A Non-Contrast Multi-Parametric MRI Biomarker for Assessment of MR-Guided Focused Ultrasound Thermal Therapies

• Published in: IEEE transactions on biomedical engineering Vol. 71; no. 1; pp. 1 - 12
• Main Authors: Johnson, Sara, Zimmerman, Blake, Odeen, Henrik, Shea, Jill, Winkler, Nicole, Factor, Rachel, Joshi, Sarang, Payne, Allison
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Animals; Biomarkers; Classifiers; Diffusion coefficient; Diffusion Magnetic Resonance Imaging; Focused ultrasound; Histology; histology registration; Histopathology; Humans; Image segmentation; Labels; Lesions; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Measurement; MR-guided; multi-parametric MRI; Necrosis; Neoplasms; Quadriceps muscle; Rabbits; Regression analysis; Supervised learning; Support vector machines; thermal ablation; Tumors; Ultrasonic imaging; Ultrasonography; Ultrasound
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2023.3303445

Objective: We present the development of a non-contrast multi-parametric magnetic resonance (MPMR) imaging biomarker to assess treatment outcomes for magnetic resonance-guided focused ultrasound (MRgFUS) ablations of localized tumors. Images obtained immediately following MRgFUS ablation were inputs for voxel- wise supervised learning classifiers, trained using registered histology as a label for thermal necrosis. Methods: VX2 tumors in New Zealand white rabbits quadriceps were thermally ablated using an MRgFUS system under 3 T MRI guidance. Animals were re-imaged three days post-ablation and euthanized. Histological necrosis labels were created by 3D registration between MR images and digitized H&E segmentations of thermal necrosis to enable voxel- wise classification of necrosis. Supervised MPMR classifier inputs included maximum temperature rise, cumulative thermal dose (CTD), post-FUS differences in T2-weighted images, and apparent diffusion coefficient, or ADC, maps. A logistic regression, support vector machine, and random forest classifier were trained in red a leave-one-out strategy in test data from four subjects. Results: In the validation dataset, the MPMR classifiers achieved higher recall and Dice than than a clinically adopted 240 cumulative equivalent minutes at 43 <inline-formula><tex-math notation="LaTeX">^{\circ }</tex-math></inline-formula>C (CEM<inline-formula><tex-math notation="LaTeX">_{43}</tex-math></inline-formula>) threshold (0.43) in all subjects.redThe average Dice scores of overlap with the registered histological label for the logistic regression (0.63) and support vector machine (0.63) MPMR classifiers were within 6% of the acute contrast-enhanced non-perfused volume (0.67). Conclusions: Voxel- wise registration of MPMR data to histological outcomes facilitated supervised learning of an accurate non-contrast MR biomarker for MRgFUS ablations in a rabbit VX2 tumor model.