Topological alterations in white matter anatomical networks in cervical dystonia.

BACKGROUND: Accumulating neuroimaging evidence indicates that patients with cervical dystonia (CD) have changes in the cortico-subcortical white matter (WM) bundle. However, whether these patients' WM structural networks undergo reorganization remains largely unclear. We aimed to investigate topological changes in large-scale WM structural networks in patients with CD compared to healthy controls (HCs), and explore the network changes associated with clinical manifestations. METHODS: Diffusion tensor imaging (DTI) was conducted in 30 patients with CD and 30 HCs, and WM network construction was based on the BNA-246 atlas and deterministic tractography. Based on the graph theoretical analysis, global and local topological properties were calculated and compared between patients with CD and HCs. Then, the AAL-90 atlas was used for the reproducibility analyses. In addition, the relationship between abnormal topological properties and clinical characteristics was analyzed. RESULTS: Compared with HCs, patients with CD showed changes in network segregation and resilience, characterized by increased local efficiency and assortativity, respectively. In addition, a significant decrease of network strength was also found in patients with CD relative to HCs. Validation analyses using the AAL-90 atlas similarly showed increased assortativity and network strength in patients with CD. No significant correlations were found between altered network properties and clinical characteristics in patients with CD. CONCLUSION: Our findings show that reorganization of the large-scale WM structural network exists in patients with CD. However, this reorganization is attributed to dystonia-specific abnormalities or hyperkinetic movements that need further identification.

Regional structural abnormalities in thalamus in idiopathic cervical dystonia.

BACKGROUND: The thalamus has a central role in the pathophysiology of idiopathic cervical dystonia (iCD); however, the nature of alterations occurring within this structure remain largely elusive. Using a structural magnetic resonance imaging (MRI) approach, we examined whether abnormalities differ across thalamic subregions/nuclei in patients with iCD. METHODS: Structural MRI data were collected from 37 patients with iCD and 37 healthy controls (HCs). Automatic parcellation of 25 thalamic nuclei in each hemisphere was performed based on the FreeSurfer program. Differences in thalamic nuclei volumes between groups and their relationships with clinical information were analysed in patients with iCD. RESULTS: Compared to HCs, a significant reduction in thalamic nuclei volume primarily in central medial, centromedian, lateral geniculate, medial geniculate, medial ventral, paracentral, parafascicular, paratenial, and ventromedial nuclei was found in patients with iCD (P < 0.05, false discovery rate corrected). However, no statistically significant correlations were observed between altered thalamic nuclei volumes and clinical characteristics in iCD group. CONCLUSION: This study highlights the neurobiological mechanisms of iCD related to thalamic volume changes.

Supplementary motor area driving changes of structural brain network in blepharospasm.

Blepharospasm is traditionally thought to be a movement disorder that results from basal ganglia dysfunction. Recently, accumulating morphometric studies have revealed structural alterations outside the basal ganglia, such as in the brainstem, cerebellum and sensorimotor cortex, suggesting that blepharospasm may result from network disorders. However, the temporal and causal relationships between structural alterations and whether there are disease duration-related hierarchical structural changes in these patients remain largely unknown. Structural MRI was performed in 62 patients with blepharospasm, 62 patients with hemifacial spasm and 62 healthy controls to assess the structural alterations using voxel-based morphology and structural covariance networks. The use of the causal structural covariance network, modularity analysis and functional decoding were subsequently performed to map the causal effect of grey matter change pattern, hierarchical topography and functional characterizations of the structural network throughout the disease duration of blepharospasm. Greater grey matter volume in the left and right supplementary motor areas was identified in patients with blepharospasm compared to that in patients with hemifacial spasm and healthy controls, whereas no significant difference was identified between patients with hemifacial spasm and healthy controls. In addition, increased grey matter volume covariance between the right supplementary motor area and right brainstem, left superior frontal gyrus, left supplementary motor area and left paracentral gyrus was found in patients with blepharospasm compared to healthy controls. Further causal structural covariance network, modularity analysis and functional decoding showed that the right supplementary motor area served as a driving core in patients with blepharospasm, extending greater grey matter volume to areas in the cortico-basal ganglia-brainstem motor pathway and cortical regions in the vision-motor integration pathway. Taken together, our results suggest that the right supplementary motor area is an early and important pathologically impaired region in patients with blepharospasm. With a longer duration of blepharospasm, increased grey matter volume extends from the right supplementary motor area to the cortico-basal ganglia motor and visual-motor integration pathways, showing a hierarchy of structural abnormalities in the disease progression of blepharospasm, which provides novel evidence to support the notion that blepharospasm may arise from network disorders and is associated with a wide range of grey matter abnormalities.

Abnormal dynamic brain activity and functional connectivity of primary motor cortex in blepharospasm.

BACKGROUND AND PURPOSE: Accumulating evidence indicates that dynamic amplitude of low-frequency fluctuations (dALFF) or dynamic functional connectivity (dFC) can provide complementary information, distinct from static amplitude of low-frequency fluctuations (sALFF) or static functional connectivity (sFC), in detecting brain functional abnormalities in brain diseases. We aimed to examine whether dALFF and dFC can offer valuable information for the detection of functional brain abnormalities in patients with blepharospasm. METHODS: We collected resting-state functional magnetic resonance imaging data from 46 patients each of blepharospasm, hemifacial spasm (HFS), and healthy controls (HCs). We examined intergroup differences in sALFF and dALFF to investigate abnormal regional brain activity in patients with blepharospasm. Based on the dALFF results, we conducted seed-based sFC and dFC analyses to identify static and dynamic connectivity changes in brain networks centered on areas showing abnormal temporal variability of local brain activity in patients with blepharospasm. RESULTS: Compared with HCs, patients with blepharospasm displayed different brain functional change patterns characterized by increased sALFF in the left primary motor cortex (PMC) but increased dALFF variance in the right PMC. However, differences were not found between patients with HFS and HCs. Additionally, patients with blepharospasm exhibited decreased dFC strength, but no change in sFC, between right PMC and ipsilateral cerebellum compared with HCs; these findings were replicated when patients with blepharospasm were compared to those with HFS. CONCLUSIONS: Our findings highlight that dALFF and dFC are complementary to sALFF and sFC and can provide valuable information for detecting brain functional abnormalities in blepharospasm. Blepharospasm may be a network disorder involving the cortico-ponto-cerebello-thalamo-cortical circuit.

Topological Alterations in White Matter Structural Networks in Blepharospasm.

BACKGROUND: Accumulating evidence indicates regional structural changes in the white matter (WM) of brains in patients with blepharospasm (BSP); however, whether large-scale WM structural networks undergo widespread reorganization in these patients remains unclear. OBJECTIVE: We investigated topology changes and global and local features of large-scale WM structural networks in BSP patients compared with hemifacial spasm (HFS) patients or healthy controls (HCs). METHODS: This cross-sectional study applied graph theoretical analysis to assess deterministic diffusion tensor tractography findings in 41 BSP patients, 41 HFS patients, and 41 HCs. WM structural connectivity in 246 cortical and subcortical regions was assessed, and topological parameters of the resulting graphs were calculated. Networks were compared among BSP, HFS, and HCs groups. RESULTS: Compared to HCs, both BSP and HFS patients showed alterations in network integration and segregation characterized by increased global efficiency and modularity and reduced shortest path length. Moreover, increased nodal efficiency in multiple cortical and subcortical regions was found in BSP and HFS patients compared with HCs. However, these differences were not found between BSP and HFS patients. Whereas all participants showed highly similar hub distribution patterns, BSP patients had additional hub regions not present in either HFS patients or HCs, which were located in the primary head and face motor cortex and basal ganglia. CONCLUSIONS: Our findings suggest that the large-scale WM structural network undergoes an extensive reorganization in BSP, probably due to both dystonia-specific abnormalities and facial hyperkinetic movements. © 2021 International Parkinson and Movement Disorder Society.

Longitudinal changes in the inferior cerebellar peduncle and lower limb motor recovery following subcortical infarction.

BACKGROUND: The cerebellum receives afferent signals from spinocerebellar pathways regulating lower limb movements. However, the longitudinal changes in the spinocerebellar pathway in the early stage of unilateral supratentorial stroke and their potential clinical significance have received little attention. METHODS: Diffusion tensor imaging and Fugl-Meyer assessment of lower limb were performed 1, 4, and 12 weeks after onset in 33 patients with acute subcortical infarction involving the supratentorial areas, and in 33 healthy subjects. We evaluated group differences in diffusion metrics in the bilateral inferior cerebellar peduncle (ICP) and analyzed the correlation between ICP diffusion metrics and changes to the Fugl-Meyer scores of the affected lower limb within 12 weeks after stroke. RESULTS: Significantly decreased fractional anisotropy and increased mean diffusivity were found in the contralesional ICP at week 12 after stroke compared to controls (all P < 0.01) and those at week 1 (all P < 0.05). There were significant fractional anisotropy decreases in the ipsilesional ICP at week 4 (P = 0.008) and week 12 (P = 0.004) compared to controls. Both fractional anisotropy (rs = 0.416, P = 0.025) and mean diffusivity (rs = -0.507, P = 0.005) changes in the contralesional ICP correlated with changes in Fugl-Meyer scores of the affected lower limb in all patients. CONCLUSIONS: Bilateral ICP degeneration occurs in the early phase of supratentorial stroke, and diffusion metric values of the contralesional ICP are useful indicators of affected lower limb function after supratentorial stroke.

Motor Recovery Prediction With Clinical Assessment and Local Diffusion Homogeneity After Acute Subcortical Infarction.

BACKGROUND AND PURPOSE: Initial clinical assessment or conventional diffusion tensor imaging parameters alone do not reliably predict poststroke recovery of motor function. Recently, local diffusion homogeneity (LDH) has been proposed to represent the local coherence of water molecule diffusion and can serve as a complementary marker for investigating white matter alterations of the brain. We aimed to determine whether a combination of initial clinical assessment and LDH could predict motor recovery after acute subcortical infarction. METHODS: Standard upper extremity Fugl-Meyer assessment and diffusion tensor imaging were performed 1, 4, and 12 weeks after onset in 50 patients with subcortical infarction. Proportional recovery model residuals were used to assign patients to proportional recovery and poor recovery groups. Tract-based spatial statistics analysis was used to compare diffusion differences between proportional and poor recovery outcomes. Multivariate logistic regression model was used to identify the predictors of motor improvement within 12 weeks after stroke. RESULTS: The poor recovery group had lower LDH than the proportional recovery group, mainly in the ipsilesional corticospinal tract in the superior corona radiate and posterior limb of internal capsule 1 week after stroke (P<0.005; family-wise error corrected). Multivariate logistic regression analysis indicated that both initial Fugl-Meyer assessment and LDH in the ipsilesional corticospinal tract in the superior corona radiate and posterior limb of internal capsule were predictors of motor improvement within 12 weeks after stroke (G=47.22; P<0.001). Leave-one-out cross-validation confirmed a positive predictive value of 0.818, a negative predictive value of 0.833, and an accuracy of 0.824 (P<0.00 001; permutation test). CONCLUSIONS: These results suggest that a combination of clinical assessment and LDH in the ipsilesional corticospinal tract in the acute phase can accurately predict resolution of upper limb impairment within 12 weeks after subcortical infarction.

Abnormal supplementary motor areas are associated with idiopathic and acquired blepharospasm.

Blepharospasm is a common form of focal dystonia characterized by excessive and involuntary spasms of the orbicularis oculi. In addition to idiopathic blepharospasm, lesions in various brain regions can also cause acquired blepharospasm. Whether these two types of blepharospasm share a common brain network remains largely unknown. Herein, we performed lesion coactivation network mapping, based on meta-analytic connectivity modeling, to test whether lesions causing blepharospasm could be mapped to a common coactivation brain network. We then tested the abnormality of the network in patients with idiopathic blepharospasm (n = 42) compared with healthy controls (n = 44). We identified 21 cases of lesion-induced blepharospasms through a systematic literature search. Although these lesions were heterogeneous, they were part of a co-activated brain network that mainly included the bilateral supplementary motor areas. Coactivation of these regions defines a single brain network that encompasses or is adjacent to most heterogeneous lesions causing blepharospasm. Moreover, the bilateral supplementary motor area is primarily associated with action execution, visual motion, and imagination, and participates in finger tapping and saccades. They also reported decreased functional connectivity with the left posterior cingulate cortex in patients with idiopathic blepharospasm. These results demonstrate a common convergent abnormality of the supplementary motor area across idiopathic and acquired blepharospasms, providing additional evidence that the supplementary motor area is an important brain region that is pathologically impaired in patients with blepharospasm.

Progressive thalamic nuclear atrophy in blepharospasm and blepharospasm-oromandibular dystonia.

The thalamus is considered a key region in the neuromechanisms of blepharospasm. However, previous studies considered it as a single, homogeneous structure, disregarding potentially useful information about distinct thalamic nuclei. Herein, we aimed to examine (i) whether grey matter volume differs across thalamic subregions/nuclei in patients with blepharospasm and blepharospasm-oromandibular dystonia; (ii) causal relationships among abnormal thalamic nuclei; and (iii) whether these abnormal features can be used as neuroimaging biomarkers to distinguish patients with blepharospasm from blepharospasm-oromandibular dystonia and those with dystonia from healthy controls. Structural MRI data were collected from 56 patients with blepharospasm, 20 with blepharospasm-oromandibular dystonia and 58 healthy controls. Differences in thalamic nuclei volumes between groups and their relationships to clinical information were analysed in patients with dystonia. Granger causality analysis was employed to explore the causal effects among abnormal thalamic nuclei. Support vector machines were used to test whether these abnormal features could distinguish patients with different forms of dystonia and those with dystonia from healthy controls. Compared with healthy controls, patients with blepharospasm exhibited reduced grey matter volume in the lateral geniculate and pulvinar inferior nuclei, whereas those with blepharospasm-oromandibular dystonia showed decreased grey matter volume in the ventral anterior and ventral lateral anterior nuclei. Atrophy in the pulvinar inferior nucleus in blepharospasm patients and in the ventral lateral anterior nucleus in blepharospasm-oromandibular dystonia patients was negatively correlated with clinical severity and disease duration, respectively. The proposed machine learning scheme yielded a high accuracy in distinguishing blepharospasm patients from healthy controls (accuracy: 0.89), blepharospasm-oromandibular dystonia patients from healthy controls (accuracy: 0.82) and blepharospasm from blepharospasm-oromandibular dystonia patients (accuracy: 0.94). Most importantly, Granger causality analysis revealed that a progressive driving pathway from pulvinar inferior nuclear atrophy extends to lateral geniculate nuclear atrophy and then to ventral lateral anterior nuclear atrophy with increasing clinical severity in patients with blepharospasm. These findings suggest that the pulvinar inferior nucleus in the thalamus is the focal origin of blepharospasm, extending to pulvinar inferior nuclear atrophy and subsequently extending to the ventral lateral anterior nucleus causing involuntary lower facial and masticatory movements known as blepharospasm-oromandibular dystonia. Moreover, our results also provide potential targets for neuromodulation especially deep brain stimulation in patients with blepharospasm and blepharospasm-oromandibular dystonia.

Longitudinal cortical volume changes correlate with motor recovery in patients after acute local subcortical infarction.

BACKGROUND AND PURPOSE: Secondary changes in the volume of motor-related cortical regions and the relationship with functional recovery during the acute stage after cerebral infarction have not been determined. In the present study, we quantified changes in gray matter (GM) volume in motor-related cortical regions and analyzed their correlations to clinical scores in patients with focal cerebral infarct. METHODS: Fifteen patients with acute subcortical infarct underwent longitudinal high-resolution structural MRI and clinical assessment 3 times during a 12-week period (weeks 1, 4, and 12). Fourteen age- and sex-matched controls underwent MRI examination. Voxel-based morphometry was used to quantify changes in global GM volume; in addition, relationships between GM volume changes in volumes of interest and clinical scores were analyzed. RESULTS: In patients with cerebral infarction, GM volumes detected by voxel-based morphometry both decreased and increased significantly in diffuse cortical regions during the observation period (P<0.001). GM volumes within volumes of interest decreased significantly in the ipsilateral supplementary motor area and contralateral insula, but they increased in the contralateral supplementary motor area over time (all P<0.017). The changes of GM volumes in the ipsilesional and contralesional supplementary motor area correlated with the changes in the Fugl-Meyer scale scores (ipsilesional, rs=0.52; P=0.048; contralesional, rs=0.74; P=0.002) and Barthel Index (ipsilesional, rs=0.56; P=0.030; contralesional, rs=0.65; P=0.009). CONCLUSIONS: These results suggest that secondary GM changes occur in diffuse areas and structural changes in some specific motor-related cortex may inhibit or promote functional recovery after an acute subcortical cerebral infarct.

Neural Correlates of Facial Emotion Recognition Impairment in Blepharospasm: A Functional Magnetic Resonance Imaging Study.

Selective impairment in recognizing facial expressions of disgust was reported in patients with focal dystonia several years ago, but the basic neural mechanisms remain largely unexplored. Therefore, we investigated whether dysfunction of the brain network involved in disgust recognition processing was related to this selective impairment in blepharospasm. Facial emotion recognition evaluations and resting-state functional magnetic resonance imaging were performed in 33 blepharospasm patients and 33 healthy controls (HCs). The disgust processing network was constructed, and modularity analyses were performed to identify sub-networks. Regional functional indexes and intra- and inter-functional connections were calculated and compared between the groups. Compared to HCs, blepharospasm patients demonstrated a worse performance in disgust recognition. In addition, functional connections within the sub-network involved in perception processing rather than recognition processing of disgust were significantly decreased in blepharospasm patients compared to HCs. Specifically, decreased functional connections were noted between the left fusiform gyrus (FG) and right middle occipital gyrus (MOG), the left FG and right FG, and the right FG and left MOG. We identified decreased functional activity in these regions, as indicated by a lower amplitude of low-frequency fluctuation in the left MOG, fractional amplitude of low-frequency fluctuation in the right FG, and regional homogeneity in the right FG and left MOG in blepharospasm patients versus HCs. Our results suggest that dysfunctions of the disgust processing network exist in blepharospasm. A deficit in disgust emotion recognition may be attributed to disturbances in the early perception of visual disgust stimuli in blepharospasm patients.

An exploratory analysis of MR-guided fractionated stereotactic radiotherapy in patients with brain metastases.

Purpose: To assess the feasibility and potential benefits of online adaptive MR-guided fractionated stereotatic radiotherapy (FSRT) in patients with brain metastases (BMs). Methods and materials: Twenty-eight consecutive patients with BMs were treated with FSRT of 30 Gy in 5 fractions on the 1.5 T MR-Linac. The FSRT fractions employed daily MR scans and the contours were utilized to create each adapted plan. The brain lesions and perilesional edema were delineated on MR images of pre-treatment simulation (Fx0) and all fractions (Fx1, Fx2, Fx3, Fx4 and Fx5) to evaluate the inter-fractional changes. These changes were quantified using absolute/relative volume, Dice similarity coefficient (DSC) and Hausdorff distance (HD) metrics. Planning target volume (PTV) coverage and organ at risk (OAR) constraints were used to compare non-adaptive and adaptive plans. Results: A total of 28 patients with 88 lesions were evaluated, and 23 patients (23/28, 82.1%) had primary lung adenocarcinoma. Significant tumor volume reduction had been found during FSRT compared to Fx0 for all 88 lesions (median -0.75%, -5.33%, -9.32%, -17.96% and -27.73% at Fx1, Fx2, Fx3, Fx4 and Fx5, p < 0.05). There were 47 (47/88, 53.4%) lesions being accompanied by perilesional edema and the inter-fractional changes were significantly different compared to those without perilesional edema (p < 0.001). Patients with multiple lesions (13/28, 46.4%) had more significant inter-fractional tumor changes than those with single lesion (15/28, 53.6%), including tumor volume reduction and anatomical shift (p < 0.001). PTV coverage of non-adaptive plans was below the prescribed coverage in 26/140 fractions (19%), with 12 (9%) failing by more than 10%. All 140 adaptive fractions met prescribed target coverage. The adaptive plans also had lower dose to whole brain than non-adaptive plans (p < 0.001). Conclusions: Significant inter-fractional tumor changes could be found during FSRT in patients with BMs treated on the 1.5 T MR-Linac. Daily MR-guided re-optimization of treatment plans showed dosimetric benefit in patients with perilesional edema or multiple lesions.

Cortico-basal ganglia networks dysfunction associated with disease severity in patients with idiopathic blepharospasm.

Background: Structural changes occur in brain regions involved in cortico-basal ganglia networks in idiopathic blepharospasm (iBSP); whether these changes influence the function connectivity patterns of cortico-basal ganglia networks remains largely unknown. Therefore, we aimed to investigate the global integrative state and organization of functional connections of cortico-basal ganglia networks in patients with iBSP. Methods: Resting-state functional magnetic resonance imaging data and clinical measurements were acquired from 62 patients with iBSP, 62 patients with hemifacial spasm (HFS), and 62 healthy controls (HCs). Topological parameters and functional connections of cortico-basal ganglia networks were evaluated and compared among the three groups. Correlation analyses were performed to explore the relationship between topological parameters and clinical measurements in patients with iBSP. Results: We found significantly increased global efficiency and decreased shortest path length and clustering coefficient of cortico-basal ganglia networks in patients with iBSP compared with HCs, however, such differences were not observed between patients with HFS and HCs. Further correlation analyses revealed that these parameters were significantly correlated with the severity of iBSP. At the regional level, the functional connectivity between the left orbitofrontal area and left primary somatosensory cortex and between the right anterior part of pallidum and right anterior part of dorsal anterior cingulate cortex was significantly decreased in patients with iBSP and HFS compared with HCs. Conclusion: Dysfunction of the cortico-basal ganglia networks occurs in patients with iBSP. The altered network metrics of cortico-basal ganglia networks might be served as quantitative markers for evaluation of the severity of iBSP.

Hypofractionated Radiotherapy followed by Hypofractionated Boost with weekly concurrent chemotherapy for Unresectable Stage III Non-Small Cell Lung Cancer: Results of A Prospective Phase II Study (GASTO-1049).

PURPOSE: We launched a prospective phase 2 clinical trial to explore the safety and efficacy of hypofractionated radiation therapy (hypo-RT) followed by hypofractionated boost (hypo-boost) combined with concurrent weekly chemotherapy in patients with unresectable locally advanced non-small cell lung cancer (LA-NSCLC). METHODS AND MATERIALS: Patients with newly diagnosed LA-NSCLC with unresectable stage III disease were recruited between June 2018 and June 2020. Patients were treated with hypo-RT (40 Gy in 10 fractions) followed by hypo-boost (24-28 Gy in 6-7 fractions) combined with concurrent weekly chemotherapy (docetaxel 25 mg/m2 and nedaplatin 25 mg/m2). The primary endpoint of the study was progression-free survival (PFS), and the secondary endpoints included overall survival (OS), locoregional failure-free survival (LRFS), distant metastasis-free survival (DMFS), objective response rate (ORR), and toxicities. RESULTS: From June 2018 to June 2020, 75 patients were enrolled with a median follow-up duration of 28.0 months. The ORR of the whole cohort was 94.7%. Disease progression or death was recorded in 44 (58.7%) patients, with a median PFS of 21.6 months (95% confidence interval [CI], 15.6-27.6 months). The 1- and 2-year PFS rates were 81.3% (95% CI, 72.5%-90.1%) and 43.3% (95% CI, 31.5%-55.1%), respectively. The median OS, DMFS, and LRFS had not been reached at the time of the last follow-up. The 1- and 2-year OS rates were 94.7% (95% CI, 89.6%-99.8%) and 72.4% (95% CI, 62.0%-82.8%), respectively. The most frequent acute nonhematologic toxicity was radiation esophagitis. Grade (G) 2 and G3 acute radiation esophagitis were observed in 20 (26.7%) and 4 (5.3%) patients, respectively. Thirteen patients (13/75, 17.3%) had G2 pneumonitis and no G3-G5 acute pneumonitis occurred during follow-up. CONCLUSIONS: Hypo-RT followed by hypo-boost combined with concurrent weekly chemotherapy could yield satisfactory local control and survival outcomes with moderate radiation-induced toxicity in patients with LA-NSCLC. The new potent hypo-CCRT regimen significantly shortened treatment time and provided the potential opportunity for the combination of consolidative immunotherapy.

Machine Learning for Predicting Motor Improvement After Acute Subcortical Infarction Using Baseline Whole Brain Volumes.

Background. Neuroimaging biomarkers are valuable predictors of motor improvement after stroke, but there is a gap between published evidence and clinical usage. Objective. In this work, we aimed to investigate whether machine learning techniques, when applied to a combination of baseline whole brain volumes and clinical data, can accurately predict individual motor outcome after stroke. Methods. Upper extremity Fugl-Meyer Assessments (FMA-UE) were conducted 1 week and 12 weeks, and structural MRI was performed 1 week, after onset in 56 patients with subcortical infarction. Proportional recovery model residuals were employed to assign patients to proportional and poor recovery groups (34 vs 22). A sophisticated machine learning scheme, consisting of conditional infomax feature extraction, synthetic minority over-sampling technique for nominal and continuous, and bagging classification, was employed to predict motor outcomes, with the input features being a combination of baseline whole brain volumes and clinical data (FMA-UE scores). Results. The proposed machine learning scheme yielded an overall balanced accuracy of 87.71% in predicting proportional vs poor recovery outcomes, a sensitivity of 93.77% in correctly identifying poor recovery outcomes, and a ROC AUC of 89.74%. Compared with only using clinical data, adding whole brain volumes can significantly improve the classification performance, especially in terms of the overall balanced accuracy (from 80.88% to 87.71%) and the sensitivity (from 92.23% to 93.77%). Conclusions. Experimental results suggest that a combination of baseline whole brain volumes and clinical data, when equipped with appropriate machine learning techniques, may provide valuable information for personalized rehabilitation planning after subcortical infarction.

Tumor response evaluation by combined modalities of chest magnetic resonance imaging and computed tomography in locally advanced non-small cell lung cancer after concurrent chemoradiotherapy.

PURPOSE: This study aimed to explore the role of a modified criteria for assessing tumor response to concurrent chemoradiotherapy (CCRT) in locally advanced non-small cell lung cancer (LA-NSCLC), using the combined modalities of anatomical and functional MRI and CT. MATERIALS AND METHODS: One hundred and fifty-three patients with LA-NSCLC who underwent CCRT with continuous chest MRI and CT follow-up were analyzed. The tumor response to CCRT was evaluated two months after the completion of CCRT. The RECIST criteria (CT imaging) and modified criteria (combined chest MRI and CT imaging) were compared and validated on follow-up imaging. The chest MRI scan analysis included T1C, T2fs, DWI imaging and the apparent diffusion coefficient values. Progression free survival (PFS) ≥ 18 months was used as a surrogate endpoint of complete response to analyze the accuracy of tumor response assessment. RESULTS: Eight (5.2%) patients were considered to have complete response (CR) by the RECIST criteria while fifty-five (35.9%) were considered to have CR (CT + MRI) by the modified criteria. Using PFS ≥ 18 months as a surrogate for CR, the sensitivity and specificity of the modified criteria were 71.2% and 90.8% (AUC = 0.810, 95%CI 0.735-0.885), but were 9.1% and 97.7%, respectively, for the RECIST criteria (AUC = 0.534, 95%CI 0.441-0.627). The median PFS was 58.4 months for patients with CR (CT + MRI) and 9.7 months for those with non-CR (P < 0.001). Multivariate analysis showed that the tumor response evaluated by the modified criteria [CR (CT + MRI) vs. non-CR] was an independent factor for both PFS (HR 0.182, 95%CI 0.088-0.373, P < 0.001) and overall survival (HR 0.134, 95%CI 0.044-0.410, P < 0.001). CONCLUSIONS: Combined multi-parameter MRI and CT imaging could improve the accuracy of tumor response assessment in LA-NSCLC patients after definitive CCRT, therefore contributed to the risk stratification and survival prediction for clinical practice.

CT radiomics-based long-term survival prediction for locally advanced non-small cell lung cancer patients treated with concurrent chemoradiotherapy using features from tumor and tumor organismal environment.

BACKGROUND: Definitive concurrent chemoradiotherapy (CCRT) is the standard treatment for locally advanced non-small cell lung cancer (LANSCLC) patients, but the treatment response and survival outcomes varied among these patients. We aimed to identify pretreatment computed tomography-based radiomics features extracted from tumor and tumor organismal environment (TOE) for long-term survival prediction in these patients treated with CCRT. METHODS: A total of 298 eligible patients were randomly assigned into the training cohort and validation cohort with a ratio 2:1. An integrated feature selection and model training approach using support vector machine combined with genetic algorithm was performed to predict 3-year overall survival (OS). Patients were stratified into the high-risk and low-risk group based on the predicted survival status. Pulmonary function test and blood gas analysis indicators were associated with radiomic features. Dynamic changes of peripheral blood lymphocytes counts before and after CCRT had been documented. RESULTS: Nine features including 5 tumor-related features and 4 pulmonary features were selected in the predictive model. The areas under the receiver operating characteristic curve for the training and validation cohort were 0.965 and 0.869, and were reduced by 0.179 and 0.223 when all pulmonary features were excluded. Based on radiomics-derived stratification, the low-risk group yielded better 3-year OS (68.4% vs. 3.3%, p < 0.001) than the high-risk group. Patients in the low-risk group had better baseline FEV1/FVC% (96.3% vs. 85.9%, p = 0.046), less Grade ≥ 3 lymphopenia during CCRT (63.2% vs. 83.3%, p = 0.031), better recovery of lymphopenia from CCRT (71.4% vs. 27.8%, p < 0.001), lower incidence of Grade ≥ 2 radiation-induced pneumonitis (31.6% vs. 53.3%, p = 0.040), superior tumor remission (84.2% vs. 66.7%, p = 0.003). CONCLUSION: Pretreatment radiomics features from tumor and TOE could boost the long-term survival forecast accuracy in LANSCLC patients, and the predictive results could be utilized as an effective indicator for survival risk stratification. Low-risk patients might benefit more from radical CCRT and further adjuvant immunotherapy. TRIAL REGISTRATION: retrospectively registered.

Machine Learning for Predicting Individual Severity of Blepharospasm Using Diffusion Tensor Imaging.

Accumulating diffusion tensor imaging (DTI) evidence suggests that white matter abnormalities evaluated by local diffusion homogeneity (LDH) or fractional anisotropy (FA) occur in patients with blepharospasm (BSP), both of which are significantly correlated with disease severity. However, whether the individual severity of BSP can be identified using these DTI metrics remains unknown. We aimed to investigate whether a combination of machine learning techniques and LDH or FA can accurately identify the individual severity of BSP. Forty-one patients with BSP were assessed using the Jankovic Rating Scale and DTI. The patients were assigned to non-functionally and functionally limited groups according to their Jankovic Rating Scale scores. A machine learning scheme consisting of beam search and support vector machines was designed to identify non-functionally versus functionally limited outcomes, with the input features being LDH or FA in 68 white matter regions. The proposed machine learning scheme with LDH or FA yielded an overall accuracy of 88.67 versus 85.19% in identifying non-functionally limited versus functionally limited outcomes. The scheme also identified a sensitivity of 91.40 versus 85.87% in correctly identifying functionally limited outcomes, a specificity of 83.33 versus 83.67% in accurately identifying non-functionally limited outcomes, and an area under the curve of 93.7 versus 91.3%. These findings suggest that a combination of LDH or FA measurements and a sophisticated machine learning scheme can accurately and reliably identify the individual disease severity in patients with BSP.

Structural Brain Changes in Blepharospasm: A Cortical Thickness and Diffusion Tensor Imaging Study.

White matter abnormalities in blepharospasm (BSP) have been evaluated using conventional intra-voxel metrics, and changes in patterns of cortical thickness in BSP remain controversial. We aimed to determine whether local diffusion homogeneity, an inter-voxel diffusivity metric, could be valuable in detecting white matter abnormalities for BSP; whether these changes are related to disease features; and whether cortical thickness changes occur in BSP patients. Diffusion tensor and structural magnetic resonance imaging were collected for 29 patients with BSP and 30 healthy controls. Intergroup diffusion differences were compared using tract-based spatial statistics analysis and measures of cortical thickness were obtained. The relationship among cortical thickness, diffusion metric in significantly different regions, and behavioral measures were further assessed. There were no significant differences in cortical thickness and fractional anisotropy between the groups. Local diffusion homogeneity was higher in BSP patients than controls, primarily in the left superior longitudinal fasciculus, corpus callosum, left posterior corona radiata, and left posterior thalamic radiata (P < 0.05, family-wise error corrected). The local diffusion homogeneity values in these regions were positively correlated with the Jankovic rating scale (r s = 0.416, P = 0.031) and BSP disability index (r s = 0.453, P = 0.018) in BSP patients. These results suggest that intra- and inter-voxel diffusive parameters are differentially sensitive to detecting BSP-related white matter abnormalities and that local diffusion homogeneity might be useful in assessing disability in BSP patients.

Prognostic value of early radiological response to first-line platinum-containing chemotherapy in patients with metastatic nasopharyngeal carcinoma.

BACKGROUND: To explore the prognostic value of early radiological response (ERR) to first-line platinum-containing chemotherapy in patients with metastatic nasopharyngeal carcinoma (mNPC), as well as its correlation with the best radiological response (BRR). PATIENTS AND METHODS: A total of 756 mNPC patients with measurable lesions who received first-line platinum-containing chemotherapy were enrolled in this study. ERR was defined as complete or partial response after 6 weeks of chemotherapy according to the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1. We performed survival analyses according to the radiological response after repeated chemotherapy. Log-rank test and Cox regression were used to analyze the survival data. RESULTS: About 470 patients achieved ERR and 78 patients achieved subsequent response (objective response after repeated chemotherapy). ERR patients had better OS (P < .001, median OS: 34.3 vs 22.2 months) and PFS (P < .001, median PFS: 10.2 vs 7.4 months) than non-ERR ones. ERR (OS: HR = 0.591, 95% CI, 0.495-0.705, P < .001, PFS: HR = 0.586, 95% CI, 0.500-0.686, P < .001) was independently prolonged survival compared with non-ERR ones. Besides, ERR was significantly correlated with the BRR (Kappa: 0.73; Pearson: 0.74, P < .001), and had significantly longer OS and PFS than patients with subsequent response, respectively. CONCLUSION: ERR is an independent prognostic factor in determining survival in mNPC patients received first-line platinum-containing chemotherapy, which may be a more sensitive predictor to assess overall efficacy of systemic treatment than BRR in mNPC. Prospective validation studies are needed.