Top

Insights into Imaging

Published in:

Open Access 01-12-2023 | Metastasis | Original Article

MRI feature-based radiomics models to predict treatment outcome after stereotactic body radiotherapy for spinal metastases

Authors: Yongye Chen, Siyuan Qin, Weili Zhao, Qizheng Wang, Ke Liu, Peijin Xin, Huishu Yuan, Hongqing Zhuang, Ning Lang

Published in: Insights into Imaging | Issue 1/2023

Abstract

Objective

This study aimed to extract radiomics features from MRI using machine learning (ML) algorithms and integrate them with clinical features to build response prediction models for patients with spinal metastases undergoing stereotactic body radiotherapy (SBRT).

Methods

Patients with spinal metastases who were treated using SBRT at our hospital between July 2018 and April 2023 were recruited. We assessed their response to treatment using the revised Response Evaluation Criteria in Solid Tumors (version 1.1). The lesions were categorized into progressive disease (PD) and non-PD groups. Radiomics features were extracted from T1-weighted image (T1WI), T2-weighted image (T2WI), and fat-suppression T2WI sequences. Feature selection involved intraclass correlation coefficients, minimal-redundancy-maximal-relevance, and least absolute shrinkage and selection operator methods. Thirteen ML algorithms were employed to construct the radiomics prediction models. Clinical, conventional imaging, and radiomics features were integrated to develop combined models. Model performance was evaluated using receiver operating characteristic (ROC) curve analysis, and the clinical value was assessed using decision curve analysis.

Results

We included 194 patients with 142 (73.2%) lesions in the non-PD group and 52 (26.8%) in the PD group. Each region of interest generated 2264 features. The clinical model exhibited a moderate predictive value (area under the ROC curve, AUC = 0.733), while the radiomics models demonstrated better performance (AUC = 0.745–0.825). The combined model achieved the best performance (AUC = 0.828).

Conclusion

The MRI-based radiomics models exhibited valuable predictive capability for treatment outcomes in patients with spinal metastases undergoing SBRT.

Critical relevance statement

Radiomics prediction models have the potential to contribute to clinical decision-making and improve the prognosis of patients with spinal metastases undergoing SBRT.

Key points

• Stereotactic body radiotherapy effectively delivers high doses of radiation to treat spinal metastases.

• Accurate prediction of treatment outcomes has crucial clinical significance.

• MRI-based radiomics models demonstrated good performance to predict treatment outcomes.

Graphical Abstract

Coleman RE, Croucher PI, Padhani AR et al (2020) Bone metastases. Nat Rev Dis Primers 6:83CrossRefPubMed

Allemani C, Matsuda T, Di Carlo V et al (2018) Global surveillance of trends in cancer survival 2000–14 (CONCORD-3): analysis of individual records for 37 513 025 patients diagnosed with one of 18 cancers from 322 population-based registries in 71 countries. Lancet 391:1023–1075CrossRefPubMedPubMedCentral

Glicksman RM, Tjong MC, Neves-Junior WFP et al (2020) Stereotactic ablative radiotherapy for the management of spinal metastases: a review. JAMA Oncol 6:567–577CrossRefPubMed

Thibault I, Chang EL, Sheehan J et al (2015) Response assessment after stereotactic body radiotherapy for spinal metastasis: a report from the SPIne response assessment in Neuro-Oncology (SPINO) group. Lancet Oncol 16:e595–603CrossRefPubMed

Kollar L, Rengan R (2014) Stereotactic body radiotherapy. Semin Oncol 41:776–789CrossRefPubMed

Kowalchuk RO, Waters MR, Richardson KM et al (2020) Stereotactic radiosurgery for the treatment of bulky spine metastases. J Neurooncol 148:381–388CrossRefPubMed

Husain ZA, Sahgal A, De Salles A et al (2017) Stereotactic body radiotherapy for de novo spinal metastases: systematic review. J Neurosurg Spine 27:295–302CrossRefPubMed

Sahgal A, Larson DA, Chang EL (2008) Stereotactic body radiosurgery for spinal metastases: a critical review. Int J Radiat Oncol Biol Phys 71:652–665CrossRefPubMed

Sahgal A, Bilsky M, Chang EL et al (2011) Stereotactic body radiotherapy for spinal metastases: current status, with a focus on its application in the postoperative patient. J Neurosurg Spine 14:151–166CrossRefPubMed

10.

Zeng KL, Sahgal A, Tseng CL et al (2021) Prognostic factors associated with surviving less than 3 months vs greater than 3 years specific to spine stereotactic body radiotherapy and late adverse events. Neurosurgery 88:971–979CrossRefPubMedPubMedCentral

11.

Zeng KL, Sahgal A, Husain ZA et al (2021) Local control and patterns of failure for “Radioresistant” spinal metastases following stereotactic body radiotherapy compared to a “Radiosensitive” reference. J Neurooncol 152:173–182CrossRefPubMed

12.

Park HJ, Kim HJ, Won JH, Lee SC, Chang AR (2015) Stereotactic body radiotherapy (SBRT) for spinal metastases: who will benefit the most from SBRT? Technol Cancer Res Treat 14:159–167CrossRefPubMed

13.

Chao ST, Koyfman SA, Woody N et al (2012) Recursive partitioning analysis index is predictive for overall survival in patients undergoing spine stereotactic body radiation therapy for spinal metastases. Int J Radiat Oncol Biol Phys 82:1738–1743CrossRefPubMed

14.

Prins FM, van der Velden JM, Gerlich AS et al (2017) Superior target delineation for stereotactic body radiotherapy of bone metastases from renal cell carcinoma on MRI compared to CT. Ann Palliat Med 6:S147–s154CrossRefPubMed

15.

Avanzo M, Wei L, Stancanello J et al (2020) Machine and deep learning methods for radiomics. Med Phys 47:e185–e202CrossRefPubMed

16.

Cox BW, Spratt DE, Lovelock M et al (2012) International Spine Radiosurgery Consortium consensus guidelines for target volume definition in spinal stereotactic radiosurgery. Int J Radiat Oncol Biol Phys 83:e597–605CrossRefPubMed

17.

Eisenhauer EA, Therasse P, Bogaerts J et al (2009) New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 45:228–247CrossRefPubMed

18.

Karcioglu O, Topacoglu H, Dikme O, Dikme O (2018) A systematic review of the pain scales in adults: which to use? Am J Emerg Med 36:707–714CrossRefPubMed

19.

Puvanesarajah V, Lo SL, Aygun N et al (2015) Prognostic factors associated with pain palliation after spine stereotactic body radiation therapy. J Neurosurg Spine 23:620–629CrossRefPubMedPubMedCentral

20.

Fisher CG, DiPaola CP, Ryken TC et al (2010) A novel classification system for spinal instability in neoplastic disease: an evidence-based approach and expert consensus from the Spine Oncology Study Group. Spine (Phila Pa 1976) 35:E1221–1229CrossRefPubMed

21.

Bilsky MH, Laufer I, Fourney DR et al (2010) Reliability analysis of the epidural spinal cord compression scale. J Neurosurg Spine 13:324–328CrossRefPubMed

22.

Zwanenburg A, Leger S, Vallières M, Lck SJR, Oncology (2016) Image biomarker standardisation initiative

23.

Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27:1226–1238CrossRefPubMed

24.

Tibshirani R (1996) Regression Shrinkage and Selection Via the Lasso. J R Stat Soc B (Methodological) 58:267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x

25.

Tree AC, Khoo VS, Eeles RA et al (2013) Stereotactic body radiotherapy for oligometastases. Lancet Oncol 14:e28–37CrossRefPubMed

26.

Luksanapruksa P, Buchowski JM, Hotchkiss W, Tongsai S, Wilartratsami S, Chotivichit A (2017) Prognostic factors in patients with spinal metastasis: a systematic review and meta-analysis. Spine J 17:689–708CrossRefPubMed

27.

Jabbari S, Gerszten PC, Ruschin M, Larson DA, Lo SS, Sahgal A (2016) Stereotactic body radiotherapy for spinal metastases: Practice Guidelines, Outcomes, and Risks. Cancer J 22:280–289CrossRefPubMed

28.

Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefPubMed

29.

Mayerhoefer ME, Materka A, Langs G et al (2020) Introduction to Radiomics. J Nucl Med 61:488–495CrossRefPubMedPubMedCentral

30.

Uribe CF, Mathotaarachchi S, Gaudet V et al (2019) Machine learning in nuclear medicine: Part 1-Introduction. J Nucl Med 60:451–458CrossRefPubMed

31.

Rasmussen CE, Williams C (2006) Gaussian Process for Machine Learning

32.

Solberg HE (1978) Discriminant analysis. CRC Crit Rev Clin Lab Sci 9:209–242CrossRefPubMed

33.

Yamada Y, Katsoulakis E, Laufer I et al (2017) The impact of histology and delivered dose on local control of spinal metastases treated with stereotactic radiosurgery. Neurosurg Focus 42:E6CrossRefPubMedPubMedCentral

34.

Wakabayashi K, Koide Y, Aoyama T et al (2021) A predictive model for pain response following radiotherapy for treatment of spinal metastases. Sci Rep 11:12908CrossRefPubMedPubMedCentral

Title: MRI feature-based radiomics models to predict treatment outcome after stereotactic body radiotherapy for spinal metastases
Authors: Yongye Chen
Siyuan Qin
Weili Zhao
Qizheng Wang
Ke Liu
Peijin Xin
Huishu Yuan
Hongqing Zhuang
Ning Lang
Publication date: 01-12-2023
Publisher: Springer Vienna
Keywords: Metastasis
Radiotherapy
Published in: Insights into Imaging / Issue 1/2023
Electronic ISSN: 1869-4101
DOI: https://doi.org/10.1186/s13244-023-01523-5

Keynote webinar | Spotlight on medication adherence

Springer Medicine

MRI feature-based radiomics models to predict treatment outcome after stereotactic body radiotherapy for spinal metastases

Abstract

Objective

Methods

Results

Conclusion

Critical relevance statement

Key points

Graphical Abstract

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objective

Methods

Results

Conclusion

Critical relevance statement

Key points

Graphical Abstract

Please log in to get access to this content

Other articles of this Issue 1/2023

Dual-energy CT virtual non-calcium: an accurate method for detection of knee osteoarthritis-related edema-like marrow signal intensity

Generalizable transfer learning of automated tumor segmentation from cervical cancers toward a universal model for uterine malignancies in diffusion-weighted MRI

An active learning approach to train a deep learning algorithm for tumor segmentation from brain MR images

A systematic review and meta-analysis of CT and MRI radiomics in ovarian cancer: methodological issues and clinical utility

Radiomics-based analysis of CT imaging for the preoperative prediction of invasiveness in pure ground-glass nodule lung adenocarcinomas

Does clinical decision support system promote expert consensus for appropriate imaging referrals? Chest–abdominal–pelvis CT as a case study