Radiomics of dual-energy computed tomography for predicting progression-free survival in patients with early glottic cancer

Aim: This study aimed to predict progression-free survival (PFS) in patients with early glottic cancer using radiomic features on dual-energy computed tomography iodine maps. Methods: Radiomic features were extracted from arterial and venous phase iodine maps, and radiomic risk scores were determined by univariate Cox proportional hazards regression analysis and least absolute shrinkage and selection operator regression with tenfold cross-validation. The Kaplan-Meier method was used to evaluate the association between radiomic risk scores and PFS. Results: Patients were stratified into low-risk and high-risk groups using radiomics, the PFS corresponding rates with statistical significance between the two groups. The high-risk group showed better survival, benefiting from laryngectomy. Conclusion: Radiomics could provide a promising biomarker for predicting the PFS of early glottic cancer patients.

Cerebral Blood Flow Pattern Changes in Unilateral Sudden Sensorineural Hearing Loss

Objective

This study analyzed the differences in the cerebral blood flow (CBF) between unilateral Sudden Sensorineural Hearing Loss (SSNHL) patients and healthy controls (HCs). We also investigated CBF differences in auditory-related areas in patients with left- and right-sided SSNHL (lSSNHL and rSSNHL) and HCs. We further explore the correlation between unilateral SSNHL characteristics and changes in the CBF.

Methods

36 patients with unilateral SSNHL (15 males and 21 females, 40.39 ± 13.42 years) and 36 HCs (15 males and 21 females, 40.39 ± 14.11 years) were recruited. CBF images were collected and analyzed using arterial spin labeling (ASL). CereFlow software was used for the post-processing of the ASL data to obtain the CBF value of 246 subregions within brainnetome atlas (BNA). The Two-sample t-test was used to compare CBF differences between SSNHL patients and HCs. One-way ANOVA or Kruskal-Wallis test was used to compare the CBF difference of auditory-related areas among the three groups (lSSNHL, rSSNHL, and HCs). Then, the correlation between CBF changes and specific clinical characteristics were calculated.

Results

The SSNHL patients exhibited decreased CBF in the bilateral middle frontal gyrus (MFG, MFG_7_1 and MFG_7_3), the contralateral precentral gyrus (PrG, PrG_6_3) and the bilateral superior parietal lobule (SPL, bilateral SPL_5_1, SPL_5_2, and ipsilateral SPL_5_4), p < 0.0002. Compared with HCs, unilateral SSNHL patients exhibited increased rCBF in the bilateral orbital gyrus (OrG, OrG_6_5), the bilateral inferior temporal gyrus (ITG, contralateral ITG_7_1 and bilateral ITG_7_7), p < 0.0002. lSSNHL showed abnormal CBF in left BA21 caudal (p = 0.02) and left BA37 dorsolateral (p = 0.047). We found that the CBF in ipsilateral MFG_7_1 of SSNHL patients was positively correlated with tinnitus Visual Analog Scale (VAS) score (r = 0.485, p = 0.008).

Conclusion

Our preliminary study explored CBF pattern changes in unilateral SSNHL patients in auditory-related areas and non-auditory areas, suggesting that there may exist reduced attention and some sensory compensation in patients with SSNHL. These findings could advance our understanding of the potential pathophysiology of unilateral SSNHL.

Liquid metal biomaterials for biomedical imaging

Liquid metals (LMs) not only retain the basic properties of metallic biomaterials, such as high thermal conductivity and high electrical conductivity, but also possess flexibility, flowability, deformability, plasticity, good adhesion, and so on. Therefore, they open many possibilities of extending soft metals into biomedical sciences including biomedical imaging. One of the special properties of LMs is that they can provide a controllable material system in which the electrical, thermal, mechanical, and chemical properties can be controlled on a large scale. This paper reviews the preparation and characteristics of LM-based biomaterials classified into four categories: LM micro/nanoparticles, surface modified LM droplets, LM composites with inorganic substances, and LM composites with organic polymers. Besides, considering the most important requirement for biomaterials is biocompatibility, the paper also analyzes the toxicity results of various LM biomaterials when used in the biomedical area, from different levels including body weight measurement, histology evaluation, and blood biochemistry tests. Next, the applications of LMs in X-ray, CT, MRI, photoacoustic imaging, and molecular imaging are introduced in detail. And finally, the challenges and opportunities of their application in medical imaging are also discussed.

Multi-center sparse learning and decision fusion for automatic COVID-19 diagnosis

The coronavirus disease 2019 (COVID-19) pandemic caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a sharp increase in hospitalized patients with multi-organ disease pneumonia. Early and automatic diagnosis of COVID-19 is essential to slow down the spread of this epidemic and reduce the mortality of patients infected with SARS-CoV-2. In this paper, we propose a joint multi-center sparse learning (MCSL) and decision fusion scheme exploiting chest CT images for automatic COVID-19 diagnosis. Specifically, considering the inconsistency of data in multiple centers, we first convert CT images into histogram of oriented gradient (HOG) images to reduce the structural differences between multi-center data and enhance the generalization performance. We then exploit a 3-dimensional convolutional neural network (3D-CNN) model to learn the useful information between and within 3D HOG image slices and extract multi-center features. Furthermore, we employ the proposed MCSL method that learns the intrinsic structure between multiple centers and within each center, which selects discriminative features to jointly train multi-center classifiers. Finally, we fuse these decisions made by these classifiers. Extensive experiments are performed on chest CT images from five centers to validate the effectiveness of the proposed method. The results demonstrate that the proposed method can improve COVID-19 diagnosis performance and outperform the state-of-the-art methods.

Altered Cortical-Striatal Network in Patients With Hemifacial Spasm

Objective: Hemifacial spasm (HFS) is a kind of motor disorder, and the striatum plays a significant role in motor function. The purpose of this study was to explore the alterations of the cortical-striatal network in HFS using resting-state functional magnetic resonance imaging (fMRI). Methods: The fMRI data of 30 adult patients with primary unilateral HFS (15 left-side and 15 right-side) and 30 healthy controls were collected. Six subregions of the striatum in each hemisphere were selected for functional connectivity (FC) analysis. One-sample t-test was used to analyze the intragroup FC of the HFS group and the control group. Two-sample t-test was used to compare the difference of FC between the two groups. The correlation between the abnormal FC and severity of HFS was evaluated by using the Spearman correlation analysis. Results: Compared with the controls, the striatal subregions had altered FC with motor and orbitofrontal cortex in patients with HFS. The altered FC between striatal subregions and motor cortex was correlated with the spasm severity in patients with HFS. Conclusion: The FC of the cortical-striatal network was altered in primary HFS, and these alterations were correlated with the severity of HFS. This study indicated that the cortical-striatal network may play different roles in the underlying pathological mechanism of HFS.

Acute Angle of Multilobulated Contours Improves the Risk Classification of Thymomas

Background: Computed tomography plays an important role in the identification and characterization of thymomas. It has been mainly used during preoperative evaluation for clinical staging. However, the reliable prediction of histological risk types of thymomas based on CT imaging features requires further study. In this study, we developed and validated a nomogram based on CT imaging and included new indices for individualized preoperative prediction of the risk classification of thymomas.

Methods: We conducted a retrospective, multicenter study that included 229 patients from two Chinese medical centers. All the patients underwent cross-sectional CT imaging within 2 weeks before surgery. The results of pathological assessments were retrieved from existing reports of the excised lesions. The tumor perimeter that contacted the lung (TPCL) was evaluated and a new quantitative indicator, the acute angle (AA) formed by adjacent lobulations, was measured. Two predictive models of risk classification were created using the least absolute shrinkage and selection operator (LASSO) method in a training cohort for features selection. The model with a smaller Akaike information criterion was then used to create an individualized imaging nomogram, which we evaluated regarding its prediction ability and clinical utility.

Results: A new CT imaging-based model incorporating AA was developed and validated, which had improved predictive performance during risk classification of thymomas when compared with a model using traditional imaging predictors. The new imaging nomogram with AA demonstrated its clinical utility by decision curve analysis.

Conclusions: Acute angle can improve the performance of a CT-based predictive model during the preoperative risk classification of thymomas and should be considered a new imaging marker for the evaluation and treatment of patients with thymomas. On the contrary, TPCL is not useful as a predictor for the risk classification of thymomas in this study.

[The application of artificial intelligence on the classification of benign and malignant breast tumors based on dynamic enhanced MR images]

This retrospective analysis was conducted on clinical obtained DCE-MR images of 198 patients, age from 21 to 79 years(45.5±13.7). The CBAM-ResNet model was developed to perform the classification automatically at the image-level based on deep learning method using the pathological examination as the reference standard,then the classification result of each individual patient was obtained by ensemble learning. The proposed method can have an accuracy of 82.69% for correctly distinguishing between benign and malignant breast tumors at the slice-level based on CBAM-ResNet model and with a sensitivity of 85.67%.. After the voting mechanism is applied, the classification accuracy can reach up to 88.24% at the patient-level with a sensitivity of 87.50%. Our experimental results demonstrated the proposed approach have a high classification accuracy.

Augmented Multicenter Graph Convolutional Network for COVID-19 Diagnosis

Chest computed tomography (CT) scans of coronavirus 2019 (COVID-19) disease usually come from multiple datasets gathered from different medical centers, and these images are sampled using different acquisition protocols. While integrating multicenter datasets increases sample size, it suffers from inter-center heterogeneity. To address this issue, we propose an augmented multicenter graph convolutional network (AM-GCN) to diagnose COVID-19 with steps as follows. First, we use a 3-D convolutional neural network to extract features from the initial CT scans, where a ghost module and a multitask framework are integrated to improve the network's performance. Second, we exploit the extracted features to construct a multicenter graph, which considers the intercenter heterogeneity and the disease status of training samples. Third, we propose an augmentation mechanism to augment training samples which forms an augmented multicenter graph. Finally, the diagnosis results are obtained by inputting the augmented multi-center graph into GCN. Based on 2223 COVID-19 subjects and 2221 normal controls from seven medical centers, our method has achieved a mean accuracy of 97.76%. The code for our model is made publicly.1.

[Analysis of cerebral perfusion of leptomeningeal branch and perforating branch of unilateral middle cerebral artery with severe stenosis or occlusion based on multi-delay arterial spin labeling]

Objective: To compare the cerebral perfusion differences between the symptomatic patients and the asymptomatic patients with unilateral middle cerebral artery (MCA) severe stenosis or occlusion by using three post labeling delays (PLD) of the three-dimensional pseudo-continuous arterial spin labeling (pCASL) technique. Methods: The clinical characteristics and ASL data of the 27 patients with severe stenosis or occlusion of unilateral MCA (18 symptomatic, 9 asymptomatic) were prospectively enrolled from April 2018 to November 2019 in the Department of Radiology of China-Japan Friendship Hospital. There were 16 males and 11 females, age range from 29 to 85 (55±13) years. According to the symptoms, they were divided into symptomatic group (18 cases) and asymptomatic group (9 cases). The parameters of cerebral blood flow (CBF), mean cerebral blood flow (mCBF), arterial transit time (ATT) and arterial cerebral blood volume (aCBV) were obtained using the Cereflow software. One-way multivariate analysis of variance (one-way MANOVA) was used to compare the differences of cerebral perfusion parameters between symptomatic group and asymptomatic group, and between the affected side and the control side in the two groups. Two-way ANOVA was used to evaluate the effects of symptoms, hemisphere (affected and control side), PLD times (1.5, 2.0 and 2.5 s) and the interaction between the two factors. Results: The CBF of the affected leptomeningeal branch and perforating branch of MCA in symptomatic group was lower than that in asymptomatic group [(36.8±10.2) ml·100 g^-1·min^-1 versus (46.6±13.9) ml·100 g^-1·min^-1, F(1, 75)=13.279, P=0.000 49; (32.3±8.3) ml·100 g^-1·min^-1 versus (36.2±7.5) ml·100 g^-1·min^-1, F (1, 75)=4.065, P=0.047], and there was no interaction between the symptom and PLD [F(2, 75) =0.061, P=0.940]. In the symptomatic group, the CBF of the leptomeningeal branch and perforating branch of MCA in affected side was lower than that in control side [(36.8±10.2) ml·100 g^-1·min^-1 versus (43.7±10.0) ml·100 g^-1·min^-1, F(1, 102)=12.559, P=0.000 59; (32.3±8.3) ml·100 g^-1·min^-1 versus (36.4±8.0) ml·100 g^-1·min^-1, F(1, 102)=6.493, P=0.012]. In the symptomatic group, the CBF of leptomeningeal branch of MCA when PLD was 2.5 s was 7.34 ml·100 g^-1·min^-1, which were higher than that when PLD of 1.5 s (95%CI: 0.72-13.9, P=0.03). There was no interaction between PLD and hemisphere [F(2, 102) =0.307, P=0.736]. Conclusions: The collateral circulation in the blood supply area of MCA in asymptomatic patients with severe unilateral MCA stenosis or occlusion is more abundant than that in symptomatic patients. ASL can be an effective technique for evaluating the cerebral perfusion of collateral circulation in patients with severe stenosis or occlusion of MCA.

3D Multi-Attention Guided Multi-Task Learning Network for Automatic Gastric Tumor Segmentation and Lymph Node Classification

Automatic gastric tumor segmentation and lymph node (LN) classification not only can assist radiologists in reading images, but also provide image-guided clinical diagnosis and improve diagnosis accuracy. However, due to the inhomogeneous intensity distribution of gastric tumor and LN in CT scans, the ambiguous/missing boundaries, and highly variable shapes of gastric tumor, it is quite challenging to develop an automatic solution. To comprehensively address these challenges, we propose a novel 3D multi-attention guided multi-task learning network for simultaneous gastric tumor segmentation and LN classification, which makes full use of the complementary information extracted from different dimensions, scales, and tasks. Specifically, we tackle task correlation and heterogeneity with the convolutional neural network consisting of scale-aware attention-guided shared feature learning for refined and universal multi-scale features, and task-aware attention-guided feature learning for task-specific discriminative features. This shared feature learning is equipped with two types of scale-aware attention (visual attention and adaptive spatial attention) and two stage-wise deep supervision paths. The task-aware attention-guided feature learning comprises a segmentation-aware attention module and a classification-aware attention module. The proposed 3D multi-task learning network can balance all tasks by combining segmentation and classification loss functions with weight uncertainty. We evaluate our model on an in-house CT images dataset collected from three medical centers. Experimental results demonstrate that our method outperforms the state-of-the-art algorithms, and obtains promising performance for tumor segmentation and LN classification. Moreover, to explore the generalization for other segmentation tasks, we also extend the proposed network to liver tumor segmentation in CT images of the MICCAI 2017 Liver Tumor Segmentation Challenge. Our implementation is released at https://github.com/infinite-tao/MA-MTLN.

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor

Automatic segmentation of gastric tumor not only provides image-guided clinical diagnosis but also assists radiologists to read images and improve the diagnostic accuracy. However, due to the inhomogeneous intensity distribution of gastric tumors in CT scans, the ambiguous/missing boundaries, and the highly variable shapes of gastric tumors, it is quite challenging to develop an automatic solution. This study designs a novel 3D improved feature pyramidal network (3D IFPN) to automatically segment gastric tumors in computed tomography (CT) images. To meet the challenges of this extremely difficult task, the proposed 3D IFPN makes full use of the complementary information within the low and high layers of deep convolutional neural networks, which is equipped with three types of feature enhancement modules: 3D adaptive spatial feature fusion (ASFF) module, single-level feature refinement (SLFR) module, and multi-level feature refinement (MLFR) module. The 3D ASFF module adaptively suppresses the feature inconsistency in different levels and hence obtains the multi-level features with high feature invariance. Then, the SLFR module combines the adaptive features and previous multi-level features at each level to generate the multi-level refined features by skip connection and attention mechanism. The MLFR module adaptively recalibrates the channel-wise and spatial-wise responses by adding the attention operation, which improves the prediction capability of the network. Furthermore, a stage-wise deep supervision (SDS) mechanism and a hybrid loss function are also embedded to enhance the feature learning ability of the network. CT volumes dataset collected in three Chinese medical centers was used to evaluate the segmentation performance of the proposed 3D IFPN model. Experimental results indicate that our method outperforms state-of-the-art segmentation networks in gastric tumor segmentation. Moreover, to explore the generalization for other segmentation tasks, we also extend the proposed network to liver tumor segmentation in CT images of the MICCAI 2017 Liver Tumor Segmentation Challenge.

Dual-energy computed tomography could reliably differentiate metastatic from non-metastatic lymph nodes of less than 0.5 cm in patients with papillary thyroid carcinoma

Background

Dual-energy computed tomography (DECT) has been widely applied to detect lymph node (LN) and lymph node metastasis (LNM) in various cancers, including papillary thyroid carcinoma (PTC). This study aimed to quantitatively evaluate metastatic cervical lymph nodes (LNs) <0.5 cm in patients with PTC using DECT, which has not been done in previous studies.

Methods

Preoperative DECT data of patients with pathologically confirmed PTC were retrospectively collected and analyzed between May 2016 and June 2018. A total of 359 LNs from 52 patients were included. Diameter, iodine concentration (IC), normalized iodine concentration (NIC), and the slope of the energy spectrum curve (λ_HU) of LNs in the arterial and the venous phases were compared between metastatic and non-metastatic LNs. The optimal parameters were obtained from the receiver operating characteristic (ROC) curves. The generalized estimation equation (GEE) model was used to evaluate independent diagnostic factors for LNM.

Results

A total of 139 metastatic and 220 non-metastatic LNs were analyzed. There were statistical differences of quantitative parameters between the two groups (P value 0.000-0.007). The optimal parameter for diagnosing LNM was IC in the arterial phase, and its area under the curve (AUC), sensitivity, and specificity were 0.775, 71.9%, and 73.6%, respectively. When the three parameters of diameter, IC in the arterial phase, and NIC in the venous phase were combined, the prediction efficiency was better, and the AUC was 0.819. The GEE results showed that LNs located in level VIa [odds ratio (OR) 2.030, 95% confidence interval (CI): 1.134-3.634, P=0.017], VIb (OR 2.836, 95% CI: 1.597-5.038, P=0.000), diameter (OR 2.023, 95% CI: 1.158-3.532, P=0.013), IC in the arterial phase (OR 4.444, 95% CI: 2.808-7.035, P=0.000), and IC in the venous phase (OR 5.387, 95% CI: 3.449-8.413, P=0.000) were independent risk factors for LNM in patients with PTC.

Conclusions

DECT had good diagnostic performance in the differentiation of cervical metastatic LNs <0.5 cm in patients with PTC.

Regional brain network and behavioral alterations in EGR3 gene transfected rat model of schizophrenia

Schizophrenia is a severe psychiatric disease while its etiology and effective treatment are not completely clear. A rat model of schizophrenia was previously established by transfecting EGR3 gene into the hippocampus of rats. This study aimed to investigate the behavioral and cerebral alterations of the schizophrenic model rats and the risperidone effects. Twenty-six rats were divided into 3 groups: schizophrenia model group (E group), risperidone treatment group (T group), and healthy control group (H group). Morris water maze and open field test were used as behavioral tests, resting-state functional magnetic resonance imaging (fMRI) was performed after EGR3 gene transfection and risperidone therapy. Graph analyses were used for examining cerebral alterations of the rats. Behavioral tests demonstrated reduced spatial working memory and exploring unfamiliar space ability in schizophrenic model rats. Graph analyses revealed reduced regional architectures in the olfactory bulb, nucleus accumbens, and pineal gland in group E compared to group H (p < 0.05), while group T showed increased regional architecture in pineal gland compared to group E (p < 0.05). Besides, the regional architectures in the olfactory bulb, nucleus accumbens were lower in group T than group H, while the hippocampus showed increased regional architecture in group T compared to group H (p < 0.05). Schizophrenia induced several regional alterations in the cerebrum while risperidone can reverse part of these alterations. This study lends support for future research on the pathology of schizophrenia and provides new insights on the role of risperidone in schizophrenia.

Predicting the Level of Tumor-Infiltrating Lymphocytes in Patients With Breast Cancer: Usefulness of Mammographic Radiomics Features

Objectives

This study aimed to investigate whether radiomics classifiers from mammography can help predict tumor-infiltrating lymphocyte (TIL) levels in breast cancer.

Methods

Data from 121 consecutive patients with pathologically-proven breast cancer who underwent preoperative mammography from February 2018 to May 2019 were retrospectively analyzed. Patients were randomly divided into a training dataset (n = 85) and a validation dataset (n = 36). A total of 612 quantitative radiomics features were extracted from mammograms using the Pyradiomics software. Radiomics feature selection and radiomics classifier were generated through recursive feature elimination and logistic regression analysis model. The relationship between radiomics features and TIL levels in breast cancer patients was explored. The predictive capacity of the radiomics classifiers for the TIL levels was investigated through receiver operating characteristic curves in the training and validation groups. A radiomics score (Rad score) was generated using a logistic regression analysis method to compute the training and validation datasets, and combining the Mann–Whitney U test to evaluate the level of TILs in the low and high groups.

Results

Among the 121 patients, 32 (26.44%) exhibited high TIL levels, and 89 (73.56%) showed low TIL levels. The ER negativity (p = 0.01) and the Ki-67 negative threshold level (p = 0.03) in the low TIL group was higher than that in the high TIL group. Through the radiomics feature selection, six top-class features [Wavelet GLDM low gray-level emphasis (mediolateral oblique, MLO), GLRLM short-run low gray-level emphasis (craniocaudal, CC), LBP2D GLRLM short-run high gray-level emphasis (CC), LBP2D GLDM dependence entropy (MLO), wavelet interquartile range (MLO), and LBP2D median (MLO)] were selected to constitute the radiomics classifiers. The radiomics classifier had an excellent predictive performance for TIL levels both in the training and validation sets [area under the curve (AUC): 0.83, 95% confidence interval (CI), 0.738–0.917, with positive predictive value (PPV) of 0.913; AUC: 0.79, 95% CI, 0.615–0.964, with PPV of 0.889, respectively]. Moreover, the Rad score in the training dataset was higher than that in the validation dataset (p = 0.007 and p = 0.001, respectively).

Conclusion

Radiomics from digital mammograms not only predicts the TIL levels in breast cancer patients, but can also serve as non-invasive biomarkers in precision medicine, allowing for the development of treatment plans.

Alterations and Associations Between Magnetic Susceptibility of the Basal Ganglia and Diffusion Properties in Alzheimer's Disease

This study adopted diffusion tensor imaging to detect alterations in the diffusion parameters of the white matter fiber in Alzheimer’s disease (AD) and used quantitative susceptibility mapping to detect changes in magnetic susceptibility. However, whether the changes of susceptibility values due to excessive iron in the basal ganglia have correlations with the alterations of the diffusion properties of the white matter in patients with AD are still unknown. We aim to investigate the correlations among magnetic susceptibility values of the basal ganglia, diffusion indexes of the white matter, and cognitive function in patients with AD. Thirty patients with AD and nineteen healthy controls (HCs) were recruited. Diffusion indexes of the whole brain were detected using tract-based spatial statistics. The caudate nucleus, putamen, and globus pallidus were selected as regions of interest, and their magnetic susceptibility values were measured. Compared with HCs, patients with AD showed that there were significantly increased axial diffusivity (AxD) in the internal capsule, superior corona radiata (SCR), and right anterior corona radiata (ACR); increased radial diffusivity (RD) in the right anterior limb of the internal capsule, ACR, and genu of the corpus callosum (GCC); and decreased fractional anisotropy (FA) in the right ACR and GCC. The alterations of RD values, FA values, and susceptibility values of the right caudate nucleus in patients with AD were correlated with cognitive scores. Besides, AxD values in the right internal capsule, ACR, and SCR were positively correlated with the magnetic susceptibility values of the right caudate nucleus in patients with AD. Our findings revealed that the magnetic susceptibility of the caudate nucleus may be an MRI-based biomarker of the cognitive dysfunction of AD and abnormal excessive iron distribution in the basal ganglia had adverse effects on the diffusion properties of the white matter.

Anterior Mediastinal Lesion Segmentation Based on Two-Stage 3D ResUNet With Attention Gates and Lung Segmentation

OBJECTIVES

Anterior mediastinal disease is a common disease in the chest. Computed tomography (CT), as an important imaging technology, is widely used in the diagnosis of mediastinal diseases. Doctors find it difficult to distinguish lesions in CT images because of image artifact, intensity inhomogeneity, and their similarity with other tissues. Direct segmentation of lesions can provide doctors a method to better subtract the features of the lesions, thereby improving the accuracy of diagnosis.

METHOD

As the trend of image processing technology, deep learning is more accurate in image segmentation than traditional methods. We employ a two-stage 3D ResUNet network combined with lung segmentation to segment CT images. Given that the mediastinum is between the two lungs, the original image is clipped through the lung mask to remove some noises that may affect the segmentation of the lesion. To capture the feature of the lesions, we design a two-stage network structure. In the first stage, the features of the lesion are learned from the low-resolution downsampled image, and the segmentation results under a rough scale are obtained. The results are concatenated with the original image and encoded into the second stage to capture more accurate segmentation information from the image. In addition, attention gates are introduced in the upsampling of the network, and these gates can focus on the lesion and play a role in filtering the features. The proposed method has achieved good results in the segmentation of the anterior mediastinal.

RESULTS

The proposed method was verified on 230 patients, and the anterior mediastinal lesions were well segmented. The average Dice coefficient reached 87.73%. Compared with the model without lung segmentation, the model with lung segmentation greatly improved the accuracy of lesion segmentation by approximately 9%. The addition of attention gates slightly improved the segmentation accuracy.

CONCLUSION

The proposed automatic segmentation method has achieved good results in clinical data. In clinical application, automatic segmentation of lesions can assist doctors in the diagnosis of diseases and may facilitate the automated diagnosis of illnesses in the future.

Alterations of Iron Level in the Bilateral Basal Ganglia Region in Patients With Middle Cerebral Artery Occlusion

Background and Purpose: The purpose of this study was to explore the changes of iron level using quantitative susceptibility mapping (QSM) in the bilateral basal ganglia region in middle cerebral artery occlusion (MCAO) patients with long-term ischemia.

Methods: Twenty-seven healthy controls and nine patients with MCAO were recruited, and their QSM images were obtained. The bilateral caudate nucleus (Cd), putamen (Pt), and globus pallidus (Gp) were selected as the regions of interest (ROIs). Susceptibility values of bilateral ROIs were calculated and compared between the affected side and unaffected side in patients with MCAO and between patients with MCAO and healthy controls. In addition, receiver operating characteristic (ROC) curves were performed to evaluate the diagnostic capability of susceptibility values in differentiating healthy controls and patients with MCAO by the area under the curve (AUC).

Results: The susceptibility values of bilateral Cd were asymmetric in healthy controls; however, this asymmetry disappeared in patients with MCAO. In addition, compared with healthy controls, the average susceptibility values of the bilateral Pt in patients with MCAO were increased (P < 0.05), and the average susceptibility value of the bilateral Gp was decreased (P < 0.05). ROC curves showed that the susceptibility values of the Pt and Gp had a larger AUC (AUC = 0.700 and 0.889, respectively).

Conclusion: As measured by QSM, the iron levels of the bilateral basal ganglia region were significantly changed in patients with MCAO. Iron dyshomeostasis in the basal ganglia region might be involved in the pathophysiological process of middle cerebral artery stenosis and occlusion. These findings may provide a novel insight to profoundly address the pathophysiological mechanisms of MCAO.

Microwave-Induced Thermal Lesion Detection via Ultrasonic Scatterer Center Frequency Analysis with Autoregressive Cepstrum

We proposed a new method for microwave-induced thermal lesion detection using the autoregressive spectrum analysis of ultrasonic backscattered signals in this paper. Eighteen cases of microwave ablation experiments and twenty cases of water bath heating experiments were conducted. Ultrasonic radiofrequency data of normal and coagulated porcine liver tissues were collected through these two experiments. Then, autoregressive spectrum analysis was performed; the mean frequency of the dominant peak in the autoregressive spectrum was computed based on water bath experiments; and a method for recognizing normal and solidified tissues was obtained by comparing the difference of the dominant peak in the autoregressive spectrum. Two bandpass finite impulse response filters, whose passbands corresponded respectively to the dominant peak in the autoregressive spectrum of normal and coagulated tissues, were used to compute the power spectral integration for the microwave-induced experiments. Microwave-induced thermal lesions were detected based on the differences between the power spectral integrations from the two filters. Compared to the caliper-measured area, the power spectral integration detected area had an error of (10.25 ± 3.59). Experimental results indicated that the proposed method may be used in preliminary detection of microwave-induced thermal lesions.

Anisotropy of Anomalous Diffusion Improves the Accuracy of Differentiating and Grading Alzheimer's Disease Using Novel Fractional Motion Model

Background and Purpose: Recent evidence shows that the fractional motion (FM) model may be a more appropriate model for describing the complex diffusion process of water in brain tissue and has shown to be beneficial in clinical applications of Alzheimer's disease (AD). However, the FM model averaged the anomalous diffusion parameter values, which omitted the impacts of anisotropy. This study aimed to investigate the potential feasibility of anisotropy of anomalous diffusion using the FM model for distinguishing and grading AD patients. Methods: Twenty-four patients with AD and 11 matched healthy controls were recruited, diffusion MRI was obtained from all participants and analyzed using the FM model. Generalized fractional anisotropy (gFA), an anisotropy metric, was introduced and the gFA values of FM-related parameters, Noah exponent (α) and the Hurst exponent (H), were calculated and compared between the healthy group and AD group and between the mild AD group and moderate AD group. The receiver-operating characteristic (ROC) analysis and the multivariate logistic regression analysis were used to assess the diagnostic performances of the anisotropy values and the directionally averaged values. Results: The gFA(α) and gFA(H) values of the moderate AD group were higher than those of the mild AD group in left hippocampus. The gFA(α) value of the moderate AD group was significantly higher than that of the healthy control group in both the left and right hippocampus. The gFA(ADC) values of the moderate AD group were significantly lower than those of the mild AD group and healthy control group in the right hippocampus. Compared with the gFA(α), gFA(H), α, and H, the ROC analysis showed larger areas under the curves for combination of α + gFA(α) and the combination of H + gFA(H) in differentiating the mild AD and moderate AD groups, and larger area under the curves for combination of α + gFA(α) in differentiating the healthy controls and AD groups. Conclusion: The anisotropy of anomalous diffusion could significantly differentiate and grade patients with AD, and the diagnostic performance was improved when the anisotropy metric was combined with commonly used directionally averaged values. The utility of anisotropic anomalous diffusion may provide novel insights to profoundly understand the neuropathology of AD.

Medical Imaging Engineering and Technology Branch of the Chinese Society of Biomedical Engineering expert consensus on the application of Emergency Mobile Cabin CT

Started during December 2019, following the emergence of several COVID-19 cases in Wuhan City, Hubei Province, there was a rapid surge and spread of new COVID-19 cases throughout China. The disease has since been included in the Class B infectious diseases category, as stipulated in the Law of the People's Republic of China on the Prevention and Treatment of Infectious Diseases and shall be managed according to Class A infectious diseases. During the early phases of COVID-19 infection, no specific pulmonary imaging features may be evident, or features overlapping with other pneumonia may be observed. Although CT is not the gold standard for the diagnosis of COVID-19, it nonetheless is a convenient and fast method, and its application can be deployed in community hospitals. Furthermore, CT can be used to render a suggestive diagnosis and evaluate the severity as well as the effects of therapeutic interventions for typical cases of COVID-19. The mobile emergency special CT device described in this document (also known as Emergency Mobile Cabin CT) has several unique characteristics, including its mobility, flexibility, and networking capabilities. Furthermore, it adopts a fully independent isolation design to avoid cross-infection between patients and medical staff. It can play an important role in screening suspected cases presenting with imaging features of COVID-19 in hospitals of various levels that provide care to suspected or confirmed COVID-19 patients as part of the first line procedures of epidemic prevention and control.

Identification and Classification of Alzheimer's Disease Patients Using Novel Fractional Motion Model

Most diffusion magnetic resonance imaging (dMRI) techniques use the mono-exponential model to describe the diffusion process of water in the brain. However, the observed dMRI signal decay curve deviates from the mono-exponential form. To solve this problem, the fractional motion (FM) model has been developed, which is regarded as a more appropriate model for describing the complex diffusion process in brain tissue. It is still unclear in the identification and classification of Alzheimer's disease (AD) patients using the FM model. The purpose of this study was to investigate the potential feasibility of FM model for differentiating AD patients from healthy controls and grading patients with AD. Twenty-four patients with AD and 11 healthy controls were included. The left and right hippocampus were selected as regions of interest (ROIs). The apparent diffusion coefficient (ADC) values and FM-related parameters, including the Noah exponent (α), the Hurst exponent (H), and the memory parameter (μ=H-1/α), were calculated and compared between AD patients and healthy controls and between mild AD and moderate AD patients using a two-sample t-test. The correlations between FM-related parameters α, H, μ, and ADC values and the cognitive functions assessed by mini-mental state examination (MMSE) and Montreal cognitive assessment (MoCA) scales were investigated using Pearson partial correlation analysis in patients with AD. The receiver-operating characteristic analysis was used to assess the differential performance. We found that the FM-related parameter α could be used to distinguish AD patients from healthy controls (P < 0.05) with greater sensitivity and specificity (left ROI, 0.917 and 0.636; right ROI, 0.917 and 0.727) and grade AD patients (P < 0.05) showed higher sensitivity and specificity (right ROI, 0.917, 0.75). The α was found to be positively correlated with MMSE (P < 0.05) and MoCA (P < 0.05) scores in patients with AD, indicating that the α values in the bilateral hippocampus were a potential MRI-based biomarker of disease severity in AD patients. This novel diffusion model may be useful for further understanding neuropathologic changes in patients with AD.

Sulfenic Acid-Mediated on-Site-Specific Immobilization of Mitochondrial-Targeted NIR Fluorescent Probe for Prolonged Tumor Imaging

Mitochondria plays pivotal roles in energy production and apoptotic pathways. Mitochondria-targeting strategy has been recognized as a promising way for cancer theranostics. Thus, spatiotemporally manipulating the prolonged retention of theranostic agents within mitochondria is considerably significant in cancer diagnosis and therapy. Herein, as a proof-of concept, we for the first time report a sulfenic acid-responsive platform on controlled immobilization of probes within mitochondria for prolonged tumor imaging. A novel near-infrared (NIR) probe DATC constructed with a NIR dye (Cy5) as signal unit, a cationic triphenylphosphonium (TPP) for mitochondria targeting, and a sulfenic acid-reactive group (1,3-cyclohexanedione) for mitochondrial fixation was rationally designed and synthesized. This probe displayed good target ability to mitochondria and could act as a promising fluorescent probe for specific visualization of endogenous protein sulfenic acids expressed in the mitochondria. Moreover, the probe could be spontaneously fixed on site through the specific reaction and covalent binding to the sulfenic acids of oxidized proteins under oxidative stress, resulting in enhanced intracellular uptake and prolonged retention. We thus believe that this mitochondria-targeted and locational immobilization strategy may offer a new insight for long-term tumor imaging and effective therapy.

Correlation Between Mammographic Radiomics Features and the Level of Tumor-Infiltrating Lymphocytes in Patients With Triple-Negative Breast Cancer

Objectives: Tumor-infiltrating lymphocytes (TILs) have been identified as a significant prognostic indicator of response to neoadjuvant therapy and immunotherapy for triple-negative breast cancer (TNBC) patients. Herein, we aim to assess the association between TIL levels and mammographic features in TNBC patients. Methods: Forty-three patients with surgically proven TNBC who underwent preoperative mammography from January 2018 to December 2018 were recruited. Pyradiomics software was used to extract 204 quantitative radiomics features, including morphologic, grayscale, and textural features, from the segmented lesion areas. The correlation between radiological characteristics and TIL levels was evaluated by screening the most statistically significant radiological features using Mann-Whitney U-test and Pearson correlation coefficient. The patients were divided into two groups based on tumor TIL levels: patients with TIL levels <50% and those with TIL levels ≥50%. The correlation between TIL levels and clinicopathological characteristics was assessed using the chi-square test or Fisher's exact test. Mann-Whitney U-test and Pearson correlation coefficient were used to analyze the statistical significance and Pearson correlation coefficient of clinical pathological features, age, and radiological features. Results: Of 43 patients, 32 (74.4%) had low TIL levels and 11 (25.6%) had high TIL levels. The histological grade of the low TIL group was higher than that of the high TIL group (p = 0.043). The high TIL group had a more negative threshold Ki-67 level (<14%) than the low TIL group (p = 0.017). The six most important radiomics features [uniformity, variance, grayscale symbiosis matrix (GLCM) correlation, GLCM autocorrelation, gray level difference matrix (GLDM) low gray level emphasis, and neighborhood gray-tone difference matrix (NGTDM) contrast], representing qualitative mammographic image characteristics, were statistically different (p < 0.05) among the low and high TIL groups. Tumors in the high TIL group had a more non-uniform density and a smoother gradient of the tumor pattern than the low TIL group. The changes in Ki-67, age, epidermal growth factor receptor, radiomic characteristics, and Pearson correlation coefficient were statistically significant (p < 0.05). Conclusion: Mammography features not only distinguish high and low TIL levels in TNBC patients but also can act as imaging biomarkers to enhance diagnosis and the response of patients to neoadjuvant therapies and immunotherapies.