For medical imaging tasks, it is a prevalent practice to have a multi-modality image dataset, as experts prefer using multiple medical devices to diagnose a disease. Each device can show different aspects of segmentation, which in our case, is magnetic resonance imaging (MRI) brain tumor segmentation. For such medical imaging tasks, researchers tend to combine all modalities as an input into the network for feature extraction, and neglect the complexity between different modalities. It is no longer novel to use an encoder-decoder-based model and residual connections to transfer information from high-resolution maps to lower-resolution maps in medical segmentation tasks. In this work, we propose a multimodal fusion network with bi-directional feature pyramid network (MM-BiFPN) using an individual encoder to extract the features of each of the four modalities (FLAIR, T1-weighted, T1-c, and T2-weighted) to focus on the exploitation of the complex relationships among the modalities. In addition, by using the bi-directional feature pyramid network (Bi-FPN) layer, we focus on the aggregation of multiple modalities to study the cross-modality relationship and multi-scale features. Our experiment was conducted on the brain segmentation challenge datasets, the MICCAI BraTS2018 and MICCAI BraTS2020 datasets. We also implemented two ablation studies on our model with different cross-scale modalities fusion networks, as well as a study on different modality settings to see the effect each modality brings in detecting tumor content. With missing modalities, our method achieves a comparable result, demonstrating that our method is robust for brain tumor segmentation.

Image forgery is easily manufactured for illegal acts such as spreading misleading information, which can have unfortunate consequences for society. In this work, we propose a Discrete Cosine Transformation (DCT) based multi-task learning network named FBI-Net, for forgery localization. Our proposed network adopts a fully convolutional encoder-decoder architecture, consisting of three encoders sharing parameters, a bridge attention module, and two output streams in the decoder. The encoder takes three inputs: RGB images and high-/low- DCT-filtered images. High-frequency components help learn object characteristics that improve CNN accuracy; low-frequency components are essential frequency information to keep most of the energy found in the typical DCT. Subsequently, Dilated Frequency Self-Attention Module, DFSAM in the bridge layer, is incorporated into the network to recalibrate the fused features and enhance the representation. Finally, in the decoder stage, region and edge information of the label are learned through multi-task learning to provide more extensive supervision for forged region localization; the edge stream will give a deeper understanding of features between forged and authentic images and help learn how to predict exquisite representations in images. Simultaneously, the auxiliary features from the pre-trained segmentation model are fused to separate the segmented background and objects, drawing the segmentation result of the dense region obtained. Extensive experiments show that our proposed FBI-Net outperforms existing forgery localization methods on six benchmark splicing and copy-move image datasets, CASIA TIDE v 1.0, CASIA TIDE v 2.0, Carvalho, Columbia, Coverage, IMD2020, achieving the best performance in an average of IoU of 70.99% and F1-score of 76.98% which is 9.79%, 9.82% higher than the previous method, respectively.

Background: There is a paucity of data on artificial intelligence-estimated biological electrocardiography (ECG) heart age (AI ECG-heart age) for predicting cardiovascular outcomes, distinct from the chronological age (CA). We developed a deep learning-based algorithm to estimate the AI ECG-heart age using standard 12-lead ECGs and evaluated whether it predicted mortality and cardiovascular outcomes.Methods: We trained and validated a deep neural network using the raw ECG digital data from 425,051 12-lead ECGs acquired between January 2006 and December 2021. The network performed a holdout test using a separate set of 97,058 ECGs. The deep neural network was trained to estimate the AI ECG-heart age [mean absolute error, 5.8 ± 3.9 years; R-squared, 0.7 (r = 0.84, p < 0.05)].Findings: In the Cox proportional hazards models, after adjusting for relevant comorbidity factors, the patients with an AI ECG-heart age of 6 years older than the CA had higher all-cause mortality (hazard ratio (HR) 1.60 [1.42–1.79]) and more major adverse cardiovascular events (MACEs) [HR: 1.91 (1.66–2.21)], whereas those under 6 years had an inverse relationship (HR: 0.82 [0.75–0.91] for all-cause mortality; HR: 0.78 [0.68–0.89] for MACEs). Additionally, the analysis of ECG features showed notable alterations in the PR interval, QRS duration, QT interval and corrected QT Interval (QTc) as the AI ECG-heart age increased.Conclusion: Biological heart age estimated by AI had a significant impact on mortality and MACEs, suggesting that the AI ECG-heart age facilitates primary prevention and health care for cardiovascular outcomes.