HFRU-Net: High-Level Feature Fusion and Recalibration UNet for Automatic Liver and Tumor Segmentation in CT Images

•The deep learning approach is progressing day by day and has gained significant attention in medical image segmentation.•Medical imaging is a non-invasive technique to diagnose internal injuries and abnormalities in the human body.•Automatic liver and tumor segmentation from CT images is essential in many clinical procedures and treatment strategies planning related to hepatic anomalies.•Automatic segmentation of the liver and tumor is challenging due to its appearance and anatomical characteristics.•The proposed deep learning-based HFRU-Net uplifted segmentation performance by modifying the high-level and low-level features using feature fusion and multiscale feature extraction techniques.•The efficacy of the proposed method is demonstrated on the LiTS and 3DIRCADb dataset and compared performance with state-of-the-art methods. Automatic liver and tumor segmentation are essential steps to take decisive action in hepatic disease detection, deciding therapeutic planning, and post-treatment assessment. The computed tomography (CT) scan has become the choice of medical experts to diagnose hepatic anomalies. However, due to advancements in CT image acquisition protocol, CT scan data is growing and manual delineation of the liver and tumor from the CT volume becomes cumbersome and tedious for medical experts. Thus, the outcome becomes highly reliant on the operator's proficiency. Further, automatic liver and tumor segmentation from CT images is challenging due to complicated parenchyma, highly variable shape, and fewer voxel intensity variation among the liver, tumor, neighbouring organs, and discontinuity in liver boundaries. Recently deep learning (DL) exhibited extraordinary potential in medical image interpretation. Because of its effectiveness in performance advancement, the DL-based convolutional neural networks (CNN) gained significant interest in the medical realm. The proposed HFRU-Net is derived from the UNet architecture by modifying the skip pathways using local feature reconstruction and feature fusion mechanism that represents the detailed contextual information in the high-level features. Further, the fused features are adaptively recalibrated by learning the channel-wise interdependencies to acquire the prominent details of the modified high-level features using the squeeze-and-Excitation network (SENet). Also, in the bottleneck layer, we employed the atrous spatial pyramid pooling (ASPP) module to represent the multiscale features with dissimi