A generalized framework of feature learning enhanced convolutional neural network for pathology-image-oriented cancer diagnosis

S3T-Net: A novel electroencephalogram signals-oriented emotion recognition model

In this paper, a novel skipping spatial-spectral-temporal network (S3T-Net) is developed to handle intra-individual differences in electroencephalogram (EEG) signals for accurate, robust, and generalized emotion recognition. In particular, aiming at the 4D features extracted from the raw EEG signals, a multi-branch architecture is proposed to learn spatial-spectral cross-domain representations, which benefits enhancing the model generalization ability. Time dependency among different spatial-spectral features is further captured via a bi-directional long-short term memory module, which employs an attention mechanism to integrate context information. Moreover, a skip-change unit is designed to add another auxiliary pathway for updating model parameters, which alleviates the vanishing gradient problem in complex spatial-temporal network. Evaluation results show that the proposed S3T-Net outperforms other advanced models in terms of the emotion recognition accuracy, which yields an performance improvement of 0.23% , 0.13%, and 0.43% as compared to the sub-optimal model in three test scenes, respectively. In addition, the effectiveness and superiority of the key components of S3T-Net are demonstrated from various experiments. As a reliable and competent emotion recognition model, the proposed S3T-Net contributes to the development of intelligent sentiment analysis in human-computer interaction (HCI) realm.

DAX-Net: A dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images

BACKGROUND AND OBJECTIVE

Multi-class cancer classification has been extensively studied in digital and computational pathology due to its importance in clinical decision-making. Numerous computational tools have been proposed for various types of cancer classification. Many of them are built based on convolutional neural networks. Recently, Transformer-style networks have shown to be effective for cancer classification. Herein, we present a hybrid design that leverages both convolutional neural networks and transformer architecture to obtain superior performance in cancer classification.

METHODS

We propose a dual-branch dual-task adaptive cross-weight feature fusion network, called DAX-Net, which exploits heterogeneous feature representations from the convolutional neural network and Transformer network, adaptively combines them to boost their representation power, and conducts cancer classification as categorical classification and ordinal classification. For an efficient and effective optimization of the proposed model, we introduce two loss functions that are tailored to the two classification tasks.

RESULTS

To evaluate the proposed method, we employed colorectal and prostate cancer datasets, of which each contains both in-domain and out-of-domain test sets. For colorectal cancer, the proposed method obtained an accuracy of 88.4%, a quadratic kappa score of 0.945, and an F1 score of 0.831 for the in-domain test set, and 84.4%, 0.910, and 0.768 for the out-of-domain test set. For prostate cancer, it achieved an accuracy of 71.6%, a kappa score of 0.635, and an F1 score of 0.655 for the in-domain test set, 79.2% accuracy, 0.721 kappa score, and 0.686 F1 score for the first out-of-domain test set, and 58.1% accuracy, 0.564 kappa score, and 0.493 F1 score for the second out-of-domain test set. It is worth noting that the performance of the proposed method outperformed other competitors by significant margins, in particular, with respect to the out-of-domain test sets.

CONCLUSIONS

The experimental results demonstrate that the proposed method is not only accurate but also robust to varying conditions of the test sets in comparison to several, related methods. These results suggest that the proposed method can facilitate automated cancer classification in various clinical settings.

Boosted Additive Angular Margin Loss for breast cancer diagnosis from histopathological images

Pathologists use biopsies and microscopic examination to accurately diagnose breast cancer. This process is time-consuming, labor-intensive, and costly. Convolutional neural networks (CNNs) offer an efficient and highly accurate approach to reduce analysis time and automate the diagnostic workflow in pathology. However, the softmax loss commonly used in existing CNNs leads to noticeable ambiguity in decision boundaries and lacks a clear constraint for minimizing within-class variance. In response to this problem, a solution in the form of softmax losses based on angular margin was developed. These losses were introduced in the context of face recognition, with the goal of integrating an angular margin into the softmax loss. This integration improves discrimination features during CNN training by effectively increasing the distance between different classes while reducing the variance within each class. Despite significant progress, these losses are limited to target classes only when margin penalties are applied, which may not lead to optimal effectiveness. In this paper, we introduce Boosted Additive Angular Margin Loss (BAM) to obtain highly discriminative features for breast cancer diagnosis from histopathological images. BAM not only penalizes the angle between deep features and their target class weights, but also considers angles between deep features and non-target class weights. We performed extensive experiments on the publicly available BreaKHis dataset. BAM achieved remarkable accuracies of 99.79%, 99.86%, 99.96%, and 97.65% for magnification levels of 40X, 100X, 200X, and 400X, respectively. These results show an improvement in accuracy of 0.13%, 0.34%, and 0.21% for 40X, 100X, and 200X magnifications, respectively, compared to the baseline methods. Additional experiments were performed on the BACH dataset for breast cancer classification and on the widely accepted LFW and YTF datasets for face recognition to evaluate the generalization ability of the proposed loss function. The results show that BAM outperforms state-of-the-art methods by increasing the decision space between classes and minimizing intra-class variance, resulting in improved discriminability.

A Global and Local Feature fused CNN architecture for the sEMG-based hand gesture recognition

Deep learning methods have been widely used for the classification of hand gestures using sEMG signals. Existing deep learning architectures only captures local spatial information and has limitations in extracting global temporal dependency to enhance the model's performance. In this paper, we propose a Global and Local Feature fused CNN (GLF-CNN) model that extracts features both globally and locally from sEMG signals to enhance the performance of hand gestures classification. The model contains two independent branches extracting local and global features each and fuses them to learn more diversified features and effectively improve the stability of gesture recognition. Besides, it also exhibits lower computational cost compared to the present approaches. We conduct experiments on five benchmark databases, including the NinaPro DB4, NinaPro DB5, BioPatRec DB1-DB3, and the Mendeley Data. The proposed model achieved the highest average accuracy of 88.34% on these databases, with a 9.96% average accuracy improvement and a 50% reduction in variance compared to the models with the same number of parameters. Moreover, the classification accuracies for the BioPatRec DB1, BioPatRec DB3 and Mendeley Data are 91.4%, 91.0% and 88.6% respectively, corresponding to an improvement of 13.2%, 41.5% and 12.2% over the respective state-of-the-art models. The experimental results demonstrate that the proposed model effectively enhances robustness, with improved gesture recognition performance and generalization ability. It contributes a new way for prosthetic control and human-machine interaction.

MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Breast cancer is a common malignancy and early detection and treatment of it is crucial. Computer-aided diagnosis (CAD) based on deep learning has significantly advanced medical diagnostics, enhancing accuracy and efficiency in recent years. Despite the convenience, this technology also has certain limitations. When the morphological characteristics of the patient's pathological section are not evident or complex, certain small lesions or cells deep within the lesion cannot be recognized, and misdiagnosis is prone to occur. As a result, MDFF-Net, a CNN-based multidimensional feature fusion network, is proposed. The model consists of a one-dimensional feature extraction network, a two-dimensional feature extraction network, and a feature fusion classification network. The basic part of the two-dimensional feature extraction network is stacked by modules integrated with multi-scale channel shuffling networks and channel attention modules. Furthermore, inspired by natural language processing, this model integrates a one-dimensional feature extraction network to extract detailed information in the image to avoid misdiagnosis caused by insufficient information extraction such as cell morphological characteristics and differentiation degree. Finally, the extracted one-dimensional and two-dimensional features are fused in the feature fusion network and employed for the final classification. The effectiveness of MDFF-Net and classical classification models were evaluated on the BreakHis and the BACH datasets. According to experimental results, MDFF-Net achieves an accuracy of 98.86% on the BreakHis and 86.25% on the BACH dataset. Furthermore, to further assess the effectiveness of the model in other classification tasks, the colon cancer and the lung cancer datasets were employed for additional experiments, achieving a classification accuracy of 100% in both cases.

Image-guided prostate biopsy robots: A review

At present, the incidence of prostate cancer (PCa) in men is increasing year by year. So, the early diagnosis of PCa is of great significance. Transrectal ultrasonography (TRUS)-guided biopsy is a common method for diagnosing PCa. The biopsy process is performed manually by urologists but the diagnostic rate is only 20%-30% and its reliability and accuracy can no longer meet clinical needs. The image-guided prostate biopsy robot has the advantages of a high degree of automation, does not rely on the skills and experience of operators, reduces the work intensity and operation time of urologists and so on. Capable of delivering biopsy needles to pre-defined biopsy locations with minimal needle placement errors, it makes up for the shortcomings of traditional free-hand biopsy and improves the reliability and accuracy of biopsy. The integration of medical imaging technology and the robotic system is an important means for accurate tumor location, biopsy puncture path planning and visualization. This paper mainly reviews image-guided prostate biopsy robots. According to the existing literature, guidance modalities are divided into magnetic resonance imaging (MRI), ultrasound (US) and fusion image. First, the robot structure research by different guided methods is the main line and the actuators and material research of these guided modalities is the auxiliary line to introduce and compare. Second, the robot image-guided localization technology is discussed. Finally, the image-guided prostate biopsy robot is summarized and suggestions for future development are provided.

CVCL: Context-aware Voxel-wise Contrastive Learning for label-efficient multi-organ segmentation

Despite the significant performance improvement on multi-organ segmentation with supervised deep learning-based methods, the label-hungry nature hinders their applications in practical disease diagnosis and treatment planning. Due to the challenges in obtaining expert-level accurate, densely annotated multi-organ datasets, label-efficient segmentation, such as partially supervised segmentation trained on partially labeled datasets or semi-supervised medical image segmentation, has attracted increasing attention recently. However, most of these methods suffer from the limitation that they neglect or underestimate the challenging unlabeled regions during model training. To this end, we propose a novel Context-aware Voxel-wise Contrastive Learning method, referred as CVCL, to take full advantage of both labeled and unlabeled information in label-scarce datasets for a performance improvement on multi-organ segmentation. Experimental results demonstrate that our proposed method achieves superior performance than other state-of-the-art methods.

Progressive attention integration-based multi-scale efficient network for medical imaging analysis with application to COVID-19 diagnosis

In this paper, a novel deep learning-based medical imaging analysis framework is developed, which aims to deal with the insufficient feature learning caused by the imperfect property of imaging data. Named as multi-scale efficient network (MEN), the proposed method integrates different attention mechanisms to realize sufficient extraction of both detailed features and semantic information in a progressive learning manner. In particular, a fused-attention block is designed to extract fine-grained details from the input, where the squeeze-excitation (SE) attention mechanism is applied to make the model focus on potential lesion areas. A multi-scale low information loss (MSLIL)-attention block is proposed to compensate for potential global information loss and enhance the semantic correlations among features, where the efficient channel attention (ECA) mechanism is adopted. The proposed MEN is comprehensively evaluated on two COVID-19 diagnostic tasks, and the results show that as compared with some other advanced deep learning models, the proposed method is competitive in accurate COVID-19 recognition, which yields the best accuracy of 98.68% and 98.85%, respectively, and exhibits satisfactory generalization ability as well.

Root cause prediction for failures in semiconductor industry, a genetic algorithm-machine learning approach

Failure analysis has become an important part of guaranteeing good quality in the electronic component manufacturing process. The conclusions of a failure analysis can be used to identify a component's flaws and to better understand the mechanisms and causes of failure, allowing for the implementation of remedial steps to improve the product's quality and reliability. A failure reporting, analysis, and corrective action system is a method for organizations to report, classify, and evaluate failures, as well as plan corrective actions. These text feature datasets must first be preprocessed by Natural Language Processing techniques and converted to numeric by vectorization methods before starting the process of information extraction and building predictive models to predict failure conclusions of a given failure description. However, not all-textual information is useful for building predictive models suitable for failure analysis. Feature selection has been approached by several variable selection methods. Some of them have not been adapted for use in large data sets or are difficult to tune and others are not applicable to textual data. This article aims to develop a predictive model able to predict the failure conclusions using the discriminating features of the failure descriptions. For this, we propose to combine a Genetic Algorithm with supervised learning methods for an optimal prediction of the conclusions of failure in terms of the discriminant features of failure descriptions. Since we have an unbalanced dataset, we propose to apply an F1 score as a fitness function of supervised classification methods such as Decision Tree Classifier and Support Vector Machine. The suggested algorithms are called GA-DT and GA-SVM. Experiments on failure analysis textual datasets demonstrate the effectiveness of the proposed GA-DT method in creating a better predictive model of failure conclusion compared to using the information of the entire textual features or limited features selected by a genetic algorithm based on a SVM. Quantitative performances such as BLEU score and cosine similarity are used to compare the prediction performance of the different approaches.

Preparing pathological data to develop an artificial intelligence model in the nonclinical study

Artificial intelligence (AI)-based analysis has recently been adopted in the examination of histological slides via the digitization of glass slides using a digital scanner. In this study, we examined the effect of varying the staining color tone and magnification level of a dataset on the result of AI model prediction in hematoxylin and eosin stained whole slide images (WSIs). The WSIs of liver tissues with fibrosis were used as an example, and three different datasets (N20, B20, and B10) were prepared with different color tones and magnifications. Using these datasets, we built five models trained Mask R-CNN algorithm by a single or mixed dataset of N20, B20, and B10. We evaluated their model performance using the test dataset of three datasets. It was found that the models that were trained with mixed datasets (models B20/N20 and B10/B20), which consist of different color tones or magnifications, performed better than the single dataset trained models. Consequently, superior performance of the mixed models was obtained from the actual prediction results of the test images. We suggest that training the algorithm with various staining color tones and multi-scaled image datasets would be more optimized for consistent remarkable performance in predicting pathological lesions of interest.

AA-WGAN: Attention augmented Wasserstein generative adversarial network with application to fundus retinal vessel segmentation

In this paper, a novel attention augmented Wasserstein generative adversarial network (AA-WGAN) is proposed for fundus retinal vessel segmentation, where a U-shaped network with attention augmented convolution and squeeze-excitation module is designed to serve as the generator. In particular, the complex vascular structures make some tiny vessels hard to segment, while the proposed AA-WGAN can effectively handle such imperfect data property, which is competent in capturing the dependency among pixels in the whole image to highlight the regions of interests via the applied attention augmented convolution. By applying the squeeze-excitation module, the generator is able to pay attention to the important channels of the feature maps, and the useless information can be suppressed as well. In addition, gradient penalty method is adopted in the WGAN backbone to alleviate the phenomenon of generating large amounts of repeated images due to excessive concentration on accuracy. The proposed model is comprehensively evaluated on three datasets DRIVE, STARE, and CHASE_DB1, and the results show that the proposed AA-WGAN is a competitive vessel segmentation model as compared with several other advanced models, which obtains the accuracy of 96.51%, 97.19% and 96.94% on each dataset, respectively. The effectiveness of the applied important components is validated by ablation study, which also endows the proposed AA-WGAN with considerable generalization ability.

Machine learning determination of motivators of terminal extubation during the transition to end-of-life care in intensive care unit

Procedural aspects of compassionate care such as the terminal extubation are understudied. We used machine learning methods to determine factors associated with the decision to extubate the critically ill patient at the end of life, and whether the terminal extubation shortens the dying process. We performed a secondary data analysis of a large, prospective, multicentre, cohort study, death prediction and physiology after removal of therapy (DePPaRT), which collected baseline data as well as ECG, pulse oximeter and arterial waveforms from WLST until 30 min after death. We analysed a priori defined factors associated with the decision to perform terminal extubation in WLST using the random forest method and logistic regression. Cox regression was used to analyse the effect of terminal extubation on time from WLST to death. A total of 616 patients were included into the analysis, out of which 396 (64.3%) were terminally extubated. The study centre, low or no vasopressor support, and good respiratory function were factors significantly associated with the decision to extubate. Unadjusted time to death did not differ between patients with and without extubation (median survival time extubated vs. not extubated: 60 [95% CI: 46; 76] vs. 58 [95% CI: 45; 75] min). In contrast, after adjustment for confounders, time to death of extubated patients was significantly shorter (49 [95% CI: 40; 62] vs. 85 [95% CI: 61; 115] min). The decision to terminally extubate is associated with specific centres and less respiratory and/or vasopressor support. In this context, terminal extubation was associated with a shorter time to death.

AGGN: Attention-based glioma grading network with multi-scale feature extraction and multi-modal information fusion

In this paper, a magnetic resonance imaging (MRI) oriented novel attention-based glioma grading network (AGGN) is proposed. By applying the dual-domain attention mechanism, both channel and spatial information can be considered to assign weights, which benefits highlighting the key modalities and locations in the feature maps. Multi-branch convolution and pooling operations are applied in a multi-scale feature extraction module to separately obtain shallow and deep features on each modality, and a multi-modal information fusion module is adopted to sufficiently merge low-level detailed and high-level semantic features, which promotes the synergistic interaction among different modality information. The proposed AGGN is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the proposed AGGN in comparison to other advanced models, which also presents high generalization ability and strong robustness. In addition, even without the manually labeled tumor masks, AGGN can present considerable performance as other state-of-the-art algorithms, which alleviates the excessive reliance on supervised information in the end-to-end learning paradigm.