A model to discriminate malignant from benign thyroid nodules using artificial neural network.
OBJECTIVE: This study aimed to construct a model for using in differentiating benign and malignant nodules with the artificial neural network and to increase the objective diagnostic accuracy of US. MATERIALS AND METHODS: 618 consecutive patients (528 women, 161 men) with 689 thyroid nodules (425 ma...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2013-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC3864947?pdf=render |
| _version_ | 1819056435748667392 |
|---|---|
| author | Lu-Cheng Zhu Yun-Liang Ye Wen-Hua Luo Meng Su Hang-Ping Wei Xue-Bang Zhang Juan Wei Chang-Lin Zou |
| author_facet | Lu-Cheng Zhu Yun-Liang Ye Wen-Hua Luo Meng Su Hang-Ping Wei Xue-Bang Zhang Juan Wei Chang-Lin Zou |
| author_sort | Lu-Cheng Zhu |
| collection | DOAJ |
| description | OBJECTIVE: This study aimed to construct a model for using in differentiating benign and malignant nodules with the artificial neural network and to increase the objective diagnostic accuracy of US. MATERIALS AND METHODS: 618 consecutive patients (528 women, 161 men) with 689 thyroid nodules (425 malignant and 264 benign nodules) were enrolled in the present study. The presence and absence of each sonographic feature was assessed for each nodule - shape, margin, echogenicity, internal composition, presence of calcifications, peripheral halo and vascularity on color Doppler. The variables meet the following criteria: important sonographic features and statistically significant difference were selected as the input layer to build the ANN for predicting the malignancy of nodules. RESULTS: Six sonographic features including shape (Taller than wide, p<0.001), margin (Not Well-circumscribed, p<0.001), echogenicity (Hypoechogenicity, p<0.001), internal composition (Solid, p<0.001), presence of calcifications (Microcalcification, p<0.001) and peripheral halo (Absent, p<0.001) were significantly associated with malignant nodules. A three-layer 6-8-1 feed-forward ANN model was built. In the training cohort, the accuracy of the ANN in predicting malignancy of thyroid nodules was 82.3% (AURO = 0.818), the sensitivity and specificity was 84.5% and 79.1%, respectively. In the validation cohort, the accuracy, sensitivity and specificity was 83.1%, 83.8% and 81.8%, respectively. The AUROC was 0.828. CONCLUSION: ANN constructed by sonographic features can discriminate benign and malignant thyroid nodules with high diagnostic accuracy. |
| first_indexed | 2024-12-21T13:23:22Z |
| format | Article |
| id | doaj.art-332f73818bf442c8a0e998f0ded9b474 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-21T13:23:22Z |
| publishDate | 2013-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-332f73818bf442c8a0e998f0ded9b4742022-12-21T19:02:32ZengPublic Library of Science (PLoS)PLoS ONE1932-62032013-01-01812e8221110.1371/journal.pone.0082211A model to discriminate malignant from benign thyroid nodules using artificial neural network.Lu-Cheng ZhuYun-Liang YeWen-Hua LuoMeng SuHang-Ping WeiXue-Bang ZhangJuan WeiChang-Lin ZouOBJECTIVE: This study aimed to construct a model for using in differentiating benign and malignant nodules with the artificial neural network and to increase the objective diagnostic accuracy of US. MATERIALS AND METHODS: 618 consecutive patients (528 women, 161 men) with 689 thyroid nodules (425 malignant and 264 benign nodules) were enrolled in the present study. The presence and absence of each sonographic feature was assessed for each nodule - shape, margin, echogenicity, internal composition, presence of calcifications, peripheral halo and vascularity on color Doppler. The variables meet the following criteria: important sonographic features and statistically significant difference were selected as the input layer to build the ANN for predicting the malignancy of nodules. RESULTS: Six sonographic features including shape (Taller than wide, p<0.001), margin (Not Well-circumscribed, p<0.001), echogenicity (Hypoechogenicity, p<0.001), internal composition (Solid, p<0.001), presence of calcifications (Microcalcification, p<0.001) and peripheral halo (Absent, p<0.001) were significantly associated with malignant nodules. A three-layer 6-8-1 feed-forward ANN model was built. In the training cohort, the accuracy of the ANN in predicting malignancy of thyroid nodules was 82.3% (AURO = 0.818), the sensitivity and specificity was 84.5% and 79.1%, respectively. In the validation cohort, the accuracy, sensitivity and specificity was 83.1%, 83.8% and 81.8%, respectively. The AUROC was 0.828. CONCLUSION: ANN constructed by sonographic features can discriminate benign and malignant thyroid nodules with high diagnostic accuracy.http://europepmc.org/articles/PMC3864947?pdf=render |
| spellingShingle | Lu-Cheng Zhu Yun-Liang Ye Wen-Hua Luo Meng Su Hang-Ping Wei Xue-Bang Zhang Juan Wei Chang-Lin Zou A model to discriminate malignant from benign thyroid nodules using artificial neural network. PLoS ONE |
| title | A model to discriminate malignant from benign thyroid nodules using artificial neural network. |
| title_full | A model to discriminate malignant from benign thyroid nodules using artificial neural network. |
| title_fullStr | A model to discriminate malignant from benign thyroid nodules using artificial neural network. |
| title_full_unstemmed | A model to discriminate malignant from benign thyroid nodules using artificial neural network. |
| title_short | A model to discriminate malignant from benign thyroid nodules using artificial neural network. |
| title_sort | model to discriminate malignant from benign thyroid nodules using artificial neural network |
| url | http://europepmc.org/articles/PMC3864947?pdf=render |
| work_keys_str_mv | AT luchengzhu amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT yunliangye amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT wenhualuo amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT mengsu amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT hangpingwei amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT xuebangzhang amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT juanwei amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT changlinzou amodeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT luchengzhu modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT yunliangye modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT wenhualuo modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT mengsu modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT hangpingwei modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT xuebangzhang modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT juanwei modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork AT changlinzou modeltodiscriminatemalignantfrombenignthyroidnodulesusingartificialneuralnetwork |