Changes in Gravitaxis and Gene-Expression in an Euglena gracilis Culture over Time.

Age-dependent changes in the transcription levels of 5-day-old Euglena gracilis cells, which showed positive gravitaxis, 6-day-old cells without gravitactic orientation, and older cells (9- and 11-day-old, which displayed a precise negative gravitaxis) were determined through microarray analysis. Hierarchical clustering of four independent cell cultures revealed pronounced similarities in transcription levels at the same culture age, which proves the reproducibility of the cultivation method. Employing the non-oriented cells from the 6-day-old culture as a reference, about 2779 transcripts were found to be differentially expressed. While positively gravitactic cells (5-day-old culture) showed only minor differences in gene expression compared to the 6-day reference, pronounced changes of mRNAs (mainly an increase) were found in older cells compared to the reference culture. Among others, genes coding for adenylyl cyclases, photosynthesis, and metabolic enzymes were identified to be differentially expressed. The investigated cells were grown in batch cultures, so variations in transcription levels most likely account for factors such as nutrient depletion in the medium and self-shading. Based on these findings, a particular transcript (e.g., transcript 19556) was downregulated using the RNA interference technique. Gravitaxis and phototaxis were impaired in the transformants, indicating the role of this transcript in signal transduction. Results of the experiment are discussed regarding the increasing importance of E. gracilis in biotechnology as a source of valuable products and the possible application of E. gracilis in life-support systems.

Automated identification of uncertain cases in deep learning-based classification of dopamine transporter SPECT to improve clinical utility and acceptance.

PURPOSE: Deep convolutional neural networks (CNN) are promising for automatic classification of dopamine transporter (DAT)-SPECT images. Reporting the certainty of CNN-based decisions is highly desired to flag cases that might be misclassified and, therefore, require particularly careful inspection by the user. The aim of the current study was to design and validate a CNN-based system for the identification of uncertain cases. METHODS: A network ensemble (NE) combining five CNNs was trained for binary classification of [123I]FP-CIT DAT-SPECT images as "normal" or "neurodegeneration-typical reduction" with high accuracy (NE for classification, NEfC). An uncertainty detection module (UDM) was obtained by combining two additional NE, one trained for detection of "reduced" DAT-SPECT with high sensitivity, the other with high specificity. A case was considered "uncertain" if the "high sensitivity" NE and the "high specificity" NE disagreed. An internal "development" dataset of 1740 clinical DAT-SPECT images was used for training (n = 1250) and testing (n = 490). Two independent datasets with different image characteristics were used for testing only (n = 640, 645). Three established approaches for uncertainty detection were used for comparison (sigmoid, dropout, model averaging). RESULTS: In the test data from the development dataset, the NEfC achieved 98.0% accuracy. 4.3% of all test cases were flagged as "uncertain" by the UDM: 2.5% of the correctly classified cases and 90% of the misclassified cases. NEfC accuracy among "certain" cases was 99.8%. The three comparison methods were less effective in labelling misclassified cases as "uncertain" (40-80%). These findings were confirmed in both additional test datasets. CONCLUSION: The UDM allows reliable identification of uncertain [123I]FP-CIT SPECT with high risk of misclassification. We recommend that automatic classification of [123I]FP-CIT SPECT images is combined with an UDM to improve clinical utility and acceptance. The proposed UDM method ("high sensitivity versus high specificity") might be useful also for DAT imaging with other ligands and for other binary classification tasks.

Voxel-based morphometry in single subjects without a scanner-specific normal database using a convolutional neural network.

OBJECTIVES: Reliable detection of disease-specific atrophy in individual T1w-MRI by voxel-based morphometry (VBM) requires scanner-specific normal databases (NDB), which often are not available. The aim of this retrospective study was to design, train, and test a deep convolutional neural network (CNN) for single-subject VBM without the need for a NDB (CNN-VBM). MATERIALS AND METHODS: The training dataset comprised 8945 T1w scans from 65 different scanners. The gold standard VBM maps were obtained by conventional VBM with a scanner-specific NDB for each of the 65 scanners. CNN-VBM was tested in an independent dataset comprising healthy controls (n = 37) and subjects with Alzheimer's disease (AD, n = 51) or frontotemporal lobar degeneration (FTLD, n = 30). A scanner-specific NDB for the generation of the gold standard VBM maps was available also for the test set. The technical performance of CNN-VBM was characterized by the Dice coefficient of CNN-VBM maps relative to VBM maps from scanner-specific VBM. For clinical testing, VBM maps were categorized visually according to the clinical diagnoses in the test set by two independent readers, separately for both VBM methods. RESULTS: The VBM maps from CNN-VBM were similar to the scanner-specific VBM maps (median Dice coefficient 0.85, interquartile range [0.81, 0.90]). Overall accuracy of the visual categorization of the VBM maps for the detection of AD or FTLD was 89.8% for CNN-VBM and 89.0% for scanner-specific VBM. CONCLUSION: CNN-VBM without NDB provides a similar performance in the detection of AD- and FTLD-specific atrophy as conventional VBM. CLINICAL RELEVANCE STATEMENT: A deep convolutional neural network for voxel-based morphometry eliminates the need of scanner-specific normal databases without relevant performance loss and, therefore, could pave the way for the widespread clinical use of voxel-based morphometry to support the diagnosis of neurodegenerative diseases. KEY POINTS: • The need of normal databases is a barrier for widespread use of voxel-based brain morphometry. • A convolutional neural network achieved a similar performance for detection of atrophy than conventional voxel-based morphometry. • Convolutional neural networks can pave the way for widespread clinical use of voxel-based morphometry.

AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis.

BACKGROUND: Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial intelligence (AI) tools in the clinical routine is still rare. METHODS: A three-dimensional convolutional neural network for CE lesion segmentation was trained externally on 1488 datasets of 934 MS patients from 81 scanners using concatenated information from FLAIR and T1-weighted post-contrast imaging. This externally trained model was tested on an independent dataset comprising 504 T1-weighted post-contrast and FLAIR image datasets of MS patients from clinical routine. Two neuroradiologists (R1, R2) labeled CE lesions for gold standard definition in the clinical test dataset. The algorithmic output was evaluated on both patient- and lesion-level. RESULTS: On a patient-level, recall, specificity, precision, and accuracy of the AI tool to predict patients with CE lesions were 0.75, 0.99, 0.91, and 0.96. The agreement between the AI tool and both readers was within the range of inter-rater agreement (Cohen's kappa; AI vs. R1: 0.69; AI vs. R2: 0.76; R1 vs. R2: 0.76). On a lesion-level, false negative lesions were predominately found in infratentorial location, significantly smaller, and at lower contrast than true positive lesions (p < 0.05). CONCLUSIONS: AI-based identification of CE lesions on brain MRI is feasible, approaching human reader performance in independent clinical data and might be of help as a second reader in the neuroradiological assessment of active inflammation in MS patients. CRITICAL RELEVANCE STATEMENT: Al-based detection of contrast-enhancing multiple sclerosis lesions approaches human reader performance, but careful visual inspection is still needed, especially for infratentorial, small and low-contrast lesions.

A systematic approach to deep learning-based nodule detection in chest radiographs.

Lung cancer is a serious disease responsible for millions of deaths every year. Early stages of lung cancer can be manifested in pulmonary lung nodules. To assist radiologists in reducing the number of overseen nodules and to increase the detection accuracy in general, automatic detection algorithms have been proposed. Particularly, deep learning methods are promising. However, obtaining clinically relevant results remains challenging. While a variety of approaches have been proposed for general purpose object detection, these are typically evaluated on benchmark data sets. Achieving competitive performance for specific real-world problems like lung nodule detection typically requires careful analysis of the problem at hand and the selection and tuning of suitable deep learning models. We present a systematic comparison of state-of-the-art object detection algorithms for the task of lung nodule detection. In this regard, we address the critical aspect of class imbalance and and demonstrate a data augmentation approach as well as transfer learning to boost performance. We illustrate how this analysis and a combination of multiple architectures results in state-of-the-art performance for lung nodule detection, which is demonstrated by the proposed model winning the detection track of the Node21 competition. The code for our approach is available at https://github.com/FinnBehrendt/node21-submit.

End-to-end approach for the characterization and control of product-related impurities in T cell bispecific antibody preparations.

Antibody-based T cell-activating biologics are promising therapeutic medicines being developed for a number of indications, mainly in the oncology field. Among those, T cell bispecific antibodies are designed to bind one tumor-specific antigen and the T cell receptor at the same time, leading to a robust T cell response against the tumor. Although their unique format and the versatility of the CrossMab technology allows for the generation of safer molecules in an efficient manner, product-related variants cannot be completely avoided. Therefore, it is of extreme importance that both a manufacturing process that limits or depletes product-related impurities, as well as a thorough analytical characterization are in place, starting from the development of the manufacturing cell line until the assessment of potential toxicities. Here, we describe such an end-to-end approach to minimize, quantify and control impurities and -upon their functional characterization- derive specifications that allow for the release of clinical material.

Automatic segmentation of the thalamus using a massively trained 3D convolutional neural network: higher sensitivity for the detection of reduced thalamus volume by improved inter-scanner stability.

OBJECTIVES: To develop an automatic method for accurate and robust thalamus segmentation in T1w-MRI for widespread clinical use without the need for strict harmonization of acquisition protocols and/or scanner-specific normal databases. METHODS: A three-dimensional convolutional neural network (3D-CNN) was trained on 1975 T1w volumes from 170 MRI scanners using thalamus masks generated with FSL-FIRST as ground truth. Accuracy was evaluated with 18 manually labeled expert masks. Intra- and inter-scanner test-retest stability were assessed with 477 T1w volumes of a single healthy subject scanned on 123 MRI scanners. The sensitivity of 3D-CNN-based volume estimates for the detection of thalamus atrophy was tested with 127 multiple sclerosis (MS) patients and a normal database comprising 4872 T1w volumes from 160 scanners. The 3D-CNN was compared with a publicly available 2D-CNN (FastSurfer) and FSL. RESULTS: The Dice similarity coefficient of the automatic thalamus segmentation with manual expert delineation was similar for all tested methods (3D-CNN and FastSurfer 0.86 ± 0.02, FSL 0.87 ± 0.02). The standard deviation of the single healthy subject's thalamus volume estimates was lowest with 3D-CNN for repeat scans on the same MRI scanner (0.08 mL, FastSurfer 0.09 mL, FSL 0.15 mL) and for repeat scans on different scanners (0.28 mL, FastSurfer 0.62 mL, FSL 0.63 mL). The proportion of MS patients with significantly reduced thalamus volume was highest for 3D-CNN (24%, FastSurfer 16%, FSL 11%). CONCLUSION: The novel 3D-CNN allows accurate thalamus segmentation, similar to state-of-the-art methods, with considerably improved robustness with respect to scanner-related variability of image characteristics. This might result in higher sensitivity for the detection of disease-related thalamus atrophy. KEY POINTS: • A three-dimensional convolutional neural network was trained for automatic segmentation of the thalamus with a heterogeneous sample of T1w-MRI from 1975 patients scanned on 170 different scanners. • The network provided high accuracy for thalamus segmentation with manual segmentation by experts as ground truth. • Inter-scanner variability of thalamus volume estimates across different MRI scanners was reduced by more than 50%, resulting in increased sensitivity for the detection of thalamus atrophy.

X-Band Parallel-Mode and Multifrequency Electron Paramagnetic Resonance Spectroscopy of S = 1/2 Bismuth Centers.

The recent successes in the isolation and characterization of several bismuth radicals inspire the development of new spectroscopic approaches for the in-depth analysis of their electronic structure. Electron paramagnetic resonance (EPR) spectroscopy is a powerful tool for the characterization of main group radicals. However, the large electron-nuclear hyperfine interactions of Bi (209Bi, I = 9/2) have presented difficult challenges to fully interpret the spectral properties for some of these radicals. Parallel-mode EPR (B1∥B0) is almost exclusively employed for the study of S > 1/2 systems but becomes feasible for S = 1/2 systems with large hyperfine couplings, offering a distinct EPR spectroscopic approach. Herein, we demonstrate the application of conventional X-band parallel-mode EPR for S = 1/2, I = 9/2 spin systems: Bi-doped crystalline silicon (Si:Bi) and the molecular Bi radicals [L(X)Ga]2Bi• (X = Cl or I) and [L(Cl)GaBi(MecAAC)]•+ (L = HC[MeCN(2,6-iPr2C6H3)]2). In combination with multifrequency perpendicular-mode EPR (X-, Q-, and W-band frequencies), we were able to fully refine both the anisotropic g- and A-tensors of these molecular radicals. The parallel-mode EPR experiments demonstrated and discussed here have the potential to enable the characterization of other S = 1/2 systems with large hyperfine couplings, which is often challenging by conventional perpendicular-mode EPR techniques. Considerations pertaining to the choice of microwave frequency are discussed for relevant spin-systems.

Single-subject analysis of regional brain volumetric measures can be strongly influenced by the method for head size adjustment.

PURPOSE: Total intracranial volume (TIV) is often a nuisance covariate in MRI-based brain volumetry. This study compared two TIV adjustment methods with respect to their impact on z-scores in single subject analyses of regional brain volume estimates. METHODS: Brain parenchyma, hippocampus, thalamus, and TIV were segmented in a normal database comprising 5059 T1w images. Regional volume estimates were adjusted for TIV using the residual method or the proportion method. Age was taken into account by regression with both methods. TIV- and age-adjusted regional volumes were transformed to z-scores and then compared between the two adjustment methods. Their impact on the detection of thalamus atrophy was tested in 127 patients with multiple sclerosis. RESULTS: The residual method removed the association with TIV in all regions. The proportion method resulted in a switch of the direction without relevant change of the strength of the association. The reduction of physiological between-subject variability was larger with the residual method than with the proportion method. The difference between z-scores obtained with the residual method versus the proportion method was strongly correlated with TIV. It was larger than one z-score point in 5% of the subjects. The area under the ROC curve of the TIV- and age-adjusted thalamus volume for identification of multiple sclerosis patients was larger with the residual method than with the proportion method (0.84 versus 0.79). CONCLUSION: The residual method should be preferred for TIV and age adjustments of T1w-MRI-based brain volume estimates in single subject analyses.

Cerebral desaturation during neonatal congenital heart surgery is associated with perioperative brain structure alterations but not with neurodevelopmental outcome at 1 year.

OBJECTIVES: The significance of intraoperative cerebral desaturation (CD) measured by near-infrared spectroscopy (NIRS) to predict neurological outcome after congenital heart surgery is uncertain. The goal of this study was to compare brain structure changes and neurodevelopmental outcome in patients with severe congenital heart disease with and without intraoperative CD. METHODS: Neonates requiring congenital heart surgery were enrolled in a cohort study. NIRS data from their first cardiac operation were collected. Pre- and postoperative brain magnetic resonance imaging results and Bayley-III scores at 1 year were compared between patients with and without CD, defined by 2 NIRS thresholds: regional cerebral oxygen saturation (rSO2) of 45% (45%rSO2) and rSO2 below 20% of baseline value (20%BLrSO2). RESULTS: Thirty-two patients (72% male) with d-transposition of the great arteries (n = 24, 75%) and other complex types of congenital heart diseases (n = 8, 25%) were analysed. Perioperative relative lateral ventricle volume change was increased in patients with versus without intraoperative CD (P = 0.003 for 45%rSO2, P = 0.008 for 20%BLrSO2). For 45%rSO2, the effect of CD remained significant after adjusting for age at postoperative scan, time between scans and cardiac diagnosis (P = 0.019). New intracranial lesions occurred predominantly in CD groups (6/6 patients for 45%rSO2, 5/6 patients for 20%BLrSO2). Neurodevelopmental outcome at 1 year was not associated with intraoperative CD. CONCLUSIONS: This study demonstrates the clinical relevance of NIRS monitoring during congenital heart surgery. The occurrence of intraoperative CD is associated with perioperative lateral ventricle volume change and new intracranial lesions.

Single-Electron Oxidation of Carbene-Coordinated Pnictinidenes-Entry into Heteroleptic Radical Cations and Metalloid Clusters.

Stable heavy main group element radicals are challenging synthetic targets. Although several strategies have been developed to stabilize such odd-electron species, the number of heavier pnictogen-centered radicals is limited. We report on a series of two-coordinated pnictogen-centered radical cations [(MecAAC)EGa(Cl)L][B(C6F5)4] (MecAAC = [H2C(CMe2)2NDipp]C; Dipp = 2,6-i-Pr2C6H3; E = As 1, Sb 2, Bi 3; L = HC[C(Me)NDipp]2) synthesized by one-electron oxidation of L(Cl)Ga-substituted pnictinidenes (MecAAC)EGa(Cl)L (E = As I, Sb II, Bi III). 1-3 were characterized by electron paramagnetic resonance (EPR) spectroscopy and single crystal X-ray diffraction (sc-XRD) (1, 2), while quantum chemical calculations support their description as carbene-coordinated pnictogen-centered radical cations. The low thermal stability of 3 enables access to metalloid bismuth clusters as shown by formation of [{LGa(Cl)}3Bi6][B(C6F5)4] (4).

Eating disorder related research using Amazon Mechanical Turk (MTurk): Friend or foe?: Commentary on Burnette et al. (2021).

Burnette et al. reported a study that they sought to undertake to validate common eating disorder questionnaires in sexual and gender minorities. The researchers took advantage of the online recruitment platform Amazon Mechanical Turk (MTurk). Contrary to their expectations, the study proved not feasible due to invalid answering. Thus, Burnette et al. raise concerns against the trustworthiness of crowd-sourced data that may be undermined by financial interests and other kinds of motivations. Our commentary highlights the potential of the COVID-19 pandemic to inflate especially those intentions, which are monetary. Against the background of the COVID-19 pandemic, a further problem seems to be that the anonymity of online crowd sourcing platforms might tempt participants to provide inconsistent answers, possibly reflecting tendencies of reactance. The reported pattern of paradoxical responses in Burnette et al.'s work does not reflect malingering; rather we believe that the study might have served some participants as an outlet for negative emotions. We discuss mechanisms of quality control and highlight the lack of interpersonal interaction associated with online data collections.

Switching from Heteronuclear Allyl Cations to Vinyl Cations by Using a Chemical Charge Trap.

Halide abstraction of the carbene-coordinated pnictinidenes (MecAAC)EGa(Cl)L (E = As 1, Sb 2, Bi 3, MecAAC = [H2C(CMe2)2NDipp]C; L = HC[C(Me)NDipp]2; Dipp = 2,6-i-Pr2C6H3) yielded the series of cationic group 15 compounds [(MecAAC)EGaL][Al(ORF)4] (E = As 4, Sb 5; Al(ORF)4 = Al(OC(CF3)3)4) and [(MecAAC)EGaL][B(ArF)4] (E = Sb 6, Bi 7; B(ArF)4 = B[C6H3(CF3)2]4), which were characterized by heteronuclear NMR spectroscopy and sc-XRD. The electronic nature of the cations [(MecAAC)EGaL]+ is controlled by the central pnictogen atom, according to quantum chemical calculations. The calculations furthermore demonstrated that compounds containing the lighter pnictogens (E = N, P) are best described as heteronuclear allyl cations, whereas heavier pnictogen atoms (E = As, Sb, Bi) serve as a trap for the positive charge, resulting in carbene-stabilized heterovinyl-type structures.

Infratentorial lesions in multiple sclerosis patients: intra- and inter-rater variability in comparison to a fully automated segmentation using 3D convolutional neural networks.

OBJECTIVE: Automated quantification of infratentorial multiple sclerosis lesions on magnetic resonance imaging is clinically relevant but challenging. To overcome some of these problems, we propose a fully automated lesion segmentation algorithm using 3D convolutional neural networks (CNNs). METHODS: The CNN was trained on a FLAIR image alone or on FLAIR and T1-weighted images from 1809 patients acquired on 156 different scanners. An additional training using an extra class for infratentorial lesions was implemented. Three experienced raters manually annotated three datasets from 123 MS patients from different scanners. RESULTS: The inter-rater sensitivity (SEN) was 80% for supratentorial lesions but only 62% for infratentorial lesions. There was no statistically significant difference between the inter-rater SEN and the SEN of the CNN with respect to the raters. For supratentorial lesions, the CNN featured an intra-rater intra-scanner SEN of 0.97 (R1 = 0.90, R2 = 0.84) and for infratentorial lesion a SEN of 0.93 (R1 = 0.61, R2 = 0.73). CONCLUSION: The performance of the CNN improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input and matches the detection performance of experienced raters. Furthermore, for infratentorial lesions the CNN was more robust against repeated scans than experienced raters. KEY POINTS: • A 3D convolutional neural network was trained on MRI data from 1809 patients (156 different scanners) for the quantification of supratentorial and infratentorial multiple sclerosis lesions. • Inter-rater variability was higher for infratentorial lesions than for supratentorial lesions. The performance of the 3D convolutional neural network (CNN) improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input. • The detection performance of the CNN matches the detection performance of experienced raters.

Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI.

PURPOSE: Brain Magnetic Resonance Images (MRIs) are essential for the diagnosis of neurological diseases. Recently, deep learning methods for unsupervised anomaly detection (UAD) have been proposed for the analysis of brain MRI. These methods rely on healthy brain MRIs and eliminate the requirement of pixel-wise annotated data compared to supervised deep learning. While a wide range of methods for UAD have been proposed, these methods are mostly 2D and only learn from MRI slices, disregarding that brain lesions are inherently 3D and the spatial context of MRI volumes remains unexploited. METHODS: We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance compared to learning from slices. We evaluate and compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance. RESULTS: Using two publicly available segmentation data sets for evaluation, 3D VAEs outperform their 2D counterpart, highlighting the advantage of volumetric context. Also, our 3D erasing methods allow for further performance improvements. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE. CONCLUSIONS: We propose 3D deep learning methods for UAD in brain MRI combined with 3D erasing and demonstrate that 3D methods clearly outperform their 2D counterpart for anomaly segmentation. Also, our spatial erasing method allows for further performance improvements and reduces the requirement for large data sets.

From π-Bonded Gallapnictenes to Nucleophilic, Redox-Active Metal-Coordinated Pnictanides.

A comprehensive reactivity study of gallapnictenes LGaEGa(Cl)L (E=As, Sb; L=HC[C(Me)N(Ar)]2 , Ar=Dip=2,6-i-Pr2 C6 H3 ) proved the nucleophilic character of the pnictogen and the electrophilic nature of the Ga atom. Reactions of LGaEGa(Cl)L with imidazolium chloride [IPrH][Cl] yielded {[LGa(Cl)]2 E- }{IPrH+ } (E=As 1, Sb 2), and those with HCl and MeI gave pnictanes [LGa(Cl)]2 EH (E=As 5, Sb 6) and L(I)GaE(Me)Ga(Cl)L (E=As 7, Sb 8). Pnictanides 1 and 2 also react with [H(OEt2 )2 ][BArF 4 ] (BArF 4 =B(C6 F5 )4 ) to 5 and 6, while reactions with MeI yielded [LGa(Cl)]2 EMe (E=As 9, Sb 10). Single electron oxidation reactions of pnictanides 1 and 2 gave the corresponding radicals [LGa(Cl)]2 E. (E=As, Sb).

Age-dependent cut-offs for pathological deep gray matter and thalamic volume loss using Jacobian integration.

INTRODUCTION: Several recent studies indicate that deep gray matter or thalamic volume loss (VL) might be promising surrogate markers of disease activity in multiple sclerosis (MS) patients. To allow applying these markers to individual MS patients in clinical routine, age-dependent cut-offs distinguishing physiological from pathological VL and an estimation of the measurement error, which provides the confidence of the result, are to be defined. METHODS: Longitudinal MRI scans of the following cohorts were analyzed in this study: 189 healthy controls (HC) (mean age 54 years, 22% female), 98 MS patients from Zurich university hospital (mean age 34 years, 62% female), 33 MS patients from Dresden university hospital (mean age 38 years, 60% female), and publicly available reliability data sets consisting of 162 short-term MRI scan-rescan pairs with scan intervals of days or few weeks. Percentage annualized whole brain volume loss (BVL), gray matter (GM) volume loss (GMVL), deep gray matter volume loss (deep GMVL), and thalamic volume loss (ThalaVL) were computed deploying the Jacobian integration (JI) method. BVL was additionally computed using Siena, an established method used in many Phase III drug trials. A linear mixed effect model was used to estimate the measurement error as the standard deviation (SD) of model residuals of all 162 scan-rescan pairs For estimation of age-dependent cut-offs, a quadratic regression function between age and the corresponding annualized VL values of the HC was computed. The 5th percentile was defined as the threshold for pathological VL per year since 95% of HC subjects exhibit a less pronounced VL for a given age. For the MS patients BVL, GMVL, deep GMVL, and ThalaVL were mutually compared and a paired t-test was used to test whether there are systematic differences in VL between these brain regions. RESULTS: Siena and JI showed a high agreement for BVL measures, with a median absolute difference of 0.1% and a correlation coefficient of r = 0.78. Siena and GMVL showed a similar standard deviation (SD) of the scan-rescan error of 0.28% and 0.29%, respectively. For deep GMVL, ThalaVL the SD of the scan-rescan error was slightly higher (0.43% and 0.5%, respectively). Among the HC the thalamus showed the highest mean VL (-0.16%, -0.39%, and -0.59% at ages 35, 55, and 75, respectively). Corresponding cut-offs for a pathological VL/year were -0.68%, -0.91%, and -1.11%. The MS cohorts did not differ in BVL and GMVL. However, both MS cohorts showed a significantly (p = 0.05) stronger deep GMVL than BVL per year. CONCLUSION: It might be methodologically feasible to assess deep GMVL using JI in individual MS patients. However, age and the measurement error need to be taken into account. Furthermore, deep GMVL may be used as a complementary marker to BVL since MS patients exhibit a significantly stronger deep GMVL than BVL.

Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks.

The quantification of new or enlarged lesions from follow-up MRI scans is an important surrogate of clinical disease activity in patients with multiple sclerosis (MS). Not only is manual segmentation time consuming, but inter-rater variability is high. Currently, only a few fully automated methods are available. We address this gap in the field by employing a 3D convolutional neural network (CNN) with encoder-decoder architecture for fully automatic longitudinal lesion segmentation. Input data consist of two fluid attenuated inversion recovery (FLAIR) images (baseline and follow-up) per patient. Each image is entered into the encoder and the feature maps are concatenated and then fed into the decoder. The output is a 3D mask indicating new or enlarged lesions (compared to the baseline scan). The proposed method was trained on 1809 single point and 1444 longitudinal patient data sets and then validated on 185 independent longitudinal data sets from two different scanners. From the two validation data sets, manual segmentations were available from three experienced raters, respectively. The performance of the proposed method was compared to the open source Lesion Segmentation Toolbox (LST), which is a current state-of-art longitudinal lesion segmentation method. The mean lesion-wise inter-rater sensitivity was 62%, while the mean inter-rater number of false positive (FP) findings was 0.41 lesions per case. The two validated algorithms showed a mean sensitivity of 60% (CNN), 46% (LST) and a mean FP of 0.48 (CNN), 1.86 (LST) per case. Sensitivity and number of FP were not significantly different (p < 0.05) between the CNN and manual raters. New or enlarged lesions counted by the CNN algorithm appeared to be comparable with manual expert ratings. The proposed algorithm seems to outperform currently available approaches, particularly LST. The high inter-rater variability in case of manual segmentation indicates the complexity of identifying new or enlarged lesions. An automated CNN-based approach can quickly provide an independent and deterministic assessment of new or enlarged lesions from baseline to follow-up scans with acceptable reliability.