Suggestion for a New Grading Scale for Radiation Induced Pneumonitis Based on Radiological Findings of Computerized Tomography: Correlation with Clinical and Radiotherapeutic Parameters in Lung Cancer Patients

Kouloulias, Vassilis; Zygogianni, Anna; Efstathopoulos, Efstathios; Victoria, Oikonomopoulou; Antypas, Christos; Karaiskos, P.; Koutoulidis, Vassilis; Kouvaris, John; Sandilos, P.; Varela, Maria; Aytas, Ilknur; Γουλιάμος, Αθανάσιος; Kelekis, Nikolaos

doi:10.7314/apjcp.2013.14.5.2717

Cited by 25 publications

(15 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The patients' RP were scored by five grades (CTCAE 3.0) based on clinical assessment and imaging findings [19], and here, RP with grade 2 or above (RP2) was used to represent complication of radiation treatment. The study includes 79 NSCLC patients (with 21 cases of RP2) with complete data (200 features) utilized for biophysical pathway model building and 50 additional patients (with 3 cases of RP2) with incomplete data (missing some blood sample analyses) used for model testing.…”

Section: Methodsmentioning

confidence: 99%

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis

Luo

Naqa

McShan

et al. 2017

Radiotherapy and Oncology

View full text Add to dashboard Cite

Background In non-small-cell lung cancer radiotherapy, radiation pneumonitis ≥ grade 2 (RP2) depends on patients' dosimetric, clinical, biological and genomic characteristics. Methods We developed a Bayesian network (BN) approach to explore its potential for interpreting biophysical signaling pathways influencing RP2 from a heterogeneous dataset including single nucleotide polymorphisms, micro RNAs, cytokines, clinical data, and radiation treatment plans before and during the course of radiotherapy. Model building utilized 79 patients (21 with RP2) with complete data, and model testing used 50 additional patients with incomplete data. A developed large-scale Markov blanket approach selected relevant predictors. Resampling by k-fold cross-validation determined the optimal BN structure. Area under the receiver-operating characteristics curve (AUC) measured performance. Results Pre- and during-treatment BNs identified biophysical signaling pathways from the patients' relevant variables to RP2 risk. Internal cross-validation for the pre-BN yielded an AUC=0.82 which improved to 0.87 by incorporating during treatment changes. In the testing dataset, the pre- and during AUCs were 0.78 and 0.82, respectively. Conclusions Our developed BN approach successfully handled a high number of heterogeneous variables in a small dataset, demonstrating potential for unraveling relevant biophysical features that could enhance prediction of RP2, although the current observations would require further independent validation.

show abstract

Section: Methodsmentioning

confidence: 99%

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis

Luo

Naqa

McShan

et al. 2017

Radiotherapy and Oncology

View full text Add to dashboard Cite

show abstract

“…NTD has been calculated and tabulated for both breast (α/β = 4 Gy) and acute reacting tissues (α/β = 10 Gy) [13][14][15][16][17][18][19].…”

Section: Radiobiological Calculationsmentioning

confidence: 99%

“…Lung CT scans for assessing any pulmonary toxicity were performed before treatment and 4 weeks and 6 months after radiotherapy. Pulmonary toxicity was evaluated according to a scale developed at our Institution [19]. Any injury of the brachial plexus causing arm damage and weakness was also documented with neurological examination.…”

Section: Endpointsmentioning

confidence: 99%

See 1 more Smart Citation

A Retrospective Analysis of Toxicity and Efficacy for 2 Hypofractionated Irradiation Schedules Versus a Conventional One for Post-Mastectomy Adjuvant Radiotherapy in Breast Cancer

Kouloulias¹,

Mosa²,

Zygogianni³

et al. 2016

Breast Care

Self Cite

View full text Add to dashboard Cite

Introduction: The aim of this analysis was a retrospective evaluation of the efficacy and toxicity of 2 hypofractionated irradiation schedules compared to conventional therapy in post-mastectomy patients. Methods: 3 irradiation schedules were analyzed: 48.30 Gy in 21 fractions (group A, n = 60), 42.56 Gy in 16 fractions (group B, n = 27) and 50 Gy in 25 fractions (group C, n = 30) of the front chest wall. All groups were also treated with a supraclavicular field, with 39.10 Gy in 17 fractions (group A), 37.24 Gy in 14 fractions (group B) or 45 Gy in 25 fractions (group C). Results: No local recurrences were noted in any group during 36 months of follow-up. Acute skin toxicity presented in all groups, with 58.3%, 70.4% and 60% of grade I; 35%, 25.9% and 40% of grade II; 6.7%, 3.7% and 0% of grade III being seen in groups A, B and C, respectively. Late skin toxicity was noted only as grade I in 16.7%, 25.9% and 26.7% of groups A, B and C, respectively. No significant difference was noted among all groups for either acute or late skin toxicity, or for radio-pneumonitis (chi2 test, p > 0.05). Conclusion: All schedules were equally effective with equivalent toxicity. A prospective randomized study is needed to confirm our results.

show abstract

“…We analyzed 106 nonsmall cell lung cancer (NSCLC) patients treated under IRB approved protocols. Patients’ RP statuses were evaluated by a five‐grade CTCAE 3.0 based on clinical assessment and imaging. The RP outcome was then converted into RP2 (RP2 = 1 when RP = 2 or above, RP2 = 0 otherwise), serving as an indicator of complication of radiation treatment.…”

Section: Dataset and Patient Characteristicsmentioning

confidence: 99%

Combining handcrafted features with latent variables in machine learning for prediction of radiation‐induced lung damage

et al. 2019

View full text Add to dashboard Cite

Purpose There has been burgeoning interest in applying machine learning methods for predicting radiotherapy outcomes. However, the imbalanced ratio of a large number of variables to a limited sample size in radiation oncology constitutes a major challenge. Therefore, dimensionality reduction methods can be a key to success. The study investigates and contrasts the application of traditional machine learning methods and deep learning approaches for outcome modeling in radiotherapy. In particular, new joint architectures based on variational autoencoder (VAE) for dimensionality reduction are presented and their application is demonstrated for the prediction of lung radiation pneumonitis (RP) from a large‐scale heterogeneous dataset. Methods A large‐scale heterogeneous dataset containing a pool of 230 variables including clinical factors (e.g., dose, KPS, stage) and biomarkers (e.g., single nucleotide polymorphisms (SNPs), cytokines, and micro‐RNAs) in a population of 106 nonsmall cell lung cancer (NSCLC) patients who received radiotherapy was used for modeling RP. Twenty‐two patients had grade 2 or higher RP. Four methods were investigated, including feature selection (case A) and feature extraction (case B) with traditional machine learning methods, a VAE‐MLP joint architecture (case C) with deep learning and lastly, the combination of feature selection and joint architecture (case D). For feature selection, Random forest (RF), Support Vector Machine (SVM), and multilayer perceptron (MLP) were implemented to select relevant features. Specifically, each method was run for multiple times to rank features within several cross‐validated (CV) resampled sets. A collection of ranking lists were then aggregated by top 5% and Kemeny graph methods to identify the final ranking for prediction. A synthetic minority oversampling technique was applied to correct for class imbalance during this process. For deep learning, a VAE‐MLP joint architecture where a VAE aimed for dimensionality reduction and an MLP aimed for classification was developed. In this architecture, reconstruction loss and prediction loss were combined into a single loss function to realize simultaneous training and weights were assigned to different classes to mitigate class imbalance. To evaluate the prediction performance and conduct comparisons, the area under receiver operating characteristic curves (AUCs) were performed for nested CVs for both handcrafted feature selections and the deep learning approach. The significance of differences in AUCs was assessed using the DeLong test of U‐statistics. Results An MLP‐based method using weight pruning (WP) feature selection yielded the best performance among the different hand‐crafted feature selection methods (case A), reaching an AUC of 0.804 (95% CI: 0.761–0.823) with 29 top features. A VAE‐MLP joint architecture (case C) achieved a comparable but slightly lower AUC of 0.781 (95% CI: 0.737–0.808) with the size of latent dimension being 2. The combination of handcrafted features (case A) and latent representat...

show abstract

Suggestion for a New Grading Scale for Radiation Induced Pneumonitis Based on Radiological Findings of Computerized Tomography: Correlation with Clinical and Radiotherapeutic Parameters in Lung Cancer Patients

Cited by 25 publications

References 39 publications

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis

A Retrospective Analysis of Toxicity and Efficacy for 2 Hypofractionated Irradiation Schedules Versus a Conventional One for Post-Mastectomy Adjuvant Radiotherapy in Breast Cancer

Combining handcrafted features with latent variables in machine learning for prediction of radiation‐induced lung damage

Contact Info

Product

Resources

About