Search

While Magnetic Resonance Imaging (MRI) has played an essential role in infant brain analysis, segmenting MRI into a number of tissues such as gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) is crucial and complex due to the extremely low intensity contrast between tissues at around 6-9 months of age as well as amplified noise, myelination, and incomplete volume. In this paper, we tackle those limitations by developing a new deep learning model, named DAM-AL, which contains two main contributions, i.e., dilated attention mechanism and hard-case attention loss. Our DAM-AL network is designed with skip block layers and atrous block convolution. It contains both channel-wise attention at high-level context features and spatial attention at low-level spatial structural features. Our attention loss consists of two terms corresponding to region information and hard samples attention. Our proposed DAM-AL has been evaluated on the infant brain iSeg 2017 dataset and the experiments have been conducted on both validation and testing sets. We have benchmarked DAM-AL on Dice coefficient and ASD metrics and compared it with state-of-the-art methods.

Polyps detection plays an important role in colonoscopy, cancer diagnosis, and early treatment. Many efforts have been made to improve the encoder-decoder framework using the global feature with an attention mechanism to enhance local features, helping to effectively segment diversity polyps. However, using only global information derived from the last encoder block leads to the loss of regional information from intermediate layers. Furthermore, defining the boundaries of some polyps is challenging because there is visual interference between the benign region and the polyps at the border. To address these problems, we propose two novel modules: the Cascading Context module (CCM) and the Attention Balance module (BAM), aiming to build an effective polyp segmentation model. Specifically, CCM combines the extracted regional information of the current layer and the lower layer, then pours it into the upper layer - fusing regional and global information analogous to a waterfall pattern. The BAM uses the prediction output of the adjacent lower layer as a guide map to implement the attention mechanism for the three regions separately: the background, polyp, and boundary curve. BAM enhances local context information when deriving features from the encoder block. Our proposed approach is evaluated on three benchmark datasets with six evaluation metrics for segmentation quality and gives competitive results compared to other advanced methods, for both accuracy and efficiency. Code is available at https://github.com/ntcongvn/CCBANet.

Traffic flow analysis is essential for intelligent transportation systems. In this paper, we introduce our Intelligent Traffic Analysis Software Kit (iTASK) to tackle three challenging problems: vehicle flow counting, vehicle re-identification, and abnormal event detection. For the first problem, we propose to real-time track vehicles moving along the desired direction in corresponding motion-of-interests (MOIs). For the second problem, we consider each vehicle as a document with multiple semantic words (i.e., vehicle attributes) and transform the given problem to classical document retrieval. For the last problem, we propose to forward and backward refine anomaly detection using GAN-based future prediction and backward tracking completely stalled vehicle or sudden-change direction, respectively. Experiments on the datasets of traffic flow analysis from AI City Challenge 2020 show our competitive results, namely, S1 score of 0.8297 for vehicle flow counting in Track 1, mAP score of 0.3882 for vehicle re-identification in Track 2, and S4 score of 0.9059 for anomaly detection in Track 4. All data and source code are publicly available on our project page. 1