Fragile X syndrome (FXS) and Creatine Transporter Deficiency (CTD) are the two most common causes of X-linked intellectual disability. Despite their etiological heterogeneity, FXS and CTD share common clinical traits, such as cognitive and language dysfunction, autistic-like features, motor abnormalities and seizures. Also, analogous pathological substrates, including alterations of brain energetics, concur to the pathophysiology of both FXS and CTD. There is no cure for these disorders and the efficacy study of potential treatments is hindered by the scarcity of unbiased, quantitative, non-invasive biomarkers for monitoring brain function. This is an important problem, because the phenotypic observation of behavioural endpoints is highly prone to subjective bias, and the use of objective readouts is crucial to evaluate the therapeutic response to new drugs. Since abnormal hemodynamic responses (HR) to sensory stimulation have been reported in preclinical studies of FXS and CTD, the objective of this project is to exploit optical imaging techniques to devise a non-invasive biomarker for these disorders. We will use imaging of intrinsic optical signals (IOS) in animal models and functional near-infrared spectroscopy (fNIRS) in patients: these non-invasive tools, indeed, allow detecting the changes of hemoglobin species and local blood flow inside the brain, providing an indirect measure of neuronal activity. Since the study of the visual phenotype is a paradigmatic model to evaluate cortical processing in neurodevelopmental disorders, we will: 1. test whether visually-evoked IOS responses can discriminate between mutants and controls in animal models of FXS and CTD, predicting phenotype severity and treatment rescue effects; 2. investigate cellular, extracellular and molecular mechanisms underlying altered IOS; 3. assess whether visually-evoked fNIRS signals classify patients and healthy controls, showing a correlation with clinical outcomes. Based on solid preliminary results, this project will set the background for the use of optical imaging as a novel analytic tool to facilitate diagnostic monitoring and to predict the response to potential therapeutic strategies in FXS and CTD. Since fNIRS is non-invasive and user-friendly, our ultimate goal is to improve the pipeline of therapeutic development in neurodevelopmental disorders, demonstrating the importance to implement HR measures in clinical trials.

Deep neural networks (DNNs) have achieved outstanding performance and broad implementation in tasks such as classification, denoising, segmentation and image synthesis, including in medical imaging. However, DNN-based models and algorithms have seen limited adaptation and development within the radiomics approach, which aims at improving diagnosis or prognosis through extraction of engineered image features (intensity, shape, textures) sometimes combined with other clinical expert-derived features. We hypothesize that, despite the potential of DNNs to improve oncological classification performances in radiomics, a lack of interpretability of such models prevents their broad utilization, performance, and generalizability. The INFORM consortium thus proposes to investigate explainable artificial intelligence (XAI) with a dual aim of i) building high performance DNN-based classifiers and ii) developing novel interpretability techniques for radiomics. First, in order to overcome the limited amount of data typically available in radiomics, we will investigate Monte Carlo simulations combined with generative adversarial networks (GAN) for producing large amounts of highly realistic simulated images to facilitate training DNNs. Second, we tackle the interpretability of DNN-based feature engineering and latent variable modeling with innovative developments of saliency maps and related approaches for relevance scores. Both supervised and unsupervised learning will be used to generate features, which can be interpreted in terms of input voxels, conventionally engineered, and expert-derived features. Third, we propose to build explainable AI models that incorporate both conventional radiomic and DNN-based features. By quantitatively understanding the interplay between expert-derived and DNN-based features, our models will be easier to understand and to translate into clinical use. Fourth, preliminary evaluation will be carried out with the help of clinical collaborators on predicting outcome of patients with lung, cervical and rectal cancer. These proposed DNN models, specifically developed to reveal their innerworkings, will leverage the robustness and trustworthiness of expert-derived features that medical practitioners are familiar with, while providing quantitative and visual feedback. Overall, our methodological research and clinical application will advance interpretability of feature engineering, generative models, and DNN classifiers with applications in radiomics and broad medical imaging. INFORM aims at maximizing the impact on the patient management of ML and DL techniques by developing novel methods to facilitate training of decision-aid systems for clinical treatment strategies optimization. The methodological approaches we propose in this specific area will play a major role in facilitating the acceptability of DL-based decision-aid systems relying on medical imaging for oncology. The proposed validated predictive models in various cancer types within the context of this project might subsequently be used to drive future prospective clinical studies in which patients could be offered alternative treatment strategies based on the results of these predictive models. Such a clinical and social potential is further enhanced by the public-private collaboration proposed in this project, where the developed methodologies will find their way in products. The multidisciplinarity of INFORM is key to meet the target challenges and achieve the proposed goals. All partners have their individual world-leading qualifications and additional scientific expertise providing all the prerequisites for the efficient implementation of INFORM’s approach. The successful implementation of this project will have a large and prolonged impact both in the Medical/Oncology and the Computing/Artificial Intelligence field of predictive radiomics, as well as the same methodology could be extended to other diagnostic and therapeutic medical applications.