Differentiation of Alzheimer Conditions in MR Brain Images Using a Single Inception Module Network

In this study, an attempt has been made to differentiate Alzheimer’s Disease (AD) stages in structural Magnetic Resonance (MR) images using single inception module network. For this, T1-weighted MR brain images of AD, mild cognitive impairment and Normal Controls (NC) are obtained from a public database. From the images, significant features are extracted and classified using an inception module network. The performance of the model is computed and analyzed for different input image sizes. Results show that the single inception module is able to classify AD stages using MR images. The end-to-end network differentiates AD from NC with 85% precision. The model is found to be effective for varied sizes of input images. Since the proposed approach is able to categorize AD stages, single inception module networks could be used for the automated AD diagnosis with minimum medical expertise.

NMN-VD: A Neural Module Network for Visual Dialog

Visual dialog demonstrates several important aspects of multimodal artificial intelligence; however, it is hindered by visual grounding and visual coreference resolution problems. To overcome these problems, we propose the novel neural module network for visual dialog (NMN-VD). NMN-VD is an efficient question-customized modular network model that combines only the modules required for deciding answers after analyzing input questions. In particular, the model includes a Refer module that effectively finds the visual area indicated by a pronoun using a reference pool to solve a visual coreference resolution problem, which is an important challenge in visual dialog. In addition, the proposed NMN-VD model includes a method for distinguishing and handling impersonal pronouns that do not require visual coreference resolution from general pronouns. Furthermore, a new Compare module that effectively handles comparison questions found in visual dialogs is included in the model, as well as a Find module that applies a triple-attention mechanism to solve visual grounding problems between the question and the image. The results of various experiments conducted using a set of large-scale benchmark data verify the efficacy and high performance of our proposed NMN-VD model.

MNBDR: A Module Network Based Method for Drug Repositioning

Drug repurposing/repositioning, which aims to find novel indications for existing drugs, contributes to reducing the time and cost for drug development. For the recent decade, gene expression profiles of drug stimulating samples have been successfully used in drug repurposing. However, most of the existing methods neglect the gene modules and the interactions among the modules, although the cross-talks among pathways are common in drug response. It is essential to develop a method that utilizes the cross-talks information to predict the reliable candidate associations. In this study, we developed MNBDR (Module Network Based Drug Repositioning), a novel method that based on module network to screen drugs. It integrated protein–protein interactions and gene expression profile of human, to predict drug candidates for diseases. Specifically, the MNBDR mined dense modules through protein–protein interaction (PPI) network and constructed a module network to reveal cross-talks among modules. Then, together with the module network, based on existing gene expression data set of drug stimulation samples and disease samples, we used random walk algorithms to capture essential modules in disease development and proposed a new indicator to screen potential drugs for a given disease. Results showed MNBDR could provide better performance than popular methods. Moreover, functional analysis of the essential modules in the network indicated our method could reveal biological mechanism in drug response.