Susceptibility Weighted Imaging (SWI) is a 3D high-spatial-resolution, velocity-corrected gradient-echo MRI sequence that uses magnitude and filtered-phase information to create images. It uses tissue magnetic susceptibility differences to generate signal contrast. Such signal arises from paramagnetic (hemosiderin), diamagnetic (minerals and calcifications), and ferromagnetic (metal) molecules, resulting in loss of signal. Contrast-Enhanced SWI (CE-SWI) is especially useful in MSK oncologic imaging, as it can help to differentiate between benign and malignant soft tissue tumors. Goal: To determine the predictive value of morphologic patterns and high-order radiomic...

A Retrospective IRB-authorized study included 26 patients with extremity non-myxoid UPS who underwent pre-surgical imaging and surgical resection from February 2021-October 2022. Volumetric tumor segmentation and CE-SWI measurements were extracted from routine advanced MRI at multiple pre-surgical time points, including Baseline, Post-Chemotherapy, and Post-Radiation. The 26 UPS patients included in this study were grouped based on pathology-reported treatment-induced necrosis (TIN) as good responders (TIN>=90%) and partial/non-responders (TIN<90%). The CE-SWI images were manually contoured using the MIM-licensed software. The contours were exported as standardized RT-Struct files...

Computational Workflow for CE-SWI Image Processing [Fig 1]Figure 1 presents the computational workflow for radiomic feature extraction developed in this study. CARPI was used to: 1) Batch-process the UPS contour files stored in the institutional network drive, 2) compute 107 radiomic features including 14 shape, 18 first-order statistics and 75 texture, and 3) automatically record them in a PostgreSQL-based relational database. CE-SWI Morphological Patterns in UPS [Fig 2]Figure 2 shows a CE-SWI image of the right thigh demonstrating an undifferentiated pleomorphic sarcoma (UPS) at different...

The high-order radiomic analysis at PRT found 2 texture features with the highest significance separating Good vs. Partial/Non-Responders. CE-SWI "Complete Ring" morphology was the most common and statistically associated pattern observed in Good Responders at PRT. The results from the UPS radiomic analysis across multiple treatment time points displayed statistically significant radiomic features that could potentially serve as imaging biomarkers of good response in patients.

R. F. Valenzuela: Nothing to disclose E. Duran-Sierra: Nothing to disclose M. Canjirathinkal: Nothing to disclose C. M. Costelloe: Nothing to disclose J. E. Madewell: Nothing to disclose W. Murphy: Nothing to disclose B. Amini: Nothing to disclose

Lambin, P., et al., Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer, 2012. 48(4): p. 441-6. Haacke, E.M. and J.R. Reichenbach, Susceptibility weighted imaging in MRI: basic concepts and clinical applications. 2014: John Wiley & Sons. Law, M.Y. and B. Liu, DICOM-RT and its utilization in radiation therapy. Radiographics, 2009. 29(3): p. 655-667. Van Griethuysen, J.J., et al., Computational radiomics system to decode the radiographic phenotype. Cancer research, 2017. 77(21): p. e104-e107. Sierra, E. D., Valenzuela, R., Canjirathinkal, M....