Prostate Cancer Risk Stratification in NRG Oncology Phase III Randomized Trials Using Multimodal Deep Learning With Digital Histopathology

被引:1
作者
Tward, Jonathan David [1 ]
Huang, Huei-Chung [2 ]
Esteva, Andre [2 ]
Mohamad, Osama [3 ]
van der Wal, Douwe [2 ]
Simko, Jeffry P. [4 ]
DeVries, Sandy [5 ]
Zhang, Jingbin [2 ]
Joun, Songwan [2 ]
Showalter, Timothy N. [2 ,6 ]
Schaeffer, Edward M. [7 ]
Morgan, Todd M. [8 ]
Monson, Jedidiah M. [9 ]
Wallace, James A. [10 ]
Bahary, Jean-Paul [11 ]
Sandler, Howard M. [12 ]
Spratt, Daniel E. [13 ]
Rodgers, Joseph P. [14 ]
Feng, Felix Y. [3 ]
Tran, Phuoc T. [15 ]
机构
[1] Univ Utah, Dept Radiat Oncol, Salt Lake City, UT 84112 USA
[2] Artera Inc, Los Altos, CA USA
[3] Univ Calif San Francisco, Dept Radiat Oncol, San Francisco, CA USA
[4] Univ Calif San Francisco, Dept Urol, San Francisco, CA USA
[5] NRG Oncol Biospecimen Bank, San Francisco, CA USA
[6] Univ Virginia, Dept Radiat Oncol, Sch Med, Charlottesville, VA USA
[7] Northwestern Univ, Dept Urol, Evanston, IL USA
[8] Univ Michigan, Div Urol Oncol, Ctr Comprehens Canc, Ann Arbor, MI USA
[9] St Agnes Med Ctr, Dept Radiat Oncol, Fresno, CA USA
[10] Ingalls Mem Hosp, Harvey, IL USA
[11] CHUM, Dept Radiat Oncol, Montreal, PQ, Canada
[12] Cedars Sinai Med Ctr, Dept Radiat Oncol, Los Angeles, CA USA
[13] Case Western Reserve Univ, Univ Hosp Seidman Canc Ctr, Dept Radiat Oncol, Cleveland, OH USA
[14] Amer Coll Radiol, NRG Oncol Stat & Data Management Ctr, Philadelphia, PA USA
[15] Univ Maryland, Dept Radiat Oncol, Baltimore, MD USA
关键词
ANDROGEN SUPPRESSION; GENOMIC CLASSIFIER; RADIATION-THERAPY; RADIOTHERAPY; METASTASIS; SCORE; CHEMOTHERAPY; DEPRIVATION; PREDICTOR; DURATION;
D O I
10.1200/PO.24.00145
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
PURPOSE Current clinical risk stratification methods for localized prostate cancer are suboptimal, leading to over- and undertreatment. Recently, machine learning approaches using digital histopathology have shown superior prognostic ability in phase III trials. This study aims to develop a clinically usable risk grouping system using multimodal artificial intelligence (MMAI) models that outperform current National Comprehensive Cancer Network (NCCN) risk groups. MATERIALS AND METHODS The cohort comprised 9,787 patients with localized prostate cancer from eight NRG Oncology randomized phase III trials, treated with radiation therapy, androgen deprivation therapy, and/or chemotherapy. Locked MMAI models, which used digital histopathology images and clinical data, were applied to each patient. Expert consensus on cut points defined low-, intermediate-, and high-risk groups on the basis of 10-year distant metastasis rates of 3% and 10%, respectively. The MMAI's reclassification and prognostic performance were compared with the three-tier NCCN risk groups. RESULTS The median follow-up for censored patients was 7.9 years. According to NCCN risk categories, 30.4% of patients were low-risk, 25.5% intermediate-risk, and 44.1% high-risk. The MMAI risk classification identified 43.5% of patients as low-risk, 34.6% as intermediate-risk, and 21.8% as high-risk. MMAI reclassified 1,039 (42.0%) patients initially categorized by NCCN. Despite the MMAI low-risk group being larger than the NCCN low-risk group, the 10-year metastasis risks were comparable: 1.7% (95% CI, 0.2 to 3.2) for NCCN and 3.2% (95% CI, 1.7 to 4.7) for MMAI. The overall 10-year metastasis risk for NCCN high-risk patients was 16.6%, with MMAI further stratifying this group into low-, intermediate-, and high-risk, showing metastasis rates of 3.4%, 8.2%, and 26.3%, respectively. CONCLUSION The MMAI risk grouping system expands the population of men identified as having low metastatic risk and accurately pinpoints a high-risk subset with elevated metastasis rates. This approach aims to prevent both overtreatment and undertreatment in localized prostate cancer, facilitating shared decision making.
引用
收藏
页数:11
相关论文
共 30 条
  • [1] D'Amico A.V., Whittington R., Malkowicz S.B., Et al., Biochemical outcome after radical prostatectomy, external beam radiation therapy, or interstitial radiation therapy for clinically localized prostate cancer, JAMA, 280, pp. 969-974, (1998)
  • [2] Klein E.A., Haddad Z., Yousefi K., Et al., Decipher genomic classifier measured on prostate biopsy predicts metastasis risk, Urology, 90, pp. 148-152, (2016)
  • [3] Tward J.D., Schlomm T., Bardot S., Et al., Personalizing localized prostate cancer: Validation of a combined clinical cell-cycle risk (CCR) score threshold for prognosticating benefit from multimodality therapy, Clin Genitourin Cancer, 19, pp. 296e3-304e3, (2021)
  • [4] Dess R.T., Suresh K., Zelefsky M.J., Et al., Development and validation of a clinical prognostic stage group system for nonmetastatic prostate cancer using disease-specific mortality results from the International staging Collaboration for cancer of the prostate, JAMA Oncol, 6, pp. 1912-1920, (2020)
  • [5] Cooperberg M.R., Pasta D.J., Elkin E.P., Et al., The University of California, San Francisco cancer of the prostate risk assessment score: A straightforward and reliable preoperative predictor of disease recurrence after radical prostatectomy, J Urol, 173, pp. 1938-1942, (2005)
  • [6] NCCN Clinical Practice Guidelines in Oncology—Prostate Cancer, (2023)
  • [7] Esteva A., Feng J., van der Wal D., Et al., Prostate cancer therapy personalization via multimodal deep learning on randomized phase III clinical trials, NPJ Digital Med, 5, 71, (2022)
  • [8] Lawton C.A.F., Lin X., Hanks G.E., Et al., Duration of androgen deprivation in locally advanced prostate cancer: Long-term update of NRG oncology RTOG 9202, Int J Radiat Oncol Biol Phys, 98, pp. 296-303, (2017)
  • [9] Jones C.U., Pugh S.L., Sandler H.M., Et al., Adding short-term androgen deprivation therapy to radiation therapy in men with localized prostate cancer: Long-term update of the NRG/RTOG 9408 randomized clinical trial, Int J Radiat Oncol Biol Phys, 112, pp. 294-303, (2022)
  • [10] Roach M., Moughan J., Lawton C.A.F., Et al., Sequence of hormonal therapy and radiotherapy field size in unfavourable, localised prostate cancer (NRG/RTOG 9413): Long-term results of a randomised, phase 3 trial, Lancet Oncol, 19, pp. 1504-1515, (2018)