ReeGAN: MRI image edge-preserving synthesis based on GANs trained with misaligned data

As a crucial medical examination technique, different modalities of magnetic resonance imaging (MRI) complement each other, offering multi-angle and multi-dimensional insights into the body's internal information. Therefore, research on MRI cross-modality conversion is of great significance, and many innovative techniques have been explored. However, most methods are trained on well-aligned data, and the impact of misaligned data has not received sufficient attention. Additionally, many methods focus on transforming the entire image and ignore crucial edge information. To address these challenges, we propose a generative adversarial network based on multi-feature fusion, which effectively preserves edge information while training on noisy data. Notably, we consider images with limited range random transformations as noisy labels and use an additional small auxiliary registration network to help the generator adapt to the noise distribution. Moreover, we inject auxiliary edge information to improve the quality of synthesized target modality images. Our goal is to find the best solution for cross-modality conversion. Comprehensive experiments and ablation studies demonstrate the effectiveness of the proposed method.

A spatial partial differential equation approach to addressing unit misalignments in Bayesian poisson space-time models

Spatial analyses using data from geographic areas that change shape and location over time, like US ZIP codes, produce biased results to the extent that unit misalignments are related to covariate effects. To address this issue, one method has incorporated a fixed effect measure of population shifts and a spatial structure as a block-diagonal neighborhood adjacency matrix within a Besag-York-Mollié (BYM) model. However, this approach assumes that spatial relationships among units change with time and precludes the assessment of temporal dynamic effects. Here, we assume that a continuous Gaussian random field underlies misaligned data and apply a stochastic partial differential equation (SPDE) approach to modeling area outcomes. We compare SPDE and BYM methods and show that both provide similar estimates of covariate effects. Importantly, we demonstrate that the SPDE approach can additionally identify autoregressive processes underlying the development of problematic health outcomes using data observed across Pennsylvania over 11 years.

Residential radon and cancer mortality in Galicia, Spain

Residential radon exposure is a serious public health concern, and as such appears in the recommendations of European Code Against Cancer. The objective of this study was to assess the association between residential radon levels and mortality due to different types of cancer, using misaligned data analysis techniques. Mortality data (observed cases) for each of the 313 Galician municipalities were drawn from the records of the National Statistics Institute for the study period (1999-2008). Expected cases were computed using Galician mortality rates for 14 types of malignant tumors as reference, with a total of 56,385 deaths due to the tumors analyzed. The effect estimates of indoor radon (3371 sampling points) were adjusted for sociodemographic variables, altitude, and arsenic topsoil levels (1069 sampling points), using spatial/geostatistical models fitted with stochastic partial differential equations and integrated nested Laplace approximations. These models are capable of processing misaligned data. The results showed a statistical association between indoor radon and lung, stomach and brain cancer in women in Galicia. Apart from lung cancer (relative risk (RR)=1.09), in which a twofold increase in radon exposure led to a 9% rise in mortality, the association was particularly relevant in stomach (RR=1.17) and brain cancer (RR=1.28). Further analytical epidemiologic studies are needed to confirm these results, and an assessment should be made of the advisability of implementing interventions targeting such exposure in higher-risk areas.

Diffusion methods for aligning medical datasets: location prediction in CT scan images

The purpose of this study is to introduce diffusion methods as a tool to label CT scan images according to their position in the human body. A comparative study of different methods based on a k-NN search is carried out and we propose a new, simple and efficient way of applying diffusion techniques that is able to give better location forecasts than methods that can be considered the current state-of-the-art.