Abstract. MR-only radiotherapy treatment planning requires accurate MR-to-CT synthesis. Current deep learning methods for MR-to-CT synthesis depend on pairwise aligned MR and CT training images of the same patient. However, misalignment between paired images could lead to errors in synthesized CT images. To overcome this, we propose to train a generative adversarial network (GAN) with unpaired MR and CT images. A GAN consisting of two synthesis convolutional neural networks (CNNs) and two discriminator CNNs was trained with cycle consistency to transform 2D brain MR image slices into 2D brain CT image slices and vice versa. Brain MR and CT images of 24 patients were analyzed. A quantitative evaluation showed that the model was able to synthesize CT images that closely approximate reference CT images, and was able to outperform a GAN model trained with paired MR and CT images.
To enable magnetic resonance (MR)-only radiotherapy and facilitate modelling of radiation attenuation in humans, synthetic CT (sCT) images need to be generated. Considering the application of MR-guided radiotherapy and online adaptive replanning, sCT generation should occur within minutes. This work aims at assessing whether an existing deep learning network can rapidly generate sCT images for accurate MR-based dose calculations in the entire pelvis. A study was conducted on data of 91 patients with prostate (59), rectal (18) and cervical (14) cancer who underwent external beam radiotherapy acquiring both CT and MRI for patients' simulation. Dixon reconstructed water, fat and in-phase images obtained from a conventional dual gradient-recalled echo sequence were used to generate sCT images. A conditional generative adversarial network (cGAN) was trained in a paired fashion on 2D transverse slices of 32 prostate cancer patients. The trained network was tested on the remaining patients to generate sCT images. For 30 patients in the test set, dose recalculations of the clinical plan were performed on sCT images. Dose distributions were evaluated comparing voxel-based dose differences, gamma and dose-volume histogram (DVH) analysis. The sCT generation required 5.6 s and 21 s for a single patient volume on a GPU and CPU, respectively. On average, sCT images resulted in a higher dose to the target of maximum 0.3%. The average gamma pass rates using the 3%, 3 mm and 2%, 2 mm criteria were above 97 and 91%, respectively, for all volumes of interests considered. All DVH points calculated on sCT differed less than ±2.5% from the corresponding points on CT. Results suggest that accurate MR-based dose calculation using sCT images generated with a cGAN trained on prostate cancer patients is feasible for the entire pelvis. The sCT generation was sufficiently fast for integration in an MR-guided radiotherapy workflow.
Superparamagnetic iron oxide nanoparticles (SPIONs) have been receiving great attention lately due to their various biomedical applications, such as in MR imaging and image guided drug delivery. However, their systemic administration still remains a challenge. In this study, the ability of biodegradable thermosensitive polymeric micelles to stably encapsulate hydrophobic oleic-acid-coated SPIONs (diameter 5-10 nm) was investigated, to result in a system fulfilling the requirements for systemic administration. The micelles were composed of amphiphilic, thermosensitive, and biodegradable block copolymers of poly(ethylene glycol)-b-poly[N-(2-hydroxypropyl) methacrylamide dilactate] (mPEG-b-p(HPMAm-Lac2)). The encapsulation was performed by addition of one volume of SPIONs in THF to nine volumes of a cold aqueous mPEG-b-p(HPMAm-Lac2) solution (0 degrees C; below the cloud point of the polymer), followed by rapid heating of the resulting mixture to 50 degrees C, to induce micelle formation ("rapid heating" procedure). Dynamic light scattering (DLS) measurements revealed that approximately 200 nm particles (PDI=0.2) were formed, while transmission electron microscopy (TEM) analysis demonstrated that clusters of SPIONs were present in the core of the micelles. A maximum loading of 40% was obtained, while magnetic resonance imaging (MRI) scanning of the samples demonstrated that the SPION-loaded micelles had high r2 and r2* relaxivities. Furthermore, the r2* values were found to be at least 2-fold higher than the r2 values, confirming the clustering of the SPIONs in the micellar core. The particles showed excellent stability under physiological conditions for 7 days, even in the presence of fetal bovine serum. This, together with their ease of preparation and their size of approximately 200 nm, makes these systems highly suitable for image-guided drug delivery.
This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Stroke is a major cause of mortality and long-term disability worldwide. The initial changes in local perfusion and tissue status underlying loss of brain function are increasingly investigated with noninvasive imaging methods. In addition, there is a growing interest in imaging of processes that contribute to post-stroke recovery. In this review, we discuss the application of magnetic resonance imaging (MRI) to assess the formation of new vessels by angiogenesis, which is hypothesized to participate in brain plasticity and functional recovery after stroke. The excellent soft tissue contrast, high spatial and temporal resolution, and versatility render MRI particularly suitable to monitor the dynamic processes involved in vascular remodeling after stroke. Here we review recent advances in the field of MR imaging that are aimed at assessment of tissue perfusion and microvascular characteristics, including cerebral blood flow and volume, vascular density, size and integrity. The potential of MRI to noninvasively monitor the evolution of post-ischemic angiogenic processes is demonstrated from a variety of in vivo studies in experimental stroke models. Finally, we discuss some pitfalls and limitations that may critically affect the accuracy and interpretation of MRI-based measures of (neo)vascularization after stroke.
Purpose To develop and evaluate a patch‐based convolutional neural network (CNN) to generate synthetic computed tomography (sCT) images for magnetic resonance (MR)‐only workflow for radiotherapy of head and neck tumors. A patch‐based deep learning method was chosen to improve robustness to abnormal anatomies caused by large tumors, surgical excisions, or dental artifacts. In this study, we evaluate whether the generated sCT images enable accurate MR‐based dose calculations in the head and neck region. Methods We conducted a retrospective study on 34 patients with head and neck cancer who underwent both CT and MR imaging for radiotherapy treatment planning. To generate the sCTs, a large field‐of‐view T2‐weighted Turbo Spin Echo MR sequence was used from the clinical protocol for multiple types of head and neck tumors. To align images as well as possible on a voxel‐wise level, CT scans were nonrigidly registered to the MR (CTreg). The CNN was based on a U‐net architecture and consisted of 14 layers with 3 × 3 × 3 filters. Patches of 48 × 48 × 48 were randomly extracted and fed into the training. sCTs were created for all patients using threefold cross validation. For each patient, the clinical CT‐based treatment plan was recalculated on sCT using Monaco TPS (Elekta). We evaluated mean absolute error (MAE) and mean error (ME) within the body contours and dice scores in air and bone mask. Also, dose differences and gamma pass rates between CT‐ and sCT‐based plans inside the body contours were calculated. Results sCT generation took 4 min per patient. The MAE over the patient population of the sCT within the intersection of body contours was 75 ± 9 Hounsfield Units (HU) (±1 SD), and the ME was 9 ± 11 HU. Dice scores of the air and bone masks (CTreg vs sCT) were 0.79 ± 0.08 and 0.70 ± 0.07, respectively. Dosimetric analysis showed mean deviations of −0.03% ± 0.05% for dose within the body contours and −0.07% ± 0.22% inside the >90% dose volume. Dental artifacts obscuring the CT could be circumvented in the sCT by the CNN‐based approach in combination with Turbo Spin Echo (TSE) magnetic resonance imaging (MRI) sequence that typically is less prone to susceptibility artifacts. Conclusions The presented CNN generated sCTs from conventional MR images without adding scan time to the acquisition. Dosimetric evaluation suggests that dose calculations performed on the sCTs are accurate, and can therefore be used for MR‐only radiotherapy treatment planning of the head and neck.
166 Ho-poly(L-lactic acid) microspheres allow for quantitative imaging with MR imaging or SPECT for microsphere biodistribution assessment after radioembolization. The purpose of this study was to evaluate SPECT-and MR imaging-based dosimetry in the first patients treated with 166 Ho radioembolization. Methods: Fifteen patients with unresectable, chemorefractory liver metastases of any origin were enrolled in this phase 1 study and were treated with 166 Ho radioembolization according to a dose escalation protocol . The contours of all liver segments and all discernible tumors were manually delineated on T2-weighted posttreatment MR images and registered to the posttreatment SPECT images (n 5 9) or SPECT/CT images (n 5 6) and MR imagingbased R 2 * maps (n 5 14). Dosimetry was based on SPECT (n 5 15) and MR imaging (n 5 9) for all volumes of interest, tumor-tonontumor (T/N) activity concentration ratios were calculated, and correlation and agreement of MR imaging-and SPECT-based measurements were evaluated. Results: The median overall T/N ratio was 1.4 based on SPECT (range, 0.9-2.8) and 1.4 based on MR imaging (range, 1.1-3.1). In 6 of 15 patients (40%), all tumors had received an activity concentration equal to or higher than the normal liver (T/N ratio $ 1). Analysis of SPECT and MR imaging measurements for dose to liver segments yielded a high correlation (R 2 5 0.91) and a moderate agreement (mean bias, 3.7 Gy; 95% limits of agreement, 211.2 to 18.7). Conclusion: With the use of 166 Ho-microspheres, in vivo dosimetry is feasible on the basis of both SPECT and MR imaging, which enables personalized treatment by selective targeting of inadequately treated tumors. Radi oembolization is an interventional oncologic treatment during which radioactive microspheres are administered in the arterial vessels supplying the liver and its tumors. The rationale behind this intraarterial liver treatment is that liver tumors are predominantly supplied by arterial blood, in contrast to the nontumorous liver, which relies mainly on the portal vein for its blood supply. Injection of a substance into the hepatic artery will therefore selectively target the tumorous tissue (1). Currently, the commercially available microspheres that are used for radioembolization are labeled with 90 Y. To be able to quantitatively evaluate the optimal and selective distribution of microspheres to the liver tumors, posttreatment imaging is indispensable. For that reason, optimization of posttreatment imaging of 90 Y-microspheres with bremsstrahlung SPECT and PET has recently gained interest (2-5).166 Ho-poly(L-lactic acid) microspheres have been developed at our institute as an alternative to 90 Y-microspheres specifically to be able to visualize the in vivo biodistribution of microspheres after radioembolization. 166 Ho-microspheres can be imaged with both SPECT and MR imaging, using the emission of g-photon radiation and the paramagnetic properties of holmium, respectively (6-10). Exploiting these qualities, multimodal dosimetry becomes feasible,...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.