LAUSR

Chordoma and chondrosarcoma account for the majority of skull base tumors affecting the petroclival region. Chondrosarcoma has better prognosis than chordoma; heavy particle therapy is often indicated for residual/recurrent chordoma. Preoperative, precise diagnosis of the tumor would be desirable, as it can potentially impact on the choice of a surgical approach and the aggressiveness of surgery. We conducted a radiomics study to create a machine learning model distinguishing chondrosarcoma from chordoma. We collected DICOM T2-weighted images and T1-weighted images with gadolinium (GdT1) enhancement in the consective patients of chordoma or chondrosarcoma who underwent surgery at The University of Tokyo Hospital from September of 2012 to January of 2019. We selected patients with uniform MRI images. VOI (volume of interest) was set using Monaco (https://www.elekta.com/software-solutions/treatment-management/external-beam-planning/monaco.html). Not only sematic features but also agnostic features were calculated. The original images and 8 wavelet transformed images were calculated for texture agnostic features such as Gray-Level Co-occurrence Matrix (GLCM). Features were selected by recursive feature elimination (RFE). The final model evaluation was performed by average area under the curve (AUC). The study population included 17 chordomas and 22 chondrosarcomas in a total of 39 patients. 476 features were obtained per image sequence. The number of features per case was 476 × 2 = 952 The most accurate machine learning model was created using the extracted three features from only T2. The best AUC was 0.77 ± 0.11 in logistic regression (dataset was divided randomly into halves, average value of AUC calculated six times). This novel machine learning model can differentiate chordoma and chondrosarcoma reasonably well. A validation study with a larger number of patients is warranted.