Arnau Oliver

Ezequiel de la Rosa, Mauricio Reyes, Sook-Lei Liew et al.

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES'22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model achieved superior ischemic lesion detection and segmentation accuracy on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm's segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model's generalizability. The algorithm's outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm (https://github.com/Tabrisrei/ISLES22_Ensemble) that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)radiologists. Second, we show the potential for biomedical challenge outputs to extend beyond the challenge's initial objectives, demonstrating their real-world clinical applicability.

Raghav Mehta, Angelos Filos, Ujjwal Baid et al.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at: https://github.com/RagMeh11/QU-BraTS.

Albert Clèrigues, Sergi Valverde, Jose Bernal et al.

Acute stroke lesion segmentation tasks are of great clinical interest as they can help doctors make better informed treatment decisions. Magnetic resonance imaging (MRI) is time demanding but can provide images that are considered gold standard for diagnosis. Automated stroke lesion segmentation can provide with an estimate of the location and volume of the lesioned tissue, which can help in the clinical practice to better assess and evaluate the risks of each treatment. We propose a deep learning methodology for acute and sub-acute stroke lesion segmentation using multimodal MR imaging. The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Lesion Segmentation challenge (ISLES 2015). These involve the tasks of sub-acute stroke lesion segmentation (SISS) and acute stroke penumbra estimation (SPES) from diffusion, perfusion and anatomical MRI modalities. The performance is compared against state-of-the-art methods with a blind online testing set evaluation on each of the challenges. At the time of submitting this manuscript, our approach is the first method in the online rankings for the SISS (DSC=0.59$\pm$0.31) and SPES sub-tasks (DSC=0.84$\pm$0.10). When compared with the rest of submitted strategies, we achieve top rank performance with a lower Hausdorff distance. Better segmentation results are obtained by leveraging the anatomy and pathophysiology of acute stroke lesions and using a combined approach to minimize the effects of class imbalance. The same training procedure is used for both tasks, showing the proposed methodology can generalize well enough to deal with different unrelated tasks and imaging modalities without training hyper-parameter tuning. A public version of the proposed method has been released to the scientific community at https://github.com/NIC-VICOROB/stroke-mri-segmentation.

Kaiyuan Yang, Fabio Musio, Yihui Ma et al.

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 neurovascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two non-invasive angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited datasets with annotations on CoW anatomy, especially for CTA. Therefore, we organized the TopCoW challenge with the release of an annotated CoW dataset. The TopCoW dataset is the first public dataset with voxel-level annotations for 13 CoW vessel components, enabled by virtual reality technology. It is also the first large dataset using 200 pairs of MRA and CTA from the same patients. As part of the benchmark, we invited submissions worldwide and attracted over 250 registered participants from six continents. The submissions were evaluated on both internal and external test datasets of 226 scans from over five centers. The top performing teams achieved over 90% Dice scores at segmenting the CoW components, over 80% F1 scores at detecting key CoW components, and over 70% balanced accuracy at classifying CoW variants for nearly all test sets. The best algorithms also showed clinical potential in classifying fetal-type posterior cerebral artery and locating aneurysms with CoW anatomy. TopCoW demonstrated the utility and versatility of CoW segmentation algorithms for a wide range of downstream clinical applications with explainability. The annotated datasets and best performing algorithms have been released as public Zenodo records to foster further methodological development and clinical tool building.

Mostafa Salem, Sergi Valverde, Mariano Cabezas et al.

In this paper, we propose generating synthetic multiple sclerosis (MS) lesions on MRI images with the final aim to improve the performance of supervised machine learning algorithms, therefore avoiding the problem of the lack of available ground truth. We propose a two-input two-output fully convolutional neural network model for MS lesion synthesis in MRI images. The lesion information is encoded as discrete binary intensity level masks passed to the model and stacked with the input images. The model is trained end-to-end without the need for manually annotating the lesions in the training set. We then perform the generation of synthetic lesions on healthy images via registration of patient images, which are subsequently used for data augmentation to increase the performance for supervised MS lesion detection algorithms. Our pipeline is evaluated on MS patient data from an in-house clinical dataset and the public ISBI2015 challenge dataset. The evaluation is based on measuring the similarities between the real and the synthetic images as well as in terms of lesion detection performance by segmenting both the original and synthetic images individually using a state-of-the-art segmentation framework. We also demonstrate the usage of synthetic MS lesions generated on healthy images as data augmentation. We analyze a scenario of limited training data (one-image training) to demonstrate the effect of the data augmentation on both datasets. Our results significantly show the effectiveness of the usage of synthetic MS lesion images. For the ISBI2015 challenge, our one-image model trained using only a single image plus the synthetic data augmentation strategy showed a performance similar to that of other CNN methods that were fully trained using the entire training set, yielding a comparable human expert rater performance

Spyridon Bakas, Mauricio Reyes, Andras Jakab et al.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Mariano Cabezas, Sergi Valverde, Sandra González-Villà et al.

Segmenting tumors and their subregions is a challenging task as demonstrated by the annual BraTS challenge. Moreover, predicting the survival of the patient using mainly imaging features, while being a desirable outcome to evaluate the treatment of the patient, it is also a difficult task. In this paper, we present a cascaded pipeline to segment the tumor and its subregions and then we use these results and other clinical features together with image features coming from a pretrained VGG-16 network to predict the survival of the patient. Preliminary results with the training and validation dataset show a promising start in terms of segmentation, while the prediction values could be improved with further testing on the feature extraction part of the network.

Sergi Valverde, Mostafa Salem, Mariano Cabezas et al.

In recent years, several convolutional neural network (CNN) methods have been proposed for the automated white matter lesion segmentation of multiple sclerosis (MS) patient images, due to their superior performance compared with those of other state-of-the-art methods. However, the accuracies of CNN methods tend to decrease significantly when evaluated on different image domains compared with those used for training, which demonstrates the lack of adaptability of CNNs to unseen imaging data. In this study, we analyzed the effect of intensity domain adaptation on our recently proposed CNN-based MS lesion segmentation method. Given a source model trained on two public MS datasets, we investigated the transferability of the CNN model when applied to other MRI scanners and protocols, evaluating the minimum number of annotated images needed from the new domain and the minimum number of layers needed to re-train to obtain comparable accuracy. Our analysis comprised MS patient data from both a clinical center and the public ISBI2015 challenge database, which permitted us to compare the domain adaptation capability of our model to that of other state-of-the-art methods. For the ISBI2015 challenge, our one-shot domain adaptation model trained using only a single image showed a performance similar to that of other CNN methods that were fully trained using the entire available training set, yielding a comparable human expert rater performance. We believe that our experiments will encourage the MS community to incorporate its use in different clinical settings with reduced amounts of annotated data. This approach could be meaningful not only in terms of the accuracy in delineating MS lesions but also in the related reductions in time and economic costs derived from manual lesion labeling.

Jose Bernal, Kaisar Kushibar, Mariano Cabezas et al.

Accurate brain tissue segmentation in Magnetic Resonance Imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume help in diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNN) approaches. In particular, in this paper, we analyse a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as Fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs and local spatial dependencies may be encoded since several voxels are classified at once. Our study focuses on understanding architectural strengths and weaknesses of literature-like approaches. Hence, we implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks. We evaluate them using the IBSR18, MICCAI2012 and iSeg2017 datasets as they contain infant and adult data and exhibit varied voxel spacing, image quality, number of scans and available imaging modalities. The discussion is driven in three directions: comparison between 2D and 3D approaches, the importance of multiple modalities and overlapping as a sampling strategy for training and testing models. To encourage other researchers to explore the evaluation framework, a public version is accessible to download from our research website.

Jose Bernal, Kaisar Kushibar, Daniel S. Asfaw et al.

In recent years, deep convolutional neural networks (CNNs) have shown record-shattering performance in a variety of computer vision problems, such as visual object recognition, detection and segmentation. These methods have also been utilised in medical image analysis domain for lesion segmentation, anatomical segmentation and classification. We present an extensive literature review of CNN techniques applied in brain magnetic resonance imaging (MRI) analysis, focusing on the architectures, pre-processing, data-preparation and post-processing strategies available in these works. The aim of this study is three-fold. Our primary goal is to report how different CNN architectures have evolved, discuss state-of-the-art strategies, condense their results obtained using public datasets and examine their pros and cons. Second, this paper is intended to be a detailed reference of the research activity in deep CNN for brain MRI analysis. Finally, we present a perspective on the future of CNNs in which we hint some of the research directions in subsequent years.

Kaisar Kushibar, Sergi Valverde, Sandra Gonzalez-Villa et al.

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time because morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different available state-of-the-art methods and other recently proposed deep learning approaches. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best challenge participant strategy, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community.

Christian Mata, Alain Lalande, Paul Walker et al.

Purpose: The goal of this study is to show the advantage of a collaborative work in the annotation and evaluation of prostate cancer tissues from T2-weighted MRI compared to the commonly used double blind evaluation. Methods: The variability of medical findings focused on the prostate gland (central gland, peripheral and tumoural zones) by two independent experts was firstly evaluated, and secondly compared with a consensus of these two experts. Using a prostate MRI database, experts drew regions of interest (ROIs) corresponding to healthy prostate (peripheral and central zones) and cancer using a semi-automated tool. One of the experts then drew the ROI with knowledge of the other expert's ROI. Results: The surface area of each ROI as the Hausdorff distance and the Dice coefficient for each contour were evaluated between the different experiments, taking the drawing of the second expert as the reference. The results showed that the significant differences between the two experts became non-significant with a collaborative work. Conclusions: This study shows that collaborative work with a dedicated tool allows a better consensus between expertise than using a double blind evaluation. Although we show this for prostate cancer evaluation in T2-weighted MRI, the results of this research can be extrapolated to other diseases and kind of medical images.

Sergi Valverde, Mariano Cabezas, Eloy Roura et al.

In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from small sets of training data, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating ($r \ge 0.97$) also with the expected lesion volume.