Fully automated volumetric assessment of tumor burden using artificial intelligence on 68Ga-PSMA-11 PET predicts survival after 177Lu-PSMA therapy in metastatic Castration-resistant prostate cancer

Shiming Zang; Qingle Meng; Xiaoyuan Li; Tiantian Guo; Lele Zhang; Zhenyu Zhao; Fei Yu; Pengjun Zhang; Wenyu Wu; Yudan Ni; Yuhang Shi; Guoqiang Shao; Youdan Feng; Lingzhi Hu; Ruipeng Jia; A. Cahid Civelek; Hongqian Guo; Feng Wang

doi:10.1007/s00259-025-07628-x

Fully automated volumetric assessment of tumor burden using artificial intelligence on ⁶⁸Ga-PSMA-11 PET predicts survival after ¹⁷⁷Lu-PSMA therapy in metastatic Castration-resistant prostate cancer

Shiming Zang
, Qingle Meng
, Xiaoyuan Li
, Tiantian Guo
, Lele Zhang
, Zhenyu Zhao
, Fei Yu
, Pengjun Zhang
, Wenyu Wu
, Yudan Ni
, Yuhang Shi
, Guoqiang Shao
, Youdan Feng
, Lingzhi Hu
, Ruipeng Jia
, A. Cahid Civelek
, Hongqian Guo
, Feng Wang

School of Medicine

Research output: Contribution to journal › Article › peer-review

Abstract

Purpose: Despite the rapid development of artificial intelligence (AI)-powered automated segmentation tools for PET/CT imaging, their prognostic value in predicting survival outcomes remains inadequately assessed. Our objective was to explore the prognostic significance of tumor burden quantification derived from PSMA PET/CT using AI for metastatic castration-resistant prostate cancer (mCRPC) patients receiving Lutetium-177 (¹⁷⁷Lu) PSMA therapy. Methods: A retrospective cohort of 107 consecutive patients with mCRPC treated with ¹⁷⁷Lu-PSMA therapy were analyzed. Utilizing a deep learning algorithm, PSMA-positive lesions were automatically delineated on baseline 68Ga-PSMA-11 PET/CT scans. Key metrics were derived from the segmented lesions: total tumor volume (PSMA_TV), total tumor load (PSMA_TU = PSMA_TV × SUV_mean), and total tumor quotient (PSMA_TQ = PSMA_TV / SUV_mean). A prognostic nomogram was developed through Cox regression analysis, incorporating LASSO regularization for variable selection. Results: Univariate analysis revealed that higher PSMA_TV (HR 1.26), PSMA_TU (HR 1.18), and PSMA_TQ (HR 1.29) were significantly associated with shorter overall survival (OS). A prognostic nomogram that integrated PSMA_TQ alongside chemotherapy history, hemoglobin levels, alkaline phosphatase, and prostate-specific antigen demonstrated a bootstrap-corrected C-index of 0.71 (95% CI 0.64–0.78). Risk stratification using the nomogram showed significantly prolonged OS in low-risk vs. high-risk groups (median OS 30.9 vs. 7.9 months; HR 0.25, 95% CI 0.13–0.45, P < 0.001). The retrospective design is a study limitation. Conclusion: AI-based volumetric analysis of tumor burden on PSMA PET has prognostic significance for survival in ¹⁷⁷Lu-PSMA-treated mCRPC patients. The nomogram integrating PSMA_TQ with clinical factors might help in personalized risk stratification, facilitating AI-aided therapeutic decision-making.

Original language	English (US)
Pages (from-to)	1913-1926
Number of pages	14
Journal	European Journal of Nuclear Medicine and Molecular Imaging
Volume	53
Issue number	3
DOIs	https://doi.org/10.1007/s00259-025-07628-x
State	Published - Feb 2026

Keywords

Artificial intelligence
Lu-PSMA therapy
Metastatic castration-resistant prostate cancer
PSMA PET/CT
Tumor volume

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

Access to Document

10.1007/s00259-025-07628-x

Cite this

Zang, S., Meng, Q., Li, X., Guo, T., Zhang, L., Zhao, Z., Yu, F., Zhang, P., Wu, W., Ni, Y., Shi, Y., Shao, G., Feng, Y., Hu, L., Jia, R., Civelek, A. C., Guo, H., & Wang, F. (2026). Fully automated volumetric assessment of tumor burden using artificial intelligence on ⁶⁸Ga-PSMA-11 PET predicts survival after ¹⁷⁷Lu-PSMA therapy in metastatic Castration-resistant prostate cancer. European Journal of Nuclear Medicine and Molecular Imaging, 53(3), 1913-1926. https://doi.org/10.1007/s00259-025-07628-x

Fully automated volumetric assessment of tumor burden using artificial intelligence on ⁶⁸Ga-PSMA-11 PET predicts survival after ¹⁷⁷Lu-PSMA therapy in metastatic Castration-resistant prostate cancer. / Zang, Shiming; Meng, Qingle; Li, Xiaoyuan et al.
In: European Journal of Nuclear Medicine and Molecular Imaging, Vol. 53, No. 3, 02.2026, p. 1913-1926.

Research output: Contribution to journal › Article › peer-review

Zang, S, Meng, Q, Li, X, Guo, T, Zhang, L, Zhao, Z, Yu, F, Zhang, P, Wu, W, Ni, Y, Shi, Y, Shao, G, Feng, Y, Hu, L, Jia, R, Civelek, AC, Guo, H & Wang, F 2026, 'Fully automated volumetric assessment of tumor burden using artificial intelligence on ⁶⁸Ga-PSMA-11 PET predicts survival after ¹⁷⁷Lu-PSMA therapy in metastatic Castration-resistant prostate cancer', European Journal of Nuclear Medicine and Molecular Imaging, vol. 53, no. 3, pp. 1913-1926. https://doi.org/10.1007/s00259-025-07628-x

@article{6bec31d2b42247f2b45d4768fb208f83,

title = "Fully automated volumetric assessment of tumor burden using artificial intelligence on 68Ga-PSMA-11 PET predicts survival after 177Lu-PSMA therapy in metastatic Castration-resistant prostate cancer",

abstract = "Purpose: Despite the rapid development of artificial intelligence (AI)-powered automated segmentation tools for PET/CT imaging, their prognostic value in predicting survival outcomes remains inadequately assessed. Our objective was to explore the prognostic significance of tumor burden quantification derived from PSMA PET/CT using AI for metastatic castration-resistant prostate cancer (mCRPC) patients receiving Lutetium-177 (¹⁷⁷Lu) PSMA therapy. Methods: A retrospective cohort of 107 consecutive patients with mCRPC treated with ¹⁷⁷Lu-PSMA therapy were analyzed. Utilizing a deep learning algorithm, PSMA-positive lesions were automatically delineated on baseline 68Ga-PSMA-11 PET/CT scans. Key metrics were derived from the segmented lesions: total tumor volume (PSMATV), total tumor load (PSMATU = PSMATV {\texttimes} SUVmean), and total tumor quotient (PSMATQ = PSMATV / SUVmean). A prognostic nomogram was developed through Cox regression analysis, incorporating LASSO regularization for variable selection. Results: Univariate analysis revealed that higher PSMATV (HR 1.26), PSMATU (HR 1.18), and PSMATQ (HR 1.29) were significantly associated with shorter overall survival (OS). A prognostic nomogram that integrated PSMATQ alongside chemotherapy history, hemoglobin levels, alkaline phosphatase, and prostate-specific antigen demonstrated a bootstrap-corrected C-index of 0.71 (95\% CI 0.64{\textendash}0.78). Risk stratification using the nomogram showed significantly prolonged OS in low-risk vs. high-risk groups (median OS 30.9 vs. 7.9 months; HR 0.25, 95\% CI 0.13{\textendash}0.45, P < 0.001). The retrospective design is a study limitation. Conclusion: AI-based volumetric analysis of tumor burden on PSMA PET has prognostic significance for survival in ¹⁷⁷Lu-PSMA-treated mCRPC patients. The nomogram integrating PSMATQ with clinical factors might help in personalized risk stratification, facilitating AI-aided therapeutic decision-making.",

keywords = "Artificial intelligence, Lu-PSMA therapy, Metastatic castration-resistant prostate cancer, PSMA PET/CT, Tumor volume",

author = "Shiming Zang and Qingle Meng and Xiaoyuan Li and Tiantian Guo and Lele Zhang and Zhenyu Zhao and Fei Yu and Pengjun Zhang and Wenyu Wu and Yudan Ni and Yuhang Shi and Guoqiang Shao and Youdan Feng and Lingzhi Hu and Ruipeng Jia and Civelek, \{A. Cahid\} and Hongqian Guo and Feng Wang",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.",

year = "2026",

month = feb,

doi = "10.1007/s00259-025-07628-x",

language = "English (US)",

volume = "53",

pages = "1913--1926",

journal = "European Journal of Nuclear Medicine and Molecular Imaging",

issn = "1619-7070",

publisher = "Springer",

number = "3",

}

TY - JOUR

T1 - Fully automated volumetric assessment of tumor burden using artificial intelligence on 68Ga-PSMA-11 PET predicts survival after 177Lu-PSMA therapy in metastatic Castration-resistant prostate cancer

AU - Zang, Shiming

AU - Meng, Qingle

AU - Li, Xiaoyuan

AU - Guo, Tiantian

AU - Zhang, Lele

AU - Zhao, Zhenyu

AU - Yu, Fei

AU - Zhang, Pengjun

AU - Wu, Wenyu

AU - Ni, Yudan

AU - Shi, Yuhang

AU - Shao, Guoqiang

AU - Feng, Youdan

AU - Hu, Lingzhi

AU - Jia, Ruipeng

AU - Civelek, A. Cahid

AU - Guo, Hongqian

AU - Wang, Feng

N1 - Publisher Copyright: © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

PY - 2026/2

Y1 - 2026/2

N2 - Purpose: Despite the rapid development of artificial intelligence (AI)-powered automated segmentation tools for PET/CT imaging, their prognostic value in predicting survival outcomes remains inadequately assessed. Our objective was to explore the prognostic significance of tumor burden quantification derived from PSMA PET/CT using AI for metastatic castration-resistant prostate cancer (mCRPC) patients receiving Lutetium-177 (¹⁷⁷Lu) PSMA therapy. Methods: A retrospective cohort of 107 consecutive patients with mCRPC treated with ¹⁷⁷Lu-PSMA therapy were analyzed. Utilizing a deep learning algorithm, PSMA-positive lesions were automatically delineated on baseline 68Ga-PSMA-11 PET/CT scans. Key metrics were derived from the segmented lesions: total tumor volume (PSMATV), total tumor load (PSMATU = PSMATV × SUVmean), and total tumor quotient (PSMATQ = PSMATV / SUVmean). A prognostic nomogram was developed through Cox regression analysis, incorporating LASSO regularization for variable selection. Results: Univariate analysis revealed that higher PSMATV (HR 1.26), PSMATU (HR 1.18), and PSMATQ (HR 1.29) were significantly associated with shorter overall survival (OS). A prognostic nomogram that integrated PSMATQ alongside chemotherapy history, hemoglobin levels, alkaline phosphatase, and prostate-specific antigen demonstrated a bootstrap-corrected C-index of 0.71 (95% CI 0.64–0.78). Risk stratification using the nomogram showed significantly prolonged OS in low-risk vs. high-risk groups (median OS 30.9 vs. 7.9 months; HR 0.25, 95% CI 0.13–0.45, P < 0.001). The retrospective design is a study limitation. Conclusion: AI-based volumetric analysis of tumor burden on PSMA PET has prognostic significance for survival in ¹⁷⁷Lu-PSMA-treated mCRPC patients. The nomogram integrating PSMATQ with clinical factors might help in personalized risk stratification, facilitating AI-aided therapeutic decision-making.

AB - Purpose: Despite the rapid development of artificial intelligence (AI)-powered automated segmentation tools for PET/CT imaging, their prognostic value in predicting survival outcomes remains inadequately assessed. Our objective was to explore the prognostic significance of tumor burden quantification derived from PSMA PET/CT using AI for metastatic castration-resistant prostate cancer (mCRPC) patients receiving Lutetium-177 (¹⁷⁷Lu) PSMA therapy. Methods: A retrospective cohort of 107 consecutive patients with mCRPC treated with ¹⁷⁷Lu-PSMA therapy were analyzed. Utilizing a deep learning algorithm, PSMA-positive lesions were automatically delineated on baseline 68Ga-PSMA-11 PET/CT scans. Key metrics were derived from the segmented lesions: total tumor volume (PSMATV), total tumor load (PSMATU = PSMATV × SUVmean), and total tumor quotient (PSMATQ = PSMATV / SUVmean). A prognostic nomogram was developed through Cox regression analysis, incorporating LASSO regularization for variable selection. Results: Univariate analysis revealed that higher PSMATV (HR 1.26), PSMATU (HR 1.18), and PSMATQ (HR 1.29) were significantly associated with shorter overall survival (OS). A prognostic nomogram that integrated PSMATQ alongside chemotherapy history, hemoglobin levels, alkaline phosphatase, and prostate-specific antigen demonstrated a bootstrap-corrected C-index of 0.71 (95% CI 0.64–0.78). Risk stratification using the nomogram showed significantly prolonged OS in low-risk vs. high-risk groups (median OS 30.9 vs. 7.9 months; HR 0.25, 95% CI 0.13–0.45, P < 0.001). The retrospective design is a study limitation. Conclusion: AI-based volumetric analysis of tumor burden on PSMA PET has prognostic significance for survival in ¹⁷⁷Lu-PSMA-treated mCRPC patients. The nomogram integrating PSMATQ with clinical factors might help in personalized risk stratification, facilitating AI-aided therapeutic decision-making.

KW - Artificial intelligence

KW - Lu-PSMA therapy

KW - Metastatic castration-resistant prostate cancer

KW - PSMA PET/CT

KW - Tumor volume

UR - https://www.scopus.com/pages/publications/105019186475

UR - https://www.scopus.com/pages/publications/105019186475#tab=citedBy

U2 - 10.1007/s00259-025-07628-x

DO - 10.1007/s00259-025-07628-x

M3 - Article

C2 - 41111086

AN - SCOPUS:105019186475

SN - 1619-7070

VL - 53

SP - 1913

EP - 1926

JO - European Journal of Nuclear Medicine and Molecular Imaging

JF - European Journal of Nuclear Medicine and Molecular Imaging

IS - 3

ER -