Background Well differentiated liposarcoma (WDLPS) can be difficult to distinguish from lipoma. Currently, this distinction is made by testing for MDM2 amplification, which requires a biopsy. The aim of this study was to develop a noninvasive method to predict MDM2 amplification status using radiomics features derived from MRI. Methods Patients with an MDM2‐negative lipoma or MDM2‐positive WDLPS and a pretreatment T1‐weighted MRI scan who were referred to Erasmus MC between 2009 and 2018 were included. When available, other MRI sequences were included in the radiomics analysis. Features describing intensity, shape and texture were extracted from the tumour region. Classification was performed using various machine learning approaches. Evaluation was performed through a 100 times random‐split cross‐validation. The performance of the models was compared with the performance of three expert radiologists. Results The data set included 116 tumours (58 patients with lipoma, 58 with WDLPS) and originated from 41 different MRI scanners, resulting in wide heterogeneity in imaging hardware and acquisition protocols. The radiomics model based on T1 imaging features alone resulted in a mean area under the curve (AUC) of 0·83, sensitivity of 0·68 and specificity of 0·84. Adding the T2‐weighted imaging features in an explorative analysis improved the model to a mean AUC of 0·89, sensitivity of 0·74 and specificity of 0·88. The three radiologists scored an AUC of 0·74 and 0·72 and 0·61 respectively; a sensitivity of 0·74, 0·91 and 0·64; and a specificity of 0·55, 0·36 and 0·59. Conclusion Radiomics is a promising, non‐invasive method for differentiating between WDLPS and lipoma, outperforming the scores of the radiologists. Further optimization and validation is needed before introduction into clinical practice.

The highly conformal planned dose distribution achievable in intensity modulated proton therapy (IMPT) can severely be compromised by uncertainties in patient setup and proton range. While several robust optimization approaches have been presented to address this issue, appropriate methods to accurately estimate the robustness of treatment plans are still lacking. To fill this gap we present Polynomial Chaos Expansion (PCE) techniques which are easily applicable and create a meta-model of the dose engine by approximating the dose in every voxel with multidimensional polynomials. This Polynomial Chaos (PC) model can be built in an automated fashion relatively cheaply and subsequently it can be used to perform comprehensive robustness analysis. We adapted PC to provide among others the expected dose, the dose variance, accurate probability distribution of dose-volume histogram (DVH) metrics (e.g. minimum tumor or maximum organ dose), exact bandwidths of DVHs, and to separate the effects of random and systematic errors. We present the outcome of our verification experiments based on 6 head-and-neck (HN) patients, and exemplify the usefulness of PCE by comparing a robust and a non-robust treatment plan for a selected HN case. The results suggest that PCE is highly valuable for both research and clinical applications.

Purpose: Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI. Experimental Design: Preoperative brain MR images from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained on the basis of features extracted from post-contrast T1-weighted and T2-weighted MR images and on patients' age and sex. The performance of the algorithm compared with tissue diagnosis was assessed on an external validation dataset of MR images from 129 patients with LGG from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MR images. Results: The algorithm achieved an AUC of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52) but lower than that of the neuroradiologists (AUC of 0.81). There was a wide variability between clinical experts (AUC 0.45-0.83). Conclusions: Our results suggest that our algorithm can noninvasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons. Evaluation on an independent dataset indicates that our algorithm is robust and generalizable.