Cerebral Microbleeds is a Predictor of Recurrent Small Vessel Cerebrovascular Disease: Evaluation Based on the Recurrent Stroke Pattern.

OBJECTIVES: An increased number of cerebral microbleeds (CMBs) is considered a predictive factor for recurrent small vessel cerebrovascular diseases, including lacunar infarction and non-lobar intracerebral hemorrhage (ICH). However, it is unclear which recurrent stroke pattern is mainly reflected in the number of CMBs. MATERIALS AND METHODS: This study enrolled 217 patients with their first stroke (148 deep lacunar infarctions and 69 non-lobar ICHs), between January 2009 and March 2015. The numbers of baseline and newly appearing CMBs in patients with recurrent stroke were compared with those in patients with non-recurrent stroke, and the dynamics of the number of CMBs was evaluated according to recurrent stroke patterns. RESULTS: Fifty-nine patients with recurrent stroke were included in this study. A larger number of baseline and newly appearing CMBs was significantly associated with recurrent stroke (p=0.04, p<0.001, respectively). Recurrent stroke patterns were divided into four types: deep lacunar infarction/deep lacunar infarction (37 patients), deep lacunar infarction/non-lobar ICH (eight patients), non-lobar ICH/deep lacunar infarction (eight patients), and non-lobar ICH/non-lobar ICH (six patients). The number of newly appearing CMBs was significantly higher in patients with deep lacunar infarction/non-lobar ICH than in those with other recurrent stroke patterns (p=0.04). CONCLUSIONS: The number of CMBs is associated with recurrent stroke, including deep lacunar infarction and non-lobar ICH, and differs depending on the recurrent stroke patterns. The increase in the number of CMBs was strongly correlated with the deep lacunar infarction/non-lobar ICH recurrence pattern.

Uncovering prostate cancer aggressiveness signal in T2-weighted MRI through a three-reference tissues normalization technique.

Quantitative T2-weighted MRI (T2W) interpretation is impeded by the variability of acquisition-related features, such as field strength, coil type, signal amplification, and pulse sequence parameters. The main purpose of this work is to develop an automated method for prostate T2W intensity normalization. The procedure includes the following: (i) a deep learning-based network utilizing MASK R-CNN for automatic segmentation of three reference tissues: gluteus maximus muscle, femur, and bladder; (ii) fitting a spline function between average intensities in these structures and reference values; and (iii) using the function to transform all T2W intensities. The T2W distributions in the prostate cancer regions of interest (ROIs) and normal appearing prostate tissue (NAT) were compared before and after normalization using Student's t-test. The ROIs' T2W associations with the Gleason Score (GS), Decipher genomic score, and a three-tier prostate cancer risk were evaluated with Spearman's correlation coefficient (rS ). T2W differences in indolent and aggressive prostate cancer lesions were also assessed. The MASK R-CNN was trained with manual contours from 32 patients. The normalization procedure was applied to an independent MRI dataset from 83 patients. T2W differences between ROIs and NAT significantly increased after normalization. T2W intensities in 231 biopsy ROIs were significantly negatively correlated with GS (rS = -0.21, p = 0.001), Decipher (rS = -0.193, p = 0.003), and three-tier risk (rS = -0.235, p < 0.001). The average T2W intensities in the aggressive ROIs were significantly lower than in the indolent ROIs after normalization. In conclusion, the automated triple-reference tissue normalization method significantly improved the discrimination between prostate cancer and normal prostate tissue. In addition, the normalized T2W intensities of cancer exhibited a significant association with tumor aggressiveness. By improving the quantitative utilization of the T2W in the assessment of prostate cancer on MRI, the new normalization method represents an important advance over clinical protocols that do not include sequences for the measurement of T2 relaxation times.

Improved test-retest reliability of R2* and susceptibility quantification using multi-shot multi-echo 3D EPI.

This study aimed to evaluate the potential of 3D echo-planar imaging (EPI) for improving the reliability of T2*-weighted (T2*w) data and quantification of R2* decay rate and susceptibility (χ) compared to conventional gradient echo (GRE)-based acquisition. Eight healthy subjects in a wide age range were recruited. Each subject received repeated scans for both GRE and EPI acquisitions with an isotropic 1 mm resolution at 3 T. Maps of R2* and χ were quantified and compared using their inter-scan difference to evaluate the test-retest reliability. Inter-protocol differences of R2* and χ between GRE and EPI were also measured voxel by voxel and in selected ROIs to test the consistency between the two acquisition methods. The quantifications of R2* and χ using EPI protocols showed increased test-retest reliability with higher EPI factors up to 5 as performed in the experiment and were consistent with those based on GRE. This result suggested multi-shot multi-echo 3D EPI can be a useful alternative acquisition method for T2*w MRI and quantification of R2* and χ with reduced scan time, improved test-retest reliability and similar accuracy compared to commonly used 3D GRE.

White Cord Syndrome After Cervical Laminoplasty in an 81-Year-Old Man.

White cord syndrome (WCS) shows high intramedullary signaling in T2-weighted MRI with worsening motor nerve symptoms after cervical spinal decompression surgery. It has been reported in only 13 cases. An 81-year-old man had numbness, weakness, and impaired fine motor control in both upper limbs for the previous five years. C3, C4, C6, open-door laminoplasty, and C5 laminectomy were performed. Intraoperative transcranial motor evoked potential normalization by compound muscle action potential showed an 80% reduction in amplitude in the right abductor pollicis brevis and a 96% reduction in the right abductor hallucis. Tetraplegia occurred immediately after the operation. Magnetic resonance imaging (MRI) on the day after the operation showed intramedullary T2 high signals at the C4 and C5 levels. According to Brunnstrom's staging, the upper and lower right limbs and the lower left limb were at stage two, and the upper left limb was at stage three, six months after the operation. Thirteen cases of WCS have been reported in the literature. These were thought to be caused by reperfusion due to decompression.

Physico-chemical and MR relaxometry study of bovine serum albumin-coated magneto-plasmonic nanoparticles designed for potential use in cancer nanotheranostics.

PURPOSE: In recent years, the use of nanoparticles has been developed to improve MRI contrast. To improve the contrast agents in image-guided therapy by Multifunctional nanoparticles, in this study, we synthesized a theranostic magneto-plasmonic nanocomplex based on magnetic iron oxide nanoparticles and bovine serum albumin-modified gold nanorod (Au@BSA-Fe3O4@CMD). The purpose of synthesizing these nanoparticles was to use them as MRI contrast agent and photothermal agents in in vitro and in vivo experiments. MATERIALS AND METHODS: Initially, the properties of the synthesized nanoparticles were investigated by methods such as DLS, TEM, FTIR. MTT assay was used to evaluate the toxicity of nanoparticles. Finally, to evaluate the contrast ability of nanoparticles, MRI images were taken in in vitro and in vivo conditions and then the images were analyzed. RESULTS: MTT test results on CT26 cell line showed no significant cytotoxicity for Au@BSA-Fe3O4@CMD nanoparticles at concentrations up to 20 ppm. The in vitro results demonstrated that the Au@BSA-Fe3O4@CMD nanocomplex has high T2 relaxation rate and great relaxivities (r2 = 140.14 mM-1 s-1, r1 = 2.066 mM-1 s-1, r2/r1 = 67.83). For in vivo conditions, a decrease in T2 signal of 9.64 and 11.01, respectively, was observed for intratumoral and intraperitoneal injection of nanoparticles. CONCLUSION: These in vitro and in vivo studies show that Au @ BSA-Fe3O4@CMD nanoparticles can significantly reduce the signal intensity of T2-weight MRI images, and therefore can offer significant potential as a theranostic platform for effective tumor MR imaging.

A Semi-Supervised Graph Convolutional Network for Early Prediction of Motor Abnormalities in Very Preterm Infants.

Approximately 32-42% of very preterm infants develop minor motor abnormalities. Earlier diagnosis soon after birth is urgently needed because the first two years of life represent a critical window of opportunity for early neuroplasticity in infants. In this study, we developed a semi-supervised graph convolutional network (GCN) model that is able to simultaneously learn the neuroimaging features of subjects and consider the pairwise similarity between them. The semi-supervised GCN model also allows us to combine labeled data with additional unlabeled data to facilitate model training. We conducted our experiments on a multisite regional cohort of 224 preterm infants (119 labeled subjects and 105 unlabeled subjects) who were born at 32 weeks or earlier from the Cincinnati Infant Neurodevelopment Early Prediction Study. A weighted loss function was applied to mitigate the impact of an imbalanced positive:negative (~1:2) subject ratio in our cohort. With only labeled data, our GCN model achieved an accuracy of 66.4% and an AUC of 0.67 in the early prediction of motor abnormalities, outperforming prior supervised learning models. By taking advantage of additional unlabeled data, the GCN model had significantly better accuracy (68.0%, p = 0.016) and a higher AUC (0.69, p = 0.029). This pilot work suggests that the semi-supervised GCN model can be utilized to aid early prediction of neurodevelopmental deficits in preterm infants.

Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features.

PURPOSE: To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. METHODS: A training dataset containing 413 patients and an independent testing dataset consisting of 82 cases were employed in this retrospective study. Manual segmentation of the whole tumor volume on sagittal T2-weighted MRI was performed. Clinical and radiomic features were extracted to predict: (i) DMI of endometrial cancer patients, (ii) endometrial cancer clinical high-risk level, (iii) histological subtype of tumor, and (iv) presence of LVSI. A classification model with different automatically selected hyperparameter values was created. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, F1 score, average recall, and average precision were calculated to evaluate different models. RESULTS: Based on the independent external testing dataset, the AUCs for DMI, high-risk endometrial cancer, endometrial histological type, and LVSI classification were 0.79, 0.82, 0.91, and 0.85, respectively. The corresponding 95% confidence intervals (CI) of the AUCs were [0.69, 0.89], [0.75, 0.91], [0.83, 0.97], and [0.77, 0.93], respectively. CONCLUSION: It is possible to classify endometrial cancer DMI, risk, histology type, and LVSI using different machine learning methods.

Long-term outcomes of ultrasound guided high intensity focused ultrasound ablation for patients with uterine fibroids classified by T2WI: a multicenter retrospective study.

OBJECTIVE: To evaluate the long-term outcomes of ultrasound-guided high-intensity focused ultrasound (USgHIFU) ablation of uterine fibroids classified by T2-weighted magnetic resonance imaging (T2WI-MRI). MATERIALS AND METHODS: The data of 1427 premenopausal women with symptomatic uterine fibroids who underwent USgHIFU at four teaching hospitals in China were analyzed retrospectively. The uterine fibroids were classified based on their T2WI-MRI signal intensities relative to that of skeletal muscle, myometrium and endometrium as: hypointense, isointense, heterogeneous hyperintense fibroids (HHF), slightly HHF (sHHF) and markedly HHF (mHHF), respectively. The rates of symptom relief and reintervention post-USgHIFU ablation were compared between the classified groups. RESULTS: A total of 1303 patients were followed up for 44 (40, 49) months. The symptom relief rate of the hypointense and isointense fibroids was 83.3% and 79.5%, respectively, which were significantly higher (p < .05) compared to that of HHF, sHHF and mHHF (58.3%, 44.2% and 60.4%), respectively. sHHF had the lowest symptom relief rate (p < .05). The cumulative reintervention rate for hypointense, isointense, HHF, sHHF and mHHF types were 8.8%, 10.8%, 21.4%, 39.9% and 19.8%, respectively. The reintervention rate of hypointense/isointense fibroids was significantly lower than that of HHF/mHHF/sHHF (p < .01), while sHHF had the highest re-intervention rate (p < .01). Thus, reintervention rate is inversely correlated to the rate of symptom relief. CONCLUSIONS: USgHIFU ablation is effective for hypointense, isointense, HHF and mHHF with acceptable long-term follow-up outcomes. However, sHHF is associated with a higher reintervention rate.

Interstitial Edema of the Interatrial Septum in Patients with Atrial Fibrillation and Chronic Heart Failure.

We studied the presence of interstitial edema of the interatrial septum in patients with chronic heart failure (CHF) with atrial fibrillation (n=23) or without rhythm disturbances (n=9). The intensity of the MRI signal of the interatrial septum, interventricular septum, and skeletal muscle by T2-weighted MRI and the enhancement index of interatrial septum (the ratio of the signal intensity of the interatrial septum to the signal intensity of the skeletal muscle) were evaluated. The enhancement index of interatrial septum ⩾2 was regarded as an MRI sign of myocardial edema. The enhancement index of interatrial septum in patients with persistent atrial fibrillation was 2.4 (2.21; 2.69) and was higher than in CHF patients with paroxysmal atrial fibrillation and in CHF patients without arrhythmias and surpassed the control values (p<0.05), which indicates the presence of MRI signs of edema of the myocardium of the interatrial septum. The obtained data confirm the presence of myocardial edema of the interatrial septum in CHF patients and persistent form of atrial fibrillation, which expands the understanding of the pathogenesis of this condition.

Effect of motion, cortical orientation and spatial resolution on quantitative imaging of cortical R2* and magnetic susceptibility at 0.3 mm in-plane resolution at 7 T.

MR images of the effective relaxation rate R2* and magnetic susceptibility χ derived from multi-echo T2*-weighted (T2*w) MRI can provide insight into iron and myelin distributions in the brain, with the potential of providing biomarkers for neurological disorders. Quantification of R2* and χ at submillimeter resolution in the cortex in vivo has been difficult because of challenges such as head motion, limited signal to noise ratio, long scan time, and motion related magnetic field fluctuations. This work aimed to improve the robustness for quantifying intracortical R2* and χ and analyze the effects from motion, spatial resolution, and cortical orientation. T2*w data was acquired with a spatial resolution of 0.3 × 0.3 × 0.4 mm3 at 7 T and downsampled to various lower resolutions. A combined correction for motion and B0 changes was deployed using volumetric navigators. Such correction improved the T2*w image quality rated by experienced image readers and test-retest reliability of R2* and χ quantification with reduced median inter-scan differences up to 10 s-1 and 5 ppb, respectively. R2* and χ near the line of Gennari, a cortical layer high in iron and myelin, were as much as 10 s-1 and 10 ppb higher than the region at adjacent cortical depth. In addition, a significant effect due to the cortical orientation relative to the static field (B0) was observed in χ with a peak-to-peak amplitude of about 17 ppb. In retrospectively downsampled data, the capability to distinguish different cortical depth regions based on R2* or χ contrast remained up to isotropic 0.5 mm resolution. This study highlights the unique characteristics of R2* and χ along the cortical depth at submillimeter resolution and the need for motion and B0 corrections for their robust quantification in vivo.

An Integrated Clinical-MR Radiomics Model to Estimate Survival Time in Patients With Endometrial Cancer.

BACKGROUND: Determination of survival time in women with endometrial cancer using clinical features remains imprecise. Features from MRI may improve the survival estimation allowing improved treatment planning. PURPOSE: To identify clinical features and imaging signatures on T2-weighted MRI that can be used in an integrated model to estimate survival time for endometrial cancer subjects. STUDY TYPE: Retrospective. POPULATION: Four hundred thirteen patients with endometrial cancer as training (N = 330, 66.41 ± 11.42 years) and validation (N = 83, 67.60 ± 11.89 years) data and an independent set of 82 subjects as testing data (63.26 ± 12.38 years). FIELD STRENGTH/SEQUENCE: 1.5-T and 3-T scanners with sagittal T2-weighted spin echo sequence. ASSESSMENT: Tumor regions were manually segmented on T2-weighted images. Features were extracted from segmented masks, and clinical variables including age, cancer histologic grade and risk score were included in a Cox proportional hazards (CPH) model. A group least absolute shrinkage and selection operator method was implemented to determine the model from the training and validation datasets. STATISTICAL TESTS: A likelihood-ratio test and decision curve analysis were applied to compare the models. Concordance index (CI) and area under the receiver operating characteristic curves (AUCs) were calculated to assess the model. RESULTS: Three radiomic features (two image intensity and volume features) and two clinical variables (age and cancer grade) were selected as predictors in the integrated model. The CI was 0.797 for the clinical model (includes clinical variables only) and 0.818 for the integrated model using training and validation datasets, the associated mean AUC value was 0.805 and 0.853. Using the testing dataset, the CI was 0.792 and 0.882, significantly different and the mean AUC was 0.624 and 0.727 for the clinical model and integrated model, respectively. DATA CONCLUSION: The proposed CPH model with radiomic signatures may serve as a tool to improve estimated survival time in women with endometrial cancer. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 2.

Interface-Engineered Mesoporous FeB with Programmed Drug Release for Synergistic Cancer Theranostics.

The pursuit of mesoporous Fe-based nanoagents addresses the field of developing alternative Fe-bearing nanoagents for synergistic cancer therapy with the expectation that the use of an essential element may avoid the issues raised by the exogenous administration of other metal element-based nanoagents. Herein, we highlight the interface-engineered mesoporous FeB (mFeB) where the core mFeB is interfacially oxidized into an FeOOH nanosheet loaded with the chemotherapeutic drug doxorubicin (DOX) and further encapsuled within the double-sulfide-bonded SiO2 outer layer, denoted as mFeB@DOX-ss-SiO2, which can realize programmed drug release for synergistic cancer theranostics. When only in a tumor microenvironment, the nanoagent can be activated to release DOX from the mFeB and FeOOH nanosheets as well as expose the easily oxidized mFeB to spontaneously transform to FeOOH nanosheets with Fenton activity to facilitate chemodynamic therapy (CDT). In addition, the high photothermal conversion efficiency of mFeB@DOX-ss-SiO2 would promote CDT. Also, owing to the inherent nature of ferromagnetism and red fluorescence of DOX, mFeB@DOX-ss-SiO2 can realize T2-weighted magnetic resonance imaging and fluorescence imaging. In vivo mouse model experiments demonstrate that mFeB@DOX-ss-SiO2 with good biocompatibility realizing CDT/photothermal therapy/chemotherapy achieved complete tumor suppression. This study opens up a new way to explore theranostic nanoagents.

Texture analysis in brain T2 and diffusion MRI differentiates histology-verified grey and white matter pathology types in multiple sclerosis.

BACKGROUND: Multiple sclerosis (MS) is a co mplex disease of the central nervous system involving several types of brain pathology that are difficult to characterize using conventional imaging methods. NEW METHOD: We originated novel texture analysis and machine learning approaches for classifying MS pathology subtypes as compared with 2 common advanced MRI measures: magnetization transfer ratio (MTR) and fractional anisotropy (FA). Texture analysis used an optimized grey level co-occurrence matrix method with histology-informed 7T T2-weighted magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI) from 15 MS and 12 control brain specimens. DTI analysis took an innovative approach that assessed the texture across diffusion directions upsampled from 30 to 90. Tissue types included de- and re-myelinated lesions and normal-appearing areas in both grey and white matter, and diffusely abnormal white matter. Data analyses were stepwise, including: (1) group-wise classification using random forest algorithms based on all or individual imaging parameters; (2) parameter importance ranking; and (3) pairwise analysis using top-ranked features. RESULTS: Texture analysis performed better than MTR and FA, with T2 texture performed the best. T2 texture measures ranked the highest in classifying most grey and white matter tissue types, including de- versus re-myelinated lesions and among grey matter lesion subtypes (accuracy=0.86-0.59; kappa=0.60-0.41). Diffusion texture best differentiated normal appearing and control white matter. COMPARISON WITH EXISTING METHODS: There is no established method in imaging for differentiating MS pathology subtypes. In combined texture analysis and machine learning studies, there is also no direct evidence comparing conventional with advanced MRI measures for assessing MS pathology. Further, this study is unique in conducting innovative texture analysis with DTI following data-augmentation using robust methods. CONCLUSIONS: T2 and diffusion MRI texture analysis integrated with machine learning may be valuable approaches for characterizing MS pathology.

Quantitative water T2 relaxometry in the early detection of neuromuscular diseases: a retrospective biopsy-controlled analysis.

OBJECTIVES: To assess quantitative water T2 relaxometry for the early detection of neuromuscular diseases (NMDs) in comparison to standard qualitative MR imaging in a clinical setting. METHODS: This retrospective study included 83 patients with suspected NMD who underwent multiparametric MRI at 3 T with a subsequent muscle biopsy between 2015 and 2019. Qualitative T1-weighted and T2-TIRM images were graded by two neuroradiologists to be either pathological or normal. Mean and median water T2 relaxation times (water T2) were obtained from manually drawn volumes of interests in biopsied muscle from multi-echo sequence. Histopathologic pattern of corresponding muscle biopsies was used as a reference. RESULTS: In 34 patients, the T1-weighted images showed clear pathological alternations indicating late-stage fatty infiltration in NMDs. In the remaining 49 patients without late-stage changes, T2-TIRM grading achieved a sensitivity of 56.4%, and mean and median water T2 a sensitivity of 87.2% and 97.4% to detect early-stage NMDs. Receiver operating characteristic (ROC) analysis revealed an area under the curve (AUC) of 0.682, 0.715, and 0.803 for T2-TIRM, mean water T2, and median water T2, respectively. Median water T2 ranged between 36 and 42 ms depending on histopathologic pattern. CONCLUSIONS: Quantitative water T2 relaxometry had a significantly higher sensitivity in detecting muscle abnormalities than subjective grading of T2-TIRM, prior to late-stage fatty infiltration signal alternations in T1-weighted images. Normal-appearing T2-TIRM does not rule out early-stage NMDs. Our findings suggest considering water T2 relaxometry complementary to T2-TIRM for early detection of NMDs in clinical diagnostic routine. KEY POINTS: • Quantitative water T2 relaxometry is more sensitive than subjective assessment of fat-suppressed T2-weighted images for the early detection of neuromuscular diseases, prior to late-stage fatty infiltration signal alternations in T1-weighted images. • Normal-appearing muscles in fat-suppressed T2-weighted images do not rule out early-stage neuromuscular diseases. • Quantitative water T2 relaxometry should be considered complementary to subjectively rated fat-suppressed T2-weighted images in clinical practice.

Acute cerebral microbleeds at the edge of lacunar strokes: cause or result.

We investigated the pathogenic relationship between cerebral microbleeds and lacunar strokes. Two cases of lacunar strokes in the region of the basal ganglia, a 72-year-old man and a 67-year-old man, were studied; both cases showed cerebral microbleeds in the stroke areas. The cerebral microbleeds were surrounded by oedema, and the oedema faded out over time, suggesting the cerebral microbleeds had developed acutely. The cerebral microbleeds were located at the ventrolateral edge of the lacunar infarctions, and the locations appeared to be at or near the sites of occlusion of the lenticulostriatal branches. Although a cerebral microbleed and a lacunar infarction may be two unrelated events on juxtapositioned vessels, or a cerebral microbleed may be haemorrhagic conversion of an infarction, a cerebral microbleed could cause an occlusion of the arterial branch, leading to lacunar infarction of its supplying territories.

T2* weighted placental MRI in relation to placental histology and birth weight.

INTRODUCTION: Placental dysfunction may be found among normal birth weight (BW) pregnancies, as indicated by abnormal histological findings in postnatal placental examination in some of these pregnancies. T2* weighted placental MRI provides non-invasive information on placental oxygenation and thereby placental function. The aim of this study was to investigate the correlation between placental T2*, BW and placental histology. METHODS: A total of 63 pregnant women underwent T2* weighted placental MRI at 15-40 week's gestation and a standardized placental histological examination (PHE). Abnormal PHE was defined by vascular malperfusion according to the Amsterdam workshop consensus. The correlation between PHE, BW z-score and T2* z-score was analyzed by logistic regression. RESULTS: Abnormal PHE was revealed in 28 pregnancies. Multiple logistic regression revealed a significant correlation between abnormal PHE and T2* z-score (OR = 0.34, p = 0.008), whereas BW z-score did not add significantly to the correlation of placental histology (OR = 0.52, p = 0.115). In BW z-score≥0, PHE was normal in 100% of pregnancies. In BW z-score ≤ -2, PHE was abnormal in 89% of pregnancies. In intermediate BW (z-score between -2 and 0), PPE was abnormal in 35% of pregnancies. In this intermediate group, placental T2* z-score was reduced (-1.52 ± 1.22 (mean SD)) when compared to normal PHE pregnancies (-0.28 ± 1.17), p = 0.006. DISCUSSION: This study demonstrates a correlation between abnormal placental histology and low placental T2* value regardless of fetal size. This indicates that T2* provides information of placental function in vivo even when fetal size is normal. This finding highlights that fetal size alone is not a valid marker of placental dysfunction.

Spatial-Frequency dual-branch attention model for determining KRAS mutation status in colorectal cancer with T2-weighted MRI.

BACKGROUND AND OBJECTIVE: Identifying the KRAS mutation status accurately in medical images is very important for the diagnosis and treatment of colorectal cancer. Despite the substantial progress achieved by existing methods, it remains challenging due to limited annotated dataset, large intra-class variances, and a high degree of inter-class similarities. METHODS: To tackle these challenges, we propose a spatial-frequency dual-branch attention model (SF-DBAM) to determine the KRAS mutation status of colorectal cancer patients using a limited T2-weighted MRI dataset. The dataset contains 169 wild-type patients (2151 images) and 137 mutation-type patients (1666 images). The first branch utilizes part of the pre-trained Xception model to capture spatial-domain information and alleviate the small-scale dataset problem. The second branch builds frequency-domain information into cube columns using block-based discrete cosine transform and channel rearrangement. Then the cube columns are fed into convolutional long short-term memory (convLSTM) to explore the effective information between the reconstructed frequency-domain channels. Also, we design a channel enhanced attention module (CEAM) at the end of each branch to make them focus on the lesion areas. Finally, we concatenate the two branches and output the classified results through fully connected layers. RESULTS: The proposed method achieves 88.03% overall accuracy with AUC of 94.27% and specificity of 90.75% in 10-fold cross-validation, which is better than the current non-invasive methods for determining KRAS mutation status. CONCLUSIONS: We believe that the proposed method can assist physicians to diagnose the KRAS mutation status in patients with colorectal cancer, and other medical problems can benefit from the spatial and frequency domains information.

Automatic brain extraction and hemisphere segmentation in rat brain MR images after stroke using deformable models.

PURPOSE: Experimental ischemic stroke models play an essential role in understanding the mechanisms of cerebral ischemia and evaluating the development of pathological extent. An important precursor to the investigation of ischemic strokes associated with rodents is the brain extraction and hemisphere segmentation in rat brain diffusion-weighted imaging (DWI) and T2-weighted MRI (T2WI) images. Accurate and reliable image segmentation tools for extracting the rat brain and hemispheres in the MR images are critical in subsequent processes, such as lesion identification and injury analysis. This study is an attempt to investigate rat brain extraction and hemisphere segmentation algorithms that are practicable in both DWI and T2WI images. METHODS: To automatically perform brain extraction, the proposed framework is based on an efficient geometric deformable model. By introducing an additional image force in response to the rat brain characteristics into the skull stripping model, we establish a unique rat brain extraction scheme in DWI and T2WI images. For the subsequent hemisphere segmentation, we develop an efficient brain feature detection algorithm to approximately separate the rat brain. A refinement process is enforced by constructing a gradient vector flow in the proximity of the midsurface, where a parametric active contour is attracted to achieve hemisphere segmentation. RESULTS: Extensive experiments with 55 DWI and T2WI subjects were executed in comparison with the state-of-the-art methods. Experimental results indicated that our rat brain extraction and hemisphere segmentation schemes outperformed the competitive methods and exhibited high performance both qualitatively and quantitatively. For rat brain extraction, the average Dice scores were 97.13% and 97.42% in DWI and T2WI image volumes, respectively. Rat hemisphere segmentation results based on the Hausdorff distance metric revealed average values of 0.17 and 0.15 mm for DWI and T2WI subjects, respectively. CONCLUSIONS: We believe that the established frameworks are advantageous to facilitate preclinical stroke investigation and relevant neuroscience research that requires accurate brain extraction and hemisphere segmentation using rat DWI and T2WI images.

Spinal cord compression is associated with brain plasticity in degenerative cervical myelopathy.

The impact of spinal cord compression severity on brain plasticity and prognostic determinates is not yet fully understood. We investigated the association between the severity of spinal cord compression in patients with degenerative cervical myelopathy, a progressive disease of the spine, and functional plasticity in the motor cortex and subcortical areas using functional magnetic resonance imaging. A 3.0 T MRI scanner was used to acquire functional images of the brain in 23 degenerative cervical myelopathy patients. Patients were instructed to perform a structured finger-tapping task to activate the motor cortex to assess the extent of cortical activation. T2-weighted images of the brain and spine were also acquired to quantify the severity of spinal cord compression. The observed blood oxygen level-dependent signal increase in the contralateral primary motor cortex was associated with spinal cord compression severity when patients tapped with their left hand (r = 0.49, P = 0.02) and right hand (r = 0.56, P = 0.005). The volume of activation in the contralateral primary motor cortex also increased with spinal cord compression severity when patients tapped with their left hand (r = 0.55, P = 0.006) and right hand (r = 0.45, P = 0.03). The subcortical areas (cerebellum, putamen, caudate and thalamus) also demonstrated a significant relationship with compression severity. It was concluded that degenerative cervical myelopathy patients with severe spinal cord compression recruit larger regions of the motor cortex to perform finger-tapping tasks, which suggests that this adaptation is a compensatory response to neurological injury and tissue damage in the spinal cord.

The therapeutic response of somatotropinomas according to the T2-weighted signal intensity on the MRI.

Background and aim: Identifying the predictive factors of tumoral and hormonal answer of somatotropinomas to the medical treatment with somatostatin analogs represent an important element for treatment management. The aim of this study was to assess the therapeutic answer of the somatotropinomas according to the T2-weighted signal intensity on the MRI. Methods: We included 31 acromegalic patients, mean age 51.35 ± 10.37 years, who underwent surgery. The patients were divided according to the T2-weighted MRI signal intensity - hypointense, hyperintense and isointense - of the GH-secreting pituitary adenoma and were evaluated after surgery, 3, 6 and 12 months with somatostatin analogs therapy. Results: 16 (51.61%) somatropinomas were hypointense, 9 (29.03%) were hyperintense and 6 (19.35%) were isointense. The median IGF-1 and GH level decreased significantly in macroadenomas (p<0.001, p<0.001, respectively), whereas GH decreased significantly only in microadenomas (p=0.010). A significant statistical correlation was found between IGF-1 or GH levels and tumor volume before surgery (Spearman=0.38, p<0.001; Spearman=0.64, p<0.001, respectively) and after surgery (Spearman=0.61, p=0.001; Spearman=0.74, p<0.001). The percentage of optimally controlled patients increased from 12.9% after surgery, to 28.57% after 12 months with somatostatin analogs. The highest percentage of optimally controlled patients with somatostatin analogs treatment was in hypointense somatotropinomas (50%). Conclusion: The T2-weighted MRI signal intensity classifies the somatotropinomas into groups with certain evolutive and medical treatment response particularities, of which we found that the hypointense somatotropinomas have a better therapeutic response after surgery and after long-term treatment with somatostatin analogs.