Enabling uncertainty estimation in neural networks through weight perturbation for improved Alzheimer's disease classification.

Background: The willingness to trust predictions formulated by automatic algorithms is key in a wide range of domains. However, a vast number of deep architectures are only able to formulate predictions without associated uncertainty. Purpose: In this study, we propose a method to convert a standard neural network into a Bayesian neural network and estimate the variability of predictions by sampling different networks similar to the original one at each forward pass. Methods: We combine our method with a tunable rejection-based approach that employs only the fraction of the data, i.e., the share that the model can classify with an uncertainty below a user-set threshold. We test our model in a large cohort of brain images from patients with Alzheimer's disease and healthy controls, discriminating the former and latter classes based on morphometric images exclusively. Results: We demonstrate how combining estimated uncertainty with a rejection-based approach increases classification accuracy from 0.86 to 0.95 while retaining 75% of the test set. In addition, the model can select the cases to be recommended for, e.g., expert human evaluation due to excessive uncertainty. Importantly, our framework circumvents additional workload during the training phase by using our network "turned into Bayesian" to implicitly investigate the loss landscape in the neighborhood of each test sample in order to determine the reliability of the predictions. Conclusion: We believe that being able to estimate the uncertainty of a prediction, along with tools that can modulate the behavior of the network to a degree of confidence that the user is informed about (and comfortable with), can represent a crucial step in the direction of user compliance and easier integration of deep learning tools into everyday tasks currently performed by human operators.

Effects of transcranial magnetic stimulation on reactive response inhibition.

Reactive response inhibition cancels impending actions to enable adaptive behavior in ever-changing environments and has wide neuropsychiatric implications. A canonical paradigm to measure the covert inhibition latency is the stop-signal task (SST). To probe the cortico-subcortical network underlying motor inhibition, transcranial magnetic stimulation (TMS) has been applied over central nodes to modulate SST performance, especially to the right inferior frontal cortex and the presupplementary motor area. Since the vast parameter spaces of SST and TMS enabled diverse implementations, the insights delivered by emerging TMS-SST studies remain inconclusive. Therefore, a systematic review was conducted to account for variability and synthesize converging evidence. Results indicate certain protocol specificity through the consistent perturbations induced by online TMS, whereas offline protocols show paradoxical effects on different target regions besides numerous null effects. Ancillary neuroimaging findings have verified and dissociated the underpinning network dynamics. Sources of heterogeneity in designs and risk of bias are highlighted. Finally, we outline best-practice recommendations to bridge methodological gaps and subserve the validity as well as replicability of future work.

Beyond multilayer perceptrons: Investigating complex topologies in neural networks.

This study delves into the crucial aspect of network topology in artificial neural networks (NNs) and its impact on model performance. Addressing the need to comprehend how network structures influence learning capabilities, the research contrasts traditional multilayer perceptrons (MLPs) with models built on various complex topologies using novel network generation techniques. Drawing insights from synthetic datasets, the study reveals the remarkable accuracy of complex NNs, particularly in high-difficulty scenarios, outperforming MLPs. Our exploration extends to real-world datasets, highlighting the task-specific nature of optimal network topologies and unveiling trade-offs, including increased computational demands and reduced robustness to graph damage in complex NNs compared to MLPs. This research underscores the pivotal role of complex topologies in addressing challenging learning tasks. However, it also signals the necessity for deeper insights into the complex interplay among topological attributes influencing NN performance. By shedding light on the advantages and limitations of complex topologies, this study provides valuable guidance for practitioners and paves the way for future endeavors to design more efficient and adaptable neural architectures across various applications.

The age-specific comorbidity burden of mild cognitive impairment: a US claims database study.

BACKGROUND: Identifying individuals with mild cognitive impairment (MCI) who are likely to progress to Alzheimer's disease and related dementia disorders (ADRD) would facilitate the development of individualized prevention plans. We investigated the association between MCI and comorbidities of ADRD. We examined the predictive potential of these comorbidities for MCI risk determination using a machine learning algorithm. METHODS: Using a retrospective matched case-control design, 5185 MCI and 15,555 non-MCI individuals aged ≥50 years were identified from MarketScan databases. Predictive models included ADRD comorbidities, age, and sex. RESULTS: Associations between 25 ADRD comorbidities and MCI were significant but weakened with increasing age groups. The odds ratios (MCI vs non-MCI) in 50-64, 65-79, and ≥ 80 years, respectively, for depression (4.4, 3.1, 2.9) and stroke/transient ischemic attack (6.4, 3.0, 2.1). The predictive potential decreased with older age groups, with ROC-AUCs 0.75, 0.70, and 0.66 respectively. Certain comorbidities were age-specific predictors. CONCLUSIONS: The comorbidity burden of MCI relative to non-MCI is age-dependent. A model based on comorbidities alone predicted an MCI diagnosis with reasonable accuracy.

Dynomics: A Novel and Promising Approach for Improved Breast Cancer Prognosis Prediction.

Traditional imaging techniques for breast cancer (BC) diagnosis and prediction, such as X-rays and magnetic resonance imaging (MRI), demonstrate varying sensitivity and specificity due to clinical and technological factors. Consequently, positron emission tomography (PET), capable of detecting abnormal metabolic activity, has emerged as a more effective tool, providing critical quantitative and qualitative tumor-related metabolic information. This study leverages a public clinical dataset of dynamic 18F-Fluorothymidine (FLT) PET scans from BC patients, extending conventional static radiomics methods to the time domain-termed as 'Dynomics'. Radiomic features were extracted from both static and dynamic PET images on lesion and reference tissue masks. The extracted features were used to train an XGBoost model for classifying tumor versus reference tissue and complete versus partial responders to neoadjuvant chemotherapy. The results underscored the superiority of dynamic and static radiomics over standard PET imaging, achieving accuracy of 94% in tumor tissue classification. Notably, in predicting BC prognosis, dynomics delivered the highest performance, achieving accuracy of 86%, thereby outperforming both static radiomics and standard PET data. This study illustrates the enhanced clinical utility of dynomics in yielding more precise and reliable information for BC diagnosis and prognosis, paving the way for improved treatment strategies.

Application of nnU-Net for Automatic Segmentation of Lung Lesions on CT Images and Its Implication for Radiomic Models.

Radiomics investigates the predictive role of quantitative parameters calculated from radiological images. In oncology, tumour segmentation constitutes a crucial step of the radiomic workflow. Manual segmentation is time-consuming and prone to inter-observer variability. In this study, a state-of-the-art deep-learning network for automatic segmentation (nnU-Net) was applied to computed tomography images of lung tumour patients, and its impact on the performance of survival radiomic models was assessed. In total, 899 patients were included, from two proprietary and one public datasets. Different network architectures (2D, 3D) were trained and tested on different combinations of the datasets. Automatic segmentations were compared to reference manual segmentations performed by physicians using the DICE similarity coefficient. Subsequently, the accuracy of radiomic models for survival classification based on either manual or automatic segmentations were compared, considering both hand-crafted and deep-learning features. The best agreement between automatic and manual contours (DICE = 0.78 ± 0.12) was achieved averaging 2D and 3D predictions and applying customised post-processing. The accuracy of the survival classifier (ranging between 0.65 and 0.78) was not statistically different when using manual versus automatic contours, both with hand-crafted and deep features. These results support the promising role nnU-Net can play in automatic segmentation, accelerating the radiomic workflow without impairing the models' accuracy. Further investigations on different clinical endpoints and populations are encouraged to confirm and generalise these findings.

Physically constrained neural networks for inferring physiological system models.

Systems biology and systems neurophysiology in particular have recently emerged as powerful tools for a number of key applications in the biomedical sciences. Nevertheless, such models are often based on complex combinations of multiscale (and possibly multiphysics) strategies that require ad hoc computational strategies and pose extremely high computational demands. Recent developments in the field of deep neural networks have demonstrated the possibility of formulating nonlinear, universal approximators to estimate solutions to highly nonlinear and complex problems with significant speed and accuracy advantages in comparison with traditional models. After synthetic data validation, we use so-called physically constrained neural networks (PINN) to simultaneously solve the biologically plausible Hodgkin-Huxley model and infer its parameters and hidden time-courses from real data under both variable and constant current stimulation, demonstrating extremely low variability across spikes and faithful signal reconstruction. The parameter ranges we obtain are also compatible with prior knowledge. We demonstrate that detailed biological knowledge can be provided to a neural network, making it able to fit complex dynamics over both simulated and real data.

Spatiotemporal learning of dynamic positron emission tomography data improves diagnostic accuracy in breast cancer.

Positron emission tomography (PET) can reveal metabolic activity in a voxelwise manner. PET analysis is commonly performed in a static manner by analyzing the standardized uptake value (SUV) obtained from the plateau region of PET acquisitions. A dynamic PET acquisition can provide a map of the spatiotemporal concentration of the tracer in vivo, hence conveying information about radiotracer delivery to tissue, its interaction with the target and washout. Therefore, tissue-specific biochemical properties are embedded in the shape of time activity curves (TACs), which are generally used for kinetic analysis. Conventionally, TACs are employed along with information about blood plasma activity concentration, i.e., the arterial input function (AIF), and specific compartmental models to obtain a full quantitative analysis of PET data. The main drawback of this approach is the need for invasive procedures requiring arterial blood sample collection during the whole PET scan. In this paper, we address the challenge of improving PET diagnostic accuracy through an alternative approach based on the analysis of time signal intensity patterns. Specifically, we demonstrate the diagnostic potential of tissue TACs provided by dynamic PET acquisition using various deep learning models. Our framework is shown to outperform the discriminative potential of classical SUV analysis, hence paving the way for more accurate PET-based lesion discrimination without additional acquisition time or invasive procedures. Clinical Relevance- The diagnostic accuracy of dynamic PET data exploited by deep-learning based time signal intensity pattern analysis is superior to that of static SUV imaging.

Motor and higher-order functions topography of the human dentate nuclei identified with tractography and clustering methods.

Deep gray matter nuclei are the synaptic relays, responsible to route signals between specific brain areas. Dentate nuclei (DNs) represent the main output channel of the cerebellum and yet are often unexplored especially in humans. We developed a multimodal MRI approach to identify DNs topography on the basis of their connectivity as well as their microstructural features. Based on results, we defined DN parcellations deputed to motor and to higher-order functions in humans in vivo. Whole-brain probabilistic tractography was performed on 25 healthy subjects from the Human Connectome Project to infer DN parcellations based on their connectivity with either the cerebral or the cerebellar cortex, in turn. A third DN atlas was created inputting microstructural diffusion-derived metrics in an unsupervised fuzzy c-means classification algorithm. All analyses were performed in native space, with probability atlas maps generated in standard space. Cerebellar lobule-specific connectivity identified one motor parcellation, accounting for about 30% of the DN volume, and two non-motor parcellations, one cognitive and one sensory, which occupied the remaining volume. The other two approaches provided overlapping results in terms of geometrical distribution with those identified with cerebellar lobule-specific connectivity, although with some differences in volumes. A gender effect was observed with respect to motor areas and higher-order function representations. This is the first study that indicates that more than half of the DN volumes is involved in non-motor functions and that connectivity-based and microstructure-based atlases provide complementary information. These results represent a step-ahead for the interpretation of pathological conditions involving cerebro-cerebellar circuits.