The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Magnetic resonance radiomics for prediction of extraprostatic extension in non-favorable intermediate- and high-risk prostate cancer patients.

BACKGROUND: To investigate whether magnetic resonance (MR) radiomic features combined with machine learning may aid in predicting extraprostatic extension (EPE) in high- and non-favorable intermediate-risk patients with prostate cancer. PURPOSE: To investigate the diagnostic performance of radiomics to detect EPE. MATERIAL AND METHODS: MR radiomic features were extracted from 228 patients, of whom 86 were diagnosed with EPE, using prostate and lesion segmentations. Prediction models were built using Random Forest. Further, EPE was also predicted using a clinical nomogram and routine radiological interpretation and diagnostic performance was assessed for individual and combined models. RESULTS: The MR radiomic model with features extracted from the manually delineated lesions performed best among the radiomic models with an area under the curve (AUC) of 0.74. Radiology interpretation yielded an AUC of 0.75 and the clinical nomogram (MSKCC) an AUC of 0.67. A combination of the three prediction models gave the highest AUC of 0.79. CONCLUSION: Radiomic analysis combined with radiology interpretation aid the MSKCC nomogram in predicting EPE in high- and non-favorable intermediate-risk patients.

Optimising preoperative risk stratification tools for prostate cancer using mpMRI.

PURPOSE: To improve preoperative risk stratification for prostate cancer (PCa) by incorporating multiparametric MRI (mpMRI) features into risk stratification tools for PCa, CAPRA and D'Amico. METHODS: 807 consecutive patients operated on by robot-assisted radical prostatectomy at our institution during the period 2010-2015 were followed to identify biochemical recurrence (BCR). 591 patients were eligible for final analysis. We employed stepwise backward likelihood methodology and penalised Cox cross-validation to identify the most significant predictors of BCR including mpMRI features. mpMRI features were then integrated into image-adjusted (IA) risk prediction models and the two risk prediction tools were then evaluated both with and without image adjustment using receiver operating characteristics, survival and decision curve analyses. RESULTS: 37 patients suffered BCR. Apparent diffusion coefficient (ADC) and radiological extraprostatic extension (rEPE) from mpMRI were both significant predictors of BCR. Both IA prediction models reallocated more than 20% of intermediate-risk patients to the low-risk group, reducing their estimated cumulative BCR risk from approximately 5% to 1.1%. Both IA models showed improved prognostic performance with a better separation of the survival curves. CONCLUSION: Integrating ADC and rEPE from mpMRI of the prostate into risk stratification tools improves preoperative risk estimation for BCR. KEY POINTS: • MRI-derived features, ADC and EPE, improve risk stratification of biochemical recurrence. • Using mpMRI to stratify prostate cancer patients improves the differentiation between risk groups. • Using preoperative mpMRI will help urologists in selecting the most appropriate treatment.

Assessing Extraprostatic Extension with Multiparametric MRI of the Prostate: Mehralivand Extraprostatic Extension Grade or Extraprostatic Extension Likert Scale?

Purpose: To validate the MRI grading system proposed by Mehralivand et al in 2019 (the "extraprostatic extension [EPE] grade") in an independent cohort and to compare the Mehralivand EPE grading system with EPE interpretation on the basis of a five-point Likert score ("EPE Likert"). Materials and Methods: A total of 310 consecutive patients underwent multiparametric MRI according to a standardized institutional protocol before radical prostatectomy was performed by using the same 1.5-T MRI unit at a single institution between 2010 and 2012. Two radiologists blinded to clinical information assessed EPE according to standardized criteria. On the basis of the readings performed until 2017, the diagnostic performance of EPE Likert and Mehralivand EPE score were compared using receiver operating characteristics (ROC) and decision curve methodology against histologic EPE as standard of reference. Prediction of biochemical recurrence-free survival (BRFS) was assessed by Kaplan-Meier analysis and log rank test. Results: Of the 310 patients, 80 patients (26%) had EPE, including 33 with radial distance 1.1 mm or greater. Interrater reliability was fair (weighted κ 0.47 and 0.45) for both EPE grade and EPE Likert. Sensitivity for identifying EPE using EPE grade versus EPE Likert was 0.83 versus 0.86 and 0.86 versus 0.91 for radiologist 1 and 2, respectively. Specificity was 0.48 versus 0.58 and 0.39 versus 0.70 (P < .05 for radiologist 2). There were no significant differences in the ROC area under the curve or on decision curve analysis. Both EPE grade and EPE Likert were significant predictors of BRFS. Conclusion: Mehralivand EPE grade and EPE Likert have equivalent diagnostic performance for predicting EPE and BRFS with a similar degree of observer dependence.© RSNA, 2020Keywords: MR-Imaging, Neoplasms-Primary, Observer Performance, Outcomes Analysis, Prostate, StagingSupplemental material is available for this article.See also the commentary by Choyke in this issue.

Intensity-based volumetric registration of magnetic resonance images and whole-mount sections of the prostate.

OBJECTIVE: Magnetic Resonance Imaging (MRI) of the prostate provides useful in vivo diagnostic tissue information such as tumor location and aggressiveness, but ex vivo histopathology remains the ground truth. There are several challenges related to the registration of MRI to histopathology. We present a method for registration of standard clinical T2-weighted MRI (T2W-MRI) and transverse histopathology whole-mount (WM) sections of the prostate. METHODS: An isotropic volume stack was created from the WM sections using 2D rigid and deformable registration combined with linear interpolation. The prostate was segmented manually from the T2W-MRI volume and registered to the WM section volume using a combination of affine and deformable registration. The method was evaluated on a set of 12 patients who had undergone radical prostatectomy. Registration accuracy was assessed using volume overlap (Dice Coefficient, DC) and landmark distances. RESULTS: The DC was 0.94 for the whole prostate, 0.63 for the peripheral zone and 0.77 for the remaining gland. The landmark distances were on average 5.4 mm. CONCLUSION: The volume overlap for the whole prostate and remaining gland, as well as the landmark distances indicate good registration accuracy for the proposed method, and shows that it can be highly useful for registering clinical available MRI and WM sections of the prostate.

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

BACKGROUND AND PURPOSE: High-risk prostate cancer patients are frequently treated with external-beam radiotherapy (EBRT). Of all patients receiving EBRT, 15-35% will experience biochemical recurrence (BCR) within five years. Magnetic resonance imaging (MRI) is commonly acquired as part of the diagnostic procedure and imaging-derived features have shown promise in tumour characterisation and biochemical recurrence prediction. We investigated the value of imaging features extracted from pre-treatment T2w anatomical MRI to predict five year biochemical recurrence in high-risk patients treated with EBRT. MATERIALS AND METHODS: In a cohort of 120 high-risk patients, imaging features were extracted from the whole-prostate and a margin surrounding it. Intensity, shape and textural features were extracted from the original and filtered T2w-MRI scans. The minimum-redundancy maximum-relevance algorithm was used for feature selection. Random forest and logistic regression classifiers were used in our experiments. The performance of a logistic regression model using the patient's clinical features was also investigated. To assess the prediction accuracy we used stratified 10-fold cross validation and receiver operating characteristic analysis, quantified by the area under the curve (AUC). RESULTS: A logistic regression model built using whole-prostate imaging features obtained an AUC of 0.63 in the prediction of BCR, outperforming a model solely based on clinical variables (AUC = 0.51). Combining imaging and clinical features did not outperform the accuracy of imaging alone. CONCLUSIONS: These results illustrate the potential of imaging features alone to distinguish patients with an increased risk of recurrence, even in a clinically homogeneous cohort.

Semi-automatic 3D morphological reconstruction of neurons with densely branching morphology: Application to retinal AII amacrine cells imaged with multi-photon excitation microscopy.

BACKGROUND: Accurate reconstruction of the morphology of single neurons is important for morphometric studies and for developing compartmental models. However, manual morphological reconstruction can be extremely time-consuming and error-prone and algorithms for automatic reconstruction can be challenged when applied to neurons with a high density of extensively branching processes. NEW METHOD: We present a procedure for semi-automatic reconstruction specifically adapted for densely branching neurons such as the AII amacrine cell found in mammalian retinas. We used whole-cell recording to fill AII amacrine cells in rat retinal slices with fluorescent dyes and acquired digital image stacks with multi-photon excitation microscopy. Our reconstruction algorithm combines elements of existing procedures, with segmentation based on adaptive thresholding and reconstruction based on a minimal spanning tree. We improved this workflow with an algorithm that reconnects neuron segments that are disconnected after adaptive thresholding, using paths extracted from the image stacks with the Fast Marching method. RESULTS: By reducing the likelihood that disconnected segments were incorrectly connected to neighboring segments, our procedure generated excellent morphological reconstructions of AII amacrine cells. COMPARISON WITH EXISTING METHODS: Reconstructing an AII amacrine cell required about 2h computing time, compared to 2-4days for manual reconstruction. To evaluate the performance of our method relative to manual reconstruction, we performed detailed analysis using a measure of tree structure similarity (DIADEM score), the degree of projection area overlap (Dice coefficient), and branch statistics. CONCLUSIONS: We expect our procedure to be generally useful for morphological reconstruction of neurons filled with fluorescent dyes.

White matter fiber tracking directed by interpolating splines and a methodological framework for evaluation.

Image-based tractography of white matter (WM) fiber bundles in the brain using diffusion weighted MRI (DW-MRI) has become a useful tool in basic and clinical neuroscience. However, proper tracking is challenging due to the anatomical complexity of fiber pathways, the coarse resolution of clinically applicable whole-brain in vivo imaging techniques, and the difficulties associated with verification. In this study we introduce a new tractography algorithm using splines (denoted Spline). Spline reconstructs smooth fiber trajectories iteratively, in contrast to most other tractography algorithms that create piecewise linear fiber tract segments, followed by spline fitting. Using DW-MRI recordings from eight healthy elderly people participating in a longitudinal study of cognitive aging, we compare our Spline algorithm to two state-of-the-art tracking methods from the TrackVis software suite. The comparison is done quantitatively using diffusion metrics (fractional anisotropy, FA), with both (1) tract averaging, (2) longitudinal linear mixed-effects model fitting, and (3) detailed along-tract analysis. Further validation is done on recordings from a diffusion hardware phantom, mimicking a coronal brain slice, with a known ground truth. Results from the longitudinal aging study showed high sensitivity of Spline tracking to individual aging patterns of mean FA when combined with linear mixed-effects modeling, moderately strong differences in the along-tract analysis of specific tracts, whereas the tract-averaged comparison using simple linear OLS regression revealed less differences between Spline and the two other tractography algorithms. In the brain phantom experiments with a ground truth, we demonstrated improved tracking ability of Spline compared to the two reference tractography algorithms being tested.

Semi-automated segmentation of the sigmoid and descending colon for radiotherapy planning using the fast marching method.

A fast and accurate segmentation of organs at risk, such as the healthy colon, would be of benefit for planning of radiotherapy, in particular in an adaptive scenario. For the treatment of pelvic tumours, a great challenge is the segmentation of the most adjacent and sensitive parts of the gastrointestinal tract, the sigmoid and descending colon. We propose a semi-automated method to segment these bowel parts using the fast marching (FM) method. Standard 3D computed tomography (CT) image data obtained from routine radiotherapy planning were used. Our pre-processing steps distinguish the intestine, muscles and air from connective tissue. The core part of our method separates the sigmoid and descending colon from the muscles and other segments of the intestine. This is done by utilizing the ability of the FM method to compute a specified minimal energy functional integrated along a path, and thereby extracting the colon centre line between user-defined control points in the sigmoid and descending colon. Further, we reconstruct the tube-shaped geometry of the sigmoid and descending colon by fitting ellipsoids to points on the path and by adding adjacent voxels that are likely voxels belonging to these bowel parts. Our results were compared to manually outlined sigmoid and descending colon, and evaluated using the Dice coefficient (DC). Tests on 11 patients gave an average DC of 0.83 (+/-0.07) with little user interaction. We conclude that the proposed method makes it possible to fast and accurately segment the sigmoid and descending colon from routine CT image data.