Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder
Purpose. Several commercial tests have been used for the classification of indeterminate thyroid nodules in cytology. However, the geographic inconvenience and high cost confine their widespread use. This study aims to develop a classifier for conveniently clinical utility. Methods. Gene expression...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | International Journal of Endocrinology |
| Online Access: | http://dx.doi.org/10.1155/2020/9015713 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832552992023248896 |
|---|---|
| author | Zexin Li Kaiji Yang Lili Zhang Chiju Wei Peixuan Yang Wencan Xu |
| author_facet | Zexin Li Kaiji Yang Lili Zhang Chiju Wei Peixuan Yang Wencan Xu |
| author_sort | Zexin Li |
| collection | DOAJ |
| description | Purpose. Several commercial tests have been used for the classification of indeterminate thyroid nodules in cytology. However, the geographic inconvenience and high cost confine their widespread use. This study aims to develop a classifier for conveniently clinical utility. Methods. Gene expression data of thyroid nodule tissues were collected from three public databases. Immune-related genes were used to construct the classifier with stacked denoising sparse autoencoder. Results. The classifier performed well in discriminating malignant and benign thyroid nodules, with an area under the curve of 0.785 [0.638–0.931], accuracy of 92.9% [92.7–93.0%], sensitivity of 98.6% [95.9–101.3%], specificity of 58.3% [30.4–86.2%], positive likelihood ratio of 2.367 [1.211–4.625], and negative likelihood ratio of 0.024 [0.003–0.177]. In the cancer prevalence range of 20–40% for indeterminate thyroid nodules in cytology, the range of negative predictive value of this classifier was 37–61%, and the range of positive predictive value was 98–99%. Conclusion. The classifier developed in this study has the superb discriminative ability for thyroid nodules. However, it needs validation in cytologically indeterminate thyroid nodules before clinical use. |
| format | Article |
| id | doaj-art-85ee260c795a4cef89458a6f89338a3c |
| institution | Kabale University |
| issn | 1687-8337 1687-8345 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Endocrinology |
| spelling | doaj-art-85ee260c795a4cef89458a6f89338a3c2025-02-03T05:57:19ZengWileyInternational Journal of Endocrinology1687-83371687-83452020-01-01202010.1155/2020/90157139015713Classification of Thyroid Nodules with Stacked Denoising Sparse AutoencoderZexin Li0Kaiji Yang1Lili Zhang2Chiju Wei3Peixuan Yang4Wencan Xu5Health Care Center, The First Affiliated Hospital of Shantou University Medical College, No. 57, Changping Road, Shantou 515041, ChinaDepartment of Radiology, The First Affiliated Hospital of Shantou University Medical College, No. 57, Changping Road, Shantou 515041, ChinaHealth Care Center, The First Affiliated Hospital of Shantou University Medical College, No. 57, Changping Road, Shantou 515041, ChinaMultidisciplinary Research Center, Shantou University, No. 243, Daxue Road, Shantou 515063, ChinaHealth Care Center, The First Affiliated Hospital of Shantou University Medical College, No. 57, Changping Road, Shantou 515041, ChinaDepartment of Endocrinology, The First Affiliated Hospital of Shantou University Medical College, No. 57, Changping Road, Shantou 515041, ChinaPurpose. Several commercial tests have been used for the classification of indeterminate thyroid nodules in cytology. However, the geographic inconvenience and high cost confine their widespread use. This study aims to develop a classifier for conveniently clinical utility. Methods. Gene expression data of thyroid nodule tissues were collected from three public databases. Immune-related genes were used to construct the classifier with stacked denoising sparse autoencoder. Results. The classifier performed well in discriminating malignant and benign thyroid nodules, with an area under the curve of 0.785 [0.638–0.931], accuracy of 92.9% [92.7–93.0%], sensitivity of 98.6% [95.9–101.3%], specificity of 58.3% [30.4–86.2%], positive likelihood ratio of 2.367 [1.211–4.625], and negative likelihood ratio of 0.024 [0.003–0.177]. In the cancer prevalence range of 20–40% for indeterminate thyroid nodules in cytology, the range of negative predictive value of this classifier was 37–61%, and the range of positive predictive value was 98–99%. Conclusion. The classifier developed in this study has the superb discriminative ability for thyroid nodules. However, it needs validation in cytologically indeterminate thyroid nodules before clinical use.http://dx.doi.org/10.1155/2020/9015713 |
| spellingShingle | Zexin Li Kaiji Yang Lili Zhang Chiju Wei Peixuan Yang Wencan Xu Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder International Journal of Endocrinology |
| title | Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder |
| title_full | Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder |
| title_fullStr | Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder |
| title_full_unstemmed | Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder |
| title_short | Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder |
| title_sort | classification of thyroid nodules with stacked denoising sparse autoencoder |
| url | http://dx.doi.org/10.1155/2020/9015713 |
| work_keys_str_mv | AT zexinli classificationofthyroidnoduleswithstackeddenoisingsparseautoencoder AT kaijiyang classificationofthyroidnoduleswithstackeddenoisingsparseautoencoder AT lilizhang classificationofthyroidnoduleswithstackeddenoisingsparseautoencoder AT chijuwei classificationofthyroidnoduleswithstackeddenoisingsparseautoencoder AT peixuanyang classificationofthyroidnoduleswithstackeddenoisingsparseautoencoder AT wencanxu classificationofthyroidnoduleswithstackeddenoisingsparseautoencoder |