Computer analysis of echographic textures in hashimoto disease of the thyroid

Mailloux, G.E.; Bertrand, Michel; Stampfler, Robert; Ethier, S

doi:10.1002/jcu.1870140705

Cited by 41 publications

(23 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most other studies regarding echogenicity of the thyroid and its function, concern patients with known Hashimoto's disease (1,3,5,(7)(8)(9) or persons referred to a hospital for some kind of thyroid disease or symptoms (10,11,16) making a comparison difficult. All studies found an association between decreased echogenicity of the thyroid and overt hypothyroidism.…”

Section: Discussionmentioning

confidence: 99%

“…Since subclinical thyroid dysfunction has a tendency to develop into overt thyroid dysfunction (4), the finding of decreased echogenicity or irregularity in echo pattern at thyroid US in these patients with the elevation of thyroid-stimulating hormone (TSH) could perhaps be seen as an early sign of thyroid failure. Most previous studies concern patients with known Hashimoto's thyroiditis (1,3,(5)(6)(7)(8)(9) or patients referred to a hospital with suspicion of thyroid disease (10,11). One study (2) concerns apparently healthy subjects from hospital staff.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The association between hypoechogenicity or irregular echo pattern at thyroid ultrasonography and thyroid function in the general population

Vejbjerg¹,

Knudsen²,

Perrild³

et al. 2006

eur j endocrinol

View full text Add to dashboard Cite

Objective: Patients with overt hypothyroidism show decreased echogenicity of the thyroid at ultrasonography (US). The aim of this study was to investigate the association between echogenicity of the thyroid/irregular echo pattern, and thyroid function in the general population, i.e. subjects without overt thyroid disease. Design: A cross-sectional investigation of 4649 randomly selected adult subjects. Methods: Blood samples were analysed for serum TSH, thyroid hormones and thyroid autoantibodies. US of the thyroid was performed. Results: Participants with decreased echogenicity (nZ379) had a higher mean TSH (1.65 mU/l) compared with subjects with normal echogenicity (1.21 mU/l, P!0.0001). The association was stronger in subjects with markedly decreased echogenicity (4.20 mU/l, P!0.0001). A similar association was seen when the subjects were divided into subgroups according to the level of TSH; more subjects with high levels of TSH had decreased echogenicity (P!0.0001). Likewise, more subjects with high levels of TSH had an irregular echo pattern (P!0.0001). Subjects with decreased echogenicity had a higher risk of having thyroid autoantibodies than subjects without decreased echogenicity (P!0.0001). This association was stronger when echogenicity was markedly decreased. Conclusions: We demonstrated an association between hypoechogenicity at thyroid US and higher levels of serum TSH even in subjects without overt thyroid disease, suggesting decreased echogenicity as an early sign of thyroid dysfunction. Irregular echo pattern, whether accompanied by hypoechogenicity or not, was another possible marker of thyroid failure. This indicates a possible use of thyroid US in detecting early and subclinical thyroid dysfunction.European Journal of Endocrinology 155 547-552

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The association between hypoechogenicity or irregular echo pattern at thyroid ultrasonography and thyroid function in the general population

Vejbjerg¹,

Knudsen²,

Perrild³

et al. 2006

eur j endocrinol

View full text Add to dashboard Cite

show abstract

“…Previous attempts on CAD categorization of thyroid nodules on US images include evaluation of parameters from the gray level histogram of thyroid US images [3], [4], intensity features extracted by the utilization of Radon transform [5], textural features extracted from gray level spatial-dependence matrices [6], [7], and the application of discriminant…”

Section: Introductionmentioning

confidence: 99%

“…In this light, the quantification of nodule boundary irregularity by boundary-based features could be valuable for malignancy risk assessment, contributing to the objectification of medical decisions. Such boundary-based features could be combined with intensity and textural information within an integrated computer-aided-diagnosis (CAD) tool.Previous attempts on CAD categorization of thyroid nodules on US images include evaluation of parameters from the gray level histogram of thyroid US images [3], [4], intensity features extracted by the utilization of Radon transform [5], textural features extracted from gray level spatial-dependence matrices [6], [7], and the application of discriminant …”

mentioning

confidence: 99%

A computer-aided system for malignancy risk assessment of nodules in thyroid US images based on boundary features

Savelonas

Maroulis

Sangriotis

2009

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

In this paper, a novel computer-based approach is proposed for malignancy risk assessment of thyroid nodules in ultrasound images. The proposed approach is based on boundary features and is motivated by the correlation which has been addressed in medical literature between nodule boundary irregularity and malignancy risk. In addition, local echogenicity variance is utilized so as to incorporate information associated with local echogenicity distribution within nodule boundary neighborhood. Such information is valuable for the discrimination of high-risk nodules with blurred boundaries from medium risk nodules with regular boundaries. Analysis of variance is performed, indicating that each boundary feature under study provides statistically significant information for the discrimination of thyroid nodules in ultrasound images, in terms of malignancy risk. k-nearest neighbor and support vector machine classifiers are employed for the classification tasks, utilizing feature vectors derived from all combinations of features under study. The classification results are evaluated with the use of the receiver operating characteristic. It is derived that the proposed approach is capable of discriminating between medium-risk and high-risk nodules, obtaining an area under curve, which reaches 0.95. Keywords:Computer-Aided Diagnosis, Ultrasound, Thyroid Nodules, Boundary Features. IntroductionThe results of clinical research demonstrate that the presence of blurred or irregular thyroid nodule boundaries on ultrasound (US) images correlate with malignancy risk [1], [2]. In this light, the quantification of nodule boundary irregularity by boundary-based features could be valuable for malignancy risk assessment, contributing to the objectification of medical decisions. Such boundary-based features could be combined with intensity and textural information within an integrated computer-aided-diagnosis (CAD) tool.Previous attempts on CAD categorization of thyroid nodules on US images include evaluation of parameters from the gray level histogram of thyroid US images [3], [4], intensity features extracted by the utilization of Radon transform [5], textural features extracted from gray level spatial-dependence matrices [6], [7], and the application of discriminant

show abstract

“…It combines a unique set of virtues including real time imaging, ability to measure dimensions and volume, low cost, mobility, and no side effects. As a result ultrasonography has become the most widely employed imaging method for the diagnosis and follow-up of thyroid disorders such as nodules, tumors and cysts [1][2][3][4]. [5].…”

Section: Introductionmentioning

confidence: 99%