Predicting dynamic, motion-related changes in B0 field in the brain at a 7T MRI using a subject-specific fine-trained U-net.

PURPOSE: Subject movement during the MR examination is inevitable and causes not only image artifacts but also deteriorates the homogeneity of the main magnetic field (B0 ), which is a prerequisite for high quality data. Thus, characterization of changes to B0 , for example induced by patient movement, is important for MR applications that are prone to B0 inhomogeneities. METHODS: We propose a deep learning based method to predict such changes within the brain from the change of the head position to facilitate retrospective or even real-time correction. A 3D U-net was trained on in vivo gradient-echo brain 7T MRI data. The input consisted of B0 maps and anatomical images at an initial position, and anatomical images at a different head position (obtained by applying a rigid-body transformation on the initial anatomical image). The output consisted of B0 maps at the new head positions. We further fine-trained the network weights to each subject by measuring a limited number of head positions of the given subject, and trained the U-net with these data. RESULTS: Our approach was compared to established dynamic B0 field mapping via interleaved navigators, which suffer from limited spatial resolution and the need for undesirable sequence modifications. Qualitative and quantitative comparison showed similar performance between an interleaved navigator-equivalent method and proposed method. CONCLUSION: It is feasible to predict B0 maps from rigid subject movement and, when combined with external tracking hardware, this information could be used to improve the quality of MR acquisitions without the use of navigators.

Fetal MRI based brain atlas analysis detects initial in utero effects of prenatal alcohol exposure.

Prenatal alcohol exposure (PAE) can change the normal trajectory of human fetal brain development and may lead to long-lasting neurodevelopmental changes in the form of fetal alcohol spectrum disorders. Currently, early prenatal patterns of alcohol-related central nervous system changes are unclear and it is unknown if small amounts of PAE may result in early detectable brain anomalies. This super-resolution fetal magnetic resonance imaging (MRI) study aimed to identify regional effects of PAE on human brain structure. Fetuses were prospectively assessed using atlas-based semi-automated 3-dimensional tissue segmentation based on 1.5 T and 3 T fetal brain MRI examinations. After expectant mothers completed anonymized PRAMS and TACE questionnaires for PAE, fetuses without gross macroscopic brain abnormalities were identified and analyzed. Linear mixed-effects modeling of regional brain volumes was conducted and multiple comparisons were corrected using the Benjamini-Hochberg procedure. In total, 500 pregnant women were recruited with 51 reporting gestational alcohol consumption. After excluding confounding comorbidities, 24 fetuses (26 observations) were identified with PAE and 52 age-matched controls without PAE were analyzed. Patients with PAE showed significantly larger volumes of the corpus callosum (P ≤ 0.001) and smaller volumes of the periventricular zone (P = 0.001). Even minor (1-3 standard drinks per week) PAE changed the neurodevelopmental trajectory.

Fetal development of functional thalamocortical and cortico-cortical connectivity.

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.

Unsupervised machine learning identifies predictive progression markers of IPF.

OBJECTIVES: To identify and evaluate predictive lung imaging markers and their pathways of change during progression of idiopathic pulmonary fibrosis (IPF) from sequential data of an IPF cohort. To test if these imaging markers predict outcome. METHODS: We studied radiological disease progression in 76 patients with IPF, including overall 190 computed tomography (CT) examinations of the chest. An algorithm identified candidates for imaging patterns marking progression by computationally clustering visual CT features. A classification algorithm selected clusters associated with radiological disease progression by testing their value for recognizing the temporal sequence of examinations. This resulted in radiological disease progression signatures, and pathways of lung tissue change accompanying progression observed across the cohort. Finally, we tested if the dynamics of marker patterns predict outcome, and performed an external validation study on a cohort from a different center. RESULTS: Progression marker patterns were identified and exhibited high stability in a repeatability experiment with 20 random sub-cohorts of the overall cohort. The 4 top-ranked progression markers were consistently selected as most informative for progression across all random sub-cohorts. After spatial image registration, local tracking of lung pattern transitions revealed a network of tissue transition pathways from healthy to a sequence of disease tissues. The progression markers were predictive for outcome, and the model achieved comparable results on a replication cohort. CONCLUSIONS: Unsupervised learning can identify radiological disease progression markers that predict outcome. Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. KEY POINTS: • Unsupervised learning can identify radiological disease progression markers that predict outcome in patients with idiopathic pulmonary fibrosis. • Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. • The progression markers achieved comparable results on a replication cohort.

Impact of a content-based image retrieval system on the interpretation of chest CTs of patients with diffuse parenchymal lung disease.

OBJECTIVES: Content-based image retrieval systems (CBIRS) are a new and potentially impactful tool for radiological reporting, but their clinical evaluation is largely missing. This study aimed at assessing the effect of CBIRS on the interpretation of chest CT scans from patients with suspected diffuse parenchymal lung disease (DPLD). MATERIALS AND METHODS: A total of 108 retrospectively included chest CT scans with 22 unique, clinically and/or histopathologically verified diagnoses were read by eight radiologists (four residents, four attending, median years reading chest CT scans 2.1± 0.7 and 12 ± 1.8, respectively). The radiologists read and provided the suspected diagnosis at a certified radiological workstation to simulate clinical routine. Half of the readings were done without CBIRS and half with the additional support of the CBIRS. The CBIRS retrieved the most likely of 19 lung-specific patterns from a large database of 6542 thin-section CT scans and provided relevant information (e.g., a list of potential differential diagnoses). RESULTS: Reading time decreased by 31.3% (p < 0.001) despite the radiologists searching for additional information more frequently when the CBIRS was available (154 [72%] vs. 95 [43%], p < 0.001). There was a trend towards higher overall diagnostic accuracy (42.2% vs 34.7%, p = 0.083) when the CBIRS was available. CONCLUSION: The use of the CBIRS had a beneficial impact on the reading time of chest CT scans in cases with DPLD. In addition, both resident and attending radiologists were more likely to consult informational resources if they had access to the CBIRS. Further studies are needed to confirm the observed trend towards increased diagnostic accuracy with the use of a CBIRS in practice. KEY POINTS: • A content-based image retrieval system for supporting the diagnostic process of reading chest CT scans can decrease reading time by 31.3% (p < 0.001). • The decrease in reading time was present despite frequent usage of the content-based image retrieval system. • Additionally, a trend towards higher diagnostic accuracy was observed when using the content-based image retrieval system (42.2% vs 34.7%, p = 0.083).

Correlation of histologic, imaging, and artificial intelligence features in NAFLD patients, derived from Gd-EOB-DTPA-enhanced MRI: a proof-of-concept study.

OBJECTIVE: 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. MATERIALS AND METHODS: 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. RESULTS: 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% and 80% accuracy, respectively, while RLE and FF distinguished NASH from simple steatosis (p ≤ 0.001 and p = 0.004, respectively), with 83% and 78% accuracy, respectively. On multivariate regression analysis, RLE and FF correlated only with fibrosis (p = 0.040) and steatosis (p ≤ 0.001), respectively. Conversely, UDC features, using Random Forest classifier predictors, correlated with all histologic NAFLD components. The validation group confirmed these results for both approaches. CONCLUSION: UDC, RLE, and FF could independently separate NASH from simple steatosis. UDC may predict all histologic NAFLD components. CLINICAL RELEVANCE STATEMENT: Using gadoxetic acid-enhanced MR, fat fraction (FF > 5%) can diagnose NAFLD, and relative liver enhancement can distinguish NASH from simple steatosis. Adding AI may let us non-invasively estimate the histologic components, i.e., fat, ballooning, inflammation, and fibrosis, the latter the main prognosticator. KEY POINTS: • 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.

Motion correction and volumetric reconstruction for fetal functional magnetic resonance imaging data.

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.

Disentangling cortical functional connectivity strength and topography reveals divergent roles of genes and environment.

The human brain varies across individuals in its morphology, function, and cognitive capacities. Variability is particularly high in phylogenetically modern regions associated with higher order cognitive abilities, but its relationship to the layout and strength of functional networks is poorly understood. In this study we disentangled the variability of two key aspects of functional connectivity: strength and topography. We then compared the genetic and environmental influences on these two features. Genetic contribution is heterogeneously distributed across the cortex and differs for strength and topography. In heteromodal areas genes predominantly affect the topography of networks, while their connectivity strength is shaped primarily by random environmental influence such as learning. We identified peak areas of genetic control of topography overlapping with parts of the processing stream from primary areas to network hubs in the default mode network, suggesting the coordination of spatial configurations across those processing pathways. These findings provide a detailed map of the diverse contribution of heritability and individual experience to the strength and topography of functional brain architecture.

Performing group-level functional image analyses based on homologous functional regions mapped in individuals.

Functional MRI (fMRI) studies have traditionally relied on intersubject normalization based on global brain morphology, which cannot establish proper functional correspondence between subjects due to substantial intersubject variability in functional organization. Here, we reliably identified a set of discrete, homologous functional regions in individuals to improve intersubject alignment of fMRI data. These functional regions demonstrated marked intersubject variability in size, position, and connectivity. We found that previously reported intersubject variability in functional connectivity maps could be partially explained by variability in size and position of the functional regions. Importantly, individual differences in network topography are associated with individual differences in task-evoked activations, suggesting that these individually specified regions may serve as the "localizer" to improve the alignment of task-fMRI data. We demonstrated that aligning task-fMRI data using the regions derived from resting state fMRI may lead to increased statistical power of task-fMRI analyses. In addition, resting state functional connectivity among these homologous regions is able to capture the idiosyncrasies of subjects and better predict fluid intelligence (gF) than connectivity measures derived from group-level brain atlases. Critically, we showed that not only the connectivity but also the size and position of functional regions are related to human behavior. Collectively, these findings suggest that identifying homologous functional regions across individuals can benefit a wide range of studies in the investigation of connectivity, task activation, and brain-behavior associations.

Variability of computed tomography radiomics features of fibrosing interstitial lung disease: A test-retest study.

OBJECTIVES: To investigate the intra- and inter-scanner repeatability and reproducibility of CT radiomics features (RF) of fibrosing interstitial lung disease (fILD). METHODS: For this prospective, IRB-approved test-retest study, CT data of sixty fILD patients were acquired. Group A (n = 30) underwent one repeated CT scan on a single scanner. Group B (n = 30) was scanned using two different CT scanners. All CT data were reconstructed using different reconstruction kernels (soft, intermediate, sharp) and slice thicknesses (one and three millimeters), resulting in twelve datasets per patient. Following ROI placement in fibrotic lung tissue, 86 RF were extracted. Intra- and inter-scanner RF repeatability and reproducibility were assessed by calculating intraclass correlation coefficients (ICCs) for corresponding kernels and slice thicknesses, and between lung-specific and non-lung-specific reconstruction parameters. Furthermore, test-retest lung volumes were compared. RESULTS: Test-retest demonstrated a majority of RF is highly repeatable for all reconstruction parameter combinations. Intra-scanner reproducibility was negatively affected by reconstruction kernel changes, and further reduced by slice thickness alterations. Inter-scanner reproducibility was highly variable, reconstruction parameter-specific, and greatest if either soft kernels and three-millimeter slice thickness, or lung-specific reconstruction parameters were used for both scans. Test-retest lung volumes showed no significant difference. CONCLUSION: CT RF of fILD are highly repeatable for constant reconstruction parameters in a single scanner. Intra- and inter-scanner reproducibility are severely impacted by alterations in slice thickness more than reconstruction kernel, and are reconstruction parameter-specific. These findings may facilitate CT data and RF selection and assessment in future fILD radiomics studies collecting data across scanners.

The Prenatal Morphomechanic Impact of Agenesis of the Corpus Callosum on Human Brain Structure and Asymmetry.

Genetic, molecular, and physical forces together impact brain morphogenesis. The early impact of deficient midline crossing in agenesis of the Corpus Callosum (ACC) on prenatal human brain development and architecture is widely unknown. Here we analyze the changes of brain structure in 46 fetuses with ACC in vivo to identify their deviations from normal development. Cases of complete ACC show an increase in the thickness of the cerebral wall in the frontomedial regions and a reduction in the temporal, insular, medial occipital and lateral parietal regions, already present at midgestation. ACC is associated with a more symmetric configuration of the temporal lobes and increased frequency of atypical asymmetry patterns, indicating an early morphomechanic effect of callosal growth on human brain development affecting the thickness of the pallium along a ventro-dorsal gradient. Altered prenatal brain architecture in ACC emphasizes the importance of conformational forces introduced by emerging interhemispheric connectivity on the establishment of polygenically determined brain asymmetries.

The Prenatal Origins of Human Brain Asymmetry: Lessons Learned from a Cohort of Fetuses with Body Lateralization Defects.

Knowledge about structural brain asymmetries of human fetuses with body lateralization defects-congenital diseases in which visceral organs are partially or completely incorrectly positioned-can improve our understanding of the developmental origins of hemispheric brain asymmetry. This study investigated structural brain asymmetry in 21 fetuses, which were diagnosed with different types of lateralization defects; 5 fetuses with ciliopathies and 26 age-matched healthy control cases, between 22 and 34 gestational weeks of age. For this purpose, a database of 4007 fetal magnetic resonance imagings (MRIs) was accessed and searched for the corresponding diagnoses. Specific temporal lobe brain asymmetry indices were quantified using in vivo, super-resolution-processed MR brain imaging data. Results revealed that the perisylvian fetal structural brain lateralization patterns and asymmetry indices did not differ between cases with lateralization defects, ciliopathies, and normal controls. Molecular mechanisms involved in the definition of the right/left body axis-including cilium-dependent lateralization processes-appear to occur independently from those involved in the early establishment of structural human brain asymmetries. Atypically inverted early structural brain asymmetries are similarly rare in individuals with lateralization defects and may have a complex, multifactorial, and neurodevelopmental background with currently unknown postnatal functional consequences.

Radiomics score predicts acute respiratory distress syndrome based on the initial CT scan after trauma.

OBJECTIVES: Acute respiratory distress syndrome (ARDS) constitutes a major factor determining the clinical outcome in polytraumatized patients. Early prediction of ARDS is crucial for timely supportive therapy to reduce morbidity and mortality. The objective of this study was to develop and test a machine learning-based method for the early prediction of ARDS derived from the first computed tomography scan of polytraumatized patients after admission to the hospital. MATERIALS AND METHODS: One hundred twenty-three patients (86 male and 37 female, age 41.2 ± 16.4) with an injury severity score (ISS) of 16 or higher (31.9 ± 10.9) were prospectively included and received a CT scan within 1 h after the accident. The lungs, including air pockets and pleural effusions, were automatically segmented using a deep learning-based algorithm. Subsequently, we extracted radiomics features from within the lung and trained an ensemble of gradient boosted trees (GBT) to predict future ARDS. RESULTS: Cross-validated ARDS prediction resulted in an area under the curve (AUC) of 0.79 for the radiomics score compared to 0.66 for ISS, and 0.68 for the abbreviated injury score of the thorax (AIS-thorax). Prediction using the radiomics score yielded an f1-score of 0.70 compared to 0.53 for ISS and 0.57 for AIS-thorax. The radiomics score achieved a sensitivity and specificity of 0.80 and 0.76. CONCLUSIONS: This study proposes a radiomics-based algorithm for the prediction of ARDS in polytraumatized patients at the time of admission to hospital with an accuracy that competes and surpasses conventional scores despite the heterogeneous, and therefore more realistic, scanning protocols. KEY POINTS: • Early prediction of acute respiratory distress syndrome in polytraumatized patients is possible, even when using heterogenous data. • Radiomics-based prediction resulted in an area under the curve of 0.79 compared to 0.66 for the injury severity score, and 0.68 for the abbreviated injury score of the thorax. • Highlighting the most relevant lung regions for prediction facilitates the understanding of machine learning-based prediction.

The role of the corpus callosum in language network connectivity in children.

The specific role of the corpus callosum (CC) in language network organization remains unclear, two contrasting models have been proposed: inhibition of homotopic areas allowing for independent functioning of the hemispheres versus integration of information from both hemispheres. This study aimed to add to this discussion with the first investigation of language network connectivity in combination with CC volume measures. In 38 healthy children aged 6-12, we performed task-based functional magnetic resonance imaging to measure language network connectivity, used structural magnetic resonance imaging to quantify CC subsection volumes, and administered various language tests to examine language abilities. We found an increase in left intrahemispheric and bilateral language network connectivity and a decrease in right intrahemispheric connectivity associated with larger volumes of the posterior, mid-posterior, and central subsections of the CC. Consistent with that, larger volumes of the posterior parts of the CC were significantly associated with better verbal fluency and vocabulary, the anterior CC volume was positively correlated with verbal span. Thus, children with larger volumes of CC subsections showed increased interhemispheric language network connectivity and were better in different language domains. This study presents the first evidence that the CC is directly linked to language network connectivity and underlines the excitatory role of the CC in the integration of information from both hemispheres.

The Subplate Layers: The Superficial and Deep Subplate Can be Discriminated on 3 Tesla Human Fetal Postmortem MRI.

The subplate (SP) is a transient structure of the human fetal brain that becomes the most prominent layer of the developing pallium during the late second trimester. It is important in the formation of thalamocortical and cortico-cortical connections. The SP is vulnerable in perinatal brain injury and may play a role in complex neurodevelopmental disorders, such as schizophrenia and autism. Nine postmortem fetal human brains (19-24 GW) were imaged on a 3 Tesla MR scanner and the T2-w images in the frontal and temporal lobes were compared, in each case, with the histological slices of the same brain. The brains were confirmed to be without any brain pathology. The purpose of this study was to demonstrate that the superficial SP (sSP) and deep SP (dSP) can be discriminated on postmortem MR images. More specifically, we aimed to clarify that the observable, thin, hyperintense layer below the cortical plate in the upper SP portion on T2-weighted MR images has an anatomical correspondence to the histologically established sSP. Therefore, the distinction between the sSP and dSP layers, using clinically available MR imaging methodology, is possible in postmortem MRI and can help in the imaging interpretation of the fetal cerebral layers.

Cross-species functional alignment reveals evolutionary hierarchy within the connectome.

Evolution provides an important window into how cortical organization shapes function and vice versa. The complex mosaic of changes in brain morphology and functional organization that have shaped the mammalian cortex during evolution, complicates attempts to chart cortical differences across species. It limits our ability to fully appreciate how evolution has shaped our brain, especially in systems associated with unique human cognitive capabilities that lack anatomical homologues in other species. Here, we develop a function-based method for cross-species alignment that enables the quantification of homologous regions between humans and rhesus macaques, even when their location is decoupled from anatomical landmarks. Critically, we find cross-species similarity in functional organization reflects a gradient of evolutionary change that decreases from unimodal systems and culminates with the most pronounced changes in posterior regions of the default mode network (angular gyrus, posterior cingulate and middle temporal cortices). Our findings suggest that the establishment of the default mode network, as the apex of a cognitive hierarchy, has changed in a complex manner during human evolution - even within subnetworks.

Joint embedding: A scalable alignment to compare individuals in a connectivity space.

A common coordinate space enabling comparison across individuals is vital to understanding human brain organization and individual differences. By leveraging dimensionality reduction algorithms, high-dimensional fMRI data can be represented in a low-dimensional space to characterize individual features. Such a representative space encodes the functional architecture of individuals and enables the observation of functional changes across time. However, determining comparable functional features across individuals in resting-state fMRI in a way that simultaneously preserves individual-specific connectivity structure can be challenging. In this work we propose scalable joint embedding to simultaneously embed multiple individual brain connectomes within a common space that allows individual representations across datasets to be aligned. Using Human Connectome Project data, we evaluated the joint embedding approach by comparing it to the previously established orthonormal alignment model. Alignment using joint embedding substantially increased the similarity of functional representations across individuals while simultaneously capturing their distinct profiles, allowing individuals to be more discriminable from each other. Additionally, we demonstrated that the common space established using resting-state fMRI provides a better overlap of task-activation across participants. Finally, in a more challenging scenario - alignment across a lifespan cohort aged from 6 to 85 - joint embedding provided a better prediction of age (r2 = 0.65) than the prior alignment model. It facilitated the characterization of functional trajectories across lifespan. Overall, these analyses establish that joint embedding can simultaneously capture individual neural representations in a common connectivity space aligning functional data across participants and populations and preserve individual specificity.

Continuous Learning AI in Radiology: Implementation Principles and Early Applications.

Artificial intelligence (AI) is becoming increasingly present in radiology and health care. This expansion is driven by the principal AI strengths: automation, accuracy, and objectivity. However, as radiology AI matures to become fully integrated into the daily radiology routine, it needs to go beyond replicating static models, toward discovering new knowledge from the data and environments around it. Continuous learning AI presents the next substantial step in this direction and brings a new set of opportunities and challenges. Herein, the authors discuss the main concepts and requirements for implementing continuous AI in radiology and illustrate them with examples from emerging applications.

[Machine learning in radiology : Terminology from individual timepoint to trajectory]. / Maschinelles Lernen in der Radiologie : Begriffsbestimmung vom Einzelzeitpunkt bis zur Trajektorie.

METHODICAL ISSUE: Machine learning (ML) algorithms have an increasingly relevant role in radiology tackling tasks such as the automatic detection and segmentation of diagnosis-relevant markers, the quantification of progression and response, and their prediction in individual patients. STANDARD RADIOLOGICAL METHODS: ML algorithms are relevant for all image acquisition techniques from computed tomography (CT) and magnetic resonance imaging (MRI) to ultrasound. However, different modalities result in different challenges with respect to standardization and variability. METHODICAL INNOVATIONS: ML algorithms are increasingly able to analyze longitudinal data for the training of prediction models. This is relevant since it enables the use of comprehensive information for predicting individual progression and response, and the associated support of treatment decisions by ML models. PERFORMANCE: The quality of detection and segmentation algorithms of lesions has reached an acceptable level in several areas. The accuracy of prediction models is still increasing, but is dependent on the availability of representative training data. ACHIEVEMENTS: The development of ML algorithms in radiology is progressing although many solutions are still at a validation stage. It is accompanied by a parallel and increasingly interlinked development of basic methods and techniques which will gradually be put into practice in radiology. PRACTICAL CONSIDERATIONS: Two factors will impact the relevance of ML in radiological practice: the thorough validation of algorithms and solutions, and the creation of representative diverse data for the training and validation in a realistic context.