Your browser doesn't support javascript.
loading
Deep learning-based segmentation for high-dose-rate brachytherapy in cervical cancer using 3D Prompt-ResUNet.
Xue, Xian; Sun, Lining; Liang, Dazhu; Zhu, Jingyang; Liu, Lele; Sun, Quanfu; Liu, Hefeng; Gao, Jianwei; Fu, Xiaosha; Ding, Jingjing; Dai, Xiangkun; Tao, Laiyuan; Cheng, Jinsheng; Li, Tengxiang; Zhou, Fugen.
Afiliación
  • Xue X; National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention, No.2 Xinkang Street, Beijing, 100088, CHINA.
  • Sun L; Radiation oncology, Fudan University Shanghai Cancer Center, Dongan Street No.270, Xuhui District, Shanghai, 200032, CHINA.
  • Liang D; Digital Health China Technologies Co., LTD, Floor 11-12, Future Science and Technology Building, No.2 Summer Palace Road, Haidian District, Beijing, 100080, CHINA.
  • Zhu J; Zhongcheng cancer hospital, Huaxiang Gaolizhuang Street No.615,Fengtai District, Beijing, 100160, CHINA.
  • Liu L; Radiation oncology, The First Affiliated Hospital of Zhengzhou University, Building east road No.1, Wulibao street,, Zhengzhou, Henan, 450000, CHINA.
  • Sun Q; National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention, No.2 Xinkang Street, Beijing, 100088, CHINA.
  • Liu H; Digital Health China Technologies Co., LTD, Floor 11-12, Future Science and Technology Building, No.2 Summer Palace Road, Haidian District, Beijing, 100080, CHINA.
  • Gao J; Digital Health China Technologies Co., LTD, Floor 11-12, Future Science and Technology Building, No.2 Summer Palace Road, Haidian District, Beijing, 100080, CHINA.
  • Fu X; Sheffield Hallam University, City Campus, Howard Street, Sheffield, S1 1WB, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND.
  • Ding J; Chinese PLA General Hospital, Fuxing Road No.28, Wanshou Road Street, Haidian District, Beijing, 100853, CHINA.
  • Dai X; Chinese PLA General Hospital, Fuxing Road No.28, Wanshou Road Street, Haidian District, Beijing, 100853, CHINA.
  • Tao L; Digital Health China Technologies Co., LTD, Floor 11-12, Future Science and Technology Building, No.2 Summer Palace Road, Haidian District, Beijing, 100080, CHINA.
  • Cheng J; National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention, No.2 Xinkang Street, Beijing, 100088, CHINA.
  • Li T; School of Nuclear Science and Technology, University of South China, No.28 Changsheng West Road, Hyang, Hunan, 421001, CHINA.
  • Zhou F; Aero-space Information Engineering, Beihang University, Xueyuan Road No.37, Haidian District,, Beijing, 100191, CHINA.
Phys Med Biol ; 2024 Sep 13.
Article en En | MEDLINE | ID: mdl-39270708
ABSTRACT

OBJECTIVE:

To develop and evaluate a 3D Prompt-ResUNet module that utilized the prompt-based model combined with 3D nnUNet for rapid and consistent autosegmentation of high-risk clinical target volume and organ at risk in high-dose-rate brachytherapy for cervical cancer patients. Approach. We used 73 computed tomography (CT) and 62 magnetic resonance imaging (MRI) scans from 135 (103 for training, 16 for validation, and 16 for testing) cervical cancer patients across two hospitals for HRCTV and OAR segmentation. A novel comparison of the deep learning neural networks 3D Prompt-ResUNet, nnUNet, and SAM-Med3D was applied for the segmentation. Evaluation was conducted in two parts geometric and clinical assessments. Quantitative metrics included the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95%), Jaccard index (JI), and Matthews correlation coefficient (MCC). Clinical evaluation involved interobserver comparison, 4-grade expert scoring, and a double-blinded Turing test. Main results. The Prompt-ResUNet model performed most similarly to experienced radiation oncologists, outperforming less experienced ones. During testing, the DSC, HD95% (mm), JI, and MCC value (mean ± SD) for HRCTV were 0.92±0.03, 2.91 ± 0.69, 0.85± 0.04, and 0.92 ± 0.02, respectively. For the bladder, these values were 0.93 ± 0.05, 3.07 ± 1.05, 0.87 ± 0.08, and 0.93 ± 0.05, respectively. For the rectum, they were 0.87 ± 0.03, 3.54 ± 1.46, 0.78 ± 0.05, and 0.87 ± 0.03, respectively. For the sigmoid, they were 0.76 ± 0.11, 7.54 ± 5.54, 0.63 ± 0.14, and 0.78 ± 0.09, respectively. The Prompt-ResUNet achieved a clinical viability score of at least 2 in all evaluation cases (100%) for both HRCTV and bladder and exceeded the 30% positive rate benchmark for all evaluated structures in the Turing test. Significance. The Prompt-ResUNet architecture demonstrated high consistency with ground truth (GT) in autosegmentation of HRCTV and OARs, reducing interobserver variability and shortening treatment times. .
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Phys Med Biol Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Phys Med Biol Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido