DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound
Placental maturity grading (PMG) is often utilized for evaluating fetal growth and maternal health. Currently, PMG often relied on the subjective judgment of the clinician, which is time-consuming and tends to incur a wrong estimation due to redundancy and repeatability of the process. The existing...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2023.1239400/full |
| _version_ | 1797693091205873664 |
|---|---|
| author | Yunzhu Wu Yunzhu Wu Yijun Yang Lei Zhu Lei Zhu Zhenyan Han Hong Luo Hong Luo Xue Xue Xue Xue Weiming Wang |
| author_facet | Yunzhu Wu Yunzhu Wu Yijun Yang Lei Zhu Lei Zhu Zhenyan Han Hong Luo Hong Luo Xue Xue Xue Xue Weiming Wang |
| author_sort | Yunzhu Wu |
| collection | DOAJ |
| description | Placental maturity grading (PMG) is often utilized for evaluating fetal growth and maternal health. Currently, PMG often relied on the subjective judgment of the clinician, which is time-consuming and tends to incur a wrong estimation due to redundancy and repeatability of the process. The existing methods often focus on designing diverse hand-crafted features or combining deep features and hand-crafted features to learn a hybrid feature with an SVM for grading the placental maturity of ultrasound images. Motivated by the dominated performance of end-to-end convolutional neural networks (CNNs) at diverse medical imaging tasks, we devise a dilated granularity transformer network for learning multi-scale global transformer features for boosting PMG. Our network first devises dilated transformer blocks to learn multi-scale transformer features at each convolutional layer and then integrates these obtained multi-scale transformer features for predicting the final result of PMG. We collect 500 ultrasound images to verify our network, and experimental results show that our network clearly outperforms state-of-the-art methods on PMG. In the future, we will strive to improve the computational complexity and generalization ability of deep neural networks for PMG. |
| first_indexed | 2024-03-12T02:38:32Z |
| format | Article |
| id | doaj.art-aa48c98255da4437989e004fd49988a7 |
| institution | Directory Open Access Journal |
| issn | 2296-424X |
| language | English |
| last_indexed | 2024-03-12T02:38:32Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj.art-aa48c98255da4437989e004fd49988a72023-09-04T09:56:37ZengFrontiers Media S.A.Frontiers in Physics2296-424X2023-09-011110.3389/fphy.2023.12394001239400DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasoundYunzhu Wu0Yunzhu Wu1Yijun Yang2Lei Zhu3Lei Zhu4Zhenyan Han5Hong Luo6Hong Luo7Xue Xue8Xue Xue9Weiming Wang10Department of Ultrasound, West China Second University Hospital, Sichuan University, Chengdu, ChinaKey Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, Chengdu, ChinaThe Hong Kong University of Science and Technology (Guangzhou), Guangzhou, ChinaThe Hong Kong University of Science and Technology (Guangzhou), Guangzhou, ChinaHenan Key Laboratory of Imaging and Intelligent Processing, Zhengzhou, ChinaThe Department of Obstetrics and Gynecology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, ChinaDepartment of Ultrasound, West China Second University Hospital, Sichuan University, Chengdu, ChinaKey Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, Chengdu, ChinaJiangxi Boku Information Technology Co., Ltd., Nanchang, ChinaSmart City and IoT Research Institute, Nanchang Institute of Technology, Nanchang, ChinaHong Kong Metropolitan University, Kowloon, Hong Kong SAR, ChinaPlacental maturity grading (PMG) is often utilized for evaluating fetal growth and maternal health. Currently, PMG often relied on the subjective judgment of the clinician, which is time-consuming and tends to incur a wrong estimation due to redundancy and repeatability of the process. The existing methods often focus on designing diverse hand-crafted features or combining deep features and hand-crafted features to learn a hybrid feature with an SVM for grading the placental maturity of ultrasound images. Motivated by the dominated performance of end-to-end convolutional neural networks (CNNs) at diverse medical imaging tasks, we devise a dilated granularity transformer network for learning multi-scale global transformer features for boosting PMG. Our network first devises dilated transformer blocks to learn multi-scale transformer features at each convolutional layer and then integrates these obtained multi-scale transformer features for predicting the final result of PMG. We collect 500 ultrasound images to verify our network, and experimental results show that our network clearly outperforms state-of-the-art methods on PMG. In the future, we will strive to improve the computational complexity and generalization ability of deep neural networks for PMG.https://www.frontiersin.org/articles/10.3389/fphy.2023.1239400/fulltransformerdilated convolutiondeep learning on ultrasound imagesplacental maturity grading frontiersmedical image analysis |
| spellingShingle | Yunzhu Wu Yunzhu Wu Yijun Yang Lei Zhu Lei Zhu Zhenyan Han Hong Luo Hong Luo Xue Xue Xue Xue Weiming Wang DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound Frontiers in Physics transformer dilated convolution deep learning on ultrasound images placental maturity grading frontiers medical image analysis |
| title | DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound |
| title_full | DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound |
| title_fullStr | DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound |
| title_full_unstemmed | DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound |
| title_short | DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound |
| title_sort | dilatedformer dilated granularity transformer network for placental maturity grading in ultrasound |
| topic | transformer dilated convolution deep learning on ultrasound images placental maturity grading frontiers medical image analysis |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2023.1239400/full |
| work_keys_str_mv | AT yunzhuwu dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT yunzhuwu dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT yijunyang dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT leizhu dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT leizhu dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT zhenyanhan dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT hongluo dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT hongluo dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT xuexue dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT xuexue dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound AT weimingwang dilatedformerdilatedgranularitytransformernetworkforplacentalmaturitygradinginultrasound |