Citations

Objectives: High throughput pre-treatment imaging features may predict radiation treatment outcome and guide individualized treatment in radiotherapy (RT). Given relatively small patient sample (as compared with high dimensional imaging features), identifying potential prognostic imaging biomarkers is typically challenging. We aimed to develop robust machine learning methods for patient survival prediction using pre-treatment quantitative CT image features for a subgroup of head-and-neck cancer patients. Methods: Three neural network models, including back propagation (BP), Genetic Algorithm-Back Propagation (GA-BP), and Probabilistic Genetic Algorithm-Back Propagation (PGA-BP) neural networks were trained to simulate association between patient survival and radiomics data in radiotherapy. To evaluate the models, a subgroup of 59 head-and-neck patients with primary cancers in oral tongue area were utilized. Quantitative image features were extracted from planning CT images, a novel t-Distributed Stochastic Neighbor Embedding (t-SNE) method was used to remove irrelevant and redundant image features before fed into the network models. 80% patients were used to train the models, and remaining 20% were used for evaluation. Results: Of the three supervised machine-learning methods studied, PGA-BP yielded the best predictive performance. The reported actual patient survival interval of 30.5 ± 21.3 months, the predicted survival times were 47.3 ± 38.8, 38.5 ± 13.5 and 29.9 ± 15.3 months using the traditional PCA. Combining with the novel t-SNE dimensionality reduction algorithm, the predicted survival intervals are 35.8 ± 15.2, 32.3 ± 13.1 and 31.6 ± 15.8 months for the BP, GA-BP and PGA-BP neural network models, respectively. Conclusion: The work demonstrated that the proposed probabilistic genetic algorithm optimized neural network models, integrating with the t-SNE dimensionality reduction algorithm, achieved accurate prediction of patient survival. Advances in knowledge: The proposed PGA-BP neural network, integrating with an advanced dimensionality reduction algorithm (t-SNE), improved patient survival prediction accuracy using pre-treatment quantitative CT image features of head-and-neck cancer patients.

BACKGROUNDExisting data supporting the use of proton‐beam therapy (PBT) for limited‐stage small cell lung cancer (LS‐SCLC) are limited to a single 6‐patient case series. This is the first prospective study to evaluate clinical outcomes and toxicities of PBT for LS‐SCLC.METHODSThis study prospectively analyzed patients with primary, nonrecurrent LS‐SCLC definitively treated with PBT and concurrent chemotherapy from 2011 to 2016. Clinical backup intensity‐modulated radiotherapy (IMRT) plans were generated for each patient and were compared with PBT plans. Outcome measures included local control (LC), recurrence‐free survival (RFS), and overall survival (OS) rates and toxicities.RESULTSThirty consecutive patients were enrolled and evaluated. The median dose was 63.9 cobalt gray equivalents (range, 45‐66.6 cobalt gray equivalents) in 33 to 37 fractions delivered daily (n = 18 [60.0%]) or twice daily (n = 12 [40.0%]). The concurrent chemotherapy was cisplatin/etoposide (n = 21 [70.0%]) or carboplatin/etoposide (n = 9 [30.0%]). In comparison with the backup IMRT plans, PBT allowed statistically significant reductions in the cord, heart, and lung mean doses and the volume receiving at least 5 Gy but not in the esophagus mean dose or the lung volume receiving at least 20 Gy. At a median follow‐up of 14 months, the 1‐/2‐year LC and RFS rates were 85%/69% and 63%/42%, respectively. The median OS was 28.2 months, and the 1‐/2‐year OS rates were 72%/58%. There was 1 case each (3.3%) of grade 3 or higher esophagitis, pneumonitis, anorexia, and pericardial effusion. Grade 2 pneumonitis and esophagitis were seen in 10.0% and 43.3% of patients, respectively.CONCLUSIONSIn the first prospective registry study and largest analysis to date of PBT for LS‐SCLC, PBT was found to be safe with a limited incidence of high‐grade toxicities. Cancer 2017;123:4244–4251. © 2017 American Cancer Society.