Jin Chen

Md Selim, Jie Zhang, Baowei Fei et al.

While remarkable advances have been made in Computed Tomography (CT), capturing CT images with non-standardized protocols causes low reproducibility regarding radiomic features, forming a barrier on CT image analysis in a large scale. RadiomicGAN is developed to effectively mitigate the discrepancy caused by using non-standard reconstruction kernels. RadiomicGAN consists of hybrid neural blocks including both pre-trained and trainable layers adopted to learn radiomic feature distributions efficiently. A novel training approach, called Dynamic Window-based Training, has been developed to smoothly transform the pre-trained model to the medical imaging domain. Model performance evaluated using 1401 radiomic features show that RadiomicGAN clearly outperforms the state-of-art image standardization models.

Lucas J. Liu, Hongwei Zhang, Jianzhong Di et al.

Many real-world Electronic Health Record (EHR) data contains a large proportion of missing values. Leaving substantial portion of missing information unaddressed usually causes significant bias, which leads to invalid conclusion to be drawn. On the other hand, training a machine learning model with a much smaller nearly-complete subset can drastically impact the reliability and accuracy of model inference. Data imputation algorithms that attempt to replace missing data with meaningful values inevitably increase the variability of effect estimates with increased missingness, making it unreliable for hypothesis validation. We propose a novel Ensemble-Learning for Missing Value (ELMV) framework, which introduces an effective approach to construct multiple subsets of the original EHR data with a much lower missing rate, as well as mobilizing a dedicated support set for the ensemble learning in the purpose of reducing the bias caused by substantial missing values. ELMV has been evaluated on a real-world healthcare data for critical feature identification as well as a batch of simulation data with different missing rates for outcome prediction. On both experiments, ELMV clearly outperforms conventional missing value imputation methods and ensemble learning models.

Kaihua Zhang, Tengpeng Li, Shiwen Shen et al.

Co-saliency detection aims to discover the common and salient foregrounds from a group of relevant images. For this task, we present a novel adaptive graph convolutional network with attention graph clustering (GCAGC). Three major contributions have been made, and are experimentally shown to have substantial practical merits. First, we propose a graph convolutional network design to extract information cues to characterize the intra- and interimage correspondence. Second, we develop an attention graph clustering algorithm to discriminate the common objects from all the salient foreground objects in an unsupervised fashion. Third, we present a unified framework with encoder-decoder structure to jointly train and optimize the graph convolutional network, attention graph cluster, and co-saliency detection decoder in an end-to-end manner. We evaluate our proposed GCAGC method on three cosaliency detection benchmark datasets (iCoseg, Cosal2015 and COCO-SEG). Our GCAGC method obtains significant improvements over the state-of-the-arts on most of them.

Jin Chen, Huihui Song, Kaihua Zhang et al.

Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP). To address this issue, we develop an effective spatiotemporal feature alignment network tailored to VSP, mainly including two key sub-networks: a multi-scale deformable convolutional alignment network (MDAN) and a bidirectional convolutional Long Short-Term Memory (Bi-ConvLSTM) network. The MDAN learns to align the features of the neighboring frames to the reference one in a coarse-to-fine manner, which can well handle various motions. Specifically, the MDAN owns a pyramidal feature hierarchy structure that first leverages deformable convolution (Dconv) to align the lower-resolution features across frames, and then aggregates the aligned features to align the higher-resolution features, progressively enhancing the features from top to bottom. The output of MDAN is then fed into the Bi-ConvLSTM for further enhancement, which captures the useful long-time temporal information along forward and backward timing directions to effectively guide attention orientation shift prediction under complex scene transformation. Finally, the enhanced features are decoded to generate the predicted saliency map. The proposed model is trained end-to-end without any intricate post processing. Extensive evaluations on four VSP benchmark datasets demonstrate that the proposed method achieves favorable performance against state-of-the-art methods. The source codes and all the results will be released.