 | Related Articles |
Multi-parametric MRI tumor probability model for the detection of locally recurrent prostate cancer after radiotherapy: pathological validation and comparison with manual tumor delineations.
Int J Radiat Oncol Biol Phys. 2019 May 11;:
Authors: Fernandes CD, Simões R, Ghobadi G, Heijmink SW, Schoots IG, de Jong J, Walraven I, van der Poel HG, van Houdt PJ, Smolic M, Pos FJ, van der Heide UA
Abstract
PURPOSE: Focal salvage treatments of recurrent prostate cancer (PCa) after radiotherapy require accurate delineation of the target volume. Magnetic resonance imaging (MRI) is used for this purpose, however radiotherapy-induced changes complicate image interpretation, and guidelines are lacking on the assessment and delineation of recurrent PCa. A tumor probability (TP) model was trained and independently tested using multi-parametric MRI (mp-MRI) of radio-recurrent PCa patients. The resulting probability maps were used to derive target regions for radiotherapy treatment planning.
METHODS AND MATERIALS: Two cohorts of radio-recurrent PCa patients were used in this study. All patients received mp-MRI (T2w, DWI and DCE). A logistic regression model was trained using imaging features from 21 patients with biopsy-proven recurrence, qualifying for salvage treatment. The test cohort consisted of 17 patients treated with salvage prostatectomy. The model was tested against histopathology-derived tumor delineations. The voxel-wise TP maps were clustered using k-means to generate a GTV contour for voxel-level comparisons with manual tumor delineations performed by two radiologists and with histopathology-validated contours. Later, k-means was used with three clusters to define a CTV, high-risk CTV and GTV, with increasing tumor risk.
RESULTS: In the test cohort, the model obtained a median (range) AUC of 0.77 (0.41 - 0.99) for the whole prostate. The GTV delineation resulted in a median sensitivity of 0.31 (0 - 0.87) and specificity of 0.97 (0.84 - 1.0) with no significant differences between model and manual delineations. The three-level clustering GTV and high-risk CTV delineations had median sensitivities of 0.17 (0-0.59) and 0.49 (0-0.97) and specificities of 0.98 (0.84-1.00) and 0.94 (0.84-0.99), respectively.
CONCLUSIONS: The TP model obtained a good performance in predicting voxel-wise presence of recurrent tumor. Model-derived tumor risk-levels achieved similar sensitivity and specificity as manual delineations in localizing recurrent tumor. Voxel-wise TP derived from mp-MRI can in this way be incorporated for target definition in focal salvage of radio-recurrent PCa.
PURPOSE: Focal salvage treatments of recurrent prostate cancer (PCa) after radiotherapy require accurate delineation of the target volume. Magnetic resonance imaging (MRI) is used for this purpose, however radiotherapy-induced changes complicate image interpretation, and guidelines are lacking on the assessment and delineation of recurrent PCa. A tumor probability (TP) model was trained and independently tested using multi-parametric MRI (mp-MRI) of radio-recurrent PCa patients. The resulting probability maps were used to derive target regions for radiotherapy treatment planning.
METHODS AND MATERIALS: Two cohorts of radio-recurrent PCa patients were used in this study. All patients received mp-MRI (T2w, DWI and DCE). A logistic regression model was trained using imaging features from 21 patients with biopsy-proven recurrence, qualifying for salvage treatment. The test cohort consisted of 17 patients treated with salvage prostatectomy. The model was tested against histopathology-derived tumor delineations. The voxel-wise TP maps were clustered using k-means to generate a GTV contour for voxel-level comparisons with manual tumor delineations performed by two radiologists and with histopathology-validated contours. Later, k-means was used with three clusters to define a CTV, high-risk CTV and GTV, with increasing tumor risk.
RESULTS: In the test cohort, the model obtained a median (range) AUC of 0.77 (0.41 - 0.99) for the whole prostate. The GTV delineation resulted in a median sensitivity of 0.31 (0 - 0.87) and specificity of 0.97 (0.84 - 1.0) with no significant differences between model and manual delineations. The three-level clustering GTV and high-risk CTV delineations had median sensitivities of 0.17 (0-0.59) and 0.49 (0-0.97) and specificities of 0.98 (0.84-1.00) and 0.94 (0.84-0.99), respectively.
CONCLUSIONS: The TP model obtained a good performance in predicting voxel-wise presence of recurrent tumor. Model-derived tumor risk-levels achieved similar sensitivity and specificity as manual delineations in localizing recurrent tumor. Voxel-wise TP derived from mp-MRI can in this way be incorporated for target definition in focal salvage of radio-recurrent PCa.
PMID: 31085288 [PubMed - as supplied by publisher]
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου