Computed Tomography Radiomics Predicts HPV Status and Local Tumor Control After Definitive Radiochemotherapy in Head and Neck Squamous Cell Carcinoma

Bogowicz, Marta; Riesterer, Oliver; Ikenberg, Kristian; Stieb, Sonja; Moch, Holger; Studer, Gabriela; Gückenberger, Matthias; Tanadini‐Lang, Stephanie

doi:10.1016/j.ijrobp.2017.06.002

Cited by 160 publications

(165 citation statements)

References 16 publications

Supporting

Mentioning

156

Contrasting

Unclassified

Order By: Relevance

“…This result is consistent with previously published studies investigating local control [12] and overall survival [13,15] as endpoints. To understand the underlying biological processes of these findings, it would be of great interest to investigate if radiomic features corresponding to heterogeneity correlate with histopathological stainings of cell proliferation, microvessel density or hypoxia.…”

Section: Discussionsupporting

confidence: 93%

“…It would also eliminate a potential bias introduced by tumor progression between CT and PET scans [23]. Previous works [12][13] have shown that the inclusion of clinical parameters (tumor stage or volume) may result in more accurate predictions. However, so far other important clinical factors such as smoking status or performance status were not studied in combination with radiomics.…”

Section: Discussionmentioning

confidence: 99%

“…On the level of anatomical imaging, pre-treatment CT radiomics was found to be prognostic for local tumor control [12] and overall survival [11,13,14,15] in head and neck cancer, significantly stratifying patients into low-and high-risk groups. Those studies showed that tumors, which are heterogeneous in terms of CT density are associated with a worse prognosis.…”

Section: Introductionmentioning

confidence: 99%

“…This study was not successful. Considering the increasing evidence of the association between CT radiomics and local tumor control [12], the mixed experiences using functional and anatomical imaging could be explained by other non-tumor related factors influencing nodal recurrence or too large number of studied radiomic features in relation to number of included patients.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma

et al. 2017

Self Cite

View full text Add to dashboard Cite

(2017). Material and methodsData from HNSCC patients (n=121) treated with definitive radiochemotherapy were used for model training. In total, 569 radiomic features were extracted from both contrast enhanced CT and 18F-FDG PET images in the primary tumor region.CT, PET and combined PET/CT radiomic models to assess local tumor control were trained separately. Five feature selection and three classification methods were implemented. The performance of the models was quantified using concordance index (CI) in 5-fold cross-validation in the training cohort. The best models, per image modality, were compared and verified in the independent validation cohort (n=51). The difference in CI was investigated using bootstrapping. Additionally, the observed and radiomics-based estimated probabilities of local tumor control were compared between two risk groups. ResultsThe feature selection using principal component analysis and the classification based on the multivariabale Cox regression with backward selection of the variables resulted in the best models for all image modalities (CICT=0.72, CIPET=0.74, CIPET/CT=0.77). Tumors more homogenous in CT density (decreased GLSZMsize_zone_entropy) and with a focused region of high FDG uptake (higher GLSZMSZLGE) indicated better prognosis. No significant difference in the performance of the models in the validation cohort was observed (CICT=0.73, CIPET=0.71, CIPET/CT=0.73). However, the CT radiomics based model overestimated the probability of tumor control in the poor prognostic group (predicted=68%, observed=56%). ConclusionBoth CT and PET radiomics showed equally good discriminative power for local tumor control modeling in HNSCC. However, CT-based predictions overestimated the local control rate in the poor prognostic validation cohort and thus we recommend to base the local control modeling on the 18F-FDG PET.

show abstract

Section: Discussionsupporting

confidence: 93%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Different characteristics were analyzed to find possible predictors for LRC, DFS, or OS: age, gender, initial performance status, site (oropharyngeal tumor relative to all the other sites), histology, tumor‐node‐metastasis stage, induction chemotherapy (yes/no), concomitant chemotherapy (no, cisplatin, cetuximab), fractionation, and overall treatment time. We acknowledge the importance of human papillomavirus for oropharyngeal cancer in consideration of recent literature . However, due the percentage of patients with unknown status treated in the past years, we decided not to include these data in our outcome analysis.…”

Section: Resultsmentioning

confidence: 99%

Impact of hypofractionated schemes in radiotherapy for locally advanced head and neck cancer patients

et al. 2019

View full text Add to dashboard Cite

Objective To analyze two cohorts of locally advanced head and neck cancer (LAHNC) patients treated with two schedules of hypofractionated radiotherapy and 5 versus 3 mm clinical target volume–planning target volume (CTV‐PTV) margins. Methods 145 patients were included. The patient cohort was divided into two groups. Group A included 97 patients treated with 69.96/54.45 grays (Gy) to the high‐risk and low‐risk volumes, respectively, in 33 fractions, with 5 mm margins. Group B included 48 patients treated with 66/54 Gy in 30 fractions using 3 mm margins. Toxicity was recorded according to the Common Toxicity Criteria version 3. Patient outcomes for locoregional control (LRC), disease‐free survival (DFS), and overall survival (OS) were determined. Results Median follow‐up was 26 months. In terms of toxicity, acute dysphagia worsened significantly (P = 0.003) in group B, whereas acute salivary toxicity tended to significance (P = 0.071). No significant late toxicity differences were recorded. Rates of LRC at 1 and 2 years were 90.1% ± 2.6% and 84.2% ± 3.4%, respectively, with superiority for group A (P = 0.045). The statistical significance remained for the low‐dose level (P = 0.007) but not for high dose (P = 0.110). Rates of DFS at 1 and 2 years were 84.9% ± 3.1% and 76.5% ± 3.9%, respectively, whereas rates of OS were 95.9% ± 1.8% and 91.6% ± 2.7%, respectively. No differences were observed between the two groups in terms of DFS (P = 0.270) and OS (P = 0.152). Conclusion The use of reduced CTV to PTV margins and dose reduction with hypofractionation schedule can improve the pattern of toxicity in LAHNC patients. This approach resulted in an increased rate of locoregional progression, particularly in low‐risk regions. Level of Evidence 4 Laryngoscope, 130:E163–E170, 2020

show abstract

Quantitative ultrasound radiomics in predicting recurrence for patients with node‐positive head‐neck squamous cell carcinoma treated with radical radiotherapy

et al. 2020

View full text Add to dashboard Cite

This prospective study was conducted to investigate the role of quantitative ultrasound (QUS) radiomics in predicting recurrence for patients with node‐positive head‐neck squamous cell carcinoma (HNSCC) treated with radical radiotherapy (RT). The most prominent cervical lymph node (LN) was scanned with a clinical ultrasound device having central frequency of 6.5 MHz. Ultrasound radiofrequency data were processed to obtain 7 QUS parameters. Color‐coded parametric maps were generated based on individual QUS spectral features corresponding to each of the smaller units. A total of 31 (7 primary QUS and 24 texture) features were obtained before treatment. All patients were treated with radical RT and followed according to standard institutional practice. Recurrence (local, regional, or distant) served as an endpoint. Three different machine learning classifiers with a set of maximally three features were used for model development and tested with leave‐one‐out cross‐validation for nonrecurrence and recurrence groups. Fifty‐one patients were included, with a median follow up of 38 months (range 7–64 months). Recurrence was observed in 17 patients. The best results were obtained using a k‐nearest neighbor (KNN) classifier with a sensitivity, specificity, accuracy, and an area under curve of 76%, 71%, 75%, and 0.74, respectively. All the three features selected for the KNN model were texture features. The KNN‐model‐predicted 3‐year recurrence‐free survival was 81% and 40% in the predicted no‐recurrence and predicted‐recurrence groups, respectively. (p = 0.001). The pilot study demonstrates pretreatment QUS‐radiomics can predict the recurrence group with an accuracy of 75% in patients with node‐positive HNSCC. Clinical trial registration: clinicaltrials.gov.in identifier NCT03908684.

show abstract

Computed Tomography Radiomics Predicts HPV Status and Local Tumor Control After Definitive Radiochemotherapy in Head and Neck Squamous Cell Carcinoma

Cited by 160 publications

References 16 publications

Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma

Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma

Impact of hypofractionated schemes in radiotherapy for locally advanced head and neck cancer patients

Quantitative ultrasound radiomics in predicting recurrence for patients with node‐positive head‐neck squamous cell carcinoma treated with radical radiotherapy

Contact Info

Product

Resources

About