Frontiers in radiology最新文献

Unlocking the vast potential of deep learning-based computer vision classification systems necessitates large data sets for model training. Natural Language Processing (NLP)-involving automation of dataset labelling-represents a potential avenue to achieve this. However, many aspects of NLP for dataset labelling remain unvalidated. Expert radiologists manually labelled over 5,000 MRI head reports in order to develop a deep learning-based neuroradiology NLP report classifier. Our results demonstrate that binary labels (normal vs. abnormal) showed high rates of accuracy, even when only two MRI sequences (T2-weighted and those based on diffusion weighted imaging) were employed as opposed to all sequences in an examination. Meanwhile, the accuracy of more specific labelling for multiple disease categories was variable and dependent on the category. Finally, resultant model performance was shown to be dependent on the expertise of the original labeller, with worse performance seen with non-expert vs. expert labellers.

Introduction: Osteoporosis (OP) results in weak bone and can ultimately lead to fracture. MRI assessment of bone structure and microarchitecture has been proposed as method to assess bone quality and fracture risk in vivo. Radiomics provides a framework to analyze the textural information of MR images. The purpose of this study was to analyze the radiomic features and its abilityto differentiate between subjects with and without prior fragility fracture.

Methods: MRI acquisition was performed on n = 45 female OP subjects: 15 with fracture history (Fx) and 30 without fracture history (nFx) using a high-resolution 3D Fast Low Angle Shot (FLASH) sequence at 3T. Second and first order radiomic features were calculated in the trabecular region of the proximal femur on T1-weighted MRI signal of a matched dataset. Significance of the feature's predictive ability was measured using Wilcoxon test and Area Under the ROC (AUROC) curve analysis. The features were correlated DXA and FRAX score.

Result: A set of three independent radiomic features (Dependence Non-Uniformity (DNU), Low Gray Level Emphasis (LGLE) and Kurtosis) showed significant ability to predict fragility fracture (AUROC DNU = 0.751, p < 0.05; AUROC LGLE = 0.729, p < 0.05; AUROC Kurtosis = 0.718, p < 0.05) with low to moderate correlation with FRAX and DXA.

Conclusion: Radiomic features can measure bone health in MRI of proximal femur and has the potential to predict fracture.

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.