MGCBFormer: The multiscale grid-prior and class-inter boundary-aware transformer for polyp segmentation.

The polyp segmentation technology based on deep learning could better and faster help doctors diagnose the polyps in the intestinal wall, which are predecessors of colorectal cancer. Mainstream polyp segmentation methods are implemented under full supervision. For these methods, expensive and precious pixel-level labels couldn't be utilized sufficiently, and it's a deviation direction to strengthen the feature expression only using the more powerful backbone network instead of fully mining existing polyp target information. To address the situation, the multiscale grid-prior and class-inter boundary-aware transformer (MGCBFormer) is proposed. MGCBFormer is composed of highly interpretable components: 1) the multiscale grid-prior and nested channel attention block (MGNAB) for seeking the optimal feature expression, 2) the class-inter boundary-aware block (CBB) for focusing on the foreground boundary and fully inhibiting the background boundary by combining the boundary preprocessing strategy, 3) reasonable deep supervision branches and noise filters called the global double-axis association coupler (GDAC). Numerous persuasive experiments are conducted on five public polyp datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, CVC-300, and ETIS-LaribPolypDB) comparing with twelve methods of polyp segmentation, and demonstrate the superior predictive performance and generalization ability of MGCBFormer over the state-of-the-art polyp segmentation methods.

Peripheral Blood Leukocyte Detection Based on an Improved Detection Transformer Algorithm.

The combination of a blood cell analyzer and artificial microscopy to detect white blood cells is used in hospitals. Blood cell analyzers not only have large throughput, but they also cannot detect cell morphology; although artificial microscopy has high accuracy, it is inefficient and prone to missed detections. In view of the above problems, a method based on Fourier ptychographic microscopy (FPM) and deep learning to detect peripheral blood leukocytes is proposed in this paper. Firstly, high-resolution and wide-field microscopic images of human peripheral blood cells are obtained using the FPM system, and the cell image data are enhanced with DCGANs (deep convolution generative adversarial networks) to construct datasets for performance evaluation. Then, an improved DETR (detection transformer) algorithm is proposed to improve the detection accuracy of small white blood cell targets; that is, the residual module Conv Block in the feature extraction part of the DETR network is improved to reduce the problem of information loss caused by downsampling. Finally, CIOU (complete intersection over union) is introduced as the bounding box loss function, which avoids the problem that GIOU (generalized intersection over union) is difficult to optimize when the two boxes are far away and the convergence speed is faster. The experimental results show that the mAP of the improved DETR algorithm in the detection of human peripheral white blood cells is 0.936. In addition, this algorithm is compared with other convolutional neural networks in terms of average accuracy, parameters, and number of inference frames per second, which verifies the feasibility of this method in microscopic medical image detection.

MFEFNet: Multi-scale feature enhancement and Fusion Network for polyp segmentation.

The polyp segmentation technology based on computer-aided can effectively avoid the deterioration of polyps and prevent colorectal cancer. To segment the polyp target precisely, the Multi-Scale Feature Enhancement and Fusion Network (MFEFNet) is proposed. First of all, to balance the network's predictive ability and complexity, ResNet50 is designed as the backbone network, and the Shift Channel Block (SCB) is used to unify the spatial location of feature mappings and emphasize local information. Secondly, to further improve the network's feature-extracting ability, the Feature Enhancement Block (FEB) is added, which decouples features, reinforces features by multiple perspectives and reconstructs features. Meanwhile, to weaken the semantic gap in the feature fusion process, we propose strong associated couplers, the Multi-Scale Feature Fusion Block (MSFFB) and the Reducing Difference Block (RDB), which are mainly composed of multiple cross-complementary information interaction modes and reinforce the long-distance dependence between features. Finally, to further refine local regions, the Polarized Self-Attention (PSA) and the Balancing Attention Module (BAM) are introduced for better exploration of detailed information between foreground and background boundaries. Experiments have been conducted under five benchmark datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ClinicDB, CVC300 and CVC-ColonDB) and compared with state-of-the-art polyp segmentation algorithms. The experimental result shows that the proposed network improves Dice and mean intersection over union (mIoU) by an average score of 3.4% and 4%, respectively. Therefore, extensive experiments demonstrate that the proposed network performs favorably against more than a dozen state-of-the-art methods on five popular polyp segmentation benchmarks.