Cuong V. Dinh

Prostate tumor delineation using multiparametric magnetic resonance imaging: Inter-observer variability and pathology validation

BACKGROUND AND PURPOSE Boosting the dose to the largest (dominant) lesion in radiotherapy of prostate cancer may improve treatment outcome. The success of this approach relies on the detection and delineation of tumors. The agreement among teams of radiation oncologists and radiologists delineating lesions on multiparametric magnetic resonance imaging (mp-MRI) was assessed by measuring the distances between observer contours. The accuracy of detection and delineation was determined using whole-mount histopathology specimens as reference. MATERIAL AND METHODS Six observer teams delineated tumors on mp-MRI of 20 prostate cancer patients who underwent a prostatectomy. To assess the inter-observer agreement, the inter-observer standard deviation (SD) of the contours was calculated for tumor sites which were identified by all teams. RESULTS Eighteen of 89 lesions were identified by all teams, all were dominant lesions. The median histological volume of these was 2.4cm(3). The median inter-observer SD of the delineations was 0.23cm. Sixty-six of 69 satellites were missed by all teams. CONCLUSION Since all teams identify most dominant lesions, dose escalation to the dominant lesion is feasible. Sufficient dose to the whole prostate may need to be maintained to prevent under treatment of smaller lesions and undetected parts of larger lesions.

Visual Analytics for the Exploration of Tumor Tissue Characterization

Tumors are heterogeneous tissues consisting of multiple regions with distinct characteristics. Characterization of these intra‐tumor regions can improve patient diagnosis and enable a better targeted treatment. Ideally, tissue characterization could be performed non‐invasively, using medical imaging data, to derive per voxel a number of features, indicative of tissue properties. However, the high dimensionality and complexity of this imaging‐derived feature space is prohibiting for easy exploration and analysis ‐ especially when clinical researchers require to associate observations from the feature space to other reference data, e.g., features derived from histopathological data. Currently, the exploratory approach used in clinical research consists of juxtaposing these data, visually comparing them and mentally reconstructing their relationships. This is a time consuming and tedious process, from which it is difficult to obtain the required insight. We propose a visual tool for: (1) easy exploration and visual analysis of the feature space of imaging‐derived tissue characteristics and (2) knowledge discovery and hypothesis generation and confirmation, with respect to reference data used in clinical research. We employ, as central view, a 2D embedding of the imaging‐derived features. Multiple linked interactive views provide functionality for the exploration and analysis of the local structure of the feature space, enabling linking to patient anatomy and clinical reference data. We performed an initial evaluation with ten clinical researchers. All participants agreed that, unlike current practice, the proposed visual tool enables them to identify, explore and analyze heterogeneous intra‐tumor regions and particularly, to generate and confirm hypotheses, with respect to clinical reference data.

Multi-center validation of prostate tumor localization using multi-parametric MRI and prior knowledge.

Purpose: Tumor localization provides crucial information for radiotherapy dose differentiation treatments, such as focal dose escalation and dose painting by numbers, which aim at achieving tumor control with minimal side effects. Multiparametric (mp‐)MRI is increasingly used for tumor detection and localization in prostate because of its ability to visualize tissue structure and to reveal tumor characteristics. However, it can be challenging to distinguish cancer, particularly in the transition zone. In this study, we enhance the performance of a mp‐MRI‐based tumor localization model by incorporating prior knowledge from two sources: a population‐based tumor probability atlas and patient‐specific biopsy examination results. This information typically would be considered by a physician when carrying out a manual tumor delineation. Materials and methods: Our study involves 40 patients from two centers: 23 patients from the University Hospital Leuven (Leuven), Leuven, Belgium and 17 patients from the Netherlands Cancer Institute (NKI), Amsterdam, the Netherlands. All patients received a mp‐MRI exam consisting of a T2‐weighted, diffusion‐weighted, and dynamic contrast‐enhanced MRI before prostatectomy. Thirty‐one features were extracted for each voxel in the prostate. Among these, 29 were from the multiparametric‐MRI, one was from the population‐based tumor probability atlas and one from the biopsy map. T2‐weighted images of each patient were registered to whole‐mount section pathology slices to obtain the ground truth. The study was validated in two settings: single‐center (training and test sets were from the same cohort); and cross‐center (training and test sets were from different cohorts). In addition, automatic delineations created by our model were compared with manual tumor delineations done by six different teams on a subset of Leuven cohort including 15 patients. Results: In the single‐center setting, mp‐MRI‐based features yielded area under the ROC curves (AUC) of 0.690 on a pooled set of patients from both cohorts. Including prevalence into mp‐MRI‐based features increased the AUC to 0.751 and including all features achieved the best performance with AUC of 0.775. Using all features always showed better results when varying the size of the training set. In addition, its performance is comparable with the average performance of six teams delineating the tumors manually. The error rate using all features was 0.22. The two prior knowledge features ranked among the top four most important features out of the 31 features. In the cross‐center setting, combining all features also yielded the best performance in terms of the mean AUC of 0.777 on the pooled set of patients from both cohorts. In addition, the difference in performance between the single‐center setting and cross‐center setting was not significant. Conclusions: The results showed significant improvements when including prior knowledge features in addition to mp‐MRI‐based features in both single‐ and cross‐center settings.

Repeatability of dose painting by numbers treatment planning in prostate cancer radiotherapy based on multiparametric magnetic resonance imaging

Dose painting by numbers (DPBN) refers to a voxel-wise prescription of radiation dose modelled from functional image characteristics, in contrast to dose painting by contours which requires delineations to define the target for dose escalation. The direct relation between functional imaging characteristics and DPBN implies that random variations in images may propagate into the dose distribution. The stability of MR-only prostate cancer treatment planning based on DPBN with respect to these variations is as yet unknown. We conducted a test-retest study to investigate the stability of DPBN for prostate cancer in a semi-automated MR-only treatment planning workflow. Twelve patients received a multiparametric MRI on two separate days prior to prostatectomy. The tumor probability (TP) within the prostate was derived from image features with a logistic regression model. Dose mapping functions were applied to acquire a DPBN prescription map that served to generate an intensity modulated radiation therapy (IMRT) treatment plan. Dose calculations were done on a pseudo-CT derived from the MRI. The TP and DPBN map and the IMRT dose distribution were compared between both MRI sessions, using the intraclass correlation coefficient (ICC) to quantify repeatability of the planning pipeline. The quality of each treatment plan was measured with a quality factor (QF). Median ICC values for the TP and DPBN map and the IMRT dose distribution were 0.82, 0.82 and 0.88, respectively, for linear dose mapping and 0.82, 0.84 and 0.94 for square root dose mapping. A median QF of 3.4% was found among all treatment plans. We demonstrated the stability of DPBN radiotherapy treatment planning in prostate cancer, with excellent overall repeatability and acceptable treatment plan quality. Using validated tumor probability modelling and simple dose mapping techniques it was shown that despite day-to-day variations in imaging data still consistent treatment plans were obtained.

OC-0157: Prostate fiducial markers detection with the use of multiparametric-MRI

Purpose or Objective: Introducing an MRI-only workflow into the radiotherapy clinic, requires that MR-images can be used both for treatment planning calculations and for patient positioning. The two-fold aim of this study was to evaluate the use of MR-images with respect to 1) the accuracy of treatment planning dose calculations, and 2) the reliability of fiducial marker identification for patient positioning.

Contouring of prostate tumors on multiparametric MRI: Evaluation of clinical delineations in a multicenter radiotherapy trial

PURPOSE To date no guidelines are available for contouring prostate cancer inside the gland, as visible on multiparametric (mp-) MRI. We assessed inter-institutional differences in interpretation of mp-MRI in the multicenter phase III FLAME trial. METHODS We analyzed clinical delineations on mp-MRI and clinical characteristics from 260 patients across three institutes. We performed a logistic regression analysis to examine each institutes weighting of T2w, ADC and Ktrans intensity maps in the delineation of the cancer. As reviewing of all delineations by an expert panel is not feasible, we made a selection based on discrepancies between a published tumor probability (TP) model and each institutes clinical delineations using Areas Under the ROC Curve (AUC) analysis. RESULTS Regression coefficients for the three institutes were -0.07, -0.27 and -0.11 for T2w, -1.96, -0.53 and -0.65 for ADC and 0.15, 0.20 and 0.62 for Ktrans, with significant differences between institutes for ADC and Ktrans. AUC analysis showed median AUC values of 0.92, 0.80 and 0.79. Five patients with lowest AUC values were reviewed by a uroradiologist. CONCLUSION Regression coefficients revealed considerably different interpretations of mp-MRI in tumor contouring between institutes and demonstrated the need for contouring guidelines. Based on AUC values outlying delineations could efficiently be identified for review.

Biochemical recurrence prediction after radiotherapy for prostate cancer with T2w magnetic resonance imaging radiomic features

Graphical abstract

PO-0772: Multi-center validation of a model for prostate tumor delineation using multi-parametric MRI

PO-0772 Multi-center validation of a model for prostate tumor delineation using multi-parametric MRI C. Dinh, K. Haustermans, P. Steenbergen, G. Ghobadi, E. Lerut, R. Oyen, H.V.D. Poel, J.D. Jong, S. Heijmink, U.V.D. Heide The Netherlands Cancer Institute, Department of Radiation Oncology, Amsterdam, The Netherlands University Hospitals Leuven, Department of Oncology KU Leuven, Leuven, Belgium University Hospitals Leuven, Department of Imaging & Pathology, Leuven, Belgium The Netherlands Cancer Institute, Department of Radiology, Amsterdam, The Netherlands The Netherlands Cancer Institute, Department of Pathology, Amsterdam, The Netherlands