Frontiers in radiology最新文献

Radiation-induced cerebral necrosis, also known as radiation encephalopathy, is a debilitating condition that significantly impacts the quality of life for affected patients. Secondary central nervous system lymphoma (SCNSL) typically arises from highly aggressive mature B-cell lymphoma, but rarely from extranodal natural killer T-cell lymphoma (ENKTL). Treatment will be guided by differentiation between lymphoma progression from brain necrosis, and is particularly important for critically ill patients in an acute setting. However, differential diagnosis remains challenging because they share similar clinical manifestations and have no specific imaging features. We present the case of a 52-year-old man with ENKTL who suffered an emergency brain herniation secondary to massive radiation necrosis. The diagnosis established by brain biopsy ultimately led to appropriate treatment. The importance of the diagnostic biopsy is highlighted in this case for distinguishing between radiation necrosis and SCNSL.

Purpose: To develop a deep learning-based method to retrospectively quantify T2 from conventional T1- and T2-weighted images.

Methods: Twenty-five subjects were imaged using a multi-echo spin-echo sequence to estimate reference prostate T2 maps. Conventional T1- and T2-weighted images were acquired as the input images. A U-Net based neural network was developed to directly estimate T2 maps from the weighted images using a four-fold cross-validation training strategy. The structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), mean percentage error (MPE), and Pearson correlation coefficient were calculated to evaluate the quality of network-estimated T2 maps. To explore the potential of this approach in clinical practice, a retrospective T2 quantification was performed on a high-risk prostate cancer cohort (Group 1) and a low-risk active surveillance cohort (Group 2). Tumor and non-tumor T2 values were evaluated by an experienced radiologist based on region of interest (ROI) analysis.

Results: The T2 maps generated by the trained network were consistent with the corresponding reference. Prostate tissue structures and contrast were well preserved, with a PSNR of 26.41 ± 1.17 dB, an SSIM of 0.85 ± 0.02, and a Pearson correlation coefficient of 0.86. Quantitative ROI analyses performed on 38 prostate cancer patients revealed estimated T2 values of 80.4 ± 14.4 ms and 106.8 ± 16.3 ms for tumor and non-tumor regions, respectively. ROI measurements showed a significant difference between tumor and non-tumor regions of the estimated T2 maps (P < 0.001). In the two-timepoints active surveillance cohort, patients defined as progressors exhibited lower estimated T2 values of the tumor ROIs at the second time point compared to the first time point. Additionally, the T2 difference between two time points for progressors was significantly greater than that for non-progressors (P = 0.010).

Conclusion: A deep learning method was developed to estimate prostate T2 maps retrospectively from clinically acquired T1- and T2-weighted images, which has the potential to improve prostate cancer diagnosis and characterization without requiring extra scans.

Introduction: Numerous techniques for myelin water imaging (MWI) have been devised to specifically assess alterations in myelin. The biomarker employed to measure changes in myelin content is known as the myelin water fraction (MWF). The short TR adiabatic inversion recovery (STAIR) sequence has recently been identified as a highly effective method for calculating MWF. The purpose of this study is to develop a new clinical transitional myelin water imaging (MWI) technique that combines STAIR preparation and echo-planar imaging (EPI) (STAIR-EPI) sequence for data acquisition.

Methods: Myelin water (MW) in the brain has shorter T₁ and T₂ relaxation times than intracellular and extracellular water. In the proposed STAIR-EPI sequence, a short TR (e.g., ≤300 ms) together with an optimized inversion time enable robust long T₁ water suppression with a wide range of T₁ values [i.e., (600, 2,000) ms]. The EPI allows fast data acquisition of the remaining MW signals. Seven healthy volunteers and seven patients with multiple sclerosis (MS) were recruited and scanned in this study. The apparent myelin water fraction (aMWF), defined as the signal ratio of MW to total water, was measured in the lesions and normal-appearing white matter (NAWM) in MS patients and compared with those measured in the normal white matter (NWM) in healthy volunteers.

Results: As seen in the STAIR-EPI images acquired from MS patients, the MS lesions show lower signal intensities than NAWM do. The aMWF measurements for both MS lesions (3.6 ± 1.3%) and NAWM (8.6 ± 1.2%) in MS patients are significantly lower than NWM (10 ± 1.3%) in healthy volunteers (P < 0.001).

Discussion: The proposed STAIR-EPI technique, which can be implemented in MRI scanners from all vendors, is able to detect myelin loss in both MS lesions and NAWM in MS patients.

Purpose: The goal of this work is to explore the best optimizers for deep learning in the context of medical image segmentation and to provide guidance on how to design segmentation networks with effective optimization strategies.

Approach: Most successful deep learning networks are trained using two types of stochastic gradient descent (SGD) algorithms: adaptive learning and accelerated schemes. Adaptive learning helps with fast convergence by starting with a larger learning rate (LR) and gradually decreasing it. Momentum optimizers are particularly effective at quickly optimizing neural networks within the accelerated schemes category. By revealing the potential interplay between these two types of algorithms [LR and momentum optimizers or momentum rate (MR) in short], in this article, we explore the two variants of SGD algorithms in a single setting. We suggest using cyclic learning as the base optimizer and integrating optimal values of learning rate and momentum rate. The new optimization function proposed in this work is based on the Nesterov accelerated gradient optimizer, which is more efficient computationally and has better generalization capabilities compared to other adaptive optimizers.

Results: We investigated the relationship of LR and MR under an important problem of medical image segmentation of cardiac structures from MRI and CT scans. We conducted experiments using the cardiac imaging dataset from the ACDC challenge of MICCAI 2017, and four different architectures were shown to be successful for cardiac image segmentation problems. Our comprehensive evaluations demonstrated that the proposed optimizer achieved better results (over a 2% improvement in the dice metric) than other optimizers in the deep learning literature with similar or lower computational cost in both single and multi-object segmentation settings.

Conclusions: We hypothesized that the combination of accelerated and adaptive optimization methods can have a drastic effect in medical image segmentation performances. To this end, we proposed a new cyclic optimization method (Cyclic Learning/Momentum Rate) to address the efficiency and accuracy problems in deep learning-based medical image segmentation. The proposed strategy yielded better generalization in comparison to adaptive optimizers.

Purpose: The purpose of this study is to utilize a two-material decomposition to quantify bone marrow edema on a dual-energy computed tomography (DECT) scanner at the cervical, thoracic, and lumbar spine acute fractures in correlation with short tau inversion recovery (STIR) hyperintensity on magnetic resonance imaging (MRI) in comparison with the normal bone marrow.

Materials and methods: This retrospective institutional review board-approved study gathered patients over 18 years old who had acute cervical, thoracic, or lumbar spinal fractures scanned on a DECT scanner. Those who had a spinal MRI done with bone marrow STIR hyperintensity within 3 weeks of the DECT were included. The water (calcium) and fat (calcium) density (mg/cm³) measurements of the region of interest of the bone marrow were obtained at a normal anatomic equivalent site and at the fracture site where STIR hyperintensity was noted on MRI. A statistical analysis was performed using the paired t-test and Wilcoxon signed rank test (p > 0.05).

Results: A total of 20 patients met the inclusion criteria (males n = 17 males, females n = 3). A total of 32 fractures were analyzed: 19 cervical and 13 thoracolumbar. There were statistically significant differences in the water (43 ± 24 mg/cm³) and fat (36 ± 31 mg/cm³) density (mg/cm³) at the acute thoracic and lumbar spine fractures in correlation with edema on STIR images (both paired t-test <0.001, both Wilcoxon signed ranked test p < 0.01). There were no significant differences in the water (-10 ± 46 mg/cm³) or fat (+7 ± 50 mg/cm³) density (mg/cm³) at the cervical spine fractures.

Conclusion: The DECT two-material decomposition using water (calcium) and fat (calcium) analyses has the ability to quantify a bone marrow edema at the acute fracture site in the thoracic and lumbar spine.

Background: Hematocrit and lactate have an established role in trauma as indicators of bleeding and cell death, respectively. The wide availability of CT imaging and clinical data poses the question of how these can be used in combination to predict outcomes.

Purpose: To assess the utility of hematocrit or lactate trends in predicting intensive care unit (ICU) admission and hospital length of stay (LOS) in patients with torso trauma combined with clinical parameters and injury findings on CT.

Materials and methods: This was a single-center retrospective study of adults with torso trauma in one year. Trends were defined as a unit change per hour. CT findings and clinical parameters were explanatory variables. Outcomes were ICU admission and hospital LOS. Multivariate logistic and negative binomial regression models were used to calculate the odds ratio (OR) and incident rate ratio (IRR).

Results: Among 840 patients, 561 (72% males, age 39 ± 18) were included, and 168 patients (30%) were admitted to the ICU. Decreasing hematocrit trend [OR 2.54 (1.41-4.58), p = 0.002] and increasing lactate trend [OR 3.85 (1.35-11.01), p = 0.012] were associated with increased odds of ICU admission. LOS median was 2 (IQR: 1-5) days. Decreasing hematocrit trend [IRR 1.37 (1.13-1.66), p = 0.002] and increasing lactate trend [2.02 (1.43-2.85), p < 0.001] were associated with longer hospital LOS.

Conclusion: Hematocrit and lactate trends may be helpful in predicting ICU admission and LOS in torso trauma independent of organ injuries on CT, age, or admission clinical parameters.

Introduction: Methods that automatically flag poor performing predictions are drastically needed to safely implement machine learning workflows into clinical practice as well as to identify difficult cases during model training.

Methods: Disagreement between the fivefold cross-validation sub-models was quantified using dice scores between folds and summarized as a surrogate for model confidence. The summarized Interfold Dices were compared with thresholds informed by human interobserver values to determine whether final ensemble model performance should be manually reviewed.

Results: The method on all tasks efficiently flagged poor segmented images without consulting a reference standard. Using the median Interfold Dice for comparison, substantial dice score improvements after excluding flagged images was noted for the in-domain CT (0.85 ± 0.20 to 0.91 ± 0.08, 8/50 images flagged) and MR (0.76 ± 0.27 to 0.85 ± 0.09, 8/50 images flagged). Most impressively, there were dramatic dice score improvements in the simulated out-of-distribution task where the model was trained on a radical nephrectomy dataset with different contrast phases predicting a partial nephrectomy all cortico-medullary phase dataset (0.67 ± 0.36 to 0.89 ± 0.10, 122/300 images flagged).

Discussion: Comparing interfold sub-model disagreement against human interobserver values is an effective and efficient way to assess automated predictions when a reference standard is not available. This functionality provides a necessary safeguard to patient care important to safely implement automated medical image segmentation workflows.

Diffusion-weighted Imaging (DWI) is a non-invasive imaging technique based on Magnetic Resonance Imaging (MRI) principles to measure water diffusivity and reveal details of the underlying brain micro-structure. By fitting a tensor model to quantify the directionality of water diffusion a Diffusion Tensor Image (DTI) can be derived and scalar measures, such as fractional anisotropy (FA), can then be estimated from the DTI to summarise quantitative microstructural information for clinical studies. In particular, FA has been shown to be a useful research metric to identify tissue abnormalities in neurological disease (e.g. decreased anisotropy as a proxy for tissue damage). However, time constraints in clinical practice lead to low angular resolution diffusion imaging (LARDI) acquisitions that can cause inaccurate FA value estimates when compared to those generated from high angular resolution diffusion imaging (HARDI) acquisitions. In this work, we propose High Angular DTI Estimation Network (HADTI-Net) to estimate an enhanced DTI model from LARDI with a set of minimal and evenly distributed diffusion gradient directions. Extensive experiments have been conducted to show the reliability and generalisation of HADTI-Net to generate high angular DTI estimation from any minimal evenly distributed diffusion gradient directions and to explore the feasibility of applying a data-driven method for this task. The code repository of this work and other related works can be found at https://mri-synthesis.github.io/.

Automated tumor segmentation tools for glioblastoma show promising performance. To apply these tools for automated response assessment, longitudinal segmentation, and tumor measurement, consistency is critical. This study aimed to determine whether BraTumIA and HD-GLIO are suited for this task. We evaluated two segmentation tools with respect to automated response assessment on the single-center retrospective LUMIERE dataset with 80 patients and a total of 502 post-operative time points. Volumetry and automated bi-dimensional measurements were compared with expert measurements following the Response Assessment in Neuro-Oncology (RANO) guidelines. The longitudinal trend agreement between the expert and methods was evaluated, and the RANO progression thresholds were tested against the expert-derived time-to-progression (TTP). The TTP and overall survival (OS) correlation was used to check the progression thresholds. We evaluated the automated detection and influence of non-measurable lesions. The tumor volume trend agreement calculated between segmentation volumes and the expert bi-dimensional measurements was high (HD-GLIO: 81.1%, BraTumIA: 79.7%). BraTumIA achieved the closest match to the expert TTP using the recommended RANO progression threshold. HD-GLIO-derived tumor volumes reached the highest correlation between TTP and OS (0.55). Both tools failed at an accurate lesion count across time. Manual false-positive removal and restricting to a maximum number of measurable lesions had no beneficial effect. Expert supervision and manual corrections are still necessary when applying the tested automated segmentation tools for automated response assessment. The longitudinal consistency of current segmentation tools needs further improvement. Validation of volumetric and bi-dimensional progression thresholds with multi-center studies is required to move toward volumetry-based response assessment.

With the increasing integration of functional imaging techniques like Positron Emission Tomography (PET) into radiotherapy (RT) practices, a paradigm shift in cancer treatment methodologies is underway. A fundamental step in RT planning is the accurate segmentation of tumours based on clinical diagnosis. Furthermore, novel tumour control methods, such as intensity modulated radiation therapy (IMRT) dose painting, demand the precise delineation of multiple intensity value contours to ensure optimal tumour dose distribution. Recently, convolutional neural networks (CNNs) have made significant strides in 3D image segmentation tasks, most of which present the output map at a voxel-wise level. However, because of information loss in subsequent downsampling layers, they frequently fail to precisely identify precise object boundaries. Moreover, in the context of dose painting strategies, there is an imperative need for reliable and precise image segmentation techniques to delineate high recurrence-risk contours. To address these challenges, we introduce a 3D coarse-to-fine framework, integrating a CNN with a kernel smoothing-based probability volume contour approach (KsPC). This integrated approach generates contour-based segmentation volumes, mimicking expert-level precision and providing accurate probability contours crucial for optimizing dose painting/IMRT strategies. Our final model, named KsPC-Net, leverages a CNN backbone to automatically learn parameters in the kernel smoothing process, thereby obviating the need for user-supplied tuning parameters. The 3D KsPC-Net exploits the strength of KsPC to simultaneously identify object boundaries and generate corresponding probability volume contours, which can be trained within an end-to-end framework. The proposed model has demonstrated promising performance, surpassing state-of-the-art models when tested against the MICCAI 2021 challenge dataset (HECKTOR).