Attri-VAE: Attribute-based interpretable representations of medical images with variational autoencoders.

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.

Murine femur micro-computed tomography and biomechanical datasets for an ovariectomy-induced osteoporosis model.

The development of new effective and safer therapies for osteoporosis, in addition to improved diagnostic and prevention strategies, represents a serious need in the scientific community. Micro-CT image-based analyses in association with biomechanical testing have become pivotal tools in identifying osteoporosis in animal models by assessment of bone microarchitecture and resistance, as well as bone strength. Here, we describe a dataset of micro-CT scans and reconstructions of 15 whole femurs and biomechanical tests on contralateral femurs from C57BL/6JOlaHsd ovariectomized (OVX), resembling human post-menopausal osteoporosis, and sham operated (sham) female mice. Data provided for each mouse include: the acquisition images (.tiff), the reconstructed images (.bmp) and an.xls file containing the maximum attenuations for each reconstructed image. Biomechanical data include an.xls file with the recorded load-displacement, a movie with the filmed test and an.xls file collecting all biomechanical results.

Abdominal Aortic Aneurysm Segmentation Using Convolutional Neural Networks Trained with Images Generated with a Synthetic Shape Model.

An abdominal aortic aneurysm (AAA) is a ballooning of the abdominal aorta, that if not treated tends to grow and rupture. Computed Tomography Angiography (CTA) is the main imaging modality for the management of AAAs, and segmenting them is essential for AAA rupture risk and disease progression assessment. Previous works have shown that Convolutional Neural Networks (CNNs) can accurately segment AAAs, but have the limitation of requiring large amounts of annotated data to train the networks. Thus, in this work we propose a methodology to train a CNN only with images generated with a synthetic shape model, and test its generalization and ability to segment AAAs from new original CTA scans. The synthetic images are created from realistic deformations generated by applying principal component analysis to the deformation fields obtained from the registration of few datasets. The results show that the performance of a CNN trained with synthetic data to segment AAAs from new scans is comparable to the one of a network trained with real images. This suggests that the proposed methodology may be applied to generate images and train a CNN to segment other types of aneurysms, reducing the burden of obtaining large annotated image databases.