A two-stream decision fusion network for cervical pap-smear image classification tasks.

Deep learning, especially Convolution Neural Networks (CNNs), has demonstrated superior performance in image recognition and classification tasks. They make complex pattern recognition possible by extracting image features through layers of abstraction. However, despite the excellent performance of deep learning in general image classification, its limitations are becoming apparent in specific domains such as cervical cell medical image classification. This is because although the morphology of cervical cells varies between normal, diseased and cancerous, these differences are sometimes very small and difficult to capture. To solve this problem, we propose a two-stream feature fusion model comprising a manual feature branch, a deep feature branch, and a decision fusion module. Specifically, We process cervical cells through a modified DarkNet backbone network to extract deep features. In order to enhance the learning of deep features, we have devised scale convolution blocks to substitute the original convolution, termed Basic convolution blocks. The manual feature branch comprises a range of traditional features and is linked to a multilayer perceptron. Additionally, we design three decision feature channels trained from both manual and deep features to enhance the model performance in cervical cell classification. Our proposed model demonstrates superior performance when compared to state-of-the-art cervical cell classification models. We establish a 15-category 148762 cervical cytopathology image dataset (CCID). In addition, we additionally conducted experiments on the SIPaKMeD dataset. Numerous experiments show that our proposed model performs excellently compared to state-of-the-art classification models. The outcomes illustrate that our approach can significantly aid pathologists in accurately evaluating cervical smears.

An efficient Fusion-Purification Network for Cervical pap-smear image classification.

BACKGROUND AND OBJECTIVES: In cervical cell diagnostics, autonomous screening technology constitutes the foundation of automated diagnostic systems. Currently, numerous deep learning-based classification techniques have been successfully implemented in the analysis of cervical cell images, yielding favorable outcomes. Nevertheless, efficient discrimination of cervical cells continues to be challenging due to large intra-class and small inter-class variations. The key to dealing with this problem is to capture localized informative differences from cervical cell images and to represent discriminative features efficiently. Existing methods neglect the importance of global morphological information, resulting in inadequate feature representation capability. METHODS: To address this limitation, we propose a novel cervical cell classification model that focuses on purified fusion information. Specifically, we first integrate the detailed texture information and morphological structure features, named cervical pathology information fusion. Second, in order to enhance the discrimination of cervical cell features and address the data redundancy and bias inherent after fusion, we design a cervical purification bottleneck module. This model strikes a balance between leveraging purified features and facilitating high-efficiency discrimination. Furthermore, we intend to unveil a more intricate cervical cell dataset: Cervical Cytopathology Image Dataset (CCID). RESULTS: Extensive experiments on two real-world datasets show that our proposed model outperforms state-of-the-art cervical cell classification models. CONCLUSIONS: The results show that our method can well help pathologists to accurately evaluate cervical smears.

PATrans: Pixel-Adaptive Transformer for edge segmentation of cervical nuclei on small-scale datasets.

Transformer has shown excellent performance in various visual tasks, making its application in medicine an inevitable trend. Nevertheless, simply using transformer for small-scale cervical nuclei datasets will result in disastrous performance. Scarce nuclei pixels are not enough to compensate for the lack of CNNs-inherent intrinsic inductive biases, making transformer difficult to model local visual structures and deal with scale variations. Thus, we propose a Pixel Adaptive Transformer(PATrans) to improve the segmentation performance of nuclei edges on small datasets through adaptive pixel tuning. Specifically, to mitigate information loss resulting from mapping different patches into similar latent representations, Consecutive Pixel Patch (CPP) embeds rich multi-scale context into isolated image patches. In this way, it can provide intrinsic scale invariance for 1D input sequences to maintain semantic consistency, allowing the PATrans to establish long-range dependencies quickly. Futhermore, due to the existing handcrafted-attention is agnostic to the widely varying pixel distributions, the Pixel Adaptive Transformer Block (PATB) effectively models the relationships between different pixels across the entire feature map in a data-dependent manner, guided by the important regions. By collaboratively learning local features and global dependencies, PATrans can adaptively reduce the interference of irrelevant pixels. Extensive experiments demonstrate the superiority of our model on three datasets(Ours, ISBI, Herlev).

Interpretable thoracic pathologic prediction via learning group-disentangled representation.

Deep learning has brought a significant progress in medical image analysis. However, their lack of interpretability might bring high risk for wrong diagnosis with limited clinical knowledge embedding. In other words, we believe it's crucial for humans to interpret how deep learning work for medical analysis, thus appropriately adding knowledge constraints to correct the bias of wrong results. With such purpose, we propose Representation Group-Disentangling Network (RGD-Net) to explain the process of feature extraction and decision making inside deep learning framework, where we completely disentangle feature space of input X-ray images into independent feature groups, and each group would contribute to diagnose of a specific disease. Specifically, we first state problem definition for interpretable prediction with auto-encoder structure. Then, group-disentangled representations are extracted from input X-ray images with the proposed Group-Disentangle Module, which constructs semantic latent space by enforcing semantic consistency of attributes. Afterwards, adversarial constricts on mapping from features to diseases are proposed to prevent model collapse during training. Finally, a novel design of local tuning medical application is proposed based on RGB-Net, which is capable to aid clinicians for reasonable diagnosis. By conducting quantity of experiments on public datasets, RGD-Net have been superior to comparative studies by leveraging potential factors contributing to different diseases. We believe our work could bring interpretability in digging inherent patterns of deep learning on medical image analysis.

A Deep Generative Model with Multiscale Features Enabled Industrial Internet of Things for Intelligent Fault Diagnosis of Bearings.

Effective condition monitoring and fault diagnosis of bearings can not only maximize the life of rolling bearings and prevent unexpected shutdowns caused by equipment failures but also eliminate unnecessary costs and waste caused by excessive maintenance. However, the existing deep-learning-based bearing fault diagnosis models have the following defects. First of all, these models have a large demand for fault data. Second, the previous models only consider that single-scale features are generally less effective in diagnosing bearing faults. Therefore, we designed a bearing fault data collection platform based on the Industrial Internet of Things, which is used to collect bearing status data from sensors in real time and feed it back into the diagnostic model. On the basis of this platform, we propose a bearing fault diagnosis model based on deep generative models with multiscale features (DGMMFs) to solve the above problems. The DGMMF model is a multiclassification model, which can directly output the abnormal type of the bearing. Specifically, the DGMMF model uses 4 different variational autoencoder models to augment the bearing data and integrates features of different scales. Compared with single-scale features, these multiscale features contain more information and can perform better. Finally, we conducted a large number of related experiments on the real bearing fault datasets and verified the effectiveness of the DGMMF model using multiple evaluation metrics. The DGMMF model has achieved the highest value under all metrics, among which the value of precision is 0.926, the value of recall is 0.924, the value of accuracy is 0.926, and the value of F1 score is 0.925.

A decision-making method for reservoir operation schemes based on deep learning and whale optimization algorithm.

Reservoir operation is an important part of basin water resources management. The rational use of reservoir operation scheme can not only enhance the capacity of flood control and disaster reduction in the basin, but also improve the efficiency of water use and give full play to the comprehensive role the reservoir. The conventional decision-making method of reservoir operation scheme is computationally large, subjectivity and difficult to capture the nonlinear relationship. To solve these problems, this paper proposes a reservoir operation scheme decision-making model IWGAN-IWOA-CNN based on artificial intelligence and deep learning technology. In view of the lack of data in the original reservoir operation scheme and the limited improvement of data characteristics by the traditional data augmentation algorithm, an improved generative adversarial network algorithm (IWGAN) is proposed. IWGAN uses the loss function which integrates Wasserstein distance, gradient penalty and difference item, and dynamically adds random noise in the process of model training. The whale optimization algorithm is improved by introducing Logistic chaotic mapping to initialize population, non-linear convergence factor and adaptive weights, and Levy flight perturbation strategy. The improved whale optimization algorithm (IWOA) is used to optimize hyperparameters of convolutional neural networks (CNN), so as to obtain the best parameters for model prediction. The experimental results show that the data generated by IWGAN has certain representation ability and high quality; IWOA has faster convergence speed, higher convergence accuracy and better stability; IWGAN-IWOA-CNN model has higher prediction accuracy and reliability of scheme selection.