RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume
Unlike the lungs or the heart, the thyroid gland is not a primary target in chest computed tomography (CT) scans and is relatively small; hence, it is difficult for radiologists to always clinically delineate it in chest CT to incidentally detect a goiter. We designed a residual and dilated convolut...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10817600/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550784273055744 |
|---|---|
| author | Min-Ji Kim Jin-A Kim Naae Kim Yul Hwangbo Hyun Jeong Jeon Dong-Hwa Lee Ji Eun Oh |
| author_facet | Min-Ji Kim Jin-A Kim Naae Kim Yul Hwangbo Hyun Jeong Jeon Dong-Hwa Lee Ji Eun Oh |
| author_sort | Min-Ji Kim |
| collection | DOAJ |
| description | Unlike the lungs or the heart, the thyroid gland is not a primary target in chest computed tomography (CT) scans and is relatively small; hence, it is difficult for radiologists to always clinically delineate it in chest CT to incidentally detect a goiter. We designed a residual and dilated convolution neural network (RED-Net), which automatically measures thyroid volume by segmenting the thyroid gland in contrast-enhanced chest CT scans. Its fundamental structure comprises a residual downsampling and upsampling pathway, complemented by a parallel dilated convolution module. This combination allows the model to extract features at multiple scales and capture contextual information to effectively segment even tiny thyroid glands in the complex anatomical structures observed in chest CT scans. Additionally, we constructed training and validation sets comprising CT scans of 1,150 adults (aged <inline-formula> <tex-math notation="LaTeX">$\ge 19$ </tex-math></inline-formula> years) who underwent chest CT scans at the National Cancer Center and included data of those without a history of thyroid nodules, C73 diagnosis, or thyroid surgery before scanning procedure. We evaluated the performance of our method on a test dataset (600 patients) comprising chest CT scans of individuals collected at Chungbuk National University Hospital using the same criteria. The results showed that it achieved state-of-the-art performance with a Dice similarity coefficient of 0.8901. |
| format | Article |
| id | doaj-art-964fe6f6e26747e58ac782cf059fe951 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-964fe6f6e26747e58ac782cf059fe9512025-01-10T00:02:46ZengIEEEIEEE Access2169-35362025-01-01133026303710.1109/ACCESS.2024.352376610817600RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid VolumeMin-Ji Kim0https://orcid.org/0009-0005-3289-0794Jin-A Kim1Naae Kim2Yul Hwangbo3Hyun Jeong Jeon4Dong-Hwa Lee5Ji Eun Oh6https://orcid.org/0000-0002-1953-9845Heathcare AI Team, National Cancer Center, Goyang-si, South KoreaHeathcare AI Team, National Cancer Center, Goyang-si, South KoreaResearch and Development Business Foundation, National Cancer Center, Goyang-si, South KoreaHeathcare AI Team, National Cancer Center, Goyang-si, South KoreaDepartment of Internal Medicine, Chungbuk National University Hospital, Cheongju-si, South KoreaDepartment of Internal Medicine, Chungbuk National University Hospital, Cheongju-si, South KoreaHeathcare AI Team, National Cancer Center, Goyang-si, South KoreaUnlike the lungs or the heart, the thyroid gland is not a primary target in chest computed tomography (CT) scans and is relatively small; hence, it is difficult for radiologists to always clinically delineate it in chest CT to incidentally detect a goiter. We designed a residual and dilated convolution neural network (RED-Net), which automatically measures thyroid volume by segmenting the thyroid gland in contrast-enhanced chest CT scans. Its fundamental structure comprises a residual downsampling and upsampling pathway, complemented by a parallel dilated convolution module. This combination allows the model to extract features at multiple scales and capture contextual information to effectively segment even tiny thyroid glands in the complex anatomical structures observed in chest CT scans. Additionally, we constructed training and validation sets comprising CT scans of 1,150 adults (aged <inline-formula> <tex-math notation="LaTeX">$\ge 19$ </tex-math></inline-formula> years) who underwent chest CT scans at the National Cancer Center and included data of those without a history of thyroid nodules, C73 diagnosis, or thyroid surgery before scanning procedure. We evaluated the performance of our method on a test dataset (600 patients) comprising chest CT scans of individuals collected at Chungbuk National University Hospital using the same criteria. The results showed that it achieved state-of-the-art performance with a Dice similarity coefficient of 0.8901.https://ieeexplore.ieee.org/document/10817600/Chest CT scansdilated convolutiongoiterRED-Netresidual blocksthyroid segmentation |
| spellingShingle | Min-Ji Kim Jin-A Kim Naae Kim Yul Hwangbo Hyun Jeong Jeon Dong-Hwa Lee Ji Eun Oh RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume IEEE Access Chest CT scans dilated convolution goiter RED-Net residual blocks thyroid segmentation |
| title | RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume |
| title_full | RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume |
| title_fullStr | RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume |
| title_full_unstemmed | RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume |
| title_short | RED-Net: A Neural Network for 3D Thyroid Segmentation in Chest CT Using Residual and Dilated Convolutions for Measuring Thyroid Volume |
| title_sort | red net a neural network for 3d thyroid segmentation in chest ct using residual and dilated convolutions for measuring thyroid volume |
| topic | Chest CT scans dilated convolution goiter RED-Net residual blocks thyroid segmentation |
| url | https://ieeexplore.ieee.org/document/10817600/ |
| work_keys_str_mv | AT minjikim rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume AT jinakim rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume AT naaekim rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume AT yulhwangbo rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume AT hyunjeongjeon rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume AT donghwalee rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume AT jieunoh rednetaneuralnetworkfor3dthyroidsegmentationinchestctusingresidualanddilatedconvolutionsformeasuringthyroidvolume |