Search

Our aim is to investigate the added value of automated machine learning (AutoML) for potential future applications in cancer diagnostics. Using two important diagnostic questions, the non-invasive determination of IDH mutation status and ATRX status, we analyze whether it is possible to use AutoML to develop models that are comparable in performance to conventional machine learning models (ML) developed by experts. For this purpose, we develop AutoML models using different feature preselection methods and compare the results with previously developed conventional ML models. The cohort used for our study comprises T2-weighted MRI images of 124 patients with histologically confirmed gliomas. Using AutoML, we were able to develop sophisticated models in a very short time with only a few lines of computer code. In predicting IDH mutation status, we obtained a mean AUC of 0.7400 and a mean AUPRC of 0.8582. ATRX mutation status was predicted with very similar discriminatory power, with a mean AUC of 0.7810 and a mean AUPRC of 0.8511. In both cases, AutoML was even able to achieve a discriminatory power slightly above that of the respective conventionally developed models in a very short computing time, thus making such methods accessible to non-experts in the near future. [ABSTRACT FROM AUTHOR]

Our aim is to predict possible gross total and subtotal resections of skull meningiomas from pre-treatment T1 post contrast MR-images using radiomics and machine learning in a representative patient cohort. We analyse the accuracy of our model predictions depending on the tumor location within the skull and the postoperative tumor volume. In this retrospective, IRB-approved study, image segmentation of the contrast enhancing parts of the tumor was semi-automatically performed using the 3D Slicer open-source software platform. Imaging data were split into training data and independent test data at random. We extracted a total of 107 radiomic features by hand-delineated regions of interest on T1 post contrast MR images. Feature preselection and model construction were performed with eight different machine learning algorithms. Each model was estimated 100 times on new training data and then tested on a previously unknown, independent test data set to avoid possible overfitting. Our cohort included 138 patients. A gross total resection of the meningioma was performed in 107 cases and a subtotal resection in the remaining 31 cases. Using the training data, the mean area under the curve (AUC), mean accuracy, mean kappa, mean sensitivity and mean specificity were 0.901, 0.875, 0.629, 0.675 and 0.933 respectively. We obtained very similar results with the independent test data: mean AUC = 0.900, mean accuracy = 0.881, mean kappa = 0.644, mean sensitivity = 0.692 and mean specificity = 0.936. Thus, our model exposes good and stable predictive performance with both training and test data. Our radiomics approach shows that with machine learning algorithms and comparatively few explanatory factors such as the location of the tumor within the skull as well as its shape, it is possible to make accurate predictions about whether a meningioma can be completely resected by surgery. Complete resections and resections with larger postoperative tumor volumes can be predicted with very high accuracy. However, cases with very small postoperative tumor volumes are comparatively difficult to predict correctly. [ABSTRACT FROM AUTHOR]

Our aim is to define the capabilities of radiomics and machine learning in predicting pseudoprogression development from pre-treatment MR images in a patient cohort diagnosed with high grade gliomas. In this retrospective analysis, we analysed 131 patients with high grade gliomas. Segmentation of the contrast enhancing parts of the tumor before administration of radio-chemotherapy was semi-automatically performed using the 3D Slicer open-source software platform (version 4.10) on T1 post contrast MR images. Imaging data was split into training data, test data and an independent validation sample at random. We extracted a total of 107 radiomic features by hand-delineated regions of interest (ROI). Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM). 131 patients were included, of which 64 patients had a histopathologically proven progressive disease and 67 were diagnosed with mixed or pure pseudoprogression after initial treatment. Our Radiomics approach is able to predict the occurrence of pseudoprogression with an AUC, mean sensitivity, mean specificity and mean accuracy of 91.49% [86.27%, 95.89%], 79.92% [73.08%, 87.55%], 88.61% [85.19%, 94.44%] and 84.35% [80.19%, 90.57%] in the full development group, 78.51% [75.27%, 82.46%], 66.26% [57.95%, 73.02%], 78.31% [70.48%, 84.19%] and 72.40% [68.06%, 76.85%] in the testing group and finally 72.87% [70.18%, 76.28%], 71.75% [62.29%, 75.00%], 80.00% [69.23%, 84.62%] and 76.04% [69.90%, 80.00%] in the independent validation sample, respectively. Our results indicate that radiomics is a promising tool to predict pseudo-progression, thus potentially allowing to reduce the use of biopsies and invasive histopathology. [ABSTRACT FROM AUTHOR]