Radiomic- and dosiomic-based clustering development for radio-induced neurotoxicity in pediatric medulloblastoma.

BACKGROUND: Texture analysis extracts many quantitative image features, offering a valuable, cost-effective, and non-invasive approach for individual medicine. Furthermore, multimodal machine learning could have a large impact for precision medicine, as texture biomarkers can underlie tissue microstructure. This study aims to investigate imaging-based biomarkers of radio-induced neurotoxicity in pediatric patients with metastatic medulloblastoma, using radiomic and dosiomic analysis. METHODS: This single-center study retrospectively enrolled children diagnosed with metastatic medulloblastoma (MB) and treated with hyperfractionated craniospinal irradiation (CSI). Histological confirmation of medulloblastoma and baseline follow-up magnetic resonance imaging (MRI) were mandatory. Treatment involved helical tomotherapy (HT) delivering a dose of 39 Gray (Gy) to brain and spinal axis and a posterior fossa boost up to 60 Gy. Clinical outcomes, such as local and distant brain control and neurotoxicity, were recorded. Radiomic and dosiomic features were extracted from tumor regions on T1, T2, FLAIR (fluid-attenuated inversion recovery) MRI-maps, and radiotherapy dose distribution. Different machine learning feature selection and reduction approaches were performed for supervised and unsupervised clustering. RESULTS: Forty-eight metastatic medulloblastoma patients (29 males and 19 females) with a mean age of 12 ± 6 years were enrolled. For each patient, 332 features were extracted. Greater level of abstraction of input data by combining selection of most performing features and dimensionality reduction returns the best performance. The resulting one-component radiomic signature yielded an accuracy of 0.73 with sensitivity, specificity, and precision of 0.83, 0.64, and 0.68, respectively. CONCLUSIONS: Machine learning radiomic-dosiomic approach effectively stratified pediatric medulloblastoma patients who experienced radio-induced neurotoxicity. Strategy needs further validation in external dataset for its potential clinical use in ab initio management paradigms of medulloblastoma.

Subtly altered topological asymmetry of brain structural covariance networks in autism spectrum disorder across 43 datasets from the ENIGMA consortium.

Small average differences in the left-right asymmetry of cerebral cortical thickness have been reported in individuals with autism spectrum disorder (ASD) compared to typically developing controls, affecting widespread cortical regions. The possible impacts of these regional alterations in terms of structural network effects have not previously been characterized. Inter-regional morphological covariance analysis can capture network connectivity between different cortical areas at the macroscale level. Here, we used cortical thickness data from 1455 individuals with ASD and 1560 controls, across 43 independent datasets of the ENIGMA consortium's ASD Working Group, to assess hemispheric asymmetries of intra-individual structural covariance networks, using graph theory-based topological metrics. Compared with typical features of small-world architecture in controls, the ASD sample showed significantly altered average asymmetry of networks involving the fusiform, rostral middle frontal, and medial orbitofrontal cortex, involving higher randomization of the corresponding right-hemispheric networks in ASD. A network involving the superior frontal cortex showed decreased right-hemisphere randomization. Based on comparisons with meta-analyzed functional neuroimaging data, the altered connectivity asymmetry particularly affected networks that subserve executive functions, language-related and sensorimotor processes. These findings provide a network-level characterization of altered left-right brain asymmetry in ASD, based on a large combined sample. Altered asymmetrical brain development in ASD may be partly propagated among spatially distant regions through structural connectivity.

Three dimensional MRF obtains highly repeatable and reproducible multi-parametric estimations in the healthy human brain at 1.5T and 3T.

Magnetic resonance fingerprinting (MRF) is highly promising as a quantitative MRI technique due to its accuracy, robustness, and efficiency. Previous studies have found high repeatability and reproducibility of 2D MRF acquisitions in the brain. Here, we have extended our investigations to 3D MRF acquisitions covering the whole brain using spiral projection k-space trajectories. Our travelling head study acquired test/retest data from the brains of 12 healthy volunteers and 8 MRI systems (3 systems at 3 T and 5 at 1.5 T, all from a single vendor), using a study design not requiring all subjects to be scanned at all sites. The pulse sequence and reconstruction algorithm were the same for all acquisitions. After registration of the MRF-derived PD T1 and T2 maps to an anatomical atlas, coefficients of variation (CVs) were computed to assess test/retest repeatability and inter-site reproducibility in each voxel, while a General Linear Model (GLM) was used to determine the voxel-wise variability between all confounders, which included test/retest, subject, field strength and site. Our analysis demonstrated a high repeatability (CVs 0.7-1.3% for T1, 2.0-7.8% for T2, 1.4-2.5% for normalized PD) and reproducibility (CVs of 2.0-5.8% for T1, 7.4-10.2% for T2, 5.2-9.2% for normalized PD) in gray and white matter. Both repeatability and reproducibility improved when compared to similar experiments using 2D acquisitions. Three-dimensional MRF obtains highly repeatable and reproducible estimations of T1 and T2, supporting the translation of MRF-based fast quantitative imaging into clinical applications.

Retrospective rigid motion correction of three-dimensional magnetic resonance fingerprinting of the human brain.

PURPOSE: To obtain three-dimensional (3D), quantitative and motion-robust imaging with magnetic resonance fingerprinting (MRF). METHODS: Our acquisition is based on a 3D spiral projection k-space scheme. We compared different orderings of trajectory interleaves in terms of rigid motion-correction robustness. In all tested orderings, we considered the whole dataset as a sum of 56 segments of 7-s duration, acquired sequentially with the same flip angle schedule. We performed a separate image reconstruction for each segment, producing whole-brain navigators that were aligned to the first segment using normalized correlation. The estimated rigid motion was used to correct the k-space data, and the aligned data were matched with the dictionary to obtain motion-corrected maps. RESULTS: A significant improvement on the motion-affected maps after motion correction is evident with the suppression of motion artifacts. Correlation with the motionless baseline improved by 20% on average for both T1 and T2 estimations after motion correction. In addition, the average motion-induced quantification bias of 70 ms for T1 and 18 ms for T2 values was reduced to 12 ms and 6 ms, respectively, improving the reliability of quantitative estimations. CONCLUSION: We established a method that allows correcting 3D rigid motion on a 7-s timescale during the reconstruction of MRF data using self-navigators, improving the image quality and the quantification robustness.

Multi-site repeatability and reproducibility of MR fingerprinting of the healthy brain at 1.5 and 3.0 T.

Fully-quantitative MR imaging methods are useful for longitudinal characterization of disease and assessment of treatment efficacy. However, current quantitative MRI protocols have not been widely adopted in the clinic, mostly due to lengthy scan times. Magnetic Resonance Fingerprinting (MRF) is a new technique that can reconstruct multiple parametric maps from a single fast acquisition in the transient state of the MR signal. Due to the relative novelty of this technique, the repeatability and reproducibility of quantitative measurements obtained using MRF has not been extensively studied. Our study acquired test/retest data from the brains of nine healthy volunteers, each scanned on five MRI systems (two at 3.0 T and three at 1.5 T, all from a single vendor) located at two different centers. The pulse sequence and reconstruction algorithm were the same for all acquisitions. After registration of the MRF-derived M0, T1 and T2 maps to an anatomical atlas, coefficients-of-variation (CVs) were computed to assess test/retest repeatability and inter-site reproducibility in each voxel, while a General Linear Model (GLM) was used to determine the voxel-wise variability between all confounders, which included test/retest, subject, field strength and site. Our analysis demonstrated an excellent repeatability (CVs of 2-3% for T1, 5-8% for T2, 3% for normalized-M0) and a good reproducibility (CVs of 3-8% for T1, 8-14% for T2, 5% for normalized-M0) in grey and white matter.

Brainstem enlargement in preschool children with autism: Results from an intermethod agreement study of segmentation algorithms.

The intermethod agreement between automated algorithms for brainstem segmentation is investigated, focusing on the potential involvement of this structure in Autism Spectrum Disorders (ASD). Inconsistencies highlighted in previous studies on brainstem in the population with ASD may in part be a result of poor agreement in the extraction of structural features between different methods. A sample of 76 children with ASD and 76 age-, gender-, and intelligence-matched controls was considered. Volumetric analyses were performed using common tools for brain structures segmentation, namely FSL-FIRST, FreeSurfer (FS), and Advanced Normalization Tools (ANTs). For shape analysis SPHARM-MAT was employed. Intermethod agreement was quantified in terms of Pearson correlations between pairs of volumes obtained by the different methods. The degree of overlap between segmented masks was quantified in terms of the Dice index. Both Pearson correlations and Dice indices, showed poor agreement between FSL-FIRST and the other methods (ANTs and FS), which by contrast, yielded Pearson correlations greater than 0.93 and average Dice indices greater than 0.76 when compared with each other. As with volume, shape analyses exhibited discrepancies between segmentation methods, with particular differences noted between FSL-FIRST and the others (ANT and FS), with under- and over-segmentation in specific brainstem regions. These data suggest that research on brain structure alterations should cross-validate findings across multiple methods. We consistently detected an enlargement of brainstem volume in the whole sample and in the male cohort across multiple segmentation methods, a feature particularly driven by the subgroup of children with idiopathic intellectual disability associated with ASD.

The effect of age, sex and clinical features on the volume of Corpus Callosum in pre-schoolers with Autism Spectrum Disorder: a case-control study.

A growing body of literature has identified volume alterations of the corpus callosum (CC) in subjects with autism spectrum disorders (ASD). However, to date very few investigations have been conducted on pre-school-age ASD children. This study aims to compare the volume of CC and its sub-regions between pre-schoolers with ASD and controls (CON) and to examine their relationship to demographic and clinical variables (sex, age, non-verbal IQ -NVIQ-, expressive non-echolalic language, emotional and behavioural problems, and autism severity). The volume of CC of 40 pre-schoolers with ASD (20 males and 20 females; mean age: 49 ± 12 months; mean NVIQ: 73 ± 22) and 40 sex-, age-, and NVIQ-matched CON subjects (20 M and 20 F; mean age: 49 ± 14 months; mean NVIQ: 73 ± 23) were quantified applying the FreeSurfer automated parcellation software on Magnetic Resonance images. No significant volumetric differences in CC total volume and in its sub-regions between ASD and CON were found using total brain volume as a covariate. Analogously, absence of CC volumetric differences was evident when boys and girls with ASD were compared with their matched controls. The CC total volume of younger ASD male subjects was found significantly larger with respect to matched CON, which is consistent with the atypical growth trajectory widely reported in these young children. The CC total volume was negatively correlated with autism severity, whereas no association between CC volume and other clinical variables was detected. If replicated, the indirect relationship between CC volume and autism severity suggests the involvement of CC in core ASD symptoms.

Hippocampal subfields at ultra high field MRI: An overview of segmentation and measurement methods.

The hippocampus is one of the most interesting and studied brain regions because of its involvement in memory functions and its vulnerability in pathological conditions, such as neurodegenerative processes. In the recent years, the increasing availability of Magnetic Resonance Imaging (MRI) scanners that operate at ultra-high field (UHF), that is, with static magnetic field strength ≥7T, has opened new research perspectives. Compared to conventional high-field scanners, these systems can provide new contrasts, increased signal-to-noise ratio and higher spatial resolution, thus they may improve the visualization of very small structures of the brain, such as the hippocampal subfields. Studying the morphometry of the hippocampus is crucial in neuroimaging research because changes in volume and thickness of hippocampal subregions may be relevant in the early assessment of pathological cognitive decline and Alzheimer's Disease (AD). The present review provides an overview of the manual, semi-automated and fully automated methods that allow the assessment of hippocampal subfield morphometry at UHF MRI, focusing on the different hippocampal segmentation produced. © 2017 Wiley Periodicals, Inc.

Temporal lobe connects regression and macrocephaly to autism spectrum disorders.

Interictal electroencephalogram (EEG) abnormalities are frequently associated with autism spectrum disorders (ASD), although their relationship with the clinical features of ASD, particularly the regressive onset, remains controversial. The aim of this study was to investigate whether the characteristics of interictal EEG abnormalities might help to distinguish and predict definite phenotypes within the heterogeneity of ASD. We reviewed the awake and sleep interictal EEGs of 220 individuals with idiopathic ASD, either with or without a history of seizures. EEG findings were analyzed with respect to a set of clinical variables to explore significant associations. A brain morphometry study was also carried out on a subgroup of patients. EEG abnormalities were seen in 154/220 individuals (70%) and were mostly focal (p < 0.01) with an anterior localization (p < 0.001). They were detected more frequently during sleep (p < 0.01), and were associated with a regressive onset of ASD (p < 0.05), particularly in individuals with focal temporal localization (p < 0.05). This association was also stronger in regressive patients with concurrent macrocephaly, together with a relative volumetric reduction of the right temporal cortex (p < 0.05). Indeed, concurrence of temporal EEG abnormalities, regression and macrocephaly might possibly define a distinct endophenotype of ASD. EEG-based endophenotypes could be useful to untangle the complexity of ASD, helping to establish anatomic or pathophysiologic subtypes of the disorder.

Investigation of maximum local specific absorption rate in 7 T magnetic resonance with respect to load size by use of electromagnetic simulations.

Local specific absorption rate (SAR) evaluation in ultra high field (UHF) magnetic resonance (MR) systems is a major concern. In fact, at UHF, radiofrequency (RF) field inhomogeneity generates hot-spots that could cause localized tissue heating. Unfortunately, local SAR measurements are not available in present MR systems; thus, electromagnetic simulations must be performed for RF fields and SAR analysis. In this study, we used three-dimensional full-wave numerical electromagnetic simulations to investigate the dependence of local SAR at 7.0 T with respect to subject size in two different scenarios: surface coil loaded by adult and child calves and quadrature volume coil loaded by adult and child heads. In the surface coil scenario, maximum local SAR decreased with decreasing load size, provided that the RF magnetic fields for the different load sizes were scaled to achieve the same slice average value. On the contrary, in the volume coil scenario, maximum local SAR was up to 15% higher in children than in adults.

Deep learning based joint fusion approach to exploit anatomical and functional brain information in autism spectrum disorders.

BACKGROUND: The integration of the information encoded in multiparametric MRI images can enhance the performance of machine-learning classifiers. In this study, we investigate whether the combination of structural and functional MRI might improve the performances of a deep learning (DL) model trained to discriminate subjects with Autism Spectrum Disorders (ASD) with respect to typically developing controls (TD). MATERIAL AND METHODS: We analyzed both structural and functional MRI brain scans publicly available within the ABIDE I and II data collections. We considered 1383 male subjects with age between 5 and 40 years, including 680 subjects with ASD and 703 TD from 35 different acquisition sites. We extracted morphometric and functional brain features from MRI scans with the Freesurfer and the CPAC analysis packages, respectively. Then, due to the multisite nature of the dataset, we implemented a data harmonization protocol. The ASD vs. TD classification was carried out with a multiple-input DL model, consisting in a neural network which generates a fixed-length feature representation of the data of each modality (FR-NN), and a Dense Neural Network for classification (C-NN). Specifically, we implemented a joint fusion approach to multiple source data integration. The main advantage of the latter is that the loss is propagated back to the FR-NN during the training, thus creating informative feature representations for each data modality. Then, a C-NN, with a number of layers and neurons per layer to be optimized during the model training, performs the ASD-TD discrimination. The performance was evaluated by computing the Area under the Receiver Operating Characteristic curve within a nested 10-fold cross-validation. The brain features that drive the DL classification were identified by the SHAP explainability framework. RESULTS: The AUC values of 0.66±0.05 and of 0.76±0.04 were obtained in the ASD vs. TD discrimination when only structural or functional features are considered, respectively. The joint fusion approach led to an AUC of 0.78±0.04. The set of structural and functional connectivity features identified as the most important for the two-class discrimination supports the idea that brain changes tend to occur in individuals with ASD in regions belonging to the Default Mode Network and to the Social Brain. CONCLUSIONS: Our results demonstrate that the multimodal joint fusion approach outperforms the classification results obtained with data acquired by a single MRI modality as it efficiently exploits the complementarity of structural and functional brain information.

Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study.

Objective. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters. This limited robustness hinders the generalizable validity of radiomics-assisted models. Our aim is to investigate a possible harmonization strategy based on matching image quality to improve feature robustness.Approach.We acquired CT scans of a phantom with two scanners across different dose levels and percentages of Iterative Reconstruction algorithms. The detectability index was used as a comprehensive task-based image quality metric. A statistical analysis based on the Intraclass Correlation Coefficient was performed to determine if matching image quality/appearance could enhance the robustness of radiomics features extracted from the phantom images. Additionally, an Artificial Neural Network was trained on these features to automatically classify the scanner used for image acquisition.Main results.We found that the ICC of the features across protocols providing a similar detectability index improves with respect to the ICC of the features across protocols providing a different detectability index. This improvement was particularly noticeable in features relevant for distinguishing between scanners.Significance.This preliminary study demonstrates that a harmonization based on image quality/appearance matching could improve radiomics features robustness and heterogeneous protocols can be used to obtain a similar image appearance in terms of the detectability index. Thus protocols with a lower dose level could be selected to reduce the amount of radiation dose delivered to the patient and simultaneously obtain a more robust quantitative analysis.

In-beam PET treatment monitoring of carbon therapy patients: Results of a clinical trial at CNAO.

PURPOSE: Carbon ion therapy treatments can be monitored non-invasively with in-beam Positron Emission Tomography (PET). At CNAO the INSIDE in-beam PET scanner has been used in a clinical trial (NCT03662373) to monitor cancer treatments with proton and carbon therapy. In this work we present the analysis results of carbon therapy data, acquired during the first phase of the clinical trial, analyzing data of nine patients treated at CNAO for various malignant tumors in the head-and-neck region. MATERIALS AND METHODS: The patient group contained two patients requiring replanning, and seven patients without replanning, based on established protocols. For each patient the PET images acquired along the course of treatment were compared with a reference, applying two analysis methods: the beam-eye-view (BEV) method and the γ-index analysis. Time trends in several parameters were investigated, as well as the agreement with control CTs, if available. RESULTS: Regarding the BEV-method, the average sigma value σ was 3.7 mm of range difference distributions for patients without changes (sensitivity of the INSIDE detector). The 3D-information obtained from the BEV analysis was partly in agreement with what was observed in the control CT. The data quality and quantity was insufficient for a definite interpretation of the time trends. CONCLUSION: We analyzed carbon therapy data acquired with the INSIDE in-beam PET detector using two analysis methods. The data allowed to evaluate sensitivity of the INSIDE detector for carbon therapy and to make several recommendations for the future.

Synthetic CT imaging for PET monitoring in proton therapy: a simulation study.

Objective.This study addresses a fundamental limitation of in-beam positron emission tomography (IB-PET) in proton therapy: the lack of direct anatomical representation in the images it produces. We aim to overcome this shortcoming by pioneering the application of deep learning techniques to create synthetic control CT images (sCT) from combining IB-PET and planning CT scan data.Approach.We conducted simulations involving six patients who underwent irradiation with proton beams. Leveraging the architecture of a visual transformer (ViT) neural network, we developed a model to generate sCT images of these patients using the planning CT scans and the inter-fractional simulated PET activity maps during irradiation. To evaluate the model's performance, a comparison was conducted between the sCT images produced by the ViT model and the authentic control CT images-serving as the benchmark.Main results.The structural similarity index was computed at a mean value across all patients of 0.91, while the mean absolute error measured 22 Hounsfield Units (HU). Root mean squared error and peak signal-to-noise ratio values were 56 HU and 30 dB, respectively. The Dice similarity coefficient exhibited a value of 0.98. These values are comparable to or exceed those found in the literature. More than 70% of the synthetic morphological changes were found to be geometrically compatible with the ones reported in the real control CT scan.Significance.Our study presents an innovative approach to surface the hidden anatomical information of IB-PET in proton therapy. Our ViT-based model successfully generates sCT images from inter-fractional PET data and planning CT scans. Our model's performance stands on par with existing models relying on input from cone beam CT or magnetic resonance imaging, which contain more anatomical information than activity maps.

Using the gamma-index analysis for inter-fractional comparison of in-beam PET images for head-and-neck treatment monitoring in proton therapy: A Monte Carlo simulation study.

GOAL: In-beam Positron Emission Tomography (PET) is a technique for in-vivo non-invasive treatment monitoring for proton therapy. To detect anatomical changes in patients with PET, various analysis methods exist, but their clinical interpretation is problematic. The goal of this work is to investigate whether the gamma-index analysis, widely used for dose comparisons, is an appropriate tool for comparing in-beam PET distributions. Focusing on a head-and-neck patient, we investigate whether the gamma-index map and the passing rate are sensitive to progressive anatomical changes. METHODS/MATERIALS: We simulated a treatment course of a proton therapy patient using FLUKA Monte Carlo simulations. Gradual emptying of the sinonasal cavity was modeled through a series of artificially modified CT scans. The in-beam PET activity distributions from three fields were evaluated, simulating a planar dual head geometry. We applied the 3D-gamma evaluation method to compare the PET images with a reference image without changes. Various tolerance criteria and parameters were tested, and results were compared to the CT-scans. RESULTS: Based on 210 MC simulations we identified appropriate parameters for the gamma-index analysis. Tolerance values of 3 mm/3% and 2 mm/2% were suited for comparison of simulated in-beam PET distributions. The gamma passing rate decreased with increasing volume change for all fields. CONCLUSION: The gamma-index analysis was found to be a useful tool for comparing simulated in-beam PET images, sensitive to sinonasal cavity emptying. Monitoring the gamma passing rate behavior over the treatment course is useful to detect anatomical changes occurring during the treatment course.

Deriving quantitative information from multiparametric MRI via Radiomics: Evaluation of the robustness and predictive value of radiomic features in the discrimination of low-grade versus high-grade gliomas with machine learning.

PURPOSE: Analysis pipelines based on the computation of radiomic features on medical images are widely used exploration tools across a large variety of image modalities. This study aims to define a robust processing pipeline based on Radiomics and Machine Learning (ML) to analyze multiparametric Magnetic Resonance Imaging (MRI) data to discriminate between high-grade (HGG) and low-grade (LGG) gliomas. METHODS: The dataset consists of 158 multiparametric MRI of patients with brain tumor publicly available on The Cancer Imaging Archive, preprocessed by the BraTS organization committee. Three different types of image intensity normalization algorithms were applied and 107 features were extracted for each tumor region, setting the intensity values according to different discretization levels. The predictive power of radiomic features in the LGG versus HGG categorization was evaluated by using random forest classifiers. The impact of the normalization techniques and of the different settings in the image discretization was studied in terms of the classification performances. A set of MRI-reliable features was defined selecting the features extracted according to the most appropriate normalization and discretization settings. RESULTS: The results show that using MRI-reliable features improves the performance in glioma grade classification (AUC=0.93±0.05) with respect to the use of raw (AUC=0.88±0.08) and robust features (AUC=0.83±0.08), defined as those not depending on image normalization and intensity discretization. CONCLUSIONS: These results confirm that image normalization and intensity discretization strongly impact the performance of ML classifiers based on radiomic features. Thus, special attention should be provided in the image preprocessing step before typical radiomic and ML analysis are carried out.

Effect of data harmonization of multicentric dataset in ASD/TD classification.

Machine Learning (ML) is nowadays an essential tool in the analysis of Magnetic Resonance Imaging (MRI) data, in particular in the identification of brain correlates in neurological and neurodevelopmental disorders. ML requires datasets of appropriate size for training, which in neuroimaging are typically obtained collecting data from multiple acquisition centers. However, analyzing large multicentric datasets can introduce bias due to differences between acquisition centers. ComBat harmonization is commonly used to address batch effects, but it can lead to data leakage when the entire dataset is used to estimate model parameters. In this study, structural and functional MRI data from the Autism Brain Imaging Data Exchange (ABIDE) collection were used to classify subjects with Autism Spectrum Disorders (ASD) compared to Typical Developing controls (TD). We compared the classical approach (external harmonization) in which harmonization is performed before train/test split, with an harmonization calculated only on the train set (internal harmonization), and with the dataset with no harmonization. The results showed that harmonization using the whole dataset achieved higher discrimination performance, while non-harmonized data and harmonization using only the train set showed similar results, for both structural and connectivity features. We also showed that the higher performances of the external harmonization are not due to larger size of the sample for the estimation of the model and hence these improved performance with the entire dataset may be ascribed to data leakage. In order to prevent this leakage, it is recommended to define the harmonization model solely using the train set.

Quantification of pulmonary involvement in COVID-19 pneumonia: an upgrade of the LungQuant software for lung CT segmentation.

Computed tomography (CT) scans are used to evaluate the severity of lung involvement in patients affected by COVID-19 pneumonia. Here, we present an improved version of the LungQuant automatic segmentation software (LungQuant v2), which implements a cascade of three deep neural networks (DNNs) to segment the lungs and the lung lesions associated with COVID-19 pneumonia. The first network (BB-net) defines a bounding box enclosing the lungs, the second one (U-net 1 ) outputs the mask of the lungs, and the final one (U-net 2 ) generates the mask of the COVID-19 lesions. With respect to the previous version (LungQuant v1), three main improvements are introduced: the BB-net, a new term in the loss function in the U-net for lesion segmentation and a post-processing procedure to separate the right and left lungs. The three DNNs were optimized, trained and tested on publicly available CT scans. We evaluated the system segmentation capability on an independent test set consisting of ten fully annotated CT scans, the COVID-19-CT-Seg benchmark dataset. The test performances are reported by means of the volumetric dice similarity coefficient (vDSC) and the surface dice similarity coefficient (sDSC) between the reference and the segmented objects. LungQuant v2 achieves a vDSC (sDSC) equal to 0.96 ± 0.01 (0.97 ± 0.01) and 0.69 ± 0.08 (0.83 ± 0.07) for the lung and lesion segmentations, respectively. The output of the segmentation software was then used to assess the percentage of infected lungs, obtaining a Mean Absolute Error (MAE) equal to 2%.

Quality assessment, variability and reproducibility of anatomical measurements derived from T1-weighted brain imaging: The RIN-Neuroimaging Network case study.

Initiatives for the collection of harmonized MRI datasets are growing continuously, opening questions on the reliability of results obtained in multi-site contexts. Here we present the assessment of the brain anatomical variability of MRI-derived measurements obtained from T1-weighted images, acquired according to the Standard Operating Procedures, promoted by the RIN-Neuroimaging Network. A multicentric dataset composed of 77 brain T1w acquisitions of young healthy volunteers (mean age = 29.7 ± 5.0 years), collected in 15 sites with MRI scanners of three different vendors, was considered. Parallelly, a dataset of 7 "traveling" subjects, each undergoing three acquisitions with scanners from different vendors, was also used. Intra-site, intra-vendor, and inter-site variabilities were evaluated in terms of the percentage standard deviation of volumetric and cortical thickness measures. Image quality metrics such as contrast-to-noise and signal-to-noise ratio in gray and white matter were also assessed for all sites and vendors. The results showed a measured global variability that ranges from 11% to 19% for subcortical volumes and from 3% to 10% for cortical thicknesses. Univariate distributions of the normalized volumes of subcortical regions, as well as the distributions of the thickness of cortical parcels appeared to be significantly different among sites in 8 subcortical (out of 17) and 21 cortical (out of 68) regions of i nterest in the multicentric study. The Bland-Altman analysis on "traveling" brain measurements did not detect systematic scanner biases even though a multivariate classification approach was able to classify the scanner vendor from brain measures with an accuracy of 0.60 ± 0.14 (chance level 0.33).

A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia.

BACKGROUND: The role of computed tomography (CT) in the diagnosis and characterization of coronavirus disease 2019 (COVID-19) pneumonia has been widely recognized. We evaluated the performance of a software for quantitative analysis of chest CT, the LungQuant system, by comparing its results with independent visual evaluations by a group of 14 clinical experts. The aim of this work is to evaluate the ability of the automated tool to extract quantitative information from lung CT, relevant for the design of a diagnosis support model. METHODS: LungQuant segments both the lungs and lesions associated with COVID-19 pneumonia (ground-glass opacities and consolidations) and computes derived quantities corresponding to qualitative characteristics used to clinically assess COVID-19 lesions. The comparison was carried out on 120 publicly available CT scans of patients affected by COVID-19 pneumonia. Scans were scored for four qualitative metrics: percentage of lung involvement, type of lesion, and two disease distribution scores. We evaluated the agreement between the LungQuant output and the visual assessments through receiver operating characteristics area under the curve (AUC) analysis and by fitting a nonlinear regression model. RESULTS: Despite the rather large heterogeneity in the qualitative labels assigned by the clinical experts for each metric, we found good agreement on the metrics compared to the LungQuant output. The AUC values obtained for the four qualitative metrics were 0.98, 0.85, 0.90, and 0.81. CONCLUSIONS: Visual clinical evaluation could be complemented and supported by computer-aided quantification, whose values match the average evaluation of several independent clinical experts. KEY POINTS: We conducted a multicenter evaluation of the deep learning-based LungQuant automated software. We translated qualitative assessments into quantifiable metrics to characterize coronavirus disease 2019 (COVID-19) pneumonia lesions. Comparing the software output to the clinical evaluations, results were satisfactory despite heterogeneity of the clinical evaluations. An automatic quantification tool may contribute to improve the clinical workflow of COVID-19 pneumonia.