Robust Ensemble of Two Different Multimodal Approaches to Segment 3D Ischemic Stroke Segmentation Using Brain Tumor Representation Among Multiple Center Datasets.

Ischemic stroke segmentation at an acute stage is vital in assessing the severity of patients' impairment and guiding therapeutic decision-making for reperfusion. Although many deep learning studies have shown attractive performance in medical segmentation, it is difficult to use these models trained on public data with private hospitals' datasets. Here, we demonstrate an ensemble model that employs two different multimodal approaches for generalization, a more effective way to perform on external datasets. First, after we jointly train a segmentation model on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) MR modalities, the model is inferred on the DWI images. Second, a channel-wise segmentation model is trained by concatenating the DWI and ADC images as input, and then is inferred using both MR modalities. Before training with ischemic stroke data, we utilized BraTS 2021, a public brain tumor dataset, for transfer learning. An extensive ablation study evaluates which strategy learns better representations for ischemic stroke segmentation. In our study, nnU-Net well-known for robustness is selected as our baseline model. Our proposed method is evaluated on three different datasets: the Asan Medical Center (AMC) I and II, and the 2022 Ischemic Stroke Lesion Segmentation (ISLES). Our experiments are widely validated over a large, multi-center, and multi-scanner dataset with a huge amount of 846 scans. Not only stroke lesion models can benefit from transfer learning using brain tumor data, but combining the MR modalities using different training schemes also highly improves segmentation performance. The method achieved a top-1 ranking in the ongoing ISLES'22 challenge and performed particularly well on lesion-wise metrics of interest to neuroradiologists, achieving a Dice coefficient of 78.69% and a lesion-wise F1 score of 82.46%. Also, the method was relatively robust on the AMC I (Dice, 60.35%; lesion-wise F1, 68.30%) and II (Dice; 74.12%; lesion-wise F1, 67.53%) datasets in different settings. The high segmentation accuracy of our proposed method could improve radiologists' ability to detect ischemic stroke lesions in MRI images. Our model weights and inference code are available on https://github.com/MDOpx/ISLES22-model-inference .

Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA.

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically.

Detecting CTP truncation artifacts in acute stroke imaging from the arterial input and the vascular output functions.

BACKGROUND: Current guidelines for CT perfusion (CTP) in acute stroke suggest acquiring scans with a minimal duration of 60-70 s. But even then, CTP analysis can be affected by truncation artifacts. Conversely, shorter acquisitions are still widely used in clinical practice and may, sometimes, be sufficient to reliably estimate lesion volumes. We aim to devise an automatic method that detects scans affected by truncation artifacts. METHODS: Shorter scan durations are simulated from the ISLES'18 dataset by consecutively removing the last CTP time-point until reaching a 10 s duration. For each truncated series, perfusion lesion volumes are quantified and used to label the series as unreliable if the lesion volumes considerably deviate from the original untruncated ones. Afterwards, nine features from the arterial input function (AIF) and the vascular output function (VOF) are derived and used to fit machine-learning models with the goal of detecting unreliably truncated scans. Methods are compared against a baseline classifier solely based on the scan duration, which is the current clinical standard. The ROC-AUC, precision-recall AUC and the F1-score are measured in a 5-fold cross-validation setting. RESULTS: The best performing classifier obtained an ROC-AUC of 0.982, precision-recall AUC of 0.985 and F1-score of 0.938. The most important feature was the AIFcoverage, measured as the time difference between the scan duration and the AIF peak. When using the AIFcoverage to build a single feature classifier, an ROC-AUC of 0.981, precision-recall AUC of 0.984 and F1-score of 0.932 were obtained. In comparison, the baseline classifier obtained an ROC-AUC of 0.954, precision-recall AUC of 0.958 and F1-Score of 0.875. CONCLUSIONS: Machine learning models fed with AIF and VOF features accurately detected unreliable stroke lesion measurements due to insufficient acquisition duration. The AIFcoverage was the most predictive feature of truncation and identified unreliable short scans almost as good as machine learning. We conclude that AIF/VOF based classifiers are more accurate than the scans' duration for detecting truncation. These methods could be transferred to perfusion analysis software in order to increase the interpretability of CTP outputs.

ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset.

Magnetic resonance imaging (MRI) is an important imaging modality in stroke. Computer based automated medical image processing is increasingly finding its way into clinical routine. The Ischemic Stroke Lesion Segmentation (ISLES) challenge is a continuous effort to develop and identify benchmark methods for acute and sub-acute ischemic stroke lesion segmentation. Here we introduce an expert-annotated, multicenter MRI dataset for segmentation of acute to subacute stroke lesions ( https://doi.org/10.5281/zenodo.7153326 ). This dataset comprises 400 multi-vendor MRI cases with high variability in stroke lesion size, quantity and location. It is split into a training dataset of n = 250 and a test dataset of n = 150. All training data is publicly available. The test dataset will be used for model validation only and will not be released to the public. This dataset serves as the foundation of the ISLES 2022 challenge ( https://www.isles-challenge.org/ ) with the goal of finding algorithmic methods to enable the development and benchmarking of automatic, robust and accurate segmentation methods for ischemic stroke.

A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms.

Accurate lesion segmentation is critical in stroke rehabilitation research for the quantification of lesion burden and accurate image processing. Current automated lesion segmentation methods for T1-weighted (T1w) MRIs, commonly used in stroke research, lack accuracy and reliability. Manual segmentation remains the gold standard, but it is time-consuming, subjective, and requires neuroanatomical expertise. We previously released an open-source dataset of stroke T1w MRIs and manually-segmented lesion masks (ATLAS v1.2, N = 304) to encourage the development of better algorithms. However, many methods developed with ATLAS v1.2 report low accuracy, are not publicly accessible or are improperly validated, limiting their utility to the field. Here we present ATLAS v2.0 (N = 1271), a larger dataset of T1w MRIs and manually segmented lesion masks that includes training (n = 655), test (hidden masks, n = 300), and generalizability (hidden MRIs and masks, n = 316) datasets. Algorithm development using this larger sample should lead to more robust solutions; the hidden datasets allow for unbiased performance evaluation via segmentation challenges. We anticipate that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke research.

A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI.

Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol. As such, devising robust methods that generalize to multi-scanner and multi-center data is crucial for transferring these techniques into clinical practice. We propose a novel data augmentation approach based on Gaussian Mixture Models (GMM-DA) with the goal of increasing the variability of a given dataset in terms of intensities and contrasts. The approach allows to augment the training dataset such that the variability in the training set compares to what is seen in real world clinical data, while preserving anatomical information. We compare the performance of a state-of-the-art U-Net model trained for segmenting brain structures with and without the addition of GMM-DA. The models are trained and evaluated on single- and multi-scanner datasets. Additionally, we verify the consistency of test-retest results on same-patient images (same and different scanners). Finally, we investigate how the presence of bias field influences the performance of a model trained with GMM-DA. We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner. Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions. We conclude that GMM-DA could increase the transferability of DL models into clinical scenarios.

AIFNet: Automatic vascular function estimation for perfusion analysis using deep learning.

Perfusion imaging is crucial in acute ischemic stroke for quantifying the salvageable penumbra and irreversibly damaged core lesions. As such, it helps clinicians to decide on the optimal reperfusion treatment. In perfusion CT imaging, deconvolution methods are used to obtain clinically interpretable perfusion parameters that allow identifying brain tissue abnormalities. Deconvolution methods require the selection of two reference vascular functions as inputs to the model: the arterial input function (AIF) and the venous output function, with the AIF as the most critical model input. When manually performed, the vascular function selection is time demanding, suffers from poor reproducibility and is subject to the professionals' experience. This leads to potentially unreliable quantification of the penumbra and core lesions and, hence, might harm the treatment decision process. In this work we automatize the perfusion analysis with AIFNet, a fully automatic and end-to-end trainable deep learning approach for estimating the vascular functions. Unlike previous methods using clustering or segmentation techniques to select vascular voxels, AIFNet is directly optimized at the vascular function estimation, which allows to better recognise the time-curve profiles. Validation on the public ISLES18 stroke database shows that AIFNet almost reaches inter-rater performance for the vascular function estimation and, subsequently, for the parameter maps and core lesion quantification obtained through deconvolution. We conclude that AIFNet has potential for clinical transfer and could be incorporated in perfusion deconvolution software.

Diagnostic Performance of Automated MRI Volumetry by icobrain dm for Alzheimer's Disease in a Clinical Setting: A REMEMBER Study.

BACKGROUND: Magnetic resonance imaging (MRI) has become important in the diagnostic work-up of neurodegenerative diseases. icobrain dm, a CE-labeled and FDA-cleared automated brain volumetry software, has shown potential in differentiating cognitively healthy controls (HC) from Alzheimer's disease (AD) dementia (ADD) patients in selected research cohorts. OBJECTIVE: This study examines the diagnostic value of icobrain dm for AD in routine clinical practice, including a comparison to the widely used FreeSurfer software, and investigates if combined brain volumes contribute to establish an AD diagnosis. METHODS: The study population included HC (n = 90), subjective cognitive decline (SCD, n = 93), mild cognitive impairment (MCI, n = 357), and ADD (n = 280) patients. Through automated volumetric analyses of global, cortical, and subcortical brain structures on clinical brain MRI T1w (n = 820) images from a retrospective, multi-center study (REMEMBER), icobrain dm's (v.4.4.0) ability to differentiate disease stages via ROC analysis was compared to FreeSurfer (v.6.0). Stepwise backward regression models were constructed to investigate if combined brain volumes can differentiate between AD stages. RESULTS: icobrain dm outperformed FreeSurfer in processing time (15-30 min versus 9-32 h), robustness (0 versus 67 failures), and diagnostic performance for whole brain, hippocampal volumes, and lateral ventricles between HC and ADD patients. Stepwise backward regression showed improved diagnostic accuracy for pairwise group differentiations, with highest performance obtained for distinguishing HC from ADD (AUC = 0.914; Specificity 83.0%; Sensitivity 86.3%). CONCLUSION: Automated volumetry has a diagnostic value for ADD diagnosis in routine clinical practice. Our findings indicate that combined brain volumes improve diagnostic accuracy, using real-world imaging data from a clinical setting.

icobrain ms 5.1: Combining unsupervised and supervised approaches for improving the detection of multiple sclerosis lesions.

Multiple sclerosis (MS) is a chronic autoimmune, inflammatory neurological disease of the central nervous system. Its diagnosis nowadays commonly includes performing an MRI scan, as it is the most sensitive imaging test for MS. MS plaques are commonly identified from fluid-attenuated inversion recovery (FLAIR) images as hyperintense regions that are highly varying in terms of their shapes, sizes and locations, and are routinely classified in accordance to the McDonald criteria. Recent years have seen an increase in works that aimed at development of various semi-automatic and automatic methods for detection, segmentation and classification of MS plaques. In this paper, we present an automatic combined method, based on two pipelines: a traditional unsupervised machine learning technique and a deep-learning attention-gate 3D U-net network. The deep-learning network is specifically trained to address the weaker points of the traditional approach, namely difficulties in segmenting infratentorial and juxtacortical plaques in real-world clinical MRIs. It was trained and validated on a multi-center multi-scanner dataset that contains 159 cases, each with T1 weighted (T1w) and FLAIR images, as well as manual delineations of the MS plaques, segmented and validated by a panel of raters. The detection rate was quantified using lesion-wise Dice score. A simple label fusion is implemented to combine the output segmentations of the two pipelines. This combined method improves the detection of infratentorial and juxtacortical lesions by 14% and 31% respectively, in comparison to the unsupervised machine learning pipeline that was used as a performance assessment baseline.

Prognostic Validation of the NINDS Common Data Elements for the Radiologic Reporting of Acute Traumatic Brain Injuries: A CENTER-TBI Study.

The aim of this study is to investigate the prognostic value of using the National Institute of Neurological Disorders and Stroke (NINDS) standardized imaging-based pathoanatomic descriptors for the evaluation and reporting of acute traumatic brain injury (TBI) lesions. For a total of 3392 patients (2244 males and 1148 females, median age = 51 years) enrolled in the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study, we extracted 96 Common Data Elements (CDEs) from the structured reports, spanning all three levels of pathoanatomic information (i.e., 20 "basic," 60 "descriptive," and 16 "advanced" CDE variables per patient). Six-month clinical outcome scores were dichotomized into favorable (Glasgow Outcome Scale Extended [GOS-E] = 5-8) versus unfavorable (GOS-E = 1-4). Regularized logistic regression models were constructed and compared using the optimism-corrected area under the curve (AUC). An abnormality was reported for the majority of patients (64.51%). In 79.11% of those patients, there was at least one coexisting pathoanatomic lesion or associated finding. An increase in lesion severity, laterality, and volume was associated with more unfavorable outcomes. Compared with the full set of pathoanatomic descriptors (i.e., all three categories of information), reporting "basic" CDE information provides at least equal discrimination between patients with favorable versus unfavorable outcome (AUC = 0.8121 vs. 0.8155, respectively). Addition of a selected subset of "descriptive" detail to the basic CDEs could improve outcome prediction (AUC = 0.8248). Addition of "advanced" or "emerging/exploratory" information had minimal prognostic value. Our results show that the NINDS standardized-imaging based pathoanatomic descriptors can be used in large-scale studies and provide important insights into acute TBI lesion patterns. When used in clinical predictive models, they can provide excellent discrimination between patients with favorable and unfavorable 6-month outcomes. If further validated, our findings could support the development of structured and itemized templates in routine clinical radiology.

Early Detection of Chronic Asymptomatic Chagas Infection.

Chagas disease, also known as American trypanosomiasis, is a chronic and systemic parasitic infection which has become a serious epidemiological problem not only in endemic regions (Latin America), but also in non-endemic ones like North America, Europe, and Oceania. Subjects with the indeterminate chagasic form (ICF), a chronic asymptomatic disease stage, are the main sources of non-vectorial dissemination through blood transfusion, organ transplantation, and congenital transmission. It has been suggested that 94% of urban infections can be explained by these subjects. Under this scenario, the availability of simple and effective screening methods for ICF detection becomes crucial for both prevention of disease propagation and detection of clinical stages. Recently, a new non-invasive method has been proposed for ICF detection. It is based on surface high-resolution ECG and it could be easily adopted and included in modern ECG devices, overcoming the limitations of serological-based tests. The proposed method shows accuracy for early ICF screening, thus improving prognosis by defining the clinical stages and allowing appropriate and effective treatment.