BACKGROUND & AIMS:The functional liver imaging score (FLIS; range 0-6, with higher scores indicating better liver function), derived from gadoxetic acid-enhanced MRI, is a prognostic imaging biomarker in advanced chronic liver disease (ACLD). Our aim was to investigate whether semi-quantitative FLIS and quantitative imaging parameters, namely relative liver enhancement (RLE), relative enhancement ratio of the biliary system (REB), and liver-to-portal vein contrast ratio (LPC), predict acute-on-chronic liver failure (ACLF; a syndrome defined by extrahepatic organ failure and high short-term mortality) and liver-related mortality in acute decompensation (AD), the main at-risk population. METHODS:We included 210 patients with ACLD who underwent GA-MRI-derived semi-quantitative FLIS assessment, in whom RLE, REB, and LPC were also computed by two independent, experienced radiologists. Patients were stratified into clinically stable ACLD (including compensated or non-acutely decompensated disease) and AD. The prognostic value of semi-quantitative FLIS and quantitative GA-MRI parameters for ACLF/liver-related death was evaluated using competing risk regression analyses, with liver transplantation considered a competing event. RESULTS:FLIS was lower in AD (vs. clinically stable ACLD). Furthermore, low FLIS was an independent risk factor for ACLF development/liver-related death in AD (adjusted subdistribution hazard ratio [aSHR]: 2.37 [95% CI 1.08-5.17], p = 0.031; adjusted for MELD-Na, albumin, and etiological cure), but not in clinically stable ACLD (aSHR: 1.58 [95% CI 0.73-3.45], p = 0.250). Conversely, while RLE, REB, and LPC distinguished between AD and clinically stable ACLD (p <0.001), they did not predict ACLF/liver-related death. CONCLUSIONS:The FLIS is a simple prognostic imaging biomarker in acute decompensation that predicts ACLF and liver-related mortality. FLIS-based risk stratification may help identify patients who could benefit from intensified monitoring or timely liver transplant evaluation. IMPACT AND IMPLICATIONS:The visual, semi-quantitative functional liver imaging score (FLIS), derived from gadoxetic acid-enhanced MRI, assesses liver function. We found that FLIS predicts acute-on-chronic liver failure and liver-related mortality in patients with acutely decompensated cirrhosis, independent of established risk scores. Conversely, quantitative MRI parameters did not add prognostic value. Thus, FLIS-based risk stratification may help identify patients who could benefit from intensified monitoring or timely liver transplant evaluation.

We aimed to quantify hepatic vessel volumes across chronic liver disease stages and healthy controls using deep learning-based magnetic resonance imaging (MRI) analysis, and assess correlations with biomarkers for liver (dys)function and fibrosis/portal hypertension. We assessed retrospectively healthy controls, non-advanced and advanced chronic liver disease (ACLD) patients using a 3D U-Net model for hepatic vessel segmentation on portal venous phase gadoxetic acid-enhanced 3-T MRI. Total (TVVR), hepatic (HVVR), and intrahepatic portal vein-to-volume ratios (PVVR) were compared between groups and correlated with: albumin-bilirubin (ALBI) and “model for end-stage liver disease-sodium” (MELD-Na) score) and fibrosis/portal hypertension (Fibrosis-4 (FIB-4) Score, liver stiffness measurement (LSM), hepatic venous pressure gradient (HVPG), platelet count (PLT), and spleen volume. We included 197 subjects, aged 54.9 ± 13.8 years (mean ± standard deviation), 111 males (56.3

Purpose: The purpose of this study was to assess the ability of pretreatment PET parameters and peripheral blood biomarkers to predict progression-free survival (PFS) and overall survival (OS) in NSCLC patients treated with ICIT.Methods: We prospectively included 87 patients in this study who underwent pre-treatment [F-18]-FDG PET/CT. Organ-specific and total metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were measured using a semiautomatic software. Sites of organ involvement (SOI) were assessed by PET/CT. The log-rank test and Cox-regression analysis were used to assess associations between clinical, laboratory, and imaging parameters with PFS and OS. Time dependent ROC were calculated and model performance was evaluated in terms of its clinical utility.Results: MTV increased with the number of SOI and was correlated with neutrophil and lymphocyte cell count (Spearman's rho = 0.27 or 0.32; p =.02 or 0.003; respectively). Even after adjustment for known risk factors, such as PD-1 expression and neutrophil cell count, the MTV and the number of SOI were independent risk factors for progression (per 100 cm(3); adjusted hazard ratio [aHR]: 1.13; 95% confidence interval [95%CI]: 1.01-1.28; p =.04; single SOI vs. >= 4 SOI: aHR: 2.26, 95%CI: 1.04-4.94; p =.04). MTV and the number of SOI were independent risk factors for overall survival (per 100 cm(3) aHR: 1.11, 95%CI: 1.01-1.23; p =.03; single SOI vs. >= 4 SOI: aHR: 4.54, 95%CI: 1.64-12.58; p =.04). The combination of MTV and the number of SOI improved the risk stratification for PFS and OS (log-rank test p <.001; C-index: 0.64 and 0.67).Conclusion: The MTV and the number of SOI are simple imaging markers that provide complementary information to facilitate risk stratification in NSCLC patients scheduled for ICIT.

Liver vessel segmentation in magnetic resonance imaging data is important for the computational analysis of vascular remodelling, associated with a wide spectrum of diffuse liver diseases. Existing approaches rely on contrast enhanced imaging data, but the necessary dedicated imaging sequences are not uniformly acquired. Images without contrast enhancement are acquired more frequently, but vessel segmentation is challenging, and requires large-scale annotated data. We propose a multi-task learning framework to segment vessels in liver MRI without contrast. It exploits auxiliary contrast enhanced MRI data available only during training to reduce the need for annotated training examples. Our approach draws on paired native and contrast enhanced data with and without vessel annotations for model training. Results show that auxiliary data improves the accuracy of vessel segmentation, even if they are not available during inference. The advantage is most pronounced if only few annotations are available for training, since the feature representation benefits from the shared task structure. A validation of this approach to augment a model for brain tumor segmentation confirms its benefits across different domains. An auxiliary informative imaging modality can augment expert annotations even if it is only available during training.

Measuring and understanding functional fetal brain development in utero is critical for the study of the developmental foundations of our cognitive abilities, possible early detection of disorders, and their prevention. Thalamocortical connections are an intricate component of shaping the cortical layout, but so far, only ex-vivo studies provide evidence of how axons enter the sub-plate and cortex during this highly dynamic phase. Evidence for normal in-utero development of the functional thalamocortical connectome in humans is missing. Here, we modeled fetal functional thalamocortical connectome development using in-utero functional magnetic resonance imaging in fetuses observed from 19th to 40th weeks of gestation (GW). We observed a peak increase of thalamocortical functional connectivity strength between 29th and 31st GW, right before axons establish synapses in the cortex. The cortico-cortical connectivity increases in a similar time window, and exhibits significant functional laterality in temporal-superior, -medial, and -inferior areas. Homologous regions exhibit overall similar mirrored connectivity profiles, but this similarity decreases during gestation giving way to a more diverse cortical interconnectedness. Our results complement the understanding of structural development of the human connectome and may serve as the basis for the investigation of disease and deviations from a normal developmental trajectory of connectivity development.

To compare unsupervised deep clustering (UDC) to fat fraction (FF) and relative liver enhancement (RLE) on Gd-EOB-DTPA-enhanced MRI to distinguish simple steatosis from non-alcoholic steatohepatitis (NASH), using histology as the gold standard. A derivation group of 46 non-alcoholic fatty liver disease (NAFLD) patients underwent 3-T MRI. Histology assessed steatosis, inflammation, ballooning, and fibrosis. UDC was trained to group different texture patterns from MR data into 10 distinct clusters per sequence on unenhanced T1- and Gd-EOB-DTPA-enhanced T1-weighted hepatobiliary phase (T1-Gd-EOB-DTPA-HBP), then on T1 in- and opposed-phase images. RLE and FF were quantified on identical sequences. Differences of these parameters between NASH and simple steatosis were evaluated with χ2- and t-tests, respectively. Linear regression and Random Forest classifier were performed to identify associations between histological NAFLD features, RLE, FF, and UDC patterns, and then determine predictors able to distinguish simple steatosis from NASH. ROC curves assessed diagnostic performance of UDC, RLE, and FF. Finally, we tested these parameters on 30 validation cohorts. For the derivation group, UDC-derived features from unenhanced and T1-Gd-EOB-DTPA-HBP, plus from T1 in- and opposed-phase, distinguished NASH from simple steatosis (p ≤ 0.001 and p = 0.02, respectively) with 85 • Unsupervised deep clustering (UDC) and MR-based parameters (FF and RLE) could independently distinguish simple steatosis from NASH in the derivation group. • On multivariate analysis, RLE could predict only fibrosis, and FF could predict only steatosis; however, UDC could predict all histologic NAFLD components in the derivation group. • The validation cohort confirmed the findings for the derivation group.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

Motion correction is an essential preprocessing step in functional Magnetic Resonance Imaging (fMRI) of the fetal brain with the aim to remove artifacts caused by fetal movement and maternal breathing and consequently to suppress erroneous signal correlations. Current motion correction approaches for fetal fMRI choose a single 3D volume from a specific acquisition timepoint with least motion artefacts as reference volume, and perform interpolation for the reconstruction of the motion corrected time series. The results can suffer, if no low-motion frame is available, and if reconstruction does not exploit any assumptions about the continuity of the fMRI signal. Here, we propose a novel framework, which estimates a high-resolution reference volume by using outlier-robust motion correction, and by utilizing Huber L2 regularization for intra-stack volumetric reconstruction of the motion-corrected fetal brain fMRI. We performed an extensive parameter study to investigate the effectiveness of motion estimation and present in this work benchmark metrics to quantify the effect of motion correction and regularised volumetric reconstruction approaches on functional connectivity computations. We demonstrate the proposed framework's ability to improve functional connectivity estimates, reproducibility and signal interpretability, which is clinically highly desirable for the establishment of prognostic noninvasive imaging biomarkers. The motion correction and volumetric reconstruction framework is made available as an open-source package of NiftyMIC.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Resting-state functional Magnetic Resonance Imaging (fMRI) is a powerful imaging technique for studying functional development of the brain in utero. However, unpredictable and excessive movement of fetuses has limited clinical application since it causes substantial signal fluctuations which can systematically alter observed patterns of functional connectivity. Previous studies have focused on the accurate estimation of the motion parameters in case of large fetal head movement and used a 3D single step interpolation approach at each timepoint to recover motion-free fMRI images. This does not guarantee that the reconstructed image corresponds to the minimum error representation of fMRI time series given the acquired data. Here, we propose a novel technique based on four dimensional iterative reconstruction of the scattered slices acquired during fetal fMRI. The accuracy of the proposed method was quantitatively evaluated on a group of real clinical fMRI fetuses. The results indicate improvements of reconstruction quality compared to the conventional 3D interpolation approach.

Zusammenfassung Methodisches Problem Maschinelles Lernen (ML) nimmt zunehmend Einzug in die Radiologie, um Aufgaben wie die automatische Detektion und Segmentation von diagnoserelevanten Bildmerkmalen, die Charakterisierung von Krankheits- und Behandlungsverläufen sowie Vorhersagen für individuelle Patienten durchzuführen. Radiologische Standardverfahren Die Anwendung von ML-Algorithmen ist für alle radiologischen Verfahren von der Computertomographie (CT), über die Magnetresonanztomographie (MRT) bis zum Ultraschall relevant. Verschiedene Modalitäten führen zu unterschiedlichen Herausforderungen bezüglich Standardisierung und Variabilität. Methodische Innovationen ML-Algorithmen sind zunehmend in der Lage, auch longitudinale Beobachtungen zu verarbeiten und für das Training von Vorhersagemodellen zu nutzen. Diese Entwicklung erlaubt es, umfassende Informationen für die Vorhersage individueller Verläufe heranzuziehen. Leistungsfähigkeit Die Qualität der Detektion und Segmentation von Läsionen hat in vielen Bereichen ein akzeptables Niveau erreicht, die Genauigkeit von Vorhersagemodellen muss diese aber erst erreichen, was u. a. auch mit der Verfügbarkeit repräsentativer Trainingsdaten zusammenhängt. Bewertung Die Entwicklung von ML-basierten Anwendungen in der Radiologie schreitet, trotz dass sich viele der Lösungen noch im Evaluationsstadium befinden, voran, und wird durch eine parallele Weiterentwicklung der grundlegenden Methoden und Techniken begleitet, die sukzessive in die Praxis übergehen werden. Empfehlung für die Praxis Maßgeblich für den effektiven Einsatz von ML in der Praxis sind die Validierung der Algorithmen und die Erstellung repräsentativer Datensätze, die sowohl für das Training als auch für die Validierung verwendet werden können.

Predictive marker patterns in imaging data are a means to quantify disease and progression, but their identification is challenging, if the underlying biology is poorly understood. Here, we present a method to identify predictive texture patterns in medical images in an unsupervised way. Based on deep clustering networks, we simultaneously encode and cluster medical image patches in a low-dimensional latent space. The resulting clusters serve as features for disease staging, linking them to the underlying disease. We evaluate the method on 70 T1-weighted magnetic resonance images of patients with different stages of liver steatosis. The deep clustering approach is able to find predictive clusters with a stable ranking, differentiating between low and high steatosis with an F1-Score of 0.78.

Fetal functional Magnetic Resonance Imaging (fMRI) has emerged as a powerful tool for investigating brain development in utero, holding promise for generating developmental disease biomarkers and supporting prenatal diagnosis. However, to date its clinical applications have been limited by unpredictable fetal and maternal motion during image acquisition. Even after spatial realignment, these cause spurious signal fluctuations confounding measures of functional connectivity and biasing statistical inference of relationships between connectivity and individual differences. As there is no ground truth for the brain’s functional structure, especially before birth, quantifying the quality of motion correction is challenging. In this paper, we propose evaluating the efficacy of different regression based methods for removing motion artifacts after realignment by assessing the residual relationship of functional connectivity with estimated motion, and with the distance between areas. Results demonstrate the sensitivity of our evaluation’s criteria to reveal the relative strengths and weaknesses among different artifact removal methods, and underscore the need for greater care when dealing with fetal motion.

Preprocessing and motion correction are essential steps in resting state functional Magnetic Resonance Imaging (rs-fMRI) of the fetal brain. They aim to address the difficult task of removing artefacts caused by fetal movement or maternal breathing, and aim to suppress erroneous signal correlations caused by motion. While preprocessing standards have been established in the adult brain, motion correction of fetal rs-fMRI and subsequent interpretation of processed data is still challenging. Here, we evaluate the effect of different preprocessing methods and motion correction on rs-fMRI sequences by assessing reproducibility of functional connectivity estimates. For slice-based motion correction of 4D fetal rs-fMRI, we extend a high-resolution reconstruction approach presented for structural fetal MRI. Correlation, standard deviation and structural similarity index are evaluated on the whole cortex, on specific regions and at different gestational ages. Results show improved reproducibility and signal interpretability after preprocessing with motion correction enabling the quantification of long-range correlation patterns of the developing default mode network in the fetal brain.