Additional Test Set Research Articles

Automated extraction of information of lung cancer staging from unstructured reports of PET-CT interpretation: natural language processing with deep-learning

BackgroundExtracting metastatic information from previous radiologic-text reports is important, however, laborious annotations have limited the usability of these texts. We developed a deep-learning model for extracting primary lung cancer sites and metastatic lymph nodes and distant metastasis information from PET-CT reports for determining lung cancer stages.MethodsPET-CT reports, fully written in English, were acquired from two cohorts of patients with lung cancer who were diagnosed at a tertiary hospital between January 2004 and March 2020. One cohort of 20,466 PET-CT reports was used for training and the validation set, and the other cohort of 4190 PET-CT reports was used for an additional-test set. A pre-processing model (Lung Cancer Spell Checker) was applied to correct the typographical errors, and pseudo-labelling was used for training the model. The deep-learning model was constructed using the Convolutional-Recurrent Neural Network. The performance metrics for the prediction model were accuracy, precision, sensitivity, micro-AUROC, and AUPRC.ResultsFor the extraction of primary lung cancer location, the model showed a micro-AUROC of 0.913 and 0.946 in the validation set and the additional-test set, respectively. For metastatic lymph nodes, the model showed a sensitivity of 0.827 and a specificity of 0.960. In predicting distant metastasis, the model showed a micro-AUROC of 0.944 and 0.950 in the validation and the additional-test set, respectively.ConclusionOur deep-learning method could be used for extracting lung cancer stage information from PET-CT reports and may facilitate lung cancer studies by alleviating laborious annotation by clinicians.

Digital finance and investment of micro and small enterprises: Evidence from China

Using China Micro and Small Enterprise Survey data, this paper examines how digital finance affects the investment behavior of MSEs in China. We find that digital finance significantly increases both MSEs' probability of applying for new investment projects and the number of projects applied. Specifically, our baseline model shows that MSEs that use digital finance are 7.5% more likely to apply for new investment projects than those who do not. The average number of new investment projects applied by MSEs that use digital finance is also 37.8% higher. Results are further substantiated by conducting a set of additional tests to rule out the potential confounding factors and a propensity score matching strategy to address for the potential self-selection bias. Heterogeneous impacts of digital finance are also studied in this paper. We find that the impact of digital finance is more prominent for younger enterprises and enterprises located in the central and western regions where there is relatively backward financial development. In the end, the underlying mechanism is further explored and the result shows that digital finance promotes the investment behavior of MSEs by reducing the degree of information asymmetry between the lender and the borrower, which alleviates the financing constraints of MSEs.

A deep learning-based hybrid artificial intelligence model for the detection and severity assessment of vitiligo lesions

BackgroundWe aimed to establish and validate a deep learning-based hybrid artificial intelligence (AI) model for the objective morphometric and colorimetric assessment of vitiligo lesions.MethodsTwo main datasets containing curated images of vitiligo lesions from Chinese patients (Fitzpatrick skin types III or IV) were established, including one with 2,720 images for lesion localization study and the other with 1,262 images for lesion segmentation study. Besides, an additional test set containing 145 images of vitiligo lesions from other Fitzpatrick skin types (I, II, or V) was also generated. A 3-stage hybrid model was constructed. YOLO v3 (You Only Look Once, v3) architecture was trained and validated to classify and localize vitiligo lesions, with sensitivity and error rate as primary performance outcomes. Then a segmentation study comparing 3 deep convolutional neural networks (DCNNs), Pyramid Scene Parsing Network (PSPNet), UNet, and UNet++, was carried out based on the Jaccard index (JI). The architecture with the best performance was integrated into the model. Three add-on metrics, namely VAreaA, VAreaR, and VColor were finally developed to measure absolute, relative size changes and pigmentation, respectively. Agreement between the AI model and dermatologist evaluators were assessed.ResultsThe sensitivity of the YOLO v3 architecture to detect vitiligo lesions was 92.91% with an error rate of 14.98%. The UNet++ architecture outperformed the others in the segmentation study (JI, 0.79) and was integrated into the model. On the additional test set, however, the model achieved a lower detection sensitivity (72.41%) and a lower segmentation score (JI, 0.69). With respect to size changes, no difference was observed between the AI model, trained dermatologists (W=0.812, P<0.05), and Photoshop analysis (P=0.075, P=0.212 respectively), which all displayed good concordance.ConclusionsWe developed a novel, convenient, objective, and quantitative deep learning-based hybrid model which simultaneously evaluated both morphometric and colorimetric vitiligo lesions from patients with Fitzpatrick skin types III or IV, rendering it suitable for the assessment of severity of vitiligo lesions in Asians in both clinic and research scenarios. More work is also warranted for its use in other ethnic skin groups.

Does directors' and officers' liability insurance induce empire building? Evidence from corporate labor investment

This study examines whether directors' and officers' (D&O) insurance affects corporate employment decision-making. Using a 2006–2018 sample of Chinese public firms, we find that firms purchasing D&O insurance exhibit lower labor investment efficiency, reflected mainly in over-hiring. The findings are strengthened by a set of additional robustness tests to mitigate endogeneity concerns and selection bias. The negative relation between D&O insurance and labor investment efficiency is more pronounced in firms with weak corporate governance, a low proportion of female executives, high labor intensity and low legal risks. Further analysis suggests that inefficient labor investment leads to worse future firm performance. This study provides the first empirical evidence that D&O insurance increases managerial empire building tendencies via over-investment in labor, which, in turn, is detrimental to shareholder value.

Customer concentration and bank loan contracting: evidence from China

ABSTRACT This study uses hand-collected data regarding bank loan terms for Chinese listed firms to investigate whether and how a concentrated customer base affects bank loan contracting. We find that a more concentrated customer base reduces suppliers’ credit risk, which results in more favorable bank loan contracting terms (i.e. lower interest rates, longer maturities, and larger loan sizes). Furthermore, we provide evidence that increased operational efficiency, reduced information risk and default risk are possible channels through which customer concentration reduces bank loan contracting costs. The results are robust to a set of additional tests. Overall, our findings document the benefits of customer concentration in developing countries such as China and reveal how this benefit is priced into bank loan contract terms.

Correcting the Estimation of Viral Taxa Distributions in Next-Generation Sequencing Data after Applying Artificial Neural Networks.

Estimating the taxonomic composition of viral sequences in a biological samples processed by next-generation sequencing is an important step in comparative metagenomics. Mapping sequencing reads against a database of known viral reference genomes, however, fails to classify reads from novel viruses whose reference sequences are not yet available in public databases. Instead of a mapping approach, and in order to classify sequencing reads at least to a taxonomic level, the performance of artificial neural networks and other machine learning models was studied. Taxonomic and genomic data from the NCBI database were used to sample labelled sequencing reads as training data. The fitted neural network was applied to classify unlabelled reads of simulated and real-world test sets. Additional auxiliary test sets of labelled reads were used to estimate the conditional class probabilities, and to correct the prior estimation of the taxonomic distribution in the actual test set. Among the taxonomic levels, the biological order of viruses provided the most comprehensive data base to generate training data. The prediction accuracy of the artificial neural network to classify test reads to their viral order was considerably higher than that of a random classification. Posterior estimation of taxa frequencies could correct the primary classification results.

Retention time prediction in hydrophilic interaction liquid chromatography with graph neural network and transfer learning

The combination of retention time (RT), accurate mass and tandem mass spectra can improve the structural annotation in untargeted metabolomics. However, the incorporation of RT for metabolite identification has received less attention because of the limitation of available RT data, especially for hydrophilic interaction liquid chromatography (HILIC). Here, the Graph Neural Network-based Transfer Learning (GNN-TL) is proposed to train a model for HILIC RTs prediction. The graph neural network was pre-trained using an in silico HILIC RT dataset (pseudo-labeling dataset) with ∼306 K molecules. Then, the weights of dense layers in the pre-trained GNN (pre-GNN) model were fine-tuned by transfer learning using a small number of experimental HILIC RTs from the target chromatographic system. The GNN-TL outperformed the methods in Retip, including the Random Forest (RF), Bayesian-regularized neural network (BRNN), XGBoost, light gradient-boosting machine (LightGBM), and Keras. It achieved the lowest mean absolute error (MAE) of 38.6 s on the test set and 33.4 s on an additional test set. It has the best ability to generalize with a small performance difference between training, test, and additional test sets. Furthermore, the predicted RTs can filter out nearly 60% false positive candidates on average, which is valuable for the identification of compounds complementary to mass spectrometry.

Deep learning for diagnosis and survival prediction in soft tissue sarcoma

Clinical management of soft tissue sarcoma (STS) is particularly challenging. Here, we used digital pathology and deep learning (DL) for diagnosis and prognosis prediction of STS. Our retrospective, multicenter study included a total of 506 histopathological slides from 291 patients with STS. The Cancer Genome Atlas cohort (240 patients) served as training and validation set. A second, multicenter cohort (51 patients) served as an additional test set. The use of the DL model (DLM) as a clinical decision support system was evaluated by nine pathologists with different levels of expertise. For prognosis prediction, 139 slides from 85 patients with leiomyosarcoma (LMS) were used. Area under the receiver operating characteristic (AUROC) and accuracy served as main outcome measures. The DLM achieved a mean AUROC of 0.97 (±0.01) and an accuracy of 79.9% (±6.1%) in diagnosing the five most common STS subtypes. The DLM significantly improved the accuracy of the pathologists from 46.3% (±15.5%) to 87.1% (±11.1%). Furthermore, they were significantly faster and more certain in their diagnosis. In LMS, the mean AUROC in predicting the disease-specific survival status was 0.91 (±0.1) and the accuracy was 88.9% (±9.9%). Cox regression showed the DLM's prediction to be a significant independent prognostic factor (P= 0.008, hazard ratio 5.5, 95% confidence interval 1.56-19.7) in these patients, outperforming other risk factors. DL can be used to accurately diagnose frequent subtypes of STS from conventional histopathological slides. It might be used for prognosis prediction in LMS, the most prevalent STS subtype in our cohort. It can also help pathologists to make faster and more accurate diagnoses. This could substantially improve the clinical management of STS patients.

How do Stock Market Participants Value ESG Performance? Evidence from Middle Eastern and North African Countries

Empirical evidence indicates that Environmental, Social, and Governance (ESG) practices are associated with firm financial performance, but little is known about stock market participants’ behaviour towards ESG practices, especially in unfavourable settings, where the level of shareholders’ protection is relatively weak. In this article, we examine whether ESG performance provides shareholders with value-relevant information to help them in their equity pricing decisions. Using a cross-country sample of non-financial firms drawn from 10 Middle East and North African (MENA) countries between the period from 2013 to 2019, we find evidence, which is based on the price specification of Ohlson (1995) valuation model, that ESG performance practices are positively priced by market participants and add incremental information content to earnings and book value of equity (BVE). However, when we split the aggregate ESG performance into its components, governance practice is found to be more value relevant than social practice, while the environmental pillar is found to be value (ir)relevant to shareholders. Results using the return valuation model complement and validate the price model specification. Our results suggest that social capital and institutional structures prevail on firm environmental impact. These results are robust to a set of additional tests. Overall, our empirical results indicate that market participants incorporate ESG performance when assessing firm value for the MENA region. Our findings could have several implications for managers, stockholders and regulatory bodies.

Do facilitation payments affect earnings management? Evidence from China

This study examines whether facilitation payments drive managers to manipulate earnings, thus weakening financial disclosure transparency. I find economically and statistically significant evidence that facilitation payments relate positively to earnings management levels in China. The impact of facilitation payments on earnings management is more pronounced when firms have relatively weak political power, less effective external monitoring, fewer growth options, and when firms are located in regions that have less efficient juridical systems. Finally, the findings are strengthened by a set of additional tests to mitigate the endogeneity problem: a difference-in-differences estimation that exploits China’s anti-corruption campaign as the exogenous shock, a dynamic analysis, an instrumental variable approach, and a Heckman analysis to adjust for selection bias. This study contributes to debates regarding corruption and transparency from a micro-economic perspective.

Fusion of neural networks, for LIDAR‐based evidential road mapping

AbstractLIDAR sensors are usually used to provide autonomous vehicles with three‐dimensional representations of their environment. In ideal conditions, geometrical models could detect the road in LIDAR scans, at the cost of a manual tuning of numerical constraints, and a lack of flexibility. We instead propose an evidential pipeline, to accumulate road detection results obtained from neural networks. First, we introduce RoadSeg, a new convolutional architecture that is optimized for road detection in LIDAR scans. RoadSeg is used to classify individual LIDAR points as either belonging to the road, or not. Yet, such point‐level classification results need to be converted into a dense representation, that can be used by an autonomous vehicle. We thus second present an evidential road mapping algorithm, that fuses consecutive road detection results. We benefitted from a reinterpretation of logistic classifiers, which can be seen as generating a collection of simple evidential mass functions. An evidential grid map that depicts the road can then be obtained, by projecting the classification results from RoadSeg into grid cells, and by handling moving objects via conflict analysis. The system was trained and evaluated on real‐life data. A python implementation maintains a 10 Hz framerate. Since road labels were needed for training, a soft labeling procedure, relying lane‐level HD maps, was used to generate coarse training and validation sets. An additional test set was manually labeled for evaluation purposes. So as to reach satisfactory results, the system fuses road detection results obtained from three variants of RoadSeg, processing different LIDAR features.

In-line Phosphoramidite Identification by FTIR to Support Real-Time Oligonucleotide Sequence Confirmation

A classification method was developed for the identification of antisense oligonucleotide phosphoramidite starting materials to support sequence confirmation in real-time during solid-phase oligonucleotide synthesis. Calibration data were collected using spectral data from a Fourier transform infrared analyzer and an attenuated total reflectance (ATR) probe. Eight different phosphoramidites were prepared in acetonitrile and sampled in-line using the ATR probe under various concentrations, flow conditions, and instrument configurations to reproduce anticipated process variability. Additional test sets were constructed from spectra that represented specific types of variability to challenge the model and set forth boundaries to define a prediction space. The identification model was confirmed suitable for checking the oligonucleotide sequence as an in-process and real-time release test.

Experimental Analysis and Optimization to Maximize Ultimate Tensile Strength and Ultimate Elongation of Friction Stir Welded AA6082 Aluminum Alloy

Friction stir welding (FSW) is a well-established welding technique, which allows joining abutting surfaces by generating heating through a rotating and translating tool specifically shaped. Differently from the conventional techniques, continuous welding processes can be executed by FSW, thus supporting the economy of scales objectives. This paper deals with the selection of the optimal process parameters for the FSW of the AA6082 aluminum alloy. Three welding parameters, namely tool plunging, rotational speed and welding speed, have been handled as independent variables for developing two mathematical models by means of a non-linear regression-based approach, with the aim of predicting both ultimate tensile strength and ultimate elongation of the welded joints. A set of additional experimental tests has been used to validate the mentioned metamodels and finally three different metaheuristic algorithms have been implemented for selecting the best process parameters able to maximize the aforementioned mechanical properties. A comparison analysis based on further experimental tests confirmed the accuracy of the predicting metamodels and the quality of solutions yielded by the proposed optimization approaches.

Evaluation of QSAR Equations for Virtual Screening.

Quantitative Structure Activity Relationship (QSAR) models can inform on the correlation between activities and structure-based molecular descriptors. This information is important for the understanding of the factors that govern molecular properties and for designing new compounds with favorable properties. Due to the large number of calculate-able descriptors and consequently, the much larger number of descriptors combinations, the derivation of QSAR models could be treated as an optimization problem. For continuous responses, metrics which are typically being optimized in this process are related to model performances on the training set, for example, and . Similar metrics, calculated on an external set of data (e.g., ), are used to evaluate the performances of the final models. A common theme of these metrics is that they are context -” ignorant”. In this work we propose that QSAR models should be evaluated based on their intended usage. More specifically, we argue that QSAR models developed for Virtual Screening (VS) should be derived and evaluated using a virtual screening-aware metric, e.g., an enrichment-based metric. To demonstrate this point, we have developed 21 Multiple Linear Regression (MLR) models for seven targets (three models per target), evaluated them first on validation sets and subsequently tested their performances on two additional test sets constructed to mimic small-scale virtual screening campaigns. As expected, we found no correlation between model performances evaluated by “classical” metrics, e.g., and and the number of active compounds picked by the models from within a pool of random compounds. In particular, in some cases models with favorable and/or values were unable to pick a single active compound from within the pool whereas in other cases, models with poor and/or values performed well in the context of virtual screening. We also found no significant correlation between the number of active compounds correctly identified by the models in the training, validation and test sets. Next, we have developed a new algorithm for the derivation of MLR models by optimizing an enrichment-based metric and tested its performances on the same datasets. We found that the best models derived in this manner showed, in most cases, much more consistent results across the training, validation and test sets and outperformed the corresponding MLR models in most virtual screening tests. Finally, we demonstrated that when tested as binary classifiers, models derived for the same targets by the new algorithm outperformed Random Forest (RF) and Support Vector Machine (SVM)-based models across training/validation/test sets, in most cases. We attribute the better performances of the Enrichment Optimizer Algorithm (EOA) models in VS to better handling of inactive random compounds. Optimizing an enrichment-based metric is therefore a promising strategy for the derivation of QSAR models for classification and virtual screening.

Intensity Augmentation to Improve Generalizability of Breast Segmentation Across Different MRI Scan Protocols.

The segmentation of the breast from the chest wall is an important first step in the analysis of breast magnetic resonance images. 3D U-Nets have been shown to obtain high segmentation accuracy and appear to generalize well when trained on one scanner type and tested on another scanner, provided that a very similar MR protocol is used. There has, however, been little work addressing the problem of domain adaptation when image intensities or patient orientation differ markedly between the training set and an unseen test set. In this work we aim to address this domain shift problem. We propose to apply extensive intensity augmentation in addition to geometric augmentation during training. We explored both style transfer and a novel intensity remapping approach as intensity augmentation strategies. For our experiments, we trained a 3D U-Net on T1-weighted scans. We tested our network on T2-weighted scans from the same dataset as well as on an additional independent test set acquired with a T1-weighted TWIST sequence and a different coil configuration. By applying intensity augmentation we increased segmentation performance for the T2-weighted scans from a Dice of 0.71 to 0.88. This performance is very close to the baseline performance of training with T2-weighted scans (0.92). On the T1-weighted dataset we obtained a performance increase from 0.77 to 0.85. Our results show that the proposed intensity augmentation increases segmentation performance across different datasets. The proposed method can improve whole breast segmentation of clinical MR scans acquired with different protocols.

Hilbert spectrum analysis for automatic detection and evaluation of Parkinson’s speech

Parkinson’s disease (PD) is a progressive neurological disorder that mainly affects people in old age. Abnormality in the speech signals has been reported as a biomarker to detect PD. This study explores the use of Hilbert spectrum (HS) based features to model voice impairments in people affected by PD. The instantaneous energy deviation cepstral coefficient (IEDCC) is proposed. Statistical analyses show that the proposed feature is an effective and relevant biomarker for PD detection and evaluation of the dysarthria level in speech affected by PD. The capability of the proposed features to differentiate between PD and healthy people is evaluated upon five sustained vowels and ten isolated words from the standard PC-GITA database. The average accuracy of the proposed approach ranges from 82 % to 90 % with vowels, whereas for words the average accuracy ranges between 80 % and 91 %. Besides PD detection, the dysarthria level is evaluated according to the m-FDA scale. Spearman’s correlation coefficients (ρ) are computed between the estimated m-FDA values and the original scores. Correlations of up to 0.75 are obtained with vowel/o/, while 0.77 is the highest correlation obtained with the word/reina/. The developed models are further validated with a separate and independent dataset. The classification accuracy in these additional recordings ranges between 50 % and 80 % with vowels and from 50 % to 82 % with words. The promising results obtained on the additional test set indicate that the proposed method is suitable to perform the automatic detection of PD speakers in real-world conditions.

Do Facilitation Payments Affect Earnings Management? Evidence from China

This study examines whether facilitation payments drive managers to manipulate earnings, thus weakening financial disclosure transparency. I find economically and statistically significant evidence that facilitation payments relate positively to earnings management levels in China. The impact of facilitation payments on earnings management is more pronounced when firms have relatively weak political power, less effective external monitoring, fewer growth options, and when firms are located in regions that have less efficient juridical systems. Finally, the findings are strengthened by a set of additional tests to mitigate the endogeneity problem: a difference-in-differences estimation that exploits China’s anti-corruption campaign as the exogenous shock, a dynamic analysis, an instrumental variable approach, and a Heckman analysis to adjust for selection bias. This study contributes to debates regarding corruption and transparency from a micro-economic perspective.

Fusion of Heterogeneous Earth Observation Data for the Classification of Local Climate Zones

This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM data, which becomes its main drawback. The proposed framework processes two data sources separately and then combines them at the model level through two fusion models (the landuse fusion model and building fusion model) that aim to fuse optical images with landuse and buildings layers of OSM data, respectively. In addition, a new approach to detecting building incompleteness of OSM data is proposed. The proposed framework was trained and tested using the data from the 2017 IEEE GRSS Data Fusion Contest and further validated on one additional test (AT) set containing test samples that are manually labeled in Munich and New York. The experimental results have indicated that compared with the feature stacking-based baseline framework, the proposed framework is effective in fusing optical images with OSM data for the classification of LCZs with high generalization capability on a large scale. The classification accuracy of the proposed framework outperforms the baseline framework by more than 6% and 2% while testing on the test set of 2017 IEEE GRSS Data Fusion Contest and the AT set, respectively. In addition, the proposed framework is less sensitive to spectral diversities of optical satellite images and thus achieves more stable classification performance than the state-of-the-art frameworks.

Time-Domain Analysis of Molecular Dynamics Trajectories Using Deep Neural Networks: Application to Activity Ranking of Tankyrase Inhibitors.

Molecular dynamics simulations provide valuable insights into the behavior of molecular systems. Extending the recent trend of using machine learning techniques to predict physicochemical properties from molecular dynamics data, we propose to consider the trajectories as multidimensional time series represented by 2D tensors containing the ligand-protein interaction descriptor values for each time step. Similar in structure to the time series encountered in modern approaches for signal, speech, and natural language processing, these time series can be directly analyzed using long short-term memory (LSTM) recurrent neural networks or convolutional neural networks (CNNs). The predictive regression models for the ligand-protein affinity were built for a subset of the PDBbind v.2017 database and applied to inhibitors of tankyrase, an enzyme of the poly(ADP-ribose)-polymerase (PARP) family that can be used in the treatment of colorectal cancer. As an additional test set, a subset of the Community Structure-Activity Resource (CSAR) data set was used. For comparison, the random forest and simple neural network models based on the crystal pose or the trajectory-averaged descriptors were used, as well as the commonly employed docking and molecular mechanics Poisson-Boltzmann surface area (MM-PBSA) scores. Convolutional neural networks based on the 2D tensors of ligand-protein interaction descriptors for short (2 ns) trajectories provide the best accuracy and predictive power, reaching the Spearman rank correlation coefficient of 0.73 and Pearson correlation coefficient of 0.70 for the tankyrase test set. Taking into account the recent increase in computational power of modern GPUs and relatively low computational complexity of the proposed approach, it can be used as an advanced virtual screening filter for compound prioritization.

Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Disease

The formation and growth of cysts in kidneys, and often liver, in autosomal dominant polycystic kidney disease (ADPKD) cause progressive increases in total kidney volume (TKV) and liver volume (TLV). Laborious and time-consuming manual tracing of kidneys and liver is the current gold standard. We developed a fully automated segmentation method for TKV and TLV measurement that uses a deep learning network optimized to perform semantic segmentation of kidneys and liver. We used 80% of a set of 440 abdominal magnetic resonance images (T2-weighted HASTE coronal sequences) from patients with ADPKD to train the network and the remaining 20% for validation. Both kidneys and liver were also segmented manually. To evaluate the method's performance, we used an additional test set of images from 100 patients, 45 of whom were also involved in longitudinal analyses. TKV and TLV measured by the automated approach correlated highly with manually traced TKV and TLV (intraclass correlation coefficients, 0.998 and 0.996, respectively), with low bias and high precision (<0.1%±2.7% for TKV and -1.6%±3.1% for TLV); this was comparable with inter-reader variability of manual tracing (<0.1%±3.5% for TKV and -1.5%±4.8% for TLV). For longitudinal analysis, bias and precision were <0.1%±3.2% for TKV and 1.4%±2.9% for TLV growth. These findings demonstrate a fully automated segmentation method that measures TKV, TLV, and changes in these parameters as accurately as manual tracing. This technique may facilitate future studies in which automated and reproducible TKV and TLV measurements are needed to assess disease severity, disease progression, and treatment response.