International Journal of Radiation Oncology*Biology*Physics
Physics ContributionSpatial-Temporal [18F]FDG-PET Features for Predicting Pathologic Response of Esophageal Cancer to Neoadjuvant Chemoradiation Therapy
Introduction
Esophageal cancer remains one of the most lethal malignancies. Historically, the primary treatment strategy has been surgery (esophagectomy) (1). Trimodal therapy, consisting of concurrent chemoradiation therapy (CRT) followed by surgery, has recently been used for managing this disease. Adoption of this approach was supported by the results of phase 2 and 3 randomized trials that showed greater long-term overall and progression-free survival (1) or disease-free survival (2) with trimodal therapy than with surgery alone. However, whether the addition of surgery to CRT provides an advantage over CRT alone remains controversial (3). Randomized trials reported equivalent 2-year overall survival rates (range, 28%-40%) for the 2 treatment strategies 4, 5. Moreover, surgery after CRT is associated with significantly higher mortality (9%-12%) and morbidity (30%) than CRT alone (mortality, 0.8%-3.5%) 4, 5.
Despite these data, strategies that forego surgery may be inappropriate for many patients. Local failure rates for CRT alone can exceed 50%, and evidence suggests that surgery after CRT improves local control 4, 5. Several investigators have shown recently that patients who responded to CRT had good prognoses (survival and local control) regardless of whether they underwent surgery, whereas patients who did not respond to CRT had poor prognoses, but surgery improved survival in these patients 3, 4, 5. With the uncertain benefit and added mortality and morbidity of surgery after CRT and the high local failure rate for CRT alone, it is critical to accurately identify patients who respond to CRT so that surgery may be safely deferred. It is equally important to accurately identify patients who do not respond to CRT so that surgery can be considered.
18F-labeled fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) has shown promising results in predicting pathologic response to and long-term prognosis after CRT in esophageal cancer, but accuracy is still low (6). Westerterp et al (7) showed that PET had similar accuracy (sensitivity, 71%-100%; specificity, 55%-100%) to and was more feasible than endoscopic ultrasonography, whereas the accuracy of computed tomography (CT) was significantly lower. In a review of 20 studies, Kwee (6) found that sensitivity and specificity of PET ranged from 33% to 100% and 30% to 100%, respectively, with pooled estimates of 67% and 68%, respectively (6). Monjazeb et al (3) demonstrated that PET complete response after CRT alone predicted improved survival and local control rates that were equivalent to those with trimodal therapy.
Almost all [18F]FDG-PET studies quantify therapeutic response in tumors by using maximum standardized uptake value (SUVmax) of [18F]FDG within a tumor (8). Changes in SUVmax and sometimes SUVmax pre- or post-CRT alone are correlated with post-CRT pathologic tumor response or survival. However, SUVmax is a single-point estimate, and most solid tumors include various malignant and nonmalignant components and show significant heterogeneity in both degree and distribution of [18F]FDG uptake. Heterogeneity in [18F]FDG uptake may be associated with important biological and physiologic parameters 9, 10 that have been shown to be prognostic factors in many cancers 10, 11. Another limitation of SUVmax is that noise effects are substantial (12). Recent studies suggest that spatial PET/CT features, including tumor volume (12), tumor shape (11), total glycolytic volume (TGV) (12), and texture features 10, 11, are more informative than SUVmax for the prediction of tumor response.
The objective of this study was to extract comprehensive spatial-temporal tumor features from PET/CT images and to assess their usefulness in predicting pathologic tumor response to neoadjuvant CRT in esophageal cancer.
Section snippets
Patient cohort
This retrospective study was approved by our Institutional Review Board. The cohort included 20 consecutive patients with esophageal cancer (Table 1), who were treated with trimodal therapy from 2006 to 2009 and underwent both pre- and post-CRT PET/CT imaging at our institution. The median age for patients was 64 years. Disease was staged according to American Joint Committee on Cancer Cancer Staging Manual (6th edition) (13). The 2 patients with stage M1a disease had extensive local-regional
Predicting accuracy of features
Features with the highest AUCs and not highly correlated (correlation coefficient, <0.8) with others in each category are listed in Table 3, along with the VOIs and images from which they were extracted. Figure 1 shows example boxplots used to visually evaluate how well and in which direction a feature separated responders from nonresponders.
Discussion
Two new PET intensity features and 3 PET texture features were found to be significant predictors of pathologic response to neoadjuvant CRT in esophageal cancer. They had the same or moderately higher AUCs than the traditional SUV response measures of SUVmax and SUVpeak. These features quantified novel spatial-temporal tumor characteristics that are not conventionally captured and may be more useful than traditional SUV response measures in evaluation of tumor response.
Both biological and
Conclusions
One limitation of this study is that only the predictive accuracy of each individual feature was examined. The fact that these features characterize different properties of a tumor suggests that they contain complementary information. We are developing machine-learning methods that selectively combine features for more reliable prediction. Another limitation is that this is a retrospective study of a small patient cohort. The predictive accuracy and stability of the new features should be
References (21)
- et al.
Exploring feature-based approaches in PET images for predicting cancer treatment outcomes
Pattern Recognit
(2009) - et al.
The integration of 18-fluoro-deoxy-glucose positron emission tomography and endoscopic ultrasound in the treatment-planning process for esophageal carcinoma
Int J Radiat Oncol Biol Phys
(2005) - et al.
Phase III trial of trimodality therapy with cisplatin, fluorouracil, radiotherapy, and surgery compared with surgery alone for esophageal cancer: CALGB 9781
J Clin Oncol
(2008) - et al.
Chemoradiotherapy followed by surgery compared with surgery alone in squamous-cell cancer of the esophagus
N Engl J Med
(1997) - et al.
Outcomes of patients with esophageal cancer staged with [(18)F]fluorodeoxyglucose positron emission tomography FDG-PET can postchemoradiotherapy FDG-PET predict the utility of resection?
J Clin Oncol
(2011) - et al.
Chemoradiation with and without surgery in patients with locally advanced squamous cell carcinoma of the esophagus
J Clin Oncol
(2005) - et al.
Chemoradiation followed by surgery compared with chemoradiation alone in squamous cancer of the esophagus: FFCD 9102
J Clin Oncol
(2007) Prediction of tumor response to neoadjuvant therapy in patients with esophageal cancer with use of 18F-FDG PET: a systematic review
Radiology
(2010)- et al.
Esophageal cancer: CT, endoscopic US, and FDG PET for assessment of response to neoadjuvant therapy—systematic review
Radiology
(2005) From tumor biology to clinical PET: a review of positron emission tomography (PET) in oncology
Ann Nucl Med
(2001)
Cited by (137)
Preoperative <sup>18</sup>F-FDG PET/CT and CT radiomics for identifying aggressive histopathological subtypes in early stage lung adenocarcinoma
2023, Computational and Structural Biotechnology JournalHistogram analysis of <sup>18</sup>F-FDG PET imaging SUVs may predict the histologic grade of oral squamous cell carcinoma
2022, Oral Surgery, Oral Medicine, Oral Pathology and Oral RadiologyImmunotherapy treatment outcome prediction in metastatic melanoma through an automated multi-objective delta-radiomics model
2021, Computers in Biology and MedicineCitation Excerpt :Fifteen rounds of five-fold cross-validation and independent testing were performed, and the mean value and standard deviation were calculated. Auto-MODR was compared with the traditional MO model [24] and the traditional single-objective model (SO-AUC) [21]. Both MO and SO-AUC require manual selection of one Pareto-optimal model, whereas SO-AUC only considers AUC as a single optimization objective.
This work was supported in part by National Cancer Institute grant R21 CA131979. Shan Tan was supported in part by National Natural Science Foundation of China grant 60971112 and Fundamental Research Funds for the Central Universities grant 2012QN086.
Conflict of interest: none.