51. User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions
- Author
-
Frank J. P. Hoebers, Leonard Wee, Alberto Traverso, Andre Dekker, Chris McIntosh, Brian O'Sullivan, Shao Hui Huang, Bei Bei Zhang, David A. Jaffray, Andrea McNiven, Mattea Welch, Radiotherapie, RS: GROW - R3 - Innovative Cancer Diagnostics & Therapy, and RS: FSE BISS
- Subjects
Databases, Factual ,Computer science ,IMPACT ,medicine.medical_treatment ,General Physics and Astronomy ,Logistic regression ,computer.software_genre ,Convolutional neural network ,030218 nuclear medicine & medical imaging ,Machine Learning ,0302 clinical medicine ,PROGNOSTIC-FACTORS ,RISK ,Phantoms, Imaging ,Radiotherapy Dosage ,General Medicine ,Outcome prediction ,Prognosis ,CANCER ,3. Good health ,Treatment Outcome ,Feature (computer vision) ,Head and Neck Neoplasms ,030220 oncology & carcinogenesis ,Area Under Curve ,SURVIVAL ,Data mining ,RADIOMICS ,RADIOTHERAPY ,CARCINOMA ,Biophysics ,03 medical and health sciences ,Head and neck ,Bias ,medicine ,Humans ,Radiology, Nuclear Medicine and imaging ,Data curation ,business.industry ,Deep learning ,Radiotherapy Planning, Computer-Assisted ,User-controlled ,Pipeline (software) ,Radiation therapy ,Logistic Models ,Artificial intelligence ,business ,Precision and recall ,Tomography, X-Ray Computed ,computer ,Head ,Neck - Abstract
Purpose: Precision cancer medicine is dependent on accurate prediction of disease and treatment outcome, requiring integration of clinical, imaging and interventional knowledge. User controlled pipelines are capable of feature integration with varied levels of human interaction. In this work we present two pipelines designed to combine clinical, radiomic (quantified imaging), and RTx-omic (quantified radiation therapy (RT) plan) information for prediction of locoregional failure (LRF) in head and neck cancer (H&N).Methods: Pipelines were designed to extract information and model patient outcomes based on clinical features, computed tomography (CT) imaging, and planned RT dose volumes. We predict H&N LRF using: 1) a highly user-driven pipeline that leverages modular design and machine learning for feature extraction and model development; and 2) a pipeline with minimal user input that utilizes deep learning convolutional neural networks to extract and combine CT imaging, RT dose and clinical features for model development.Results: Clinical features with logistic regression in our highly user-driven pipeline had the highest precision recall area under the curve (PR-AUC) of 0.66 (0.33-0.93), where a PR-AUC = 0.11 is considered random.CONCLUSIONS: Our work demonstrates the potential to aggregate features from multiple specialties for conditional-outcome predictions using pipelines with varied levels of human interaction. Most importantly, our results provide insights into the importance of data curation and quality, as well as user, data and methodology bias awareness as it pertains to result interpretation in user controlled pipelines.
- Published
- 2019