Contrast phase recognition in liver computer tomography using deep learning.

Hepatocellular carcinoma (HCC) has become the 4th leading cause of cancer-related deaths, with high social, economical and health implications. Imaging techniques such as multiphase computed tomography (CT) have been successfully used for diagnosis of liver tumors such as HCC in a feasible and accurate way and its interpretation relies mainly on comparing the appearance of the lesions in the different contrast phases of the exam. Recently, some researchers have been dedicated to the development of tools based on machine learning (ML) algorithms, especially by deep learning techniques, to improve the diagnosis of liver lesions in imaging exams. However, the lack of standardization in the naming of the CT contrast phases in the DICOM metadata is a problem for real-life deployment of machine learning tools. Therefore, it is important to correctly identify the exam phase based only on the image and not on the exam metadata, which is unreliable. Motivated by this problem, we successfully created an annotation platform and implemented a convolutional neural network (CNN) to automatically identify the CT scan phases in the HCFMUSP database in the city of São Paulo, Brazil. We improved this algorithm with hyperparameter tuning and evaluated it with cross validation methods. Comparing its predictions with the radiologists annotation, it achieved an accuracy of 94.6%, 98% and 100% in the testing dataset for the slice, volume and exam evaluation, respectively.

A method to produce evolving functional connectivity maps during the course of an fMRI experiment using wavelet-based time-varying Granger causality.

Functional magnetic resonance imaging (fMRI) is widely used to identify neural correlates of cognitive tasks. However, the analysis of functional connectivity is crucial to understanding neural dynamics. Although many studies of cerebral circuitry have revealed adaptative behavior, which can change during the course of the experiment, most of contemporary connectivity studies are based on correlational analysis or structural equations analysis, assuming a time-invariant connectivity structure. In this paper, a novel method of continuous time-varying connectivity analysis is proposed, based on the wavelet expansion of functions and vector autoregressive model (wavelet dynamic vector autoregressive-DVAR). The model also allows identification of the direction of information flow between brain areas, extending the Granger causality concept to locally stationary processes. Simulation results show a good performance of this approach even using short time intervals. The application of this new approach is illustrated with fMRI data from a simple AB motor task experiment.