Characterizing Sensitive Cardiac Substructure Excursion Due to Respiration.

PURPOSE: Whole-heart dose metrics are not as strongly linked to late cardiac morbidities as radiation doses to individual cardiac substructures. Our aim was to characterize the excursion and dosimetric variation throughout respiration of sensitive cardiac substructures for future robust safety margin design. METHODS AND MATERIALS: Eleven patients with cancer treatments in the thorax underwent 4-phase noncontrast 4-dimensional computed tomography (4DCT) with T2-weighted magnetic resonance imaging in end-exhale. The end-exhale phase of the 4DCT was rigidly registered with the magnetic resonance imaging and refined with an assisted alignment surrounding the heart from which 13 substructures (chambers, great vessels, coronary arteries, etc) were contoured by a radiation oncologist on the 4DCT. Contours were deformed to the other respiratory phases via an intensity-based deformable registration for radiation oncologist verification. Measurements of centroid and volume were evaluated between phases. Mean and maximum dose to substructures were evaluated across respiratory phases for the breast (n = 8) and thoracic cancer (n = 3) cohorts. RESULTS: Paired t tests revealed reasonable maintenance of geometric and anatomic properties (P < .05 for 4/39 volume comparisons). Maximum displacements >5 mm were found for 24.8%, 8.5%, and 64.5% of the cases in the left-right, anterior-posterior, and superior-inferior axes, respectively. Vector displacements were largest for the inferior vena cava and the right coronary artery, with displacements up to 17.9 mm. In breast, the left anterior descending artery Dmean varied 3.03 ± 1.75 Gy (range, 0.53-5.18 Gy) throughout respiration whereas lung showed patient-specific results. Across all patients, whole heart metrics were insensitive to breathing phase (mean and maximum dose variations <0.5 Gy). CONCLUSIONS: This study characterized the intrafraction displacement of the cardiac substructures through the respiratory cycle and highlighted their increased dosimetric sensitivity to local dose changes not captured by whole heart metrics. Results suggest value of cardiac substructure margin generation to enable more robust cardiac sparing and to reduce the effect of respiration on overall treatment plan quality.

Quantifying inter-fraction cardiac substructure displacement during radiotherapy via magnetic resonance imaging guidance.

PURPOSE: Emerging evidence suggests cardiac substructures are highly radiosensitive during radiation therapy for cancer treatment. However, variability in substructure position after tumor localization has not been well characterized. This study quantifies inter-fraction displacement and planning organ at risk volumes (PRVs) of substructures by leveraging the excellent soft tissue contrast of magnetic resonance imaging (MRI). METHODS: Eighteen retrospectively evaluated patients underwent radiotherapy for intrathoracic tumors with a 0.35 T MRI-guided linear accelerator. Imaging was acquired at a 17-25 s breath-hold (resolution 1.5 × 1.5 × 3 mm3). Three to four daily MRIs per patient (n = 71) were rigidly registered to the planning MRI-simulation based on tumor matching. Deep learning or atlas-based segmentation propagated 13 substructures (e.g., chambers, coronary arteries, great vessels) to daily MRIs and were verified by two radiation oncologists. Daily centroid displacements from MRI-simulation were quantified and PRVs were calculated. RESULTS: Across substructures, inter-fraction displacements for 14% in the left-right, 18% in the anterior-posterior, and 21% of fractions in the superior-inferior were > 5 mm. Due to lack of breath-hold compliance, ~4% of all structures shifted > 10 mm in any axis. For the chambers, median displacements were 1.8, 1.9, and 2.2 mm in the left-right, anterior-posterior, and superior-inferior axis, respectively. Great vessels demonstrated larger displacements (> 3 mm) in the superior-inferior axis (43% of shifts) and were only 25% (left-right) and 29% (anterior-posterior) elsewhere. PRVs from 3 to 5 mm were determined as anisotropic substructure-specific margins. CONCLUSIONS: This exploratory work derived substructure-specific safety margins to ensure highly effective cardiac sparing. Findings require validation in a larger cohort for robust margin derivation and for applications in prospective clinical trials.

A deep dive into understanding tumor foci classification using multiparametric MRI based on convolutional neural network.

PURPOSE: Deep learning models have had a great success in disease classifications using large data pools of skin cancer images or lung X-rays. However, data scarcity has been the roadblock of applying deep learning models directly on prostate multiparametric MRI (mpMRI). Although model interpretation has been heavily studied for natural images for the past few years, there has been a lack of interpretation of deep learning models trained on medical images. In this paper, an efficient convolutional neural network (CNN) was developed and the model interpretation at various convolutional layers was systematically analyzed to improve the understanding of how CNN interprets multimodality medical images and the predictive powers of features at each layer. The problem of small sample size was addressed by feeding the intermediate features into a traditional classification algorithm known as weighted extreme learning machine (wELM), with imbalanced distribution among output categories taken into consideration. METHODS: The training data collection used a retrospective set of prostate MR studies, from SPIE-AAPM-NCI PROSTATEx Challenges held in 2017. Three hundred twenty biopsy samples of lesions from 201 prostate cancer patients were diagnosed and identified as clinically significant (malignant) or not significant (benign). All studies included T2-weighted (T2W), proton density-weighted (PD-W), dynamic contrast enhanced (DCE) and diffusion-weighted (DW) imaging. After registration and lesion-based normalization, a CNN with four convolutional layers were developed and trained on tenfold cross validation. The features from intermediate layers were then extracted as input to wELM to test the discriminative power of each individual layer. The best performing model from the tenfolds was chosen to be tested on the holdout cohort from two sources. Feature maps after each convolutional layer were then visualized to monitor the trend, as the layer propagated. Scatter plotting was used to visualize the transformation of data distribution. Finally, a class activation map was generated to highlight the region of interest based on the model perspective. RESULTS: Experimental trials indicated that the best input for CNN was a modality combination of T2W, apparent diffusion coefficient (ADC) and DWIb50 . The convolutional features from CNN paired with a weighted extreme learning classifier showed substantial performance compared to a CNN end-to-end training model. The feature map visualization reveals similar findings on natural images where lower layers tend to learn lower level features such as edges, intensity changes, etc, while higher layers learn more abstract and task-related concept such as the lesion region. The generated saliency map revealed that the model was able to focus on the region of interest where the lesion resided and filter out background information, including prostate boundary, rectum, etc. CONCLUSIONS: This work designs a customized workflow for the small and imbalanced dataset of prostate mpMRI where features were extracted from a deep learning model and then analyzed by a traditional machine learning classifier. In addition, this work contributes to revealing how deep learning models interpret mpMRI for prostate cancer patient stratification.

Cardiac substructure segmentation with deep learning for improved cardiac sparing.

PURPOSE: Radiation dose to cardiac substructures is related to radiation-induced heart disease. However, substructures are not considered in radiation therapy planning (RTP) due to poor visualization on CT. Therefore, we developed a novel deep learning (DL) pipeline leveraging MRI's soft tissue contrast coupled with CT for state-of-the-art cardiac substructure segmentation requiring a single, non-contrast CT input. MATERIALS/METHODS: Thirty-two left-sided whole-breast cancer patients underwent cardiac T2 MRI and CT-simulation. A rigid cardiac-confined MR/CT registration enabled ground truth delineations of 12 substructures (chambers, great vessels (GVs), coronary arteries (CAs), etc.). Paired MRI/CT data (25 patients) were placed into separate image channels to train a three-dimensional (3D) neural network using the entire 3D image. Deep supervision and a Dice-weighted multi-class loss function were applied. Results were assessed pre/post augmentation and post-processing (3D conditional random field (CRF)). Results for 11 test CTs (seven unique patients) were compared to ground truth and a multi-atlas method (MA) via Dice similarity coefficient (DSC), mean distance to agreement (MDA), and Wilcoxon signed-ranks tests. Three physicians evaluated clinical acceptance via consensus scoring (5-point scale). RESULTS: The model stabilized in ~19 h (200 epochs, training error <0.001). Augmentation and CRF increased DSC 5.0 ± 7.9% and 1.2 ± 2.5%, across substructures, respectively. DL provided accurate segmentations for chambers (DSC = 0.88 ± 0.03), GVs (DSC = 0.85 ± 0.03), and pulmonary veins (DSC = 0.77 ± 0.04). Combined DSC for CAs was 0.50 ± 0.14. MDA across substructures was <2.0 mm (GV MDA = 1.24 ± 0.31 mm). No substructures had statistical volume differences (P > 0.05) to ground truth. In four cases, DL yielded left main CA contours, whereas MA segmentation failed, and provided improved consensus scores in 44/60 comparisons to MA. DL provided clinically acceptable segmentations for all graded patients for 3/4 chambers. DL contour generation took ~14 s per patient. CONCLUSIONS: These promising results suggest DL poses major efficiency and accuracy gains for cardiac substructure segmentation offering high potential for rapid implementation into RTP for improved cardiac sparing.

Volumetric and Voxel-Wise Analysis of Dominant Intraprostatic Lesions on Multiparametric MRI.

Introduction: Multiparametric MR imaging (mpMRI) has shown promising results in the diagnosis and localization of prostate cancer. Furthermore, mpMRI may play an important role in identifying the dominant intraprostatic lesion (DIL) for radiotherapy boost. We sought to investigate the level of correlation between dominant tumor foci contoured on various mpMRI sequences. Methods: mpMRI data from 90 patients with MR-guided biopsy-proven prostate cancer were obtained from the SPIE-AAPM-NCI Prostate MR Classification Challenge. Each case consisted of T2-weighted (T2W), apparent diffusion coefficient (ADC), and Ktrans images computed from dynamic contrast-enhanced sequences. All image sets were rigidly co-registered, and the dominant tumor foci were identified and contoured for each MRI sequence. Hausdorff distance (HD), mean distance to agreement (MDA), and Dice and Jaccard coefficients were calculated between the contours for each pair of MRI sequences (i.e., T2 vs. ADC, T2 vs. Ktrans, and ADC vs. Ktrans). The voxel wise spearman correlation was also obtained between these image pairs. Results: The DILs were located in the anterior fibromuscular stroma, central zone, peripheral zone, and transition zone in 35.2, 5.6, 32.4, and 25.4% of patients, respectively. Gleason grade groups 1-5 represented 29.6, 40.8, 15.5, and 14.1% of the study population, respectively (with group grades 4 and 5 analyzed together). The mean contour volumes for the T2W images, and the ADC and Ktrans maps were 2.14 ± 2.1, 2.22 ± 2.2, and 1.84 ± 1.5 mL, respectively. Ktrans values were indistinguishable between cancerous regions and the rest of prostatic regions for 19 patients. The Dice coefficient and Jaccard index were 0.74 ± 0.13, 0.60 ± 0.15 for T2W-ADC and 0.61 ± 0.16, 0.46 ± 0.16 for T2W-Ktrans. The voxel-based Spearman correlations were 0.20 ± 0.20 for T2W-ADC and 0.13 ± 0.25 for T2W-Ktrans. Conclusions: The DIL contoured on T2W images had a high level of agreement with those contoured on ADC maps, but there was little to no quantitative correlation of these results with tumor location and Gleason grade group. Technical hurdles are yet to be solved for precision radiotherapy to target the DILs based on physiological imaging. A Boolean sum volume (BSV) incorporating all available MR sequences may be reasonable in delineating the DIL boost volume.

Cardiac Substructure Segmentation and Dosimetry Using a Novel Hybrid Magnetic Resonance and Computed Tomography Cardiac Atlas.

PURPOSE: Radiation dose to the heart and cardiac substructures has been linked to cardiotoxicities. Because cardiac substructures are poorly visualized on treatment-planning computed tomography (CT) scans, we used the superior soft-tissue contrast of magnetic resonance (MR) imaging to optimize a hybrid MR/CT atlas for substructure dose assessment using CT. METHODS AND MATERIALS: Thirty-one patients with left-sided breast cancer underwent a T2-weighted MR imaging scan and noncontrast simulation CT scans. A radiation oncologist delineated 13 substructures (chambers, great vessels, coronary arteries, etc) using MR/CT information via cardiac-confined rigid registration. Ground-truth contours for 20 patients were inputted into an intensity-based deformable registration atlas and applied to 11 validation patients. Automatic segmentations involved using majority vote and Simultaneous Truth and Performance Level Estimation (STAPLE) strategies with 1 to 15 atlas matches. Performance was evaluated via Dice similarity coefficient (DSC), mean distance to agreement, and centroid displacement. Three physicians evaluated segmentation performance via consensus scoring by using a 5-point scale. Dosimetric assessment included measurements of mean heart dose, left ventricular volume receiving 5 Gy, and left anterior descending artery mean and maximum doses. RESULTS: Atlas approaches performed similarly well, with 7 of 13 substructures (heart, chambers, ascending aorta, and pulmonary artery) having DSC >0.75 when averaged over 11 validation patients. Coronary artery segmentations were not successful with the atlas-based approach (mean DSC <0.3). The STAPLE method with 10 matches yielded the highest DSC and the lowest mean distance to agreement for all high-performing substructures (omitting coronary arteries). For the STAPLE method with 10 matches, >50% of all validation contours had centroid displacements <3.0 mm, with the largest shifts in the coronary arteries. Atlas-generated contours had no statistical difference from ground truth for left anterior descending artery maximum dose, mean heart dose, and left ventricular volume receiving 5 Gy (P > .05). Qualitative contour grading showed that 8 substructures required minor modifications. CONCLUSIONS: The hybrid MR/CT atlas provided reliable segmentations of chambers, heart, and great vessels for patients undergoing noncontrast CT, suggesting potential widespread applicability for routine treatment planning.

Ductal carcinoma in situ of the breast: MR imaging findings with histopathologic correlation.

Ductal carcinoma in situ (DCIS) is a noninvasive malignancy that is commonly encountered at routine breast imaging. It may be a primary tumor or may be seen in association with other focal higher-grade tumors. Early detection is important because of the large proportion of DCIS that can progress to invasive carcinoma. The extent of DCIS involvement is frequently underestimated at mammography, which can reliably help detect only calcified DCIS; consequently, magnetic resonance (MR) imaging evaluation can alter the course of treatment. Seven biopsy-proved cases of DCIS were evaluated with T2-weighted MR imaging sequences, as well as T1-weighted sequences performed both before and after contrast material administration. The signal intensity and enhancement patterns of the tumors were analyzed, and the findings were correlated with the relevant underlying histopathologic features. Common enhancement patterns of DCIS include clumped linear-ductal enhancement, clumped focal enhancement, and masslike enhancement. The most common enhancement distribution pattern is segmental, followed by focal, diffuse, linear-ductal, and regional patterns. At T2-weighted MR imaging, DCIS is typically isointense relative to breast parenchyma; less commonly, it is hypointense or hyperintense. The use of MR imaging in the evaluation of DCIS is controversial, and many questions remain with regard to treatment and management. However, breast MR imaging can be extremely useful in the preoperative diagnosis and evaluation of DCIS when used in conjunction with other imaging modalities.