Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning.

BACKGROUND AND PURPOSE: Recent developments in deep learning methods offer a potential solution to the need for alternative imaging methods due to concerns about the toxicity of gadolinium-based contrast agents. The purpose of the study was to synthesize virtual gadolinium contrast-enhanced T1-weighted MR images from noncontrast multiparametric MR images in patients with primary brain tumors by using deep learning. MATERIALS AND METHODS: We trained and validated a deep learning network by using MR images from 335 subjects in the Brain Tumor Segmentation Challenge 2019 training data set. A held out set of 125 subjects from the Brain Tumor Segmentation Challenge 2019 validation data set was used to test the generalization of the model. A residual inception DenseNet network, called T1c-ET, was developed and trained to simultaneously synthesize virtual contrast-enhanced T1-weighted (vT1c) images and segment the enhancing portions of the tumor. Three expert neuroradiologists independently scored the synthesized vT1c images by using a 3-point Likert scale, evaluating image quality and contrast enhancement against ground truth T1c images (1 = poor, 2 = good, 3 = excellent). RESULTS: The synthesized vT1c images achieved structural similarity index, peak signal-to-noise ratio, and normalized mean square error scores of 0.91, 64.35, and 0.03, respectively. There was moderate interobserver agreement between the 3 raters, regarding the algorithm's performance in predicting contrast enhancement, with a Fleiss kappa value of 0.61. Our model was able to accurately predict contrast enhancement in 88.8% of the cases (scores of 2 to 3 on the 3-point scale). CONCLUSIONS: We developed a novel deep learning architecture to synthesize virtual postcontrast enhancement by using only conventional noncontrast brain MR images. Our results demonstrate the potential of deep learning methods to reduce the need for gadolinium contrast in the evaluation of primary brain tumors.

Errata: Brain tumor IDH, 1p/19q, and MGMT molecular classification using MRI-based deep learning: an initial study on the effect of motion and motion correction.

[This corrects the article DOI: 10.1117/1.JMI.9.1.016001.].

Brain tumor IDH, 1p/19q, and MGMT molecular classification using MRI-based deep learning: an initial study on the effect of motion and motion correction.

Purpose: Deep learning has shown promise for predicting the molecular profiles of gliomas using MR images. Prior to clinical implementation, ensuring robustness to real-world problems, such as patient motion, is crucial. The purpose of this study is to perform a preliminary evaluation on the effects of simulated motion artifact on glioma marker classifier performance and determine if motion correction can restore classification accuracies. Approach: T2w images and molecular information were retrieved from the TCIA and TCGA databases. Simulated motion was added in the k-space domain along the phase encoding direction. Classifier performance for IDH mutation, 1p/19q co-deletion, and MGMT methylation was assessed over the range of 0% to 100% corrupted k-space lines. Rudimentary motion correction networks were trained on the motion-corrupted images. The performance of the three glioma marker classifiers was then evaluated on the motion-corrected images. Results: Glioma marker classifier performance decreased markedly with increasing motion corruption. Applying motion correction effectively restored classification accuracy for even the most motion-corrupted images. For isocitrate dehydrogenase (IDH) classification, 99% accuracy was achieved, exceeding the original performance of the network and representing a new benchmark in non-invasive MRI-based IDH classification. Conclusions: Robust motion correction can facilitate highly accurate deep learning MRI-based molecular marker classification, rivaling invasive tissue-based characterization methods. Motion correction may be able to increase classification accuracy even in the absence of a visible artifact, representing a new strategy for boosting classifier performance.

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

Fundamentals of Radiation Oncology for Treatment of Vertebral Metastases.

The fields of both radiology and radiation oncology have evolved considerably in the past few decades, resulting in an increased ability to delineate between tumor and normal tissue to precisely target and treat vertebral metastases with radiation therapy. These scientific advances have also led to improvements in assessing treatment response and diagnosing toxic effects related to radiation treatment. However, despite technological innovations yielding greatly improved rates of palliative relief and local control of osseous spinal metastases, radiation therapy can still lead to a number of acute and delayed posttreatment complications. Treatment-related adverse effects may include pain flare, esophageal toxic effects, dermatitis, vertebral compression fracture, radiation myelopathy, and myositis, among others. The authors provide an overview of the multidisciplinary approach to the treatment of spinal metastases, indications for surgical management versus radiation therapy, various radiation technologies and techniques (along with their applications for spinal metastases), and current principles of treatment planning for conventional and stereotactic radiation treatment. Different radiologic criteria for assessment of treatment response, recent advances in radiologic imaging, and both common and rare complications related to spinal irradiation are also discussed, along with the imaging characteristics of various adverse effects. Familiarity with these topics will not only assist the diagnostic radiologist in assessing treatment response and diagnosing treatment-related complications but will also allow more effective collaboration between diagnostic radiologists and radiation oncologists to guide management decisions and ensure high-quality patient care. ©RSNA, 2021.

Fundamentals of Radiation Oncology for Neurologic Imaging.

Although the physical and biologic principles of radiation therapy have remained relatively unchanged, a technologic renaissance has led to continuous and ever-changing growth in the field of radiation oncology. As a result, medical devices, techniques, and indications have changed considerably during the past 20-30 years. For example, advances in CT and MRI have revolutionized the treatment planning process for a variety of central nervous system diseases, including primary and metastatic tumors, vascular malformations, and inflammatory diseases. The resultant improved ability to delineate normal from abnormal tissue has enabled radiation oncologists to achieve more precise targeting and helped to mitigate treatment-related complications. Nevertheless, posttreatment complications still occur and can pose a diagnostic challenge for radiologists. These complications can be divided into acute, early-delayed, and late-delayed complications on the basis of the time that they manifest after radiation therapy and include leukoencephalopathy, vascular complications, and secondary neoplasms. The different irradiation technologies and applications of these technologies in the brain, current concepts used in treatment planning, and essential roles of the radiation oncologist in the setting of brain disease are reviewed. In addition, relevant imaging findings that can be used to delineate the extent of disease before treatment, and the expected posttreatment imaging changes are described. Common and uncommon complications related to radiation therapy and the associated imaging manifestations also are discussed. Familiarity with these entities may aid the radiologist in making the diagnosis and help guide appropriate management. ©RSNA, 2020.