COgnitive MIcroscope: A cognition-driven visual explorer for histopathology. Application to breast cancer grading. – MICO

Within the last decade, histopathology became widely accepted as a powerful exam for diagnosis and prognosis in mainstream diseases such as breast cancer. Currently, analysis of medical images in histopathology largely remains the work of human experts. For pathologists, this consists of hundreds of slides examined daily. Such a tedious manual work is often inconsistent and subjective. The cognitive microscope (MICO) aims at radically modifying the medical practices by proposing a new cognitive medical imaging environment able to improve reliability of decision making in histopathology. Our goal is to realize a generic, open-ended, semantic digital histology platform including a cognitive dimension. MICO combines visual perception, context, cognition and experience to reinforce a visual diagnosis assistance following an approach centered on user behavior. MICO will be a pervasive adaptation platform through learning mechanisms facilitating fast, incremental and continuous learning of explicit and implicit medical knowledge. MICO will be able to adapt to the context at different levels, including specific domain knowledge, information about the patient, partial interpretation of the visual content and subjective feedback from the user. A major issue plaguing current computer-aided diagnosis systems is the opaqueness of their mechanism, making the users untrustworthy and the results hard to validate. MICO aims at moving a step forward in medical practice by proposing the foundations of a new confluent cognitive medical imaging technology using context in an intelligent way. Our platform will be capable of cognitive functions ranging from active perception to symbolic description, from symbolic manipulation to communication, and from an ad hoc approach to a capitalization of previous experiences. MICO will behave in a cognitively consistent way with standard medical practice, following a uniform representation of image analysis, reasoning and context elements. This transparency throughout the whole process is exploited in order to permit confluence between the user and the platform, and medical validation of the results through technologies of content-based semantic image retrieval. The platform will be fully configurable and operable through a knowledge explorer allowing, in an incremental way, new medical knowledge capture, representation, use and discovery. In order to have a structural flexibility, MICO has a modular structure. In order to allow a semantic communication between the different modules, a middleware relying on semantic web technology will be used. The middleware will link together the production base, the domain knowledge base, the rule base, the user interface and the digitization device, while using available state-of-the-art technologies and domain ontologies. This distributed structure will enable easy development, incremental evolution, self-adaptation and remote applications. Breast cancer grading will be developed, tested and validated in the frame of project MICO in order to demonstrate the viability and relevance of the system. Being part of a long term process, initiated by the experience of the industrial and university partners, MICO will be an open system, easily deployable into several specific medical domains such as histopathology, cytopathology and hematology. Besides computer-aided diagnosis, the platform opens the way to a wide range of applications requiring manipulation of medical knowledge such as telepathology, datamining, teaching and education assistance.