentation algorithms presented in this work. Due to the high dimension of the problems in question, assemblage of the data is also desired. The segmentation of the images is done by revisiting the K-nn algorithm that is a conventional nonparametric classifier. Besides its simplicity, its power to accomplish high classification results in medical applications has been demonstrated. In this work two versions of this algorithm are presented (i) an enhancement of the standard version by aggregating the data apriori and (ii) an iterative version of the same method where the training set (TS) is not static. The procedure is demonstrated in two experiments, where two images of different technologies were selected: a magnetic resonance image and an ultrasound image, respectively. The results were assessed by comparison with the K-means clustering algorithm, a well-known and robust method for this type of task. Both described versions showed results close to 100% matching with the ones obtained by the validation method, although the iterative version displays much higher reliability in the classification.

scholarly journals EXPRESS: Overcoming the Cold Start Problem of CRM using a Probabilistic Machine Learning Approach

2021 ◽  
pp. 002224372110329
Author(s):  
Nicolas Padilla ◽  
Eva Ascarza
Keyword(s):  
Machine Learning ◽  
Cold Start ◽  
Customer Relationship ◽  
Exponential Families ◽  
Modeling Framework ◽  
Wide Range ◽  
The Moment ◽  
Probabilistic Machine Learning ◽  
Marketing Actions ◽  
Cold Start Problem

The success of Customer Relationship Management (CRM) programs ultimately depends on the firm's ability to identify and leverage differences across customers — a very diffcult task when firms attempt to manage new customers, for whom only the first purchase has been observed. For those customers, the lack of repeated observations poses a structural challenge to inferring unobserved differences across them. This is what we call the “cold start” problem of CRM, whereby companies have difficulties leveraging existing data when they attempt to make inferences about customers at the beginning of their relationship. We propose a solution to the cold start problem by developing a probabilistic machine learning modeling framework that leverages the information collected at the moment of acquisition. The main aspect of the model is that it exibly captures latent dimensions that govern the behaviors observed at acquisition as well as future propensities to buy and to respond to marketing actions using deep exponential families. The model can be integrated with a variety of demand specifications and is exible enough to capture a wide range of heterogeneity structures. We validate our approach in a retail context and empirically demonstrate the model's ability at identifying high-value customers as well as those most sensitive to marketing actions, right after their first purchase.

scholarly journals Cycle and flow trusses in directed networks

2016 ◽  
Vol 3 (11) ◽  
pp. 160270 ◽  
Author(s):  
Taro Takaguchi ◽  
Yuichi Yoshida
Keyword(s):  
Truss Structures ◽  
Directed Network ◽  
Unified Framework ◽  
Directed Networks ◽  
Research Fields ◽  
Wide Range ◽  
Definition Of ◽  
Information Finding ◽  
Empirical Networks ◽  
Module Structures

When we represent real-world systems as networks, the directions of links often convey valuable information. Finding module structures that respect link directions is one of the most important tasks for analysing directed networks. Although many notions of a directed module have been proposed, no consensus has been reached. This lack of consensus results partly because there might exist distinct types of modules in a single directed network, whereas most previous studies focused on an independent criterion for modules. To address this issue, we propose a generic notion of the so-called truss structures in directed networks. Our definition of truss is able to extract two distinct types of trusses, named the cycle truss and the flow truss, from a unified framework. By applying the method for finding trusses to empirical networks obtained from a wide range of research fields, we find that most real networks contain both cycle and flow trusses. In addition, the abundance of (and the overlap between) the two types of trusses may be useful to characterize module structures in a wide variety of empirical networks. Our findings shed light on the importance of simultaneously considering different types of modules in directed networks.

Modeling framework for IoT integration of building automation systems

2017 ◽  
Vol 65 (9) ◽  
Author(s):  
Daniel Schachinger ◽  
Andreas Fernbach ◽  
Wolfgang Kastner
Keyword(s):  
Web Services ◽  
Web Service ◽  
Building Automation ◽  
Modeling Framework ◽  
Seamless Integration ◽  
Automation Systems ◽  
Wide Range ◽  
Machine To Machine Communication ◽  
Machine Communication ◽  
The Internet Of Things

AbstractAdvancements within the Internet of Things are leading to a pervasive integration of different domains including also building automation systems. As a result, device functionality becomes available to a wide range of applications and users outside of the building automation domain. In this context, Web services are identified as suitable solution for machine-to-machine communication. However, a major requirement to provide necessary interoperability is the consideration of underlying semantics. Thus, this work presents a universal framework for tag-based semantic modeling and seamless integration of building automation systems via Web service-based technologies. Using the example of the KNX Web services specification, the applicability of this approach is pointed out.

scholarly journals Development of a Gold-standard Pashto Dataset and a Segmentation App

2021 ◽  
Vol 40 (1) ◽  
Author(s):  
Yan Han ◽  
Marek Rychlik
Keyword(s):  
Gold Standard ◽  
Text Line ◽  
Writing System ◽  
Digital Repository ◽  
New Approach ◽  
Segmentation Methods ◽  
Segmentation Approach ◽  
Machine Learning Applications ◽  
Unique Approach ◽  
Selection Of

The article aims to introduce a gold-standard Pashto dataset and a segmentation app. The Pashto dataset consists of 300 line images and corresponding Pashto text from three selected books. A line image is simply an image consisting of one text line from a scanned page. To our knowledge, this is one of the first open access datasets which directly maps line images to their corresponding text in the Pashto language. We also introduce the development of a segmentation app using textbox expanding algorithms, a different approach to OCR segmentation. The authors discuss the steps to build a Pashto dataset and develop our unique approach to segmentation. The article starts with the nature of the Pashto alphabet and its unique diacritics which require special considerations for segmentation. Needs for datasets and a few available Pashto datasets are reviewed. Criteria of selection of data sources are discussed and three books were selected by our language specialist from the Afghan Digital Repository. The authors review previous segmentation methods and introduce a new approach to segmentation for Pashto content. The segmentation app and results are discussed to show readers how to adjust variables for different books. Our unique segmentation approach uses an expanding textbox method which performs very well given the nature of the Pashto scripts. The app can also be used for Persian and other languages using the Arabic writing system. The dataset can be used for OCR training, OCR testing, and machine learning applications related to content in Pashto.

Sign in / Sign up

Export Citation Format

Share Document