Skip to main content

Main menu

  • Home
  • Current Issue
  • Archive
  • Info for
    • Authors
    • Editorial Policies
    • Subscribers
    • Advertisers
    • Editorial Board
    • Special Issues 2025
  • Journal Metrics
  • Other Publications
    • In Vivo
    • Cancer Genomics & Proteomics
    • Cancer Diagnosis & Prognosis
  • More
    • IIAR
    • Conferences
    • 2008 Nobel Laureates
  • About Us
    • General Policy
    • Contact
  • Other Publications
    • Anticancer Research
    • In Vivo
    • Cancer Genomics & Proteomics

User menu

  • Register
  • Subscribe
  • My alerts
  • Log in
  • My Cart

Search

  • Advanced search
Anticancer Research
  • Other Publications
    • Anticancer Research
    • In Vivo
    • Cancer Genomics & Proteomics
  • Register
  • Subscribe
  • My alerts
  • Log in
  • My Cart
Anticancer Research

Advanced Search

  • Home
  • Current Issue
  • Archive
  • Info for
    • Authors
    • Editorial Policies
    • Subscribers
    • Advertisers
    • Editorial Board
    • Special Issues 2025
  • Journal Metrics
  • Other Publications
    • In Vivo
    • Cancer Genomics & Proteomics
    • Cancer Diagnosis & Prognosis
  • More
    • IIAR
    • Conferences
    • 2008 Nobel Laureates
  • About Us
    • General Policy
    • Contact
  • Visit us on Facebook
  • Follow us on Linkedin
Research ArticleClinical Studies
Open Access

Combination of Clinical Factors and Radiomics Can Predict Local Recurrence and Metastasis After Stereotactic Body Radiotherapy for Non-small Cell Lung Cancer

YUKO ISOYAMA-SHIRAKAWA, TADAMASA YOSHITAKE, KENTA NINOMIYA, KAORI ASAI, KEIJI MATSUMOTO, YOSHIYUKI SHIOYAMA, TAKUMI KODAMA, KOUSEI ISHIGAMI and HIDETAKA ARIMURA
Anticancer Research November 2023, 43 (11) 5003-5013; DOI: https://doi.org/10.21873/anticanres.16699
YUKO ISOYAMA-SHIRAKAWA
1Radiology Informatics and Network, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
2Department of Radiation Oncology, National Kyushu Cancer Center, Fukuoka, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • For correspondence: yiso0422@gmail.com
TADAMASA YOSHITAKE
1Radiology Informatics and Network, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
KENTA NINOMIYA
3Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
4Sanford Burnham Prebys Medical Discovery Institute, La Jolla, CA, U.S.A.;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
KAORI ASAI
5Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
KEIJI MATSUMOTO
1Radiology Informatics and Network, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
YOSHIYUKI SHIOYAMA
6Ion Beam Therapy Center, SAGA-HIMAT Foundation, Saga, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
TAKUMI KODAMA
3Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
KOUSEI ISHIGAMI
5Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
HIDETAKA ARIMURA
7Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, Fukuoka, Japan
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • Article
  • Figures & Data
  • Info & Metrics
  • PDF
Loading

Abstract

Background/Aim: Radiomics, which links radiological image features with patient prognoses, is expected to be applied for the prediction of the clinical outcomes of radiotherapy. We investigated the clinical and radiomic factors associated with recurrence patterns after stereotactic body radiotherapy (SBRT) for non-small cell lung cancer (NSCLC). Patients and Methods: We retrospectively analyzed 125 patients with histologically confirmed NSCLC who underwent SBRT between April 2003 and June 2017 at our institution. A radiomic score was calculated from five radiomics features (histogram and texture features) selected using the LASSO Cox regression model. These features were extracted from the gross tumor volume (GTV) in three-dimensional wavelet decomposition CT images. We used univariate and multivariate analyses to determine the associations between local control (LC) time and metastasis-free survival (MFS), clinical factors (age, sex, performance status, operability, smoking, histology, and tumor diameter), and the radiomic score. Results: With a median follow-up of 37 months, the following 3-year rates were observed: overall survival, 80.9%; progression-free survival, 61.7%; LC, 75.1%, and MFS; 74.5%. In multivariate analysis, histology (squamous cell carcinoma vs. non-squamous cell carcinoma, p=0.0045), tumor diameter (>3 cm vs. ≤3 cm, p=0.039); and radiomic score (>0.043 vs. ≤0.043, p=0.042) were significantly associated with LC, and the radiomic score (>0.304 vs. ≤0.304, p<0.001) was significantly associated with MFS. Conclusion: Histology, tumor diameter, and radiomic score could be significant factors for predicting NSCLC recurrence patterns after SBRT.

Key Words:
  • Radiomics
  • radiomic score
  • prediction
  • recurrence pattern
  • lung cancer
  • SBRT

Lung cancer is the leading cause of death from all malignancies worldwide, with an estimated 2.21 million new lung cancer diagnoses, 11% of all new cancer cases, and an estimated 1.8 million deaths worldwide in 2020 (1). In Japan, approximately 75,000 people died of lung cancer in 2019 (2). Stereotactic body radiotherapy (SBRT) is recommended for the treatment of medically unresectable stage I or stage IIA non-small cell lung cancer (NSCLC) (3). Stereotactic irradiation is a high-precision irradiation method that focuses X-rays from multiple directions on a localized small lesion while maintaining fixation accuracy. This technique was originally developed for brain tumors, but in the late 1990s it was applied to tumors of the trunk; this technique is called stereotactic body radiotherapy (SBRT) and was initiated internationally by Karolinska in 1991 (4) and in Japan in 1994 (5).

Various fractionated irradiation regimens have been reported, including 48 Gy/4 Fr (6), 50-60 Gy/5-6 Fr (7), 60 Gy/8 Fr (8), 45 Gy/3 Fr (9), and 70 Gy/7 Fr (10), and the local control rate of T1 tumors is 85%-97%. The Japan Clinical Oncology Group Study JCOG0403, which examined the use of 48 Gy/4 Fr (11), obtained 3-year and 5-year overall survival rates of 76% and 54% in the operable group and 60% and 43% in the inoperable group, respectively. However, Bryant et al. reported that the long-term survival rate after SBRT was lower than that after lobectomy (12).

Dose escalation studies and drug combinations have been performed to improve patient outcomes. For example, the JCOG1408 study conducted in Japan compared 42 Gy/4 Fr and 55 Gy/4 Fr for 95% of the planning target volume (PTV) (13). In addition, immune checkpoint inhibitors (ICIs) have attracted attention as adjuvant agents. A randomized placebo-controlled phase III trial (KEYNOTE-867) evaluated the safety and efficacy of SBRT with or without MK-3475 in patients with unresected stage I or stage IIA NSCLC.

However, it is unclear which patients should receive increased doses and which patients should receive concomitant medications. The ability to predict recurrence patterns may contribute to the selection of adjuvant therapy. The reported prognostic factors after SBRT include tumor diameter, sex (14), histology (15), and metabolic tumor volume on fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) (16), but the pattern of recurrence has not been adequately predicted. Radiomics is a novel noninvasive, fast, and low-cost approach for solving precision medicine issues (17), and a method of collecting and analyzing large amounts of lesion image data. It is expected that radiomics can be applied to the determination of benign and malignant lesions and to patients’ post-treatment prognoses. In the present study, we used radiomic scores calculated from radiomics analysis to create a prognostic model incorporating radiomics.

Patients and Methods

Patients. This retrospective study was approved by the Institutional Review Board of Kyushu University Hospital (2020-472). A total of 125 patients with histologically confirmed Stage 0-IIA (UICC TNM classification ver. 8) NSCLC who underwent stereotactic lung radiotherapy at our institution between April 1, 2003, and June 30, 2017, were enrolled. Table I summarizes the patient characteristics. All patients underwent a physical examination, chest, and abdominal computed tomography (CT), and brain magnetic resonance imaging (MRI) to determine the clinical staging. Most of the patients also underwent FDG-PET/CT. The clinical stage was determined according to the TNM classification system, 8th edition. ‘Tumor diameter’ was defined as the diameter of the solid part.

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table I.

Patient characteristics (n=125).

SBRT planning and treatments. The SBRT technique has been previously described (18, 19). Respiratory movement of the tumor was evaluated with an X-ray simulator or four-dimensional CT. In the present patient population, when the respiratory tumor movement was ≥1 cm, a breath-holding technique was used to reduce the internal margin (20). The patients were scanned using a planning CT (Mx 8000, Philips Healthcare, Amsterdam, the Netherlands or Aquilion Prime, Canon Medical Systems, Tochigi, Japan) with a tube voltage of 120 kV, an in-plane size of 0.98 mm, and a slice thickness of 2.0 mm without contrast for treatment planning. Treatment planning was performed using slow-scan CT in 90 patients and breath-holding CT in 35 patients.

Three-dimensional conformal radiation therapy (3DCRT) plans with non-coplanar fields were created using a radiation treatment planning (RTP) system (Eclipse, Varian Medical Systems, Palo Alto, CA, USA). The gross tumor volume (GTV) was contoured using a pulmonary window setting (window level −700 HU, window width 2,000 HU) and confirmed by several radiation oncologists. GTV includes ground-glass opacity and the solid part, which are considered tumor components. The clinical target volume (CTV) was the same as that for the GTV. The internal target volume (ITV) was defined based on three-dimensional respiratory movement and/or slow-scan images. The planning target volume (PTV) was created by adding 5 mm to the ITV in all the directions.

In most cases, the beam arrangement consisted of eight coplanar and non-coplanar static ports of 4- to 6-MV X-rays. The median prescribed radiation dose was 48 Gy in four fractions, delivered to the isocenter in 114 patients and 95% of the PTV in the remaining 11 patients. The radiation doses used are shown in Table II. The median biological effective dose (BED) for 95% of the PTV assuming α/β=10 was 88.97 Gy. The linear accelerator used was Clinac-21Ex or TrueBeam STx with a Novalis Radiosurgery system (Varian Medical Systems). The treatment setup was verified using cone-beam CT at each fraction, and adjustments were made for optimal alignment.

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table II.

Radiation dose.

The follow-up intervals were 1 or 2 months for the first 6 months after the completion of SBRT, 3 months for the next 36 months, and 6 months thereafter. Local recurrence was defined as enlargement or recurrence of the irradiated primary tumor. Metastasis was defined as lymph node metastasis or distant metastasis outside the irradiated field. The time to recurrence was determined using the starting date of SBRT.

Radiomic score. Figure 1 presents the overall scheme for the calculation of the radiomic score. We used the MATLAB-based Radiomics tools package (MATLAB 2019a, MathWorks, Natick, MA, USA) (21, 22) to calculate a total of 432 wavelet-based radiomic features from the 54 features of the GTV in the patients’ planning CT images. The 54 original radiomic features consisted of 14 histogram-based features and 40 texture features and are listed in Table III (23). The 432 wavelet-based radiomic features were derived from the 54 original radiomic features on each of the eight 3D wavelet decomposition images (24). We selected the significant features related to local control (LC) and metastasis-free survival (MFS) by performing a LASSO Cox regression (25). The radiomic score was calculated as follows:

Embedded Image

Figure 1.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 1.

The overall scheme for the radiomic score calculation.

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table III.

The 54 original radiomic features (23).

where l is the feature number, m is the number of significant features, βl is the coefficient value of the l-th feature obtained from a Cox proportional hazard model, and Featurel is the value of the l-th significant feature.

Statistical analysis. The clinical factors (sex, age, performance status, operability, maximum tumor diameter, and histology) and the score were evaluated with regard to LC and MFS using the Cox proportional hazards model. Prognostic models for local and metastatic recurrence were constructed and evaluated using the Kaplan–Meier analysis and log-rank test, respectively. All statistical analyses were performed using the R software (ver. 4.1.2: www.R-project.org) and EZR (ver. 1.54) (26).

Results

The median follow-up period for the 125 patients with NSCLC was 37 months. The 3-year overall survival (OS) rate was 80.9%, and the 3-year progression-free survival (PFS) rate was 61.7%. The 3-year LC rate was 75.1%, and the 3-year MFS rate was 74.5% (Figure 2). Twenty-eight patients (22.4%) had local recurrence, 15 (12.0%) had lymph node metastasis, and 21 (16.8%) had distant metastasis (Table IV). An overlap in the recurrence patterns was observed in some cases, as shown in Figure 3.

Figure 2.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 2.

Overall survival (OS) (A), progression-free survival (PFS) (B), local control (LC) (C), and metastasis-free survival (MFS) (D).

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table IV.

Recurrence patterns among the 125 patients with non-small cell lung cancer.

Figure 3.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 3.

Recurrence patterns. Numbers: The number of patients. Local: local recurrence; LN: lymph node recurrence; Distant: distant metastasis.

The five selected radiomic features used to calculate radiomic scores are listed in Table V. The five features that were highly related to LC were GLSZM_LZHGE_LLH, GLSZM_LZHGE_LHL, GLSZM_LZE_LHL, GLRLM_LGRE_LLH, and GLRLM_SRLGE_LLH (radiomic features are presented in Table III). The factors significantly associated with LC in univariate analysis were sex, operability, histology, tumor diameter, and radiomic score (Table VI).

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table V.

Selected radiomic features.

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table VI.

Univariate analysis for local control (LC) and metastasis-free survival (MFS) using the Cox proportional hazard model.

We divided the patients into two groups according to the radiomic score cutoff (0.043) set to the highest sum of sensitivity and specificity from the receiver operating characteristic (ROC) curve. In multivariate analysis, tumor histology [squamous cell carcinoma (SqCC) vs. non-SqCC, p=0.0045], the tumor diameter (>3 cm vs. ≤3 cm, p=0.038), and radiomic score (>0.043 vs. ≤0.043, p=0.042) were significantly associated with LC (Table VII).

View this table:
  • View inline
  • View popup
  • Download powerpoint
Table VII.

Multivariable analysis of clinical factors and radiomic scores for local control (LC) using the Cox proportional hazard model.

Kaplan–Meier curves for the LC rate of pairs of patient groups divided by histology, tumor diameter, and radiomic score are shown in Figure 4. This analysis was limited to 43 patients with SqCC and 37 patients with a tumor diameter >3 cm, who were significantly divided into two groups based on stratification by radiomic score (Figure 5).

Figure 4.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 4.

Kaplan–Meier curves for local control (LC) divided into high-risk and low-risk groups of clinical factors by histology (A), tumor diameter (B), and radiomic score (C).

Figure 5.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 5.

Kaplan–Meier curves for local control (LC) in 43 patients with squamous cell carcinoma (A) and 37 patients with a tumor diameter >3 cm (B) divided by radiomic score.

In univariate analysis, the factors significantly related to MFS were the tumor diameter (>3 cm vs. ≤3 cm, p=0.038) and radiomic score [>cutoff value (0.304) vs. ≤cutoff value, p<0.001] (Table VI). As shown in Table IV, the five features that were highly related to distant recurrence were Hist_Uniformity_LLL, GLSZM_LZE_HHL, GLSZM_LZHGE_LLL, GLSZM_LZE_LLL, and NGTDM_Busyness_LLH. In the multivariate analysis, the radiomic score [>cutoff value (0.304) vs. ≤cutoff value] was significantly associated with MFS, and the tumor diameter was negatively associated with MFS (Table VII).

Kaplan–Meier curves for MFS divided into pairs of groups according to the tumor diameter and radiomic score are shown in Figure 6. When Kaplan–Meier survival curves were calculated for patients with a tumor diameter ≥3 cm divided into two groups according to the radiomic score, the rate of metastatic recurrence was significantly higher in the high-risk group compared to the low-risk group (p<0.0001) (Figure 7).

Figure 6.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 6.

Kaplan–Meier curves for metastasis-free survival (MFS) divided into high- and low-risk groups by tumor diameter (A) and radiomic score (B).

Figure 7.
  • Download figure
  • Open in new tab
  • Download powerpoint
Figure 7.

Kaplan–Meier survival curves calculated for the patients with a tumor diameter >3 cm divided into two groups according to the radiomic score: the rate of metastatic recurrence was significantly higher in the high-risk group compared to the low-risk group (p<0.0001).

Discussion

In this retrospective examination of 125 patients with NSCLC treated with SBRT, the 3-year OS rate was 80.9%, with a median follow-up of 37 months, and the 3-year PFS rate was 61.7%. The 3-year LC rate was 75.1%, and the 3-year MFS rate was 74.5%. This LC rate is not superior to the results of several earlier studies (6-10). Possible reasons for the low LC rate in the present study are (i) the high number of isocenter-prescribed patients (114 of 125) and (ii) the low median BED of 88.97 Gy. Onishi et al. showed that a BED ≥100 Gy was associated with an LC rate ≥90% (27). The patients have been treated with 48 Gy/4 Fr of D95 prescription, with a BED of 105.6 Gy at our institution since 2015 (11 of 125 patients in this study).

Several clinical factors have been examined that may be useful in predicting prognosis after SBRT. Matsuo et al. investigated factors that influenced the clinical outcomes of 101 patients who underwent SBRT and reported the tumor diameter was a significant factor in local progression, disease progression, and overall survival (14). Horner-Rober et al. analyzed 126 patients with early-stage adenocarcinoma or SqCC treated with SBRT, and they identified the histologic subtype as a major independent prognostic factor for LC (p=0.033) (15). In that series, the patients with SqCC showed significantly worse LC compared to patients with adenocarcinoma, but when patients were treated with a total dose in EQD2≥150 Gy, no significant difference in LC for histologic subtypes was detected (15). Our present findings are consistent with these reports, as the multivariate analysis confirmed that the tumor diameter and histology were significantly associated with LC.

The use of combinations of clinical factors with radiomics to improve the prognostic accuracy has been examined. In 2015, Coroller et al. evaluated CT radiomic features for their capability to predict distant metastasis (DM) for 98 and 84 patients with lung adenocarcinoma for the training and test datasets, respectively (28); they performed univariate and multivariate analyses to evaluate the radiomics performance by using the concordance index (CI). Thirty-five radiomic features were found to be prognostic for DM, based on a CI >0.60 and false discovery rate (FDR) <5%. Notably, tumor volume was only moderately prognostic for DM in the discovery cohort (CI=0.55, p-value=2.77×10−5). A radiomic-signature had strong power for predicting DM in the independent validation dataset (CI=0.61, p-value=1.79×10−17). Adding this radiomic-signature to a clinical model resulted in a significant improvement in DM prediction in the validation dataset (p-value=1.56×10−11).

In their 2020 study, Kakino et al. used the radiomics approach with a random survival forest (RSF) to predict DM in patients with NSCLC who underwent SBRT (29). The concordance indices at 3 years of clinical, radiomic, and combined models for DM were 0.59 (CI=0.54-0.79), 0.67 (CI=0.54-0.79), and 0.68 (CI=0.55-0.81), respectively. The combined DM model significantly discriminated the cumulative incidence between the high- and low-risk score groups (p<0.05).

The present study is the first to report a multivariate analysis of clinical factors and radiomic scores to determine whether the radiomic score can be a prognostic factor for SBRT used to treat histologically confirmed NSCLC. The results of our analyses demonstrated that the radiomic score was significantly associated with recurrence of both LC and MFS. It is noteworthy that patients with low radiomic scores had fewer local recurrences, even in a study limited to patients with SqCC or a tumor diameter >3 cm. It is possible that the radiomic score contributes to the selection of patients who require increased doses. Our study also indicates that the histological type is important in local recurrence, but the radiomic score, which can be calculated noninvasively from images, might be useful in cases where a biopsy is not possible or the histology is undetermined.

The radiomic score was strongly correlated with MFS in this study, and this finding is consistent with the report by Kakino et al. (29) that a radiomics approach with an RSF might predict DM but might not have the potential to predict LR. They constructed a prediction model using RSM; however, we proposed a relatively briefly calculated radiomic score as a predictor. Finding a group of patients at high risk of distant metastatic recurrence might lead to better treatment choices.

In the present analysis, we did not include the consolidation tumor ratio (CTR), that is, the ratio of the solid tumor diameter to the total tumor diameter. This is because CTR, which reflects the internal characteristics of the tumor, is thought to correlate strongly with radiomic features. Patients with ground-glass nodules have been reported to have a better prognosis; Noguchi et al. observed that the frequencies of lymph node metastasis and vessel invasion in tumors with a CTR <50% were significantly lower and the survival rate was better than that in the other tumors (30). Onishi et al. reported that SBRT for 84 patients with stage I lung cancer with a lung tumor CTR <50% resulted in high cause-specific survival at 3 years, that is, 98.2%, with few local recurrences, lymph node metastases, or distant metastases (31). Radiomic score is more strongly correlated with DM than with LC, and is a factor that shows different characteristics from CTR.

The gray level size zone matrix (GLSZM) is a texture analysis method that quantifies the frequency related to the size of contiguous regions with the same pixel value. With this analysis method, the large zone high gray level emphasis (LZHGE) is obtained, which quantifies the number of large areas with high pixel values in the GTV. Hist_Uniformity is a histogram analysis method that evaluates the uniformity of pixel values, which can be uniform in consolidation and ground-glass opacity. A radiomic feature contains more information than CTR, which represents the ratio of consolidation within a tumor. In a study by Kakino et al. (29), the two radiomic features of gray level co-occurrence matrix (GLCM), wavelet.LH_glcm_MCC and wavelet.LL_glcm_imc2, were strongly correlated with DM. It remains necessary to identify clinically important features in these analyses and determine their clinical significance.

This study had some limitations. It was a retrospective analysis of a relatively small number of patients treated at a single institution. The treatment-planning CT results were obtained during various breathing phases, such as the slow scan and breath-hold phases, and some GTVs included images from several phases. In addition, because old cases were included in the series, genetic mutations such as those of the EGFR gene were not considered. Another limitation was that the study data were not divided into training and test data. We would like to increase the number of cases and verify the accuracy of the model using test data.

Conclusion

The results of this study indicate that the histology, tumor diameter, and radiomic score could be significant factors in the prediction of recurrence patterns after SBRT.

Acknowledgements

This study was supported by JSPS KAKENHI Grant Number 20K08113.

Footnotes

  • Authors’ Contributions

    YS: Conceptualization, data creation, investigation, and writing – original draft; TY: conceptualization, project administration, writing – review and editing; KN: formal analysis, investigation, software, , writing – review and editing; KA: data creation, writing – review and editing; YS: conceptualization, funding acquisition, writing – review and editing; TK: formal analysis, software, writing – review and editing; KI: conceptualization, supervision, writing – review and editing; HA: conceptualization, methodology, resources, supervision, software, writing – review and editing.

  • Conflicts of Interest

    The Authors have no conflicts of interest to declare in relation to this study.

  • Received September 15, 2023.
  • Revision received October 1, 2023.
  • Accepted October 3, 2023.
  • Copyright © 2023, International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY-NC-ND) 4.0 international license (https://creativecommons.org/licenses/by-nc-nd/4.0).

References

  1. ↵
    1. Sung H,
    2. Ferlay J,
    3. Siegel RL,
    4. Laversanne M,
    5. Soerjomataram I,
    6. Jemal A,
    7. Bray F
    : Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin 71(3): 209-24Po9, 2021. DOI: 10.3322/caac.21660
    OpenUrlCrossRefPubMed
  2. ↵
    1. Cancer Statistics
    . Cancer Information Service, National Cancer Center, Japan (Vital Statistics of Japan, Ministry of Health, Labour and Welfare). Available at: https://ganjoho.jp/reg_stat/statistics/data/dl/en.html [Last accessed on September 30, 2023]
  3. ↵
    1. Tandberg DJ,
    2. Tong BC,
    3. Ackerson BG,
    4. Kelsey CR
    : Surgery versus stereotactic body radiation therapy for stage I non-small cell lung cancer: A comprehensive review. Cancer 124(4): 667-678, 2018. DOI: 10.1002/cncr.31196
    OpenUrlCrossRefPubMed
  4. ↵
    1. Blomgren H,
    2. Lax I,
    3. Goranson H,
    4. Krapelin T,
    5. Nilsson B,
    6. Naslund I,
    7. Svanstrom R,
    8. Tilikidis A
    : Radiosurgery for tumors in the body: Clinical experience using a new method. J Radiosurg 1: 63-74, 1998. DOI: 10.1023/B:JORA.0000010880.40483.c4
    OpenUrlCrossRef
  5. ↵
    1. Uematsu M,
    2. Shioda A,
    3. Tahara K,
    4. Fukui T,
    5. Yamamoto F,
    6. Tsumatori G,
    7. Ozeki Y,
    8. Aoki T,
    9. Watanabe M,
    10. Kusano S
    : Focal, high dose, and fractionated modified stereotactic radiation therapy for lung carcinoma patients. Cancer 82(6): 1062-1070, 1998. DOI: 10.1002/(sici)1097-0142(19980315)82:6<1062::aid-cncr8>3.0.co;2-g
    OpenUrlCrossRefPubMed
  6. ↵
    1. Nagata Y,
    2. Takayama K,
    3. Matsuo Y,
    4. Norihisa Y,
    5. Mizowaki T,
    6. Sakamoto T,
    7. Sakamoto M,
    8. Mitsumori M,
    9. Shibuya K,
    10. Araki N,
    11. Yano S,
    12. Hiraoka M
    : Clinical outcomes of a phase I/II study of 48 Gy of stereotactic body radiotherapy in 4 fractions for primary lung cancer using a stereotactic body frame. Int J Radiat Oncol Biol Phys 63(5): 1427-1431, 2005. DOI: 10.1016/j.ijrobp.2005.05.034
    OpenUrlCrossRefPubMed
  7. ↵
    1. Uematsu M,
    2. Shioda A,
    3. Suda A,
    4. Fukui T,
    5. Ozeki Y,
    6. Hama Y,
    7. Wong JR,
    8. Kusano S
    : Computed tomography-guided frameless stereotactic radiotherapy for stage I non-small cell lung cancer: a 5-year experience. Int J Radiation Oncology Biol Phys 51(3): 666-670, 2001. DOI: 10.1016/s0360-3016(01)01703-5
    OpenUrlCrossRefPubMed
  8. ↵
    1. Onimaru R,
    2. Shirato H,
    3. Shimizu S,
    4. Kitamura K,
    5. Xu B,
    6. Fukumoto S,
    7. Chang TC,
    8. Fujita K,
    9. Oita M,
    10. Miyasaka K,
    11. Nishimura M,
    12. Dosaka-Akita H
    : Tolerance of organs at risk in small-volume, hypofractionated, image-guided radiotherapy for primary and metastatic lung cancers. Int J Radiation Oncology Biol Phys 56(1): 126-135, 2003. DOI: 10.1016/s0360-3016(03)00095-6
    OpenUrlCrossRefPubMed
  9. ↵
    1. Baumann P,
    2. Nyman J,
    3. Hoyer M,
    4. Wennberg B,
    5. Gagliardi G,
    6. Lax I,
    7. Drugge N,
    8. Ekberg L,
    9. Friesland S,
    10. Johansson K,
    11. Lund J,
    12. Morhed E,
    13. Nilsson K,
    14. Levin N,
    15. Paludan M,
    16. Sederholm C,
    17. Traberg A,
    18. Wittgren L,
    19. Lewensohn R
    : Outcome in a prospective Phase II trial of medically inoperable Stage I non-small-cell lung cancer patients treated with stereotactic body radiotherapy. J Clin Oncol 27(20): 3290-3296, 2009. DOI: 10.1200/JCO.2008.21.5681
    OpenUrlAbstract/FREE Full Text
  10. ↵
    1. Xia T,
    2. Li H,
    3. Sun Q,
    4. Wang Y,
    5. Fan N,
    6. Yu Y,
    7. Li P,
    8. Chang JY
    : Promising clinical outcome of stereotactic body radiation therapy for patients with inoperable Stage I/II non-small-cell lung cancer. Int J Radiation Oncology Biol Phys 66(1): 117-125, 2006. DOI: 10.1016/j.ijrobp.2006.04.013
    OpenUrlCrossRefPubMed
  11. ↵
    1. Nagata Y,
    2. Hiraoka M,
    3. Shibata T,
    4. Onishi H,
    5. Kokubo M,
    6. Karasawa K,
    7. Shioyama Y,
    8. Onimaru R,
    9. Kozuka T,
    10. Kunieda E,
    11. Saito T,
    12. Nakagawa K,
    13. Hareyama M,
    14. Takai Y,
    15. Hayakawa K,
    16. Mitsuhashi N,
    17. Ishikura S
    : Prospective trial of stereotactic body radiation therapy for both operable and inoperable T1N0M0 non-small cell lung cancer: Japan Clinical Oncology Group Study JCOG0403. Int J Radiation Oncology Biol Phys 93(5): 989-996, 2015. DOI: 10.1016/j.ijrobp.2015.07.2278
    OpenUrlCrossRefPubMed
  12. ↵
    1. Bryant AK,
    2. Mundt RC,
    3. Sandhu AP,
    4. Urbanic JJ,
    5. Sharabi AB,
    6. Gupta S,
    7. Daly ME,
    8. Murphy JD
    : Stereotactic body radiation therapy versus surgery for early lung cancer among US veterans. Ann Thorac Surg 105(2): 425-431, 2018. DOI: 10.1016/j.athoracsur.2017.07.048
    OpenUrlCrossRefPubMed
  13. ↵
    1. Kimura T,
    2. Nagata Y,
    3. Eba J,
    4. Ozawa S,
    5. Ishikura S,
    6. Shibata T,
    7. Ito Y,
    8. Hiraoka M,
    9. Nishimura Y, Radiation Oncology Study Group of the Japan Clinical Oncology Group
    : A randomized Phase III trial of comparing two dose-fractionations stereotactic body radiotherapy (SBRT) for medically inoperable Stage IA non-small cell lung cancer or small lung lesions clinically diagnosed as primary lung cancer: Japan Clinical Oncology Group Study JCOG1408 (J-SBRT trial). Jpn J Clin Oncol 47(3): 277-281, 2017. DOI: 10.1093/jjco/hyw198
    OpenUrlCrossRefPubMed
  14. ↵
    1. Matsuo Y,
    2. Shibuya K,
    3. Nagata Y,
    4. Takayama K,
    5. Norihisa Y,
    6. Mizowaki T,
    7. Narabayashi M,
    8. Sakanaka K,
    9. Hiraoka M
    : Prognostic factors in stereotactic body radiotherapy for non-small-cell lung cancer. Int J Radiat Oncol Biol Phys 79(4): 1104-1111, 2011. DOI: 10.1016/j.ijrobp.2009.12.022
    OpenUrlCrossRefPubMed
  15. ↵
    1. Hörner-Rieber J,
    2. Bernhardt D,
    3. Dern J,
    4. König L,
    5. Adeberg S,
    6. Paul A,
    7. Heussel CP,
    8. Kappes J,
    9. Hoffmann H,
    10. Herth FJ,
    11. Debus J,
    12. Warth A,
    13. Rieken S
    : Histology of non-small cell lung cancer predicts the response to stereotactic body radiotherapy. Radiother Oncol 125(2): 317-324, 2017. DOI: 10.1016/j.radonc.2017.08.029
    OpenUrlCrossRefPubMed
  16. ↵
    1. Takahashi N,
    2. Yamamoto T,
    3. Matsushita H,
    4. Sugawara T,
    5. Kubozono M,
    6. Umezawa R,
    7. Ishikawa Y,
    8. Kozumi M,
    9. Katagiri Y,
    10. Tasaka S,
    11. Takeda K,
    12. Takeda K,
    13. Dobashi S,
    14. Jingu K
    : Metabolic tumor volume on FDG-PET/CT is a possible prognostic factor for Stage I lung cancer patients treated with stereotactic body radiation therapy: a retrospective clinical study. J Radiat Res 57(6): 655-661, 2016. DOI: 10.1093/jrr/rrw048
    OpenUrlCrossRefPubMed
  17. ↵
    1. Arimura H,
    2. Soufi M,
    3. Kamezawa H,
    4. Ninomiya K,
    5. Yamada M
    : Radiomics with artificial intelligence for precision medicine in radiation therapy. J Radiat Res 60(1): 150-157, 2019. DOI: 10.1093/jrr/rry077
    OpenUrlCrossRefPubMed
  18. ↵
    1. Shioyama Y,
    2. Nakamura K,
    3. Anai S,
    4. Sasaki T,
    5. Ooga S,
    6. Saku M,
    7. Urashima Y,
    8. Yoshitake T,
    9. Toba T,
    10. Terashima H,
    11. Honda H
    : Stereotactic radiotherapy for lung and liver tumors using a body cast system: Setup accuracy and preliminary clinical outcome. Radiat Med 23: 407-413, 2005.
    OpenUrlPubMed
  19. ↵
    1. Yoshitake T,
    2. Nakamura K,
    3. Shioyama Y,
    4. Sasaki T,
    5. Ohga S,
    6. Shinoto M,
    7. Terashima K,
    8. Asai K,
    9. Matsumoto K,
    10. Matsuo Y,
    11. Baba S,
    12. Honda H
    : Stereotactic body radiation therapy for primary lung cancers clinically diagnosed without pathological confirmation: a single-institution experience. Int J Clin Oncol 20(1): 53-58, 2015. DOI: 10.1007/s10147-014-0698-y
    OpenUrlCrossRefPubMed
  20. ↵
    1. Yoshitake T,
    2. Shioyama Y,
    3. Nakamura K,
    4. Ohga S,
    5. Nonoshita T,
    6. Ohnishi K,
    7. Terashima K,
    8. Arimura H,
    9. Hirata H,
    10. Honda H
    : A clinical evaluation of visual feedback-guided breath-hold reproducibility of tumor location. Phys Med Biol 54(23): 7171-7182, 2009. DOI: 10.1088/0031-9155/54/23/009
    OpenUrlCrossRefPubMed
  21. ↵
    1. Vallières M
    : Radiomics: MATLAB programming tools for radiomics analysis. GitHub, 2015. Available at: https://github.com/mvallieres/radiomics [Last accessed on October 2, 2023]
  22. ↵
    1. Blondel P,
    2. Gómez Sichi O
    : Textural analyses of multibeam sonar imagery from Stanton Banks, Northern Ireland continental shelf. Appl Acoust 70: 1288-1297, 2009.
    OpenUrl
  23. ↵
    1. Hirose TA,
    2. Arimura H,
    3. Ninomiya K,
    4. Yoshitake T,
    5. Fukunaga JI,
    6. Shioyama Y
    : Radiomic prediction of radiation pneumonitis on pretreatment planning computed tomography images prior to lung cancer stereotactic body radiation therapy. Sci Rep 10(1): 20424, 2020. DOI: 10.1038/s41598-020-77552-7
    OpenUrlCrossRefPubMed
  24. ↵
    1. Soufi M,
    2. Arimura H,
    3. Nagami N
    : Identification of optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition-based radiomic features. Medical Physics 45(11): 5116-5128, 2018. DOI: 10.1002/mp.13202
    OpenUrlCrossRefPubMed
  25. ↵
    1. Tibshirani R
    : Regression shrinkage and selection via the lasso. J R Stat Soc Ser B 58: 267-288, 1996.
    OpenUrlCrossRef
  26. ↵
    1. Kanda Y
    : Investigation of the freely available easy-to-use software ‘EZR’ for medical statistics. Bone Marrow Transplant 48(3): 452-458, 2013. DOI: 10.1038/bmt.2012.244
    OpenUrlCrossRefPubMed
  27. ↵
    1. Onishi H,
    2. Shirato H,
    3. Nagata Y,
    4. Hiraoka M,
    5. Fujino M,
    6. Gomi K,
    7. Niibe Y,
    8. Karasawa K,
    9. Hayakawa K,
    10. Takai Y,
    11. Kimura T,
    12. Takeda A,
    13. Ouchi A,
    14. Hareyama M,
    15. Kokubo M,
    16. Hara R,
    17. Itami J,
    18. Yamada K,
    19. Araki T
    : Hypofractionated Stereotactic Radiotherapy (HypoFXSRT) for Stage I Non-small Cell Lung Cancer: Updated Results of 257 Patients in a Japanese Multi-institutional Study. J Thorac Oncol 2(7): S94-S100, 2007. DOI: 10.1097/JTO.0b013e318074de34
    OpenUrlCrossRefPubMed
  28. ↵
    1. Coroller TP,
    2. Grossmann P,
    3. Hou Y,
    4. Rios Velazquez E,
    5. Leijenaar RT,
    6. Hermann G,
    7. Lambin P,
    8. Haibe-Kains B,
    9. Mak RH,
    10. Aerts HJ
    : CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiother Oncol 114(3): 345-350, 2015. DOI: 10.1016/j.radonc.2015.02.015
    OpenUrlCrossRefPubMed
  29. ↵
    1. Kakino R,
    2. Nakamura M,
    3. Mitsuyoshi T,
    4. Shintani T,
    5. Kokubo M,
    6. Negoro Y,
    7. Fushiki M,
    8. Ogura M,
    9. Itasaka S,
    10. Yamauchi C,
    11. Otsu S,
    12. Sakamoto T,
    13. Sakamoto M,
    14. Araki N,
    15. Hirashima H,
    16. Adachi T,
    17. Matsuo Y,
    18. Mizowaki T
    : Application and limitation of radiomics approach to prognostic prediction for lung stereotactic body radiotherapy using breath-hold CT images with random survival forest: A multi-institutional study. Med Phys 47(9): 4634-4643, 2020. DOI: 10.1002/mp.14380
    OpenUrlCrossRefPubMed
  30. ↵
    1. Noguchi M,
    2. Morisawa A,
    3. Kawasaki M,
    4. Matsuno Y,
    5. Yamada T,
    6. Hirohashi S,
    7. Kondo H,
    8. Shimosato Y
    : Small adenocarcinoma of the lung Histologic characteristics and prognosis. Cancer 75: 2844-2852, 1995. DOI: 10.1002/1097-0142(19950615)75:12<2844::aid-cncr2820751209>3.0.co;2
    OpenUrlCrossRefPubMed
  31. ↵
    1. Onishi H,
    2. Shioyama Y,
    3. Matsumoto Y,
    4. Shibamoto Y,
    5. Miyakawa A,
    6. Suzuki G,
    7. Nishimura Y,
    8. Sasaki R,
    9. Miyawaki D,
    10. Kuriyama K,
    11. Komiyama T,
    12. Marino K,
    13. Aoki S,
    14. Saito R,
    15. Araya M,
    16. Maehata Y,
    17. Nonaka H,
    18. Tominaga L,
    19. Saito M,
    20. Sano N,
    21. Yamada S
    : Stereotactic body radiotherapy in patients with lung tumors composed of mainly ground-glass opacity. J Radiat Res 61(3): 426-430, 2020. DOI: 10.1093/jrr/rraa015
    OpenUrlCrossRefPubMed
    1. Haralick RM,
    2. Shanmugam K,
    3. Dinstein I
    : Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6): 610-621, 1973. DOI: 10.1109/TSMC.1973.4309314
    OpenUrlCrossRefPubMed
    1. Galloway MM
    : Texture analysis using gray level run lengths. Comput Graph Image Process 4(2): 172-179, 1975. DOI: 10.1016/S0146-664X(75)80008-6
    OpenUrlCrossRef
    1. Thibault G
    : Texture indexes and gray level size zone matrix. Application to cell nuclei classification. In: Proc. Pattern Recognition and Information Processing. Minsk, Belarus, 140-145, 2009.
    1. Amadasun M,
    2. King R
    : Textural features corresponding to textural properties. IEEE Trans Syst Man Cybern 19(5): 1264-1274, 1989. DOI: 10.1109/21.44046
    OpenUrlCrossRef
PreviousNext
Back to top

In this issue

Anticancer Research: 43 (11)
Anticancer Research
Vol. 43, Issue 11
November 2023
  • Table of Contents
  • Table of Contents (PDF)
  • About the Cover
  • Index by author
  • Back Matter (PDF)
  • Ed Board (PDF)
  • Front Matter (PDF)
Print
Download PDF
Article Alerts
Sign In to Email Alerts with your Email Address
Email Article

Thank you for your interest in spreading the word on Anticancer Research.

NOTE: We only request your email address so that the person you are recommending the page to knows that you wanted them to see it, and that it is not junk mail. We do not capture any email address.

Enter multiple addresses on separate lines or separate them with commas.
Combination of Clinical Factors and Radiomics Can Predict Local Recurrence and Metastasis After Stereotactic Body Radiotherapy for Non-small Cell Lung Cancer
(Your Name) has sent you a message from Anticancer Research
(Your Name) thought you would like to see the Anticancer Research web site.
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
10 + 10 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.
Citation Tools
Combination of Clinical Factors and Radiomics Can Predict Local Recurrence and Metastasis After Stereotactic Body Radiotherapy for Non-small Cell Lung Cancer
YUKO ISOYAMA-SHIRAKAWA, TADAMASA YOSHITAKE, KENTA NINOMIYA, KAORI ASAI, KEIJI MATSUMOTO, YOSHIYUKI SHIOYAMA, TAKUMI KODAMA, KOUSEI ISHIGAMI, HIDETAKA ARIMURA
Anticancer Research Nov 2023, 43 (11) 5003-5013; DOI: 10.21873/anticanres.16699

Citation Manager Formats

  • BibTeX
  • Bookends
  • EasyBib
  • EndNote (tagged)
  • EndNote 8 (xml)
  • Medlars
  • Mendeley
  • Papers
  • RefWorks Tagged
  • Ref Manager
  • RIS
  • Zotero
Reprints and Permissions
Share
Combination of Clinical Factors and Radiomics Can Predict Local Recurrence and Metastasis After Stereotactic Body Radiotherapy for Non-small Cell Lung Cancer
YUKO ISOYAMA-SHIRAKAWA, TADAMASA YOSHITAKE, KENTA NINOMIYA, KAORI ASAI, KEIJI MATSUMOTO, YOSHIYUKI SHIOYAMA, TAKUMI KODAMA, KOUSEI ISHIGAMI, HIDETAKA ARIMURA
Anticancer Research Nov 2023, 43 (11) 5003-5013; DOI: 10.21873/anticanres.16699
Twitter logo Facebook logo Mendeley logo
  • Tweet Widget
  • Facebook Like
  • Google Plus One

Jump to section

  • Article
    • Abstract
    • Patients and Methods
    • Results
    • Discussion
    • Conclusion
    • Acknowledgements
    • Footnotes
    • References
  • Figures & Data
  • Info & Metrics
  • PDF

Related Articles

  • No related articles found.
  • PubMed
  • Google Scholar

Cited By...

  • No citing articles found.
  • Google Scholar

More in this TOC Section

  • Comparison of BRCA2 Single Nucleotide Variants Between Japanese Patients With Familial Prostate Cancer, Sporadic Prostate Cancer, and Benign Prostatic Hyperplasia
  • Corrigendum
  • Sex-related Survival Differences in Patients With Glioblastoma – Results From a Retrospective Analysis
Show more Clinical Studies

Similar Articles

Keywords

  • radiomics
  • radiomic score
  • prediction
  • recurrence pattern
  • lung cancer
  • SBRT
Anticancer Research

© 2025 Anticancer Research

Powered by HighWire