Triple ANet: Adaptive Abnormal-aware Attention Network for WCE Image Classification

Automated classification of ulcerative lesions in small intestine using densenet with channel attention and residual dilated blocks

Objective. Ulceration of the small intestine, which has a high incidence, includes Crohn's disease (CD), intestinal tuberculosis (ITB), primary small intestinal lymphoma (PSIL), cryptogenic multifocal ulcerous stenosing enteritis (CMUSE), and non-specific ulcer (NSU). However, the ulceration morphology can easily be misdiagnosed through enteroscopy.Approach. In this study, DRCA-DenseNet169, which is based on DenseNet169, with residual dilated blocks and a channel attention block, is proposed to identify CD, ITB, PSIL, CMUSE, and NSU intelligently. In addition, a novel loss function that incorporates dynamic weights is designed to enhance the precision of imbalanced datasets with limited samples. DRCA-Densenet169 was evaluated using 10883 enteroscopy images, including 5375 ulcer images and 5508 normal images, which were obtained from the Shanghai Changhai Hospital.Main results. DRCA-Densenet169 achieved an overall accuracy of 85.27% ± 0.32%, a weighted-precision of 83.99% ± 2.47%, a weighted-recall of 84.36% ± 0.88% and a weighted-F1-score of 84.07% ± 2.14%.Significance. The results demonstrate that DRCA-Densenet169 has high recognition accuracy and strong robustness in identifying different types of ulcers when obtaining immediate and preliminary diagnoses.

A stereo spatial decoupling network for medical image classification

Deep convolutional neural network (CNN) has made great progress in medical image classification. However, it is difficult to establish effective spatial associations, and always extracts similar low-level features, resulting in redundancy of information. To solve these limitations, we propose a stereo spatial discoupling network (TSDNets), which can leverage the multi-dimensional spatial details of medical images. Then, we use an attention mechanism to progressively extract the most discriminative features from three directions: horizontal, vertical, and depth. Moreover, a cross feature screening strategy is used to divide the original feature maps into three levels: important, secondary and redundant. Specifically, we design a cross feature screening module (CFSM) and a semantic guided decoupling module (SGDM) to model multi-dimension spatial relationships, thereby enhancing the feature representation capabilities. The extensive experiments conducted on multiple open source baseline datasets demonstrate that our TSDNets outperforms previous state-of-the-art models.

Effective high-to-low-level feature aggregation network for endoscopic image classification

PURPOSE

The accuracy improvement in endoscopic image classification matters to the endoscopists in diagnosing and choosing suitable treatment for patients. Existing CNN-based methods for endoscopic image classification tend to use the deepest abstract features without considering the contribution of low-level features, while the latter is of great significance in the actual diagnosis of intestinal diseases.

METHODS

To make full use of both high-level and low-level features, we propose a novel two-stream network for endoscopic image classification. Specifically, the backbone stream is utilized to extract high-level features. In the fusion stream, low-level features are generated by a bottom-up multi-scale gradual integration (BMGI) method, and the input of BMGI is refined by top-down attention learning modules. Besides, a novel correction loss is proposed to clarify the relationship between high-level and low-level features.

RESULTS

Experiments on the KVASIR dataset demonstrate that the proposed framework can obtain an overall classification accuracy of 97.33% with Kappa coefficient of 95.25%. Compared to the existing models, the two evaluation indicators have increased by 2% and 2.25%, respectively, at least.

CONCLUSION

In this study, we proposed a two-stream network that fuses the high-level and low-level features for endoscopic image classification. The experiment results show that the high-to-low-level feature can better represent the endoscopic image and enable our model to outperform several state-of-the-art classification approaches. In addition, the proposed correction loss could regularize the consistency between backbone stream and fusion stream. Thus, the fused feature can reduce the intra-class distances and make accurate label prediction.

Sequential Models for Endoluminal Image Classification

Wireless Capsule Endoscopy (WCE) is a procedure to examine the human digestive system for potential mucosal polyps, tumours, or bleedings using an encapsulated camera. This work focuses on polyp detection within WCE videos through Machine Learning. When using Machine Learning in the medical field, scarce and unbalanced datasets often make it hard to receive a satisfying performance. We claim that using Sequential Models in order to take the temporal nature of the data into account improves the performance of previous approaches. Thus, we present a bidirectional Long Short-Term Memory Network (BLSTM), a sequential network that is particularly designed for temporal data. We find the BLSTM Network outperforms non-sequential architectures and other previous models, receiving a final Area under the Curve of 93.83%. Experiments show that our method of extracting spatial and temporal features yields better performance and could be a possible method to decrease the time needed by physicians to analyse the video material.

Dilated and soft attention-guided convolutional neural network for breast cancer histology images classification

Breast cancer is one of the most common types of cancer in women, and histopathological imaging is considered the gold standard for its diagnosis. However, the great complexity of histopathological images and the considerable workload make this work extremely time-consuming, and the results may be affected by the subjectivity of the pathologist. Therefore, the development of an accurate, automated method for analysis of histopathological images is critical to this field. In this article, we propose a deep learning method guided by the attention mechanism for fast and effective classification of haematoxylin and eosin-stained breast biopsy images. First, this method takes advantage of DenseNet and uses the feature map's information. Second, we introduce dilated convolution to produce a larger receptive field. Finally, spatial attention and channel attention are used to guide the extraction of the most useful visual features. With the use of fivefold cross-validation, the best model obtained an accuracy of 96.47% on the BACH2018 dataset. We also evaluated our method on other datasets, and the experimental results demonstrated that our model has reliable performance. This study indicates that our histopathological image classifier with a soft attention-guided deep learning model for breast cancer shows significantly better results than the latest methods. It has great potential as an effective tool for automatic evaluation of digital histopathological microscopic images for computer-aided diagnosis.

DSI-Net: Deep Synergistic Interaction Network for Joint Classification and Segmentation With Endoscope Images

Automatic classification and segmentation of wireless capsule endoscope (WCE) images are two clinically significant and relevant tasks in a computer-aided diagnosis system for gastrointestinal diseases. Most of existing approaches, however, considered these two tasks individually and ignored their complementary information, leading to limited performance. To overcome this bottleneck, we propose a deep synergistic interaction network (DSI-Net) for joint classification and segmentation with WCE images, which mainly consists of the classification branch (C-Branch), the coarse segmentation (CS-Branch) and the fine segmentation branches (FS-Branch). In order to facilitate the classification task with the segmentation knowledge, a lesion location mining (LLM) module is devised in C-Branch to accurately highlight lesion regions through mining neglected lesion areas and erasing misclassified background areas. To assist the segmentation task with the classification prior, we propose a category-guided feature generation (CFG) module in FS-Branch to improve pixel representation by leveraging the category prototypes of C-Branch to obtain the category-aware features. In such way, these modules enable the deep synergistic interaction between these two tasks. In addition, we introduce a task interaction loss to enhance the mutual supervision between the classification and segmentation tasks and guarantee the consistency of their predictions. Relying on the proposed deep synergistic interaction mechanism, DSI-Net achieves superior classification and segmentation performance on public dataset in comparison with state-of-the-art methods. The source code is available at https://github.com/CityU-AIM-Group/DSI-Net.

Super-Resolution Enhanced Medical Image Diagnosis With Sample Affinity Interaction

The degradation in image resolution harms the performance of medical image diagnosis. By inferring high-frequency details from low-resolution (LR) images, super-resolution (SR) techniques can introduce additional knowledge and assist high-level tasks. In this paper, we propose a SR enhanced diagnosis framework, consisting of an efficient SR network and a diagnosis network. Specifically, a Multi-scale Refined Context Network (MRC-Net) with Refined Context Fusion (RCF) is devised to leverage global and local features for SR tasks. Instead of learning from scratch, we first develop a recursive MRC-Net with temporal context, and then propose a recursion distillation scheme to enhance the performance of MRC-Net from the knowledge of the recursive one and reduce the computational cost. The diagnosis network jointly utilizes the reliable original images and more informative SR images by two branches, with the proposed Sample Affinity Interaction (SAI) blocks at different stages to effectively extract and integrate discriminative features towards diagnosis. Moreover, two novel constraints, sample affinity consistency and sample affinity regularization, are devised to refine the features and achieve the mutual promotion of these two branches. Extensive experiments of synthetic and real LR cases are conducted on wireless capsule endoscopy and histopathology images, verifying that our proposed method is significantly effective for medical image diagnosis.

Learn to Threshold: ThresholdNet With Confidence-Guided Manifold Mixup for Polyp Segmentation

The automatic segmentation of polyp in endoscopy images is crucial for early diagnosis and cure of colorectal cancer. Existing deep learning-based methods for polyp segmentation, however, are inadequate due to the limited annotated dataset and the class imbalance problems. Moreover, these methods obtained the final polyp segmentation results by simply thresholding the likelihood maps at an eclectic and equivalent value (often set to 0.5). In this paper, we propose a novel ThresholdNet with a confidence-guided manifold mixup (CGMMix) data augmentation method, mainly for addressing the aforementioned issues in polyp segmentation. The CGMMix conducts manifold mixup at the image and feature levels, and adaptively lures the decision boundary away from the under-represented polyp class with the confidence guidance to alleviate the limited training dataset and the class imbalance problems. Two consistency regularizations, mixup feature map consistency (MFMC) loss and mixup confidence map consistency (MCMC) loss, are devised to exploit the consistent constraints in the training of the augmented mixup data. We then propose a two-branch approach, termed ThresholdNet, to collaborate the segmentation and threshold learning in an alternative training strategy. The threshold map supervision generator (TMSG) is embedded to provide supervision for the threshold map, thereby inducing better optimization of the threshold branch. As a consequence, ThresholdNet is able to calibrate the segmentation result with the learned threshold map. We illustrate the effectiveness of the proposed method on two polyp segmentation datasets, and our methods achieved the state-of-the-art result with 87.307% and 87.879% dice score on the EndoScene dataset and the WCE polyp dataset. The source code is available at https://github.com/Guo-Xiaoqing/ThresholdNet.

MD-NDNet: a multi-dimensional convolutional neural network for false-positive reduction in pulmonary nodule detection

Pulmonary nodule false-positive reduction is of great significance for automated nodule detection in clinical diagnosis of low-dose computed tomography (LDCT) lung cancer screening. Due to individual intra-nodule variations and visual similarities between true nodules and false positives as soft tissues in LDCT images, the current clinical practices remain subject to shortcomings of potential high-risk and time-consumption issues. In this paper, we propose a multi-dimensional nodule detection network (MD-NDNet) for automatic nodule false-positive reduction using deep convolutional neural network (DCNNs). The underlying method collaboratively integrates multi-dimensional nodule information to complementarily and comprehensively extract nodule inter-plane volumetric correlation features using three-dimensional CNNs (3D CNNs) and spatial nodule correlation features from sagittal, coronal, and axial planes using two-dimensional CNNs (2D CNNs) with attention module. To incorporate different sizes and shapes of nodule candidates, a multi-scale ensemble strategy is employed for probability aggregation with weights. The proposed method is evaluated on the LUNA16 challenge dataset in ISBI 2016 with ten-fold cross-validation. Experiment results show that the proposed framework achieves classification performance with a CPM score of 0.9008. All of these indicate that our method enables an efficient, accurate and reliable pulmonary nodule detection for clinical diagnosis.

Zoom in Lesions for Better Diagnosis: Attention Guided Deformation Network for WCE Image Classification

Wireless capsule endoscopy (WCE) is a novel imaging tool that allows noninvasive visualization of the entire gastrointestinal (GI) tract without causing discomfort to patients. Convolutional neural networks (CNNs), though perform favorably against traditional machine learning methods, show limited capacity in WCE image classification due to the small lesions and background interference. To overcome these limits, we propose a two-branch Attention Guided Deformation Network (AGDN) for WCE image classification. Specifically, the attention maps of branch1 are utilized to guide the amplification of lesion regions on the input images of branch2, thus leading to better representation and inspection of the small lesions. What's more, we devise and insert Third-order Long-range Feature Aggregation (TLFA) modules into the network. By capturing long-range dependencies and aggregating contextual features, TLFAs endow the network with a global contextual view and stronger feature representation and discrimination capability. Furthermore, we propose a novel Deformation based Attention Consistency (DAC) loss to refine the attention maps and achieve the mutual promotion of the two branches. Finally, the global feature embeddings from the two branches are fused to make image label predictions. Extensive experiments show that the proposed AGDN outperforms state-of-the-art methods with an overall classification accuracy of 91.29% on two public WCE datasets. The source code is available at https://github.com/hathawayxxh/WCE-AGDN.