Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915796880457728 |
|---|---|
| author | Bai, Jieyun Zhou, Zihao Tang, Yitong Gan, Jie Liang, Zhuonan Fan, Jianan Mcguire, Lisa B. Clarke, Jillian L. Cai, Weidong Spurway, Jacaueline Tang, Yubo Wang, Shiye Shen, Wenda Yu, Wangwang Li, Yihao Zhang, Philippe Jiang, Weili Li, Yongjie Nasim, Salem Muhsin Ali Binqahal Al Abzhanov, Arsen Saeed, Numan Yaqub, Mohammad Xian, Zunhui Lin, Hongxing Lan, Libin Ramesh, Jayroop Bacher, Valentin Eid, Mark Kalabizadeh, Hoda Rupprecht, Christian Namburete, Ana I. L. Yeung, Pak-Hei Wyburd, Madeleine K. Dinsdale, Nicola K. Serikbey, Assanali Li, Jiankai Chen, Sung-Liang Hu, Zicheng Liu, Nana Deng, Yian Hu, Wei Tan, Cong Zhang, Wenfeng Nhi, Mai Tuyet Koehler, Gregor Stock, Rapheal Maier-Hein, Klaus Elbatel, Marawan Li, Xiaomeng Slimani, Saad Campello, Victor M. Ohene-Botwe, Benard Khobo, Isaac Huang, Yuxin Han, Zhenyan Hou, Hongying Qiu, Di Zheng, Zheng Luo, Gongning Ni, Dong Lu, Yaosheng Lekadir, Karim Li, Shuo |
| author_facet | Bai, Jieyun Zhou, Zihao Tang, Yitong Gan, Jie Liang, Zhuonan Fan, Jianan Mcguire, Lisa B. Clarke, Jillian L. Cai, Weidong Spurway, Jacaueline Tang, Yubo Wang, Shiye Shen, Wenda Yu, Wangwang Li, Yihao Zhang, Philippe Jiang, Weili Li, Yongjie Nasim, Salem Muhsin Ali Binqahal Al Abzhanov, Arsen Saeed, Numan Yaqub, Mohammad Xian, Zunhui Lin, Hongxing Lan, Libin Ramesh, Jayroop Bacher, Valentin Eid, Mark Kalabizadeh, Hoda Rupprecht, Christian Namburete, Ana I. L. Yeung, Pak-Hei Wyburd, Madeleine K. Dinsdale, Nicola K. Serikbey, Assanali Li, Jiankai Chen, Sung-Liang Hu, Zicheng Liu, Nana Deng, Yian Hu, Wei Tan, Cong Zhang, Wenfeng Nhi, Mai Tuyet Koehler, Gregor Stock, Rapheal Maier-Hein, Klaus Elbatel, Marawan Li, Xiaomeng Slimani, Saad Campello, Victor M. Ohene-Botwe, Benard Khobo, Isaac Huang, Yuxin Han, Zhenyan Hou, Hongying Qiu, Di Zheng, Zheng Luo, Gongning Ni, Dong Lu, Yaosheng Lekadir, Karim Li, Shuo |
| contents | A substantial proportion (45\%) of maternal deaths, neonatal deaths, and stillbirths occur during the intrapartum phase, with a particularly high burden in low- and middle-income countries. Intrapartum biometry plays a critical role in monitoring labor progression; however, the routine use of ultrasound in resource-limited settings is hindered by a shortage of trained sonographers. To address this challenge, the Intrapartum Ultrasound Grand Challenge (IUGC), co-hosted with MICCAI 2024, was launched. The IUGC introduces a clinically oriented multi-task automatic measurement framework that integrates standard plane classification, fetal head-pubic symphysis segmentation, and biometry, enabling algorithms to exploit complementary task information for more accurate estimation. Furthermore, the challenge releases the largest multi-center intrapartum ultrasound video dataset to date, comprising 774 videos (68,106 frames) collected from three hospitals, providing a robust foundation for model training and evaluation. In this study, we present a comprehensive overview of the challenge design, review the submissions from eight participating teams, and analyze their methods from five perspectives: preprocessing, data augmentation, learning strategy, model architecture, and post-processing. In addition, we perform a systematic analysis of the benchmark results to identify key bottlenecks, explore potential solutions, and highlight open challenges for future research. Although encouraging performance has been achieved, our findings indicate that the field remains at an early stage, and further in-depth investigation is required before large-scale clinical deployment. All benchmark solutions and the complete dataset have been publicly released to facilitate reproducible research and promote continued advances in automatic intrapartum ultrasound biometry. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12922 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos Bai, Jieyun Zhou, Zihao Tang, Yitong Gan, Jie Liang, Zhuonan Fan, Jianan Mcguire, Lisa B. Clarke, Jillian L. Cai, Weidong Spurway, Jacaueline Tang, Yubo Wang, Shiye Shen, Wenda Yu, Wangwang Li, Yihao Zhang, Philippe Jiang, Weili Li, Yongjie Nasim, Salem Muhsin Ali Binqahal Al Abzhanov, Arsen Saeed, Numan Yaqub, Mohammad Xian, Zunhui Lin, Hongxing Lan, Libin Ramesh, Jayroop Bacher, Valentin Eid, Mark Kalabizadeh, Hoda Rupprecht, Christian Namburete, Ana I. L. Yeung, Pak-Hei Wyburd, Madeleine K. Dinsdale, Nicola K. Serikbey, Assanali Li, Jiankai Chen, Sung-Liang Hu, Zicheng Liu, Nana Deng, Yian Hu, Wei Tan, Cong Zhang, Wenfeng Nhi, Mai Tuyet Koehler, Gregor Stock, Rapheal Maier-Hein, Klaus Elbatel, Marawan Li, Xiaomeng Slimani, Saad Campello, Victor M. Ohene-Botwe, Benard Khobo, Isaac Huang, Yuxin Han, Zhenyan Hou, Hongying Qiu, Di Zheng, Zheng Luo, Gongning Ni, Dong Lu, Yaosheng Lekadir, Karim Li, Shuo Computer Vision and Pattern Recognition A substantial proportion (45\%) of maternal deaths, neonatal deaths, and stillbirths occur during the intrapartum phase, with a particularly high burden in low- and middle-income countries. Intrapartum biometry plays a critical role in monitoring labor progression; however, the routine use of ultrasound in resource-limited settings is hindered by a shortage of trained sonographers. To address this challenge, the Intrapartum Ultrasound Grand Challenge (IUGC), co-hosted with MICCAI 2024, was launched. The IUGC introduces a clinically oriented multi-task automatic measurement framework that integrates standard plane classification, fetal head-pubic symphysis segmentation, and biometry, enabling algorithms to exploit complementary task information for more accurate estimation. Furthermore, the challenge releases the largest multi-center intrapartum ultrasound video dataset to date, comprising 774 videos (68,106 frames) collected from three hospitals, providing a robust foundation for model training and evaluation. In this study, we present a comprehensive overview of the challenge design, review the submissions from eight participating teams, and analyze their methods from five perspectives: preprocessing, data augmentation, learning strategy, model architecture, and post-processing. In addition, we perform a systematic analysis of the benchmark results to identify key bottlenecks, explore potential solutions, and highlight open challenges for future research. Although encouraging performance has been achieved, our findings indicate that the field remains at an early stage, and further in-depth investigation is required before large-scale clinical deployment. All benchmark solutions and the complete dataset have been publicly released to facilitate reproducible research and promote continued advances in automatic intrapartum ultrasound biometry. |
| title | Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.12922 |