ABSTRACT
OBJECTIVES: To investigate the potential of T1rho, a new quantitative imaging sequence for cancer, for pre and early intra-treatment prediction of treatment response in nasopharyngeal carcinoma (NPC) and compare the results with those of diffusion-weighted imaging (DWI). MATERIALS AND METHODS: T1rho and DWI imaging of primary NPCs were performed pre- and early intra-treatment in 41 prospectively recruited patients. The mean preT1rho, preADC, intraT1rho, intraADC, and % changes in T1rho (ΔT1rho%) and ADC (ΔADC%) were compared between residual and non-residual groups based on biopsy in all patients after chemoradiotherapy (CRT) with (n = 29) or without (n = 12) induction chemotherapy (IC), and between responders and non-responders to IC in the subgroup who received IC, using Mann-Whitney U-test. A p-value of < 0.05 indicated statistical significance. RESULTS: Significant early intra-treatment changes in mean T1rho (p = 0.049) and mean ADC (p < 0.01) were detected (using paired t-test), most showing a decrease in T1rho (63.4%) and an increase in ADC (95.1%). Responders to IC (n = 17), compared to non-responders (n = 12), showed higher preT1rho (64.0 ms vs 66.5 ms) and a greater decrease in ΔT1rho% (- 7.5% vs 1.3%) (p < 0.05). The non-residual group after CRT (n = 35), compared to the residual group (n = 6), showed higher intraADC (0.96 vs 1.09 × 10-3 mm2/s) and greater increase in ΔADC% (11.7% vs 27.0%) (p = 0.02). CONCLUSION: Early intra-treatment changes are detectable on T1rho and show potential to predict tumour shrinkage after IC. T1rho may be complementary to DWI, which, unlike T1rho, did not predict response to IC but did predict non-residual disease after CRT. CLINICAL RELEVANCE STATEMENT: T1rho has the potential to complement DWI in the prediction of treatment response. Unlike DWI, it predicted shrinkage of the primary NPC after IC but not residual disease after CRT. KEY POINTS: Changes in T1rho were detected early during cancer treatment for NPC. Pre-treatment and early intra-treatment change in T1rho predicted response to IC, but not residual disease after CRT. T1rho can be used to complement DWI with DWI predicting residual disease after CRT.
ABSTRACT
OBJECTIVES: Parotid gland tumors (PGTs) often occur as incidental findings on magnetic resonance images (MRI) that may be overlooked. This study aimed to construct and validate a deep learning model to automatically identify parotid glands (PGs) with a PGT from normal PGs, and in those with a PGT to segment the tumor. MATERIALS AND METHODS: The nnUNet combined with a PG-specific post-processing procedure was used to develop the deep learning model trained on T1-weighed images (T1WI) in 311 patients (180 PGs with tumors and 442 normal PGs) and fat-suppressed (FS)-T2WI in 257 patients (125 PGs with tumors and 389 normal PGs), for detecting and segmenting PGTs with five-fold cross-validation. Additional validation set separated by time, comprising T1WI in 34 and FS-T2WI in 41 patients, was used to validate the model performance. RESULTS AND CONCLUSION: To identify PGs with tumors from normal PGs, using combined T1WI and FS-T2WI, the deep learning model achieved an accuracy, sensitivity and specificity of 98.2% (497/506), 100% (119/119) and 97.7% (378/387), respectively, in the cross-validation set and 98.5% (67/68), 100% (20/20) and 97.9% (47/48), respectively, in the validation set. For patients with PGTs, automatic segmentation of PGTs on T1WI and FS-T2WI achieved mean dice coefficients of 86.1% and 84.2%, respectively, in the cross-validation set, and of 85.9% and 81.0%, respectively, in the validation set. The proposed deep learning model may assist the detection and segmentation of PGTs and, by acting as a second pair of eyes, ensure that incidentally detected PGTs on MRI are not missed.