Diagnosis of focal liver lesions from ultrasound images using a pretrained residual neural network.

OBJECTIVE: This study aims to develop a ResNet50-based deep learning model for focal liver lesion (FLL) classification in ultrasound images, comparing its performance with other models and prior research. METHODOLOGY: We retrospectively collected 581 ultrasound images from the Chulabhorn Hospital's HCC surveillance and screening project (2010-2018). The dataset comprised five classes: non-FLL, hepatic cyst (Cyst), hemangioma (HMG), focal fatty sparing (FFS), and hepatocellular carcinoma (HCC). We conducted 5-fold cross-validation after random dataset partitioning, enhancing training data with data augmentation. Our models used modified pre-trained ResNet50, GGN, ResNet18, and VGG16 architectures. Model performance, assessed via confusion matrices for sensitivity, specificity, and accuracy, was compared across models and with prior studies. RESULTS: ResNet50 outperformed other models, achieving a 5-fold cross-validation accuracy of 87 ± 2.2%. While VGG16 showed similar performance, it exhibited higher uncertainty. In the testing phase, the pretrained ResNet50 excelled in classifying non-FLL, cysts, and FFS. To compare with other research, ResNet50 surpassed the prior methods like two-layered feed-forward neural networks (FFNN) and CNN+ReLU in FLL diagnosis. CONCLUSION: ResNet50 exhibited good performance in FLL diagnosis, especially for HCC classification, suggesting its potential for developing computer-aided FLL diagnosis. However, further refinement is required for HCC and HMG classification in future studies.

Multimodal deep neural decoding reveals highly resolved spatiotemporal profile of visual object representation in humans.

Perception and categorization of objects in a visual scene are essential to grasp the surrounding situation. Recently, neural decoding schemes, such as machine learning in functional magnetic resonance imaging (fMRI), has been employed to elucidate the underlying neural mechanisms. However, it remains unclear as to how spatially distributed brain regions temporally represent visual object categories and sub-categories. One promising strategy to address this issue is neural decoding with concurrently obtained neural response data of high spatial and temporal resolution. In this study, we explored the spatial and temporal organization of visual object representations using concurrent fMRI and electroencephalography (EEG), combined with neural decoding using deep neural networks (DNNs). We hypothesized that neural decoding by multimodal neural data with DNN would show high classification performance in visual object categorization (faces or non-face objects) and sub-categorization within faces and objects. Visualization of the fMRI DNN was more sensitive than that in the univariate approach and revealed that visual categorization occurred in brain-wide regions. Interestingly, the EEG DNN valued the earlier phase of neural responses for categorization and the later phase of neural responses for sub-categorization. Combination of the two DNNs improved the classification performance for both categorization and sub-categorization compared with fMRI DNN or EEG DNN alone. These deep learning-based results demonstrate a categorization principle in which visual objects are represented in a spatially organized and coarse-to-fine manner, and provide strong evidence of the ability of multimodal deep learning to uncover spatiotemporal neural machinery in sensory processing.

Large-scale network integration in the human brain tracks temporal fluctuations in memory encoding performance.

Although activation/deactivation of specific brain regions has been shown to be predictive of successful memory encoding, the relationship between time-varying large-scale brain networks and fluctuations of memory encoding performance remains unclear. Here, we investigated time-varying functional connectivity patterns across the human brain in periods of 30-40 s, which have recently been implicated in various cognitive functions. During functional magnetic resonance imaging, participants performed a memory encoding task, and their performance was assessed with a subsequent surprise memory test. A graph analysis of functional connectivity patterns revealed that increased integration of the subcortical, default-mode, salience, and visual subnetworks with other subnetworks is a hallmark of successful memory encoding. Moreover, multivariate analysis using the graph metrics of integration reliably classified the brain network states into the period of high (vs. low) memory encoding performance. Our findings suggest that a diverse set of brain systems dynamically interact to support successful memory encoding.

Visual perceptual training reconfigures post-task resting-state functional connectivity with a feature-representation region.

The neural mechanisms underlying visual perceptual learning (VPL) have typically been studied by examining changes in task-related brain activation after training. However, the relationship between post-task "offline" processes and VPL remains unclear. The present study examined this question by obtaining resting-state functional magnetic resonance imaging (fMRI) scans of human brains before and after a task-fMRI session involving visual perceptual training. During the task-fMRI session, participants performed a motion coherence discrimination task in which they judged the direction of moving dots with a coherence level that varied between trials (20, 40, and 80%). We found that stimulus-induced activation increased with motion coherence in the middle temporal cortex (MT+), a feature-specific region representing visual motion. On the other hand, stimulus-induced activation decreased with motion coherence in the dorsal anterior cingulate cortex (dACC) and bilateral insula, regions involved in decision making under perceptual ambiguity. Moreover, by comparing pre-task and post-task rest periods, we revealed that resting-state functional connectivity (rs-FC) with the MT+ was significantly increased after training in widespread cortical regions including the bilateral sensorimotor and temporal cortices. In contrast, rs-FC with the MT+ was significantly decreased in subcortical regions including the thalamus and putamen. Importantly, the training-induced change in rs-FC was observed only with the MT+, but not with the dACC or insula. Thus, our findings suggest that perceptual training induces plastic changes in offline functional connectivity specifically in brain regions representing the trained visual feature, emphasising the distinct roles of feature-representation regions and decision-related regions in VPL.