Search

Most publicly available brain MRI datasets are very homogeneous in terms of scanner and protocols, and it is difficult for models that learn from such data to generalize to multi-center and multi-scanner data. We propose a novel data augmentation approach with the aim of approximating the variability in terms of intensities and contrasts present in real world clinical data. We use a Gaussian Mixture Model based approach to change tissue intensities individually, producing new contrasts while preserving anatomical information. We train a deep learning model on a single scanner dataset and evaluate it on a multi-center and multi-scanner dataset. The proposed approach improves the generalization capability of the model to other scanners not present in the training data., 5 pages, 2 figures. accepted for presentation at the International Symposium on Biomedical Imaging (ISBI) 2021. Code available at https://github.com/icometrix/gmm-augmentation

The evaluation of white matter lesion progression is an important biomarker in the follow-up of MS patients and plays a crucial role when deciding the course of treatment. Current automated lesion segmentation algorithms are susceptible to variability in image characteristics related to MRI scanner or protocol differences. We propose a model that improves the consistency of MS lesion segmentations in inter-scanner studies. First, we train a CNN base model to approximate the performance of icobrain, an FDA-approved clinically available lesion segmentation software. A discriminator model is then trained to predict if two lesion segmentations are based on scans acquired using the same scanner type or not, achieving a \(78\%\) accuracy in this task. Finally, the base model and the discriminator are trained adversarially on multi-scanner longitudinal data to improve the inter-scanner consistency of the base model. The performance of the models is evaluated on an unseen dataset containing manual delineations. The inter-scanner variability is evaluated on test-retest data, where the adversarial network produces improved results over the base model and the FDA-approved solution.

Highlights • icobrain dm is an automated brain MRI segmentation faster than Freesurfer. • Significantly higher accuracy was obtained for several brain structures, including hippocampus. • icobrain dm volumes had a test-retest error below normal annual atrophy rates. • icobrain dm temporal lobe volume had highest sensitivity in discriminating Alzheimer's., Brain volumes computed from magnetic resonance images have potential for assisting with the diagnosis of individual dementia patients, provided that they have low measurement error and high reliability. In this paper we describe and validate icobrain dm, an automatic tool that segments brain structures that are relevant for differential diagnosis of dementia, such as the hippocampi and cerebral lobes. Experiments were conducted in comparison to the widely used FreeSurfer software. The hippocampus segmentations were compared against manual segmentations, with significantly higher Dice coefficients obtained with icobrain dm (25–75th quantiles: 0.86–0.88) than with FreeSurfer (25–75th quantiles: 0.80–0.83). Other brain structures were also compared against manual delineations, with icobrain dm showing lower volumetric errors overall. Test-retest experiments show that the precision of all measurements is higher for icobrain dm than for FreeSurfer except for the parietal cortex volume. Finally, when comparing volumes obtained from Alzheimer's disease patients against age-matched healthy controls, all measures achieved high diagnostic performance levels when discriminating patients from cognitively healthy controls, with the temporal cortex volume measured by icobrain dm reaching the highest diagnostic performance level (area under the receiver operating characteristic curve = 0.99) in this dataset.

The automatic differentiation of retinal vessels into arteries and veins (A/V) is a highly relevant task within the field of retinal image analysis. However, due to limitations of retinal image acquisition devices, specialists can find it impossible to label certain vessels in eye fundus images. In this paper, we introduce a method that takes into account such uncertainty by design. For this, we formulate the A/V classification task as a four-class segmentation problem, and a Convolutional Neural Network is trained to classify pixels into background, A/V, or uncertain classes. The resulting technique can directly provide pixelwise uncertainty estimates. In addition, instead of depending on a previously available vessel segmentation, the method automatically segments the vessel tree. Experimental results show a performance comparable or superior to several recent A/V classification approaches. In addition, the proposed technique also attains state-of-the-art performance when evaluated for the task of vessel segmentation, generalizing to data that was not used during training, even with considerable differences in terms of appearance and resolution.

With the increased need for multi-center magnetic resonance imaging studies, problems arise related to differences in hardware and software between centers. Namely, current algorithms for brain volume quantification are unreliable for the longitudinal assessment of volume changes in this type of setting. Currently most methods attempt to decrease this issue by regressing the scanner- and/or center-effects from the original data. In this work, we explore a novel approach to harmonize brain volume measurements by using only image descriptors. First, we explore the relationships between volumes and image descriptors. Then, we train a Relevance Vector Machine (RVM) model over a large multi-site dataset of healthy subjects to perform volume harmonization. Finally, we validate the method over two different datasets: i) a subset of unseen healthy controls; and ii) a test-retest dataset of multiple sclerosis (MS) patients. The method decreases scanner and center variability while preserving measurements that did not require correction in MS patient data. We show that image descriptors can be used as input to a machine learning algorithm to improve the reliability of longitudinal volumetric studies., 9 pages, 4 figures. Presented at the International Workshop on Machine Learning in Clinical Neuroimaging (MLCN) 2019

In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.

The classification of retinal vessels into arteries and veins in eye fundus images is a relevant task for the automatic assessment of vascular changes. This paper presents a new approach to solve this problem by means of a Fully-Connected Convolutional Neural Network that is specifically adapted for artery/vein classification. For this, a loss function that focuses only on pixels belonging to the retinal vessel tree is built. The relevance of providing the model with different chromatic components of the source images is also analyzed. The performance of the proposed method is evaluated on the RITE dataset of retinal images, achieving promising results, with an accuracy of \(96\%\) on large caliber vessels, and an overall accuracy of \(84\%\).

Breast cancer is one of the leading causes of female death worldwide. The histological analysis of breast tissue allows for the differentiation of the tissue suspected to be abnormal into four classes: normal tissue, benign tumor, in situ carcinoma and invasive carcinoma. Automatic diagnostic systems can help in that task. In this sense, this work propose a deep neural network approach using transfer learning to classify breast cancer histology images. First, the added top layers are trained and a second fine-tunning is done on some feature extraction layers that are frozen previously. The used network is an Inception Resnet V2. In order to overcome the lack of data, data augmentation is performed too. This work is a suggested solution for the ICIAR 2018 BACH-Challenge and the accuracy is 0.76 in the blind test set.

This paper introduces a novel strategy for the task of simultaneously locating two key anatomical landmarks in retinal images of the eye fundus, namely the optic disc and the fovea. For that, instead of attempting to classify each pixel as belonging to the background, the optic disc, or the fovea center, which would lead to a highly class-imbalanced setting, the problem is reformulated as a pixelwise regression task. The regressed quantity consists of the distance from the closest landmark of interest. A Fully-Convolutional Deep Neural Network is optimized to predict this distance for each image location, implicitly casting the problem into a per-pixel Multi-Task Learning approach by which a globally consistent distribution of distances across the entire image can be learned. Once trained, the two minimal distances predicted by the model are selected as the locations of the optic disc and the fovea. The joint learning of every pixel position relative to the optic disc and the fovea favors an automatic understanding of the overall anatomical distribution. This results in an effective technique that can detect both locations simultaneously, as opposed to previous methods that handle both tasks separately. Comprehensive experimental results on a large public dataset validate the proposed approach.

Retinal vessel segmentation is a fundamental and well-studied problem in the retinal image analysis field. The standard images in this context are color photographs acquired with standard fundus cameras. Several vessel segmentation techniques have been proposed in the literature that perform successfully on this class of images. However, for other retinal imaging modalities, blood vessel extraction has not been thoroughly explored. In this paper, we propose a vessel segmentation technique for Scanning Laser Opthalmoscopy (SLO) retinal images. Our method adapts a Deep Neural Network (DNN) architecture initially devised for segmentation of biological images (U-Net), to perform the task of vessel segmentation. The model was trained on a recent public dataset of SLO images. Results show that our approach efficiently segments the vessel network, achieving a performance that outperforms the current state-of-the-art on this particular class of images.

Synthesizing images of the eye fundus is a challenging task that has been previously approached by formulating complex models of the anatomy of the eye. New images can then be generated by sampling a suitable parameter space. Here we propose a method that learns to synthesize eye fundus images directly from data. For that, we pair true eye fundus images with their respective vessel trees, by means of a vessel segmentation technique. These pairs are then used to learn a mapping from a binary vessel tree to a new retinal image. For this purpose, we use a recent image-to-image translation technique, based on the idea of adversarial learning. Experimental results show that the original and the generated images are visually different in terms of their global appearance, in spite of sharing the same vessel tree. Additionally, a quantitative quality analysis of the synthetic retinal images confirms that the produced images retain a high proportion of the true image set quality.