Imaging biomarkers are important tools for the detection and characterization of cancers as well as for monitoring the response to therapy. “Whole-body” molecular imaging, in particular using 18F-fluorodeoxyglucose (FDG) – positron emission tomography (PET), has been proven useful in the evaluation and management of lymphoma patients. FDG-PET has evolved as a valuable biomarker in aggressive lymphomas, which is the current state-of-the-art imaging technique for response assessment at the end of treatment. Additionally, the prognostic value of “interim” (during treatment) or early PET has been well established in Hodgkin lymphoma and diffuse large B-cell lymphoma, which together account for more than 50% of all lymphomas. Worldwide clinical trials are ongoing to evaluate risk-adapted individualized treatment strategy based on interim PET results. Therefore, uniform and evidence-based guidelines for the interpretation are warranted. International Workshop on Interim PET in Lymphoma recently proposed a 5-point score method and so far the results of validation studies are promising. However, one could speculate that the risk of false-positive studies due to a non-specific inflammatory effect will be greater when patients receiving more toxic regimens and the usefulness of imaging biomarkers would vary for different lymphoma subtypes. Meanwhile, thanks to rapid technical development, whole-body functional magnetic resonance imaging (MRI) in particular diffusion-weighted MRI (DWI) reflecting cell density is now feasible in the clinical setting. Quantitative parameters derived from DWI reflecting cell density may provide complementary information to current state-of-the-art FDG-PET imaging reflecting quantitatively glucose metabolism and prove to be helpful in patient management. Pilot studies have shown the potential of whole-body DWI in lymphomas for staging and response assessment on 1.5Tesla MR system but larger-scaled prospective studies are required before this new imaging-based biomarker can ever be validated for routine clinical use. Besides, technical challenges remain especially when encountering higher-field clinical MR systems. Finally, a vast amount of information generated from whole-body parametric imaging data will require development of automated image analysis software, which may help in establishing a multi-parametric approach in characterizing residual lymphoma masses. Therefore, the present study aimed, through close France-Taiwan collaboration, to further optimize a whole-body DWI protocol on 3Tesla MR and/or new system combining 3Tesla MR and PET, to develop and validate an automated whole-body parametric image analysis algorithm, and to determine the added value of whole-body DWI to FDG-PET for the management of lymphoma patients.

Automatic image interpretation has been an active field of research for several years. In this large field, this project focuses on extracting high level information from images or video sequences, when the detection and recognition of structures can benefit from prior structural knowledge (such as spatial interactions). This is in particular the case in video sequences related to a specific context (sport events for instance), in medical imaging (using anatomical knowledge), or in aerial and satellite imaging (man made structures such as airports and towns for instance). The main objective of this project is thus to extract, analyze and interpret the content (including dynamic content) of visual information supports using structural knowledge and reasoning tools, in order to enrich the visual information with semantics. The breakthrough in this project, at the cross-road of logic-based knowledge representation and reasoning, uncertainty management and spatial reasoning, is to develop a unified lattice-based theory for spatial reasoning under uncertainty with the aim of semantic image interpretation. Based on the general framework of complete lattices and on mathematical morphology, we propose, by exploiting the power of Formal Concept Analysis tools, to extend Description Logics with non-monotonic reasoning tools and with a greater ability to represent complex structural knowledge such as those involved in scene understanding. Furthermore, this proposed new unified framework is intended to represent a priori knowledge in an operational way for image interpretation and to provide reasoning tools which combine imprecise and uncertain logical and numerical reasoning, hence addressing the challenging problem of bridging the gap between symbolic representations and real data. Another original contribution of this project is to introduce bipolarity to handle positive and negative information in the framework. Two other important scientific issues are also addressed in this proposal: dynamic knowledge representation and reasoning in order to consider knowledge as a matter of belief that can evolve both in time and space, and the study of the potential of graph based representations and grammars to model and to solve the computational problem of structural scene recognition in images. The originality of the proposal is not only to provide and develop theoretically this new qualitative and quantitative framework for image interpretation but also to apply and to evaluate it on real data.