HBV-related HCC development in mice is STAT3 dependent and indicates an oncogenic effect of HBx.

Background & Aims: Although most hepatocellular carcinoma (HCC) cases are driven by hepatitis and cirrhosis, a subset of patients with chronic hepatitis B develop HCC in the absence of advanced liver disease, indicating the oncogenic potential of hepatitis B virus (HBV). We investigated the role of HBV transcripts and proteins on HCC development in the absence of inflammation in HBV-transgenic mice. Methods: HBV-transgenic mice replicating HBV and expressing all HBV proteins from a single integrated 1.3-fold HBV genome in the presence or absence of wild-type HBx (HBV1.3/HBVxfs) were analyzed. Flow cytometry, molecular, histological and in vitro analyses using human cell lines were performed. Hepatocyte-specific Stat3- and Socs3-knockout was analyzed in HBV1.3 mice. Results: Approximately 38% of HBV1.3 mice developed liver tumors. Protein expression patterns, histology, and mutational landscape analyses indicated that tumors resembled human HCC. HBV1.3 mice showed no signs of active hepatitis, except STAT3 activation, up to the time point of HCC development. HBV-RNAs covering HBx sequence, 3.5-kb HBV RNA and HBx-protein were detected in HCC tissue. Interestingly, HBVxfs mice expressing all HBV proteins except a C-terminally truncated HBx (without the ability to bind DNA damage binding protein 1) showed reduced signs of DNA damage response and had a significantly reduced HCC incidence. Importantly, intercrossing HBV1.3 mice with a hepatocyte-specific STAT3-knockout abrogated HCC development. Conclusions: Expression of HBV-proteins is sufficient to cause HCC in the absence of detectable inflammation. This indicates the oncogenic potential of HBV and in particular HBx. In our model, HBV-driven HCC was STAT3 dependent. Our study highlights the immediate oncogenic potential of HBV, challenging the idea of a benign highly replicative phase of HBV infection and indicating the necessity for an HBV 'cure'. Impact and implications: Although most HCC cases in patients with chronic HBV infection occur after a sequence of liver damage and fibrosis, a subset of patients develops HCC without any signs of advanced liver damage. We demonstrate that the expression of all viral transcripts in HBV-transgenic mice suffices to induce HCC development independent of inflammation and fibrosis. These data indicate the direct oncogenic effects of HBV and emphasize the idea of early antiviral treatment in the 'immune-tolerant' phase (HBeAg-positive chronic HBV infection).

Motion Artifact Detection for T1-Weighted Brain MR Images Using Convolutional Neural Networks.

Quality assessment (QA) of magnetic resonance imaging (MRI) encompasses several factors such as noise, contrast, homogeneity, and imaging artifacts. Quality evaluation is often not standardized and relies on the expertise, and vigilance of the personnel, posing limitations especially with large datasets. Machine learning based on convolutional neural networks (CNNs) is a promising approach to address these challenges by performing automated inspection of MR images. In this study, a CNN for the detection of random head motion artifacts (RHM) in T1-weighted MRI as one aspect of image quality is proposed. A two-step approach aimed to first identify images exhibiting pronounced motion artifacts, and second to evaluate the feasibility of a more detailed three-class classification. The utilized dataset consisted of 420 T1-weighted whole-brain image volumes with isotropic resolution. Human experts assigned each volume to one of three classes of artifact prominence. Results demonstrate an accuracy of 95% for the identification of images with pronounced artifact load. The addition of an intermediate class retained an accuracy of 76%. The findings highlight the potential of CNN-based approaches to increase the efficiency of post-hoc QAs in large datasets by flagging images with potentially relevant artifact loads for closer inspection.

Accuracy of Four Different CT Perfusion Thresholds for Ischemic Core Volume and Location Estimation Using IntelliSpace Portal.

Computed tomography perfusion (CTP) is frequently used in the triage of ischemic stroke patients for endovascular thrombectomy (EVT). We aimed to quantify the volumetric and spatial agreement of the CTP ischemic core estimated with different thresholds and follow-up MRI infarct volume on diffusion-weighted imaging (DWI). Patients treated with EVT between November 2017 and September 2020 with available baseline CTP and follow-up DWI were included. Data were processed with Philips IntelliSpace Portal using four different thresholds. Follow-up infarct volume was segmented on DWI. In 55 patients, the median DWI volume was 10 mL, and median estimated CTP ischemic core volumes ranged from 10-42 mL. In patients with complete reperfusion, the intraclass correlation coefficient (ICC) showed moderate-good volumetric agreement (range 0.55-0.76). A poor agreement was found for all methods in patients with successful reperfusion (ICC range 0.36-0.45). Spatial agreement (median Dice) was low for all four methods (range 0.17-0.19). Severe core overestimation was most frequently (27%) seen in Method 3 and patients with carotid-T occlusion. Our study shows moderate-good volumetric agreement between ischemic core estimates for four different thresholds and subsequent infarct volume on DWI in EVT-treated patients with complete reperfusion. The spatial agreement was similar to other commercially available software packages.

Activation of CD4 T cells during prime immunization determines the success of a therapeutic hepatitis B vaccine in HBV-carrier mouse models.

BACKGROUND & AIMS: We recently developed a heterologous therapeutic vaccination scheme (TherVacB) comprising a particulate protein prime followed by a modified vaccinia-virus Ankara (MVA)-vector boost for the treatment of HBV. However, the key determinants required to overcome HBV-specific immune tolerance remain unclear. Herein, we aimed to study new combination adjuvants and unravel factors that are essential for the antiviral efficacy of TherVacB. METHODS: Recombinant hepatitis B surface and core antigen (HBsAg and HBcAg) particles were formulated with different liposome- or oil-in-water emulsion-based combination adjuvants containing saponin QS21 and monophosphoryl lipid A; these formulations were compared to STING-agonist c-di-AMP and conventional aluminium hydroxide formulations. Immunogenicity and the antiviral effects of protein antigen formulations and the MVA-vector boost within TherVacB were evaluated in adeno-associated virus-HBV-infected and HBV-transgenic mice. RESULTS: Combination adjuvant formulations preserved HBsAg and HBcAg integrity for ≥12 weeks, promoted human and mouse dendritic cell activation and, within TherVacB, elicited robust HBV-specific antibody and T-cell responses in wild-type and HBV-carrier mice. Combination adjuvants that prime a balanced HBV-specific type 1 and 2 T helper response induced high-titer anti-HBs antibodies, cytotoxic T-cell responses and long-term control of HBV. In the absence of an MVA-vector boost or following selective CD8 T-cell depletion, HBsAg still declined (mediated mainly by anti-HBs antibodies) but HBV replication was not controlled. Selective CD4 T-cell depletion during the priming phase of TherVacB resulted in a complete loss of vaccine-induced immune responses and its therapeutic antiviral effect in mice. CONCLUSIONS: Our results identify CD4 T-cell activation during the priming phase of TherVacB as a key determinant of HBV-specific antibody and CD8 T-cell responses. IMPACT AND IMPLICATIONS: Therapeutic vaccination is a potentially curative treatment option for chronic hepatitis B. However, it remains unclear which factors are essential for breaking immune tolerance in HBV carriers and determining successful outcomes. Our study provides the first direct evidence that efficient priming of HBV-specific CD4 T cells determines the success of therapeutic hepatitis B vaccination in two preclinical HBV-carrier mouse models. Applying an optimal formulation of HBV antigens that activates CD4 and CD8 T cells during prime immunization provided the foundation for an antiviral effect of therapeutic vaccination, while depletion of CD4 T cells led to a complete loss of vaccine-induced antiviral efficacy. Boosting CD8 T cells was important to finally control HBV in these mouse models. Our findings provide important insights into the rational design of therapeutic vaccines for the cure of chronic hepatitis B.

AI support for accurate and fast radiological diagnosis of COVID-19: an international multicenter, multivendor CT study.

OBJECTIVES: Differentiation between COVID-19 and community-acquired pneumonia (CAP) in computed tomography (CT) is a task that can be performed by human radiologists and artificial intelligence (AI). The present study aims to (1) develop an AI algorithm for differentiating COVID-19 from CAP and (2) evaluate its performance. (3) Evaluate the benefit of using the AI result as assistance for radiological diagnosis and the impact on relevant parameters such as accuracy of the diagnosis, diagnostic time, and confidence. METHODS: We included n = 1591 multicenter, multivendor chest CT scans and divided them into AI training and validation datasets to develop an AI algorithm (n = 991 CT scans; n = 462 COVID-19, and n = 529 CAP) from three centers in China. An independent Chinese and German test dataset of n = 600 CT scans from six centers (COVID-19 / CAP; n = 300 each) was used to test the performance of eight blinded radiologists and the AI algorithm. A subtest dataset (180 CT scans; n = 90 each) was used to evaluate the radiologists' performance without and with AI assistance to quantify changes in diagnostic accuracy, reporting time, and diagnostic confidence. RESULTS: The diagnostic accuracy of the AI algorithm in the Chinese-German test dataset was 76.5%. Without AI assistance, the eight radiologists' diagnostic accuracy was 79.1% and increased with AI assistance to 81.5%, going along with significantly shorter decision times and higher confidence scores. CONCLUSION: This large multicenter study demonstrates that AI assistance in CT-based differentiation of COVID-19 and CAP increases radiological performance with higher accuracy and specificity, faster diagnostic time, and improved diagnostic confidence. KEY POINTS: • AI can help radiologists to get higher diagnostic accuracy, make faster decisions, and improve diagnostic confidence. • The China-German multicenter study demonstrates the advantages of a human-machine interaction using AI in clinical radiology for diagnostic differentiation between COVID-19 and CAP in CT scans.

Advanced Deep Learning Approach to Automatically Segment Malignant Tumors and Ablation Zone in the Liver With Contrast-Enhanced CT.

OBJECTIVE: Liver cancer is one of the most commonly diagnosed cancer, and energy-based tumor ablation is a widely accepted treatment. Automatic and robust segmentation of liver tumors and ablation zones would facilitate the evaluation of treatment success. The purpose of this study was to develop and evaluate an automatic deep learning based method for (1) segmentation of liver and liver tumors in both arterial and portal venous phase for pre-treatment CT, and (2) segmentation of liver and ablation zones in both arterial and portal venous phase for after ablation treatment. MATERIALS AND METHODS: 252 CT images from 63 patients undergoing liver tumor ablation at a large University Hospital were retrospectively included; each patient had pre-treatment and post-treatment multi-phase CT images. 3D voxel-wise manual segmentation of the liver, tumors and ablation region by the radiologist provided reference standard. Deep learning models for liver and lesion segmentation were initially trained on the public Liver Tumor Segmentation Challenge (LiTS) dataset to obtain base models. Then, transfer learning was applied to adapt the base models on the clinical training-set, to obtain tumor and ablation segmentation models both for arterial and portal venous phase images. For modeling, 2D residual-attention Unet (RA-Unet) was employed for liver segmentation and a multi-scale patch-based 3D RA-Unet for tumor and ablation segmentation. RESULTS: On the independent test-set, the proposed method achieved a dice similarity coefficient (DSC) of 0.96 and 0.95 for liver segmentation on arterial and portal venous phase, respectively. For liver tumors, the model on arterial phase achieved detection sensitivity of 71%, DSC of 0.64, and on portal venous phase sensitivity of 82%, DSC of 0.73. For liver tumors >0.5cm3 performance improved to sensitivity 79%, DSC 0.65 on arterial phase and, sensitivity 86%, DSC 0.72 on portal venous phase. For ablation zone, the model on arterial phase achieved detection sensitivity of 90%, DSC of 0.83, and on portal venous phase sensitivity of 90%, DSC of 0.89. CONCLUSION: The proposed deep learning approach can provide automated segmentation of liver tumors and ablation zones on multi-phase (arterial and portal venous) and multi-time-point (before and after treatment) CT enabling quantitative evaluation of treatment success.

Fully Automated MR Detection and Segmentation of Brain Metastases in Non-small Cell Lung Cancer Using Deep Learning.

BACKGROUND: Non-small cell lung cancer (NSCLC) is the most common tumor entity spreading to the brain and up to 50% of patients develop brain metastases (BMs). Detection of BMs on MRI is challenging with an inherent risk of missed diagnosis. PURPOSE: To train and evaluate a deep learning model (DLM) for fully automated detection and 3D segmentation of BMs in NSCLC on clinical routine MRI. STUDY TYPE: Retrospective. POPULATION: Ninety-eight NSCLC patients with 315 BMs on pretreatment MRI, divided into training (66 patients, 248 BMs) and independent test (17 patients, 67 BMs) and control (15 patients, 0 BMs) cohorts. FIELD STRENGTH/SEQUENCE: T1 -/T2 -weighted, T1 -weighted contrast-enhanced (T1 CE; gradient-echo and spin-echo sequences), and FLAIR at 1.0, 1.5, and 3.0 T from various vendors and study centers. ASSESSMENT: A 3D convolutional neural network (DeepMedic) was trained on the training cohort using 5-fold cross-validation and evaluated on the independent test and control sets. Three-dimensional voxel-wise manual segmentations of BMs by a neurosurgeon and a radiologist on T1 CE served as the reference standard. STATISTICAL TESTS: Sensitivity (recall) and false positive (FP) findings per scan, dice similarity coefficient (DSC) to compare the spatial overlap between manual and automated segmentations, Pearson's correlation coefficient (r) to evaluate the relationship between quantitative volumetric measurements of segmentations, and Wilcoxon rank-sum test to compare the volumes of BMs. A P value <0.05 was considered statistically significant. RESULTS: In the test set, the DLM detected 57 of the 67 BMs (mean volume: 0.99 ± 4.24 cm3 ), resulting in a sensitivity of 85.1%, while FP findings of 1.5 per scan were observed. Missed BMs had a significantly smaller volume (0.05 ± 0.04 cm3 ) than detected BMs (0.96 ± 2.4 cm3 ). Compared with the reference standard, automated segmentations achieved a median DSC of 0.72 and a good volumetric correlation (r = 0.95). In the control set, 1.8 FPs/scan were observed. DATA CONCLUSION: Deep learning provided a high detection sensitivity and good segmentation performance for BMs in NSCLC on heterogeneous scanner data while yielding a low number of FP findings. Level of Evidence 3 Technical Efficacy Stage 2.

Deep learning assistance increases the detection sensitivity of radiologists for secondary intracranial aneurysms in subarachnoid hemorrhage.

PURPOSE: To evaluate whether a deep learning model (DLM) could increase the detection sensitivity of radiologists for intracranial aneurysms on CT angiography (CTA) in aneurysmal subarachnoid hemorrhage (aSAH). METHODS: Three different DLMs were trained on CTA datasets of 68 aSAH patients with 79 aneurysms with their outputs being combined applying ensemble learning (DLM-Ens). The DLM-Ens was evaluated on an independent test set of 104 aSAH patients with 126 aneuryms (mean volume 129.2 ± 185.4 mm3, 13.0% at the posterior circulation), which were determined by two radiologists and one neurosurgeon in consensus using CTA and digital subtraction angiography scans. CTA scans of the test set were then presented to three blinded radiologists (reader 1: 13, reader 2: 4, and reader 3: 3 years of experience in diagnostic neuroradiology), who assessed them individually for aneurysms. Detection sensitivities for aneurysms of the readers with and without the assistance of the DLM were compared. RESULTS: In the test set, the detection sensitivity of the DLM-Ens (85.7%) was comparable to the radiologists (reader 1: 91.2%, reader 2: 86.5%, and reader 3: 86.5%; Fleiss κ of 0.502). DLM-assistance significantly increased the detection sensitivity (reader 1: 97.6%, reader 2: 97.6%,and reader 3: 96.0%; overall P=.024; Fleiss κ of 0.878), especially for secondary aneurysms (88.2% of the additional aneurysms provided by the DLM). CONCLUSION: Deep learning significantly improved the detection sensitivity of radiologists for aneurysms in aSAH, especially for secondary aneurysms. It therefore represents a valuable adjunct for physicians to establish an accurate diagnosis in order to optimize patient treatment.

Bone-Preserving Arthroplasty With Abductor Pollicis Longus Tenodesis for Trapeziometacarpal Osteoarthritis.

Purpose: The objective of this study was to describe an original method of bone-preserving arthroplasty with abductor pollicis longus (APL) tenodesis and determine its safety and effectiveness as a treatment for early-stage osteoarthritis of the trapeziometacarpal joint. Methods: Eleven patients underwent a trapezium-preserving arthroplasty with APL tenodesis for stage 1 and 2 osteoarthritis were retrospectively reviewed. This arthroplasty consisted of a distally-based APL tendon being passed through the trapeziometacarpal joint. The proximal end of the tendon was then pulled and passed through a drill hole made at the neck of the second metacarpal and sutured to itself. Thus, distraction of the first metacarpal and interposition of the tendon were created. Postoperative radiologic and clinical follow-up visits were performed at 4, 8, and 12 weeks. Range of motion and strength were assessed after surgery. Patient satisfaction and outcome were assessed, and the disabilities of the arm, shoulder, and hand (DASH) score was used. Results: After a mean follow-up of 29.5 months (range, 16-43 months), the mean patient visual analog scale pain score improved from 7.1 to 2.3. The average DASH score of all patients at the follow-up examination was 18.3 ± 19.8. Patients' mean grip strength was 25.3 kg, which represented 102% of the value on the contralateral side. The key-pinch strength was 6.2 kg on the operated hand compared with 6.5 kg on the contralateral side. The mean thumb opposition Kapandji index was 9.4, which was similar to that of the contralateral side. Three patients were very satisfied with the postoperative outcome and 3 patients were satisfied. Two patients were lost to follow-up, 1 patient did not consent to share her data, and 2 patients had to undergo trapeziectomy. Conclusions: Although a larger study population and a longer follow-up period are needed to draw conclusions, bone-preserving arthroplasty with APL tenodesis showed satisfying results in patients presenting with early-stage osteoarthritis. This method is technically simple and time-efficient, does not reduce the range of motion, and leaves open all other surgical options. Type of study/level of evidence: Therapeutic IV, Case Series.

Automated Meningioma Segmentation in Multiparametric MRI : Comparable Effectiveness of a Deep Learning Model and Manual Segmentation.

PURPOSE: Volumetric assessment of meningiomas represents a valuable tool for treatment planning and evaluation of tumor growth as it enables a more precise assessment of tumor size than conventional diameter methods. This study established a dedicated meningioma deep learning model based on routine magnetic resonance imaging (MRI) data and evaluated its performance for automated tumor segmentation. METHODS: The MRI datasets included T1-weighted/T2-weighted, T1-weighted contrast-enhanced (T1CE) and FLAIR of 126 patients with intracranial meningiomas (grade I: 97, grade II: 29). For automated segmentation, an established deep learning model architecture (3D deep convolutional neural network, DeepMedic, BioMedIA) operating on all four MR sequences was used. Segmentation included the following two components: (i) contrast-enhancing tumor volume in T1CE and (ii) total lesion volume (union of lesion volume in T1CE and FLAIR, including solid tumor parts and surrounding edema). Preprocessing of imaging data included registration, skull stripping, resampling, and normalization. After training of the deep learning model using manual segmentations by 2 independent readers from 70 patients (training group), the algorithm was evaluated on 56 patients (validation group) by comparing automated to ground truth manual segmentations, which were performed by 2 experienced readers in consensus. RESULTS: Of the 56 meningiomas in the validation group 55 were detected by the deep learning model. In these patients the comparison of the deep learning model and manual segmentations revealed average dice coefficients of 0.91 ± 0.08 for contrast-enhancing tumor volume and 0.82 ± 0.12 for total lesion volume. In the training group, interreader variabilities of the 2 manual readers were 0.92 ± 0.07 for contrast-enhancing tumor and 0.88 ± 0.05 for total lesion volume. CONCLUSION: Deep learning-based automated segmentation yielded high segmentation accuracy, comparable to manual interreader variability.

Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on Multiparametric MRI Using Deep Learning.

BACKGROUND: Precise volumetric assessment of brain tumors is relevant for treatment planning and monitoring. However, manual segmentations are time-consuming and impeded by intra- and interrater variabilities. PURPOSE: To investigate the performance of a deep-learning model (DLM) to automatically detect and segment primary central nervous system lymphoma (PCNSL) on clinical MRI. STUDY TYPE: Retrospective. POPULATION: Sixty-nine scans (at initial and/or follow-up imaging) from 43 patients with PCNSL referred for clinical MRI tumor assessment. FIELD STRENGTH/SEQUENCE: T1 -/T2 -weighted, T1 -weighted contrast-enhanced (T1 CE), and FLAIR at 1.0, 1.5, and 3.0T from different vendors and study centers. ASSESSMENT: Fully automated voxelwise segmentation of tumor components was performed using a 3D convolutional neural network (DeepMedic) trained on gliomas (n = 220). DLM segmentations were compared to manual segmentations performed in a 3D voxelwise manner by two readers (radiologist and neurosurgeon; consensus reading) from T1 CE and FLAIR, which served as the reference standard. STATISTICAL TESTS: Dice similarity coefficient (DSC) for comparison of spatial overlap with the reference standard, Pearson's correlation coefficient (r) to assess the relationship between volumetric measurements of segmentations, and Wilcoxon rank-sum test for comparison of DSCs obtained in initial and follow-up imaging. RESULTS: The DLM detected 66 of 69 PCNSL, representing a sensitivity of 95.7%. Compared to the reference standard, DLM achieved good spatial overlap for total tumor volume (TTV, union of tumor volume in T1 CE and FLAIR; average size 77.16 ± 62.4 cm3 , median DSC: 0.76) and tumor core (contrast enhancing tumor in T1 CE; average size: 11.67 ± 13.88 cm3 , median DSC: 0.73). High volumetric correlation between automated and manual segmentations was observed (TTV: r = 0.88, P < 0.0001; core: r = 0.86, P < 0.0001). Performance of automated segmentations was comparable between pretreatment and follow-up scans without significant differences (TTV: P = 0.242, core: P = 0.177). DATA CONCLUSION: In clinical MRI scans, a DLM initially trained on gliomas provides segmentation of PCNSL comparable to manual segmentation, despite its complex and multifaceted appearance. Segmentation performance was high in both initial and follow-up scans, suggesting its potential for application in longitudinal tumor imaging. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning.

In aneurysmal subarachnoid hemorrhage (aSAH), accurate diagnosis of aneurysm is essential for subsequent treatment to prevent rebleeding. However, aneurysm detection proves to be challenging and time-consuming. The purpose of this study was to develop and evaluate a deep learning model (DLM) to automatically detect and segment aneurysms in patients with aSAH on computed tomography angiography. In this retrospective single-center study, three different DLMs were trained on 68 patients with 79 aneurysms treated for aSAH (2016-2017) using five-fold-cross-validation. Their outputs were combined to a single DLM via ensemble-learning. The DLM was evaluated on an independent test set consisting of 185 patients with 215 aneurysms (2010-2015). Independent manual segmentations of aneurysms in a 3D voxel-wise manner by two readers (neurosurgeon, radiologist) provided the reference standard. For aneurysms > 30 mm3 (mean diameter of ~ 4 mm) on the test set, the DLM provided a detection sensitivity of 87% with false positives (FPs)/scan of 0.42. Automatic segmentations achieved a median dice similarity coefficient (DSC) of 0.80 compared to the reference standard. Aneurysm location (anterior vs. posterior circulation; P = .07) and bleeding severity (Fisher grade ≤ 3 vs. 4; P = .33) did not impede detection sensitivity or segmentation performance. For aneurysms > 100 mm3 (mean diameter of ~ 6 mm), a sensitivity of 96% with DSC of 0.87 and FPs/scan of 0.14 were obtained. In the present study, we demonstrate that the proposed DLM detects and segments aneurysms > 30 mm3 in patients with aSAH with high sensitivity independent of cerebral circulation and bleeding severity while producing FP findings of less than one per scan. Hence, the DLM can potentially assist treating physicians in aSAH by providing automated detection and segmentations of aneurysms.

A Broad-Spectrum Antiviral Peptide Blocks Infection of Viruses by Binding to Phosphatidylserine in the Viral Envelope.

The ongoing threat of viral infections and the emergence of antiviral drug resistance warrants a ceaseless search for new antiviral compounds. Broadly-inhibiting compounds that act on elements shared by many viruses are promising antiviral candidates. Here, we identify a peptide derived from the cowpox virus protein CPXV012 as a broad-spectrum antiviral peptide. We found that CPXV012 peptide hampers infection by a multitude of clinically and economically important enveloped viruses, including poxviruses, herpes simplex virus-1, hepatitis B virus, HIV-1, and Rift Valley fever virus. Infections with non-enveloped viruses such as Coxsackie B3 virus and adenovirus are not affected. The results furthermore suggest that viral particles are neutralized by direct interactions with CPXV012 peptide and that this cationic peptide may specifically bind to and disrupt membranes composed of the anionic phospholipid phosphatidylserine, an important component of many viral membranes. The combined results strongly suggest that CPXV012 peptide inhibits virus infections by direct interactions with phosphatidylserine in the viral envelope. These results reiterate the potential of cationic peptides as broadly-acting virus inhibitors.

Towards subject-level cerebral infarction classification of CT scans using convolutional networks.

Automatic evaluation of 3D volumes is a topic of importance in order to speed up clinical decision making. We describe a method to classify computed tomography scans on volume level for the presence of non-acute cerebral infarction. This is not a trivial task, as the lesions are often similar to other areas in the brain regarding shape and intensity. A three stage architecture is used for classification: 1) A cranial cavity segmentation network is developed, trained and applied. 2) Region proposals are generated 3) Connected regions are classified using a multi-resolution, densely connected 3D convolutional network. Mean area under curve values for subject level classification are 0.95 for the unstratified test set, 0.88 for stratification by patient age and 0.93 for stratification by CT scanner model. We use a partly segmented dataset of 555 scans of which 186 scans are used in the unstratified test set. Furthermore we examine possible dataset bias for scanner model and patient age parameters. We show a successful application of the proposed three-stage model for full volume classification. In contrast to black-box approaches, the convolutional network's decision can be further assessed by examination of intermediate segmentation results.

Comparison of Accuracy of Arrival-Time-Insensitive and Arrival-Time-Sensitive CTP Algorithms for Prediction of Infarct Tissue Volumes.

The purpose of this study was to compare the performance of arrival-time-insensitive (ATI) and arrival-time-sensitive (ATS) computed tomography perfusion (CTP) algorithms in Philips IntelliSpace Portal (v9, ISP) and to investigate optimal thresholds for ATI regarding the prediction of final infarct volume (FIV). Retrospective, single-center study with 54 patients (mean 67.0 ± 13.1 years, 68.5% male) who received Stroke-CT/CTP-imaging between 2010 and 2018 with occlusion of the middle cerebral artery in the M1-/proximal M2-segment or terminal internal carotid artery. FIV was determined on short-term follow-up imaging in two patient groups: A) not attempted or failed mechanical thrombectomy (MT) and B) successful MT. ATS (default settings) and ATI (full-range of threshold settings regarding FIV prediction) maps were coregistered in 3D with FIV using voxel-wise overlap measurement. Based on an average imaging follow-up of 2.6 ± 2.1 days, the estimation regarding penumbra (group A, ATI: r = 0.63/0.69, ATS: r = 0.64) and infarct core (group B, ATI: r = 0.60/0.68, ATS: r = 0.63) was slightly higher in ATI but the effect was not significant (p > 0.05). Regarding ATI, Tmax (AUC 0.9) was the best estimator of the penumbra (group A), CBF relative to the contralateral hemisphere (AUC 0.80) showed the best estimation of the infarct core (group B). There was a broad range of thresholds of optimal ATI settings in both groups. Prediction of FIV with ATI was slightly better compared to ATS. However, this difference was not significant. Since ATI showed a broad range of optimal thresholds, exact thresholds regarding the ATI algorithm should be evaluated in further prospective, clinical studies.

Mutation in Bmpr1b Leads to Optic Disc Coloboma and Ventral Retinal Gliosis in Mice.

Purpose: The clinical phenotype of retinal gliosis occurs in different forms; here, we characterize one novel genetic feature, (i.e., signaling via BMP-receptor 1b). Methods: Mouse mutants were generated within a recessive ENU mutagenesis screen; the underlying mutation was identified by linkage analysis and Sanger sequencing. The eye phenotype was characterized by fundoscopy, optical coherence tomography, optokinetic drum, electroretinography, and visual evoked potentials, by histology, immunohistology, and electron-microscopy. Results: The mutation affects intron 10 of the Bmpr1b gene, which is causative for skipping of exon 10. The expression levels of pSMAD1/5/8 were reduced in the mutant retina. The loss of BMPR1B-mediated signaling leads to optic nerve coloboma, gliosis in the optic nerve head and ventral retina, defective optic nerve axons, and irregular retinal vessels. The ventral retinal gliosis is proliferative and hypertrophic, which is concomitant with neuronal delamination and the reduction of retinal ganglion cells (RGCs); it is dominated by activated astrocytes overexpressing PAX2 and SOX2 but not PAX6, indicating that they may retain properties of gliogenic precursor cells. The expression pattern of PAX2 in the optic nerve head and ventral retina is altered during embryonic development. These events finally result in reduced electrical transmission of the retina and optic nerve and significantly reduced visual acuity. Conclusions: Our study demonstrates that BMPR1B is necessary for the development of the optic nerve and ventral retina. This study could also indicate a new mechanism in the formation of retinal gliosis; it opens new routes for its treatment eventually preventing scar formation in the retina.

Accuracy of Radiomics-Based Feature Analysis on Multiparametric Magnetic Resonance Images for Noninvasive Meningioma Grading.

OBJECTIVE: Meningioma grading is relevant to therapy decisions in complete or partial resection, observation, and radiotherapy because higher grades are associated with tumor growth and recurrence. The differentiation of low and intermediate grades is particularly challenging. This study attempts to apply radiomics-based shape and texture analysis on routine multiparametric magnetic resonance imaging (MRI) from different scanners and institutions for grading. METHODS: We used MRI data (T1-weighted/T2-weighted, T1-weighted-contrast-enhanced [T1CE], fluid-attenuated inversion recovery [FLAIR], diffusion-weighted imaging [DWI], apparent diffusion coefficient [ADC]) of grade I (n = 46) and grade II (n = 25) nontreated meningiomas with histologic workup. Two experienced radiologists performed manual tumor segmentations on FLAIR, T1CE, and ADC images in consensus. The MRI data were preprocessed through T1CE and T1-subtraction, coregistration, resampling, and normalization. A PyRadiomics package was used to generate 990 shape/texture features. Stepwise dimension reduction and robust radiomics feature selection were performed. Biopsy results were used as standard of reference. RESULTS: Four statistically independent radiomics features were identified as showing the strongest predictive values for higher tumor grades: roundness-of-FLAIR-shape (area under curve [AUC], 0.80), cluster-shades-of-FLAIR/T1CE-gray-level (AUC, 0.80), DWI/ADC-gray-level-variability (AUC, 0.72), and FLAIR/T1CE-gray-level-energy (AUC, 0.76). In a multivariate logistic regression model, the combination of the features led to an AUC of 0.91 for the differentiation of grade I and grade II meningiomas. CONCLUSIONS: Our results indicate that radiomics-based feature analysis applied on routine MRI is viable for meningioma grading, and a multivariate logistic regression model yielded strong classification performances. More advanced tumor stages are identifiable through certain shape parameters of the lesion, textural patterns in morphologic MRI sequences, and DWI/ADC variability.

Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI.

OBJECTIVES: Magnetic resonance imaging (MRI) is the method of choice for imaging meningiomas. Volumetric assessment of meningiomas is highly relevant for therapy planning and monitoring. We used a multiparametric deep-learning model (DLM) on routine MRI data including images from diverse referring institutions to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations. METHODS: We included 56 of 136 consecutive preoperative MRI datasets [T1/T2-weighted, T1-weighted contrast-enhanced (T1CE), FLAIR] of meningiomas that were treated surgically at the University Hospital Cologne and graded histologically as tumour grade I (n = 38) or grade II (n = 18). The DLM was trained on an independent dataset of 249 glioma cases and segmented different tumour classes as defined in the brain tumour image segmentation benchmark (BRATS benchmark). The DLM was based on the DeepMedic architecture. Results were compared to manual segmentations by two radiologists in a consensus reading in FLAIR and T1CE. RESULTS: The DLM detected meningiomas in 55 of 56 cases. Further, automated segmentations correlated strongly with manual segmentations: average Dice coefficients were 0.81 ± 0.10 (range, 0.46-0.93) for the total tumour volume (union of tumour volume in FLAIR and T1CE) and 0.78 ± 0.19 (range, 0.27-0.95) for contrast-enhancing tumour volume in T1CE. CONCLUSIONS: The DLM yielded accurate automated detection and segmentation of meningioma tissue despite diverse scanner data and thereby may improve and facilitate therapy planning as well as monitoring of this highly frequent tumour entity. KEY POINTS: • Deep learning allows for accurate meningioma detection and segmentation • Deep learning helps clinicians to assess patients with meningiomas • Meningioma monitoring and treatment planning can be improved.

Clinical Evaluation of a Multiparametric Deep Learning Model for Glioblastoma Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine.

OBJECTIVES: The aims of this study were, first, to evaluate a deep learning-based, automatic glioblastoma (GB) tumor segmentation algorithm on clinical routine data from multiple centers and compare the results to a ground truth, manual expert segmentation, and second, to evaluate the quality of the segmentation results across heterogeneous acquisition protocols of routinely acquired clinical magnetic resonance imaging (MRI) examinations from multiple centers. MATERIALS AND METHODS: The data consisted of preoperative MRI scans (T1, T2, FLAIR, and contrast-enhanced [CE] T1) of 64 patients with an initial diagnosis of primary GB, which were acquired in 15 institutions with varying protocols. All images underwent preprocessing (coregistration, skull stripping, resampling to isotropic resolution, normalization) and were fed into an independently trained deep learning model based on DeepMedic, a multilayer, multiscale convolutional neural network for detection and segmentation of tumor compartments. Automatic segmentation results for the whole tumor, necrosis, and CE tumor were compared with manual segmentations. RESULTS: Whole tumor and CE tumor compartments were correctly detected in 100% of the cases; necrosis was correctly detected in 91% of the cases. A high segmentation accuracy comparable to interrater variability was achieved for the whole tumor (mean dice similarity coefficient [DSC], 0.86 ± 0.09) and CE tumor (DSC, 0.78 ± 0.15). The DSC for tumor necrosis was 0.62 ± 0.30. We have observed robust segmentation quality over heterogeneous image acquisition protocols, for example, there were no correlations between resolution and segmentation accuracy of the single tumor compartments. Furthermore, no relevant correlation was found between quality of automatic segmentation and volume of interest properties (surface-to-volume ratio and volume). CONCLUSIONS: The proposed approach for automatic segmentation of GB proved to be robust on routine clinical data and showed on all tumor compartments a high automatic detection rate and a high accuracy, comparable to interrater variability. Further work on improvements of the segmentation accuracy for the necrosis compartments should be guided by the evaluation of the clinical relevance.Therefore, we propose this approach as a suitable building block for automatic tumor segmentation to support radiologists or neurosurgeons in the preoperative reading of GB MRI images and characterization of primary GB.

Construction and comparative evaluation of different activity detection methods in brain FDG-PET.

AIM: We constructed and evaluated reference brain FDG-PET databases for usage by three software programs (Computer-aided diagnosis for dementia (CAD4D), Statistical Parametric Mapping (SPM) and NEUROSTAT), which allow a user-independent detection of dementia-related hypometabolism in patients' brain FDG-PET. METHODS: Thirty-seven healthy volunteers were scanned in order to construct brain FDG reference databases, which reflect the normal, age-dependent glucose consumption in human brain, using either software. Databases were compared to each other to assess the impact of different stereotactic normalization algorithms used by either software package. In addition, performance of the new reference databases in the detection of altered glucose consumption in the brains of patients was evaluated by calculating statistical maps of regional hypometabolism in FDG-PET of 20 patients with confirmed Alzheimer's dementia (AD) and of 10 non-AD patients. Extent (hypometabolic volume referred to as cluster size) and magnitude (peak z-score) of detected hypometabolism was statistically analyzed. RESULTS: Differences between the reference databases built by CAD4D, SPM or NEUROSTAT were observed. Due to the different normalization methods, altered spatial FDG patterns were found. When analyzing patient data with the reference databases created using CAD4D, SPM or NEUROSTAT, similar characteristic clusters of hypometabolism in the same brain regions were found in the AD group with either software. However, larger z-scores were observed with CAD4D and NEUROSTAT than those reported by SPM. Better concordance with CAD4D and NEUROSTAT was achieved using the spatially normalized images of SPM and an independent z-score calculation. The three software packages identified the peak z-scores in the same brain region in 11 of 20 AD cases, and there was concordance between CAD4D and SPM in 16 AD subjects. CONCLUSION: The clinical evaluation of brain FDG-PET of 20 AD patients with either CAD4D-, SPM- or NEUROSTAT-generated databases from an identical reference dataset showed similar patterns of hypometabolism in the brain regions known to be involved in AD. The extent of hypometabolism and peak z-score appeared to be influenced by the calculation method used in each software package rather than by different spatial normalization parameters.