Automated data preparation for in vivo tumor characterization with machine learning

Denis Krajnc; Clemens P Spielvogel; Marko Grahovac; Boglarka Ecsedi; Sazan Rasul; Nina Poetsch; Tatjana Traub-Weidinger; Alexander R Haug; Zsombor Ritter; Hussain Alizadeh; Marcus Hacker; Thomas Beyer; Laszlo Papp

doi:10.3389/fonc.2022.1017911

Automated data preparation for in vivo tumor characterization with machine learning

Front Oncol. 2022 Oct 11:12:1017911. doi: 10.3389/fonc.2022.1017911. eCollection 2022.

Authors

Affiliations

¹ QIMP Team, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.
² Department of Biomedical Imaging and Image-guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.
³ Christian Doppler Laboratory for Applied Metabolomics, Medical University of Vienna, Vienna, Austria.
⁴ Department of Medical Imaging, University of Pécs, Medical School, Pécs, Hungary.
⁵ 1st Department of Internal Medicine, University of Pécs, Medical School, Pécs, Hungary.
⁶ Applied Quantum Computing group, Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.

Abstract

Background: This study proposes machine learning-driven data preparation (MLDP) for optimal data preparation (DP) prior to building prediction models for cancer cohorts.

Methods: A collection of well-established DP methods were incorporated for building the DP pipelines for various clinical cohorts prior to machine learning. Evolutionary algorithm principles combined with hyperparameter optimization were employed to iteratively select the best fitting subset of data preparation algorithms for the given dataset. The proposed method was validated for glioma and prostate single center cohorts by 100-fold Monte Carlo (MC) cross-validation scheme with 80-20% training-validation split ratio. In addition, a dual-center diffuse large B-cell lymphoma (DLBCL) cohort was utilized with Center 1 as training and Center 2 as independent validation datasets to predict cohort-specific clinical endpoints. Five machine learning (ML) classifiers were employed for building prediction models across all analyzed cohorts. Predictive performance was estimated by confusion matrix analytics over the validation sets of each cohort. The performance of each model with and without MLDP, as well as with manually-defined DP were compared in each of the four cohorts.

Results: Sixteen of twenty established predictive models demonstrated area under the receiver operator characteristics curve (AUC) performance increase utilizing the MLDP. The MLDP resulted in the highest performance increase for random forest (RF) (+0.16 AUC) and support vector machine (SVM) (+0.13 AUC) model schemes for predicting 36-months survival in the glioma cohort. Single center cohorts resulted in complex (6-7 DP steps) DP pipelines, with a high occurrence of outlier detection, feature selection and synthetic majority oversampling technique (SMOTE). In contrast, the optimal DP pipeline for the dual-center DLBCL cohort only included outlier detection and SMOTE DP steps.

Conclusions: This study demonstrates that data preparation prior to ML prediction model building in cancer cohorts shall be ML-driven itself, yielding optimal prediction models in both single and multi-centric settings.

Keywords: PET; cancer; data preprocessing; hybrid imaging; machine learning.