A novel dilated contextual attention module for breast cancer mitosis cell detection.

Background and object: Mitotic count (MC) is a critical histological parameter for accurately assessing the degree of invasiveness in breast cancer, holding significant clinical value for cancer treatment and prognosis. However, accurately identifying mitotic cells poses a challenge due to their morphological and size diversity. Objective: We propose a novel end-to-end deep-learning method for identifying mitotic cells in breast cancer pathological images, with the aim of enhancing the performance of recognizing mitotic cells. Methods: We introduced the Dilated Cascading Network (DilCasNet) composed of detection and classification stages. To enhance the model's ability to capture distant feature dependencies in mitotic cells, we devised a novel Dilated Contextual Attention Module (DiCoA) that utilizes sparse global attention during the detection. For reclassifying mitotic cell areas localized in the detection stage, we integrate the EfficientNet-B7 and VGG16 pre-trained models (InPreMo) in the classification step. Results: Based on the canine mammary carcinoma (CMC) mitosis dataset, DilCasNet demonstrates superior overall performance compared to the benchmark model. The specific metrics of the model's performance are as follows: F1 score of 82.9%, Precision of 82.6%, and Recall of 83.2%. With the incorporation of the DiCoA attention module, the model exhibited an improvement of over 3.5% in the F1 during the detection stage. Conclusion: The DilCasNet achieved a favorable detection performance of mitotic cells in breast cancer and provides a solution for detecting mitotic cells in pathological images of other cancers.

Automated inter-patient arrhythmia classification with dual attention neural network.

BACKGROUND AND OBJECTIVES: Arrhythmia classification based on electrocardiograms (ECG) can enhance clinical diagnostic efficiency. However, due to the significant differences in the number of different categories of heartbeats, the performance of classes with fewer samples in arrhythmia classification have not met expectations under the inter-patient paradigm. This paper aims to mitigate the adverse effects of category imbalance and improve arrhythmia classification performance. METHODS: We constructed a novel dual attention hybrid network (DA-Net) for arrhythmia classification under sample imbalance, based on modified convolutional networks with channel attention (MCC-Net) and sequence-to-sequence network with global attention (Seq2Seq). The refined local features of the input heartbeat are first extracted by MCC-Net and then sent to Seq2Seq for further feature fusion. By applying local and global attention in the feature extraction and fusion parts, respectively, the method fully fuses low-level feature details and high-level context information and enhances the ability to extract discriminative features. RESULTS: Based on the MIT-BIH arrhythmia database, under the inter-patient paradigm without any data augmentation methods, the proposed method achieved 99.98% accuracy (ACC) for five categories. The various performance indicators are as follows: Class N: sensitivity (SEN) = 99.96%, specificity (SPEC) = 99.93%, positive predictive value (PPV) = 99.99%; Class S: SEN = 99.67%, SPEC = 99.98%, PPV = 99.56%; Class V: SEN = 100%, SPEC = 99.99%, PPV = 99.91%; Class F: SEN = 100%, PPV = 99.98%, SPEC = 97.17%. In further experiments simulating extreme cases, the model still achieved ACC of 99.54% and 98.91% in the three-category and five-category categories when the training sample size was much smaller than the test sample. CONCLUSIONS: Without any data augmentation methods, the proposed model not only alleviates the negative impact of class imbalance and achieves excellent performance in all categories but also provides a new approach for dealing with class imbalance in arrhythmia classification. Additionally, our method demonstrates potential in conditions with fewer samples.

Rethinking the Dilated Encoder in TE-YOLOF: An Approach Based on Attention Mechanism to Improve Performance for Blood Cell Detection.

Blood cell detection is an essential branch of microscopic imaging for disease diagnosis. TE-YOLOF is an effective model for blood cell detection, and was recently found to have an outstanding trade-off between accuracy and model complexity. However, there is a lack of understanding of whether the dilated encoder in TE-YOLOF works well for blood cell detection. To address this issue, we perform a thorough experimental analysis and find the interesting fact that the dilated encoder is not necessary for TE-YOLOF to perform the blood cell detection task. For the purpose of increasing performance on blood cell detection, in this research, we use the attention mechanism to dominate the dilated encoder place in TE-YOLOF and find that the attention mechanism is effective to address this problem. Based upon these findings, we propose a novel approach, named Enhanced Channel Attention Module (ECAM), based on attention mechanism to achieve precision improvement with less growth on model complexity. Furthermore, we examine the proposed ECAM method compared with other tip-top attention mechanisms and find that the proposed attention method is more effective on blood cell detection task. We incorporate the spatial attention mechanism in CBAM with our ECAM to form a new module, which is named Enhanced-CBAM. We propose a new network named Enhanced Channel Attention Network (ENCANet) based upon Enhanced-CBAM to perform blood cell detection on BCCD dataset. This network can increase the accuracy to 90.3 AP while the parameter is only 6.5 M. Our ENCANet is also effective for conducting cross-domain blood cell detection experiments.