A Multimodal Affinity Fusion Network for Predicting the Survival of Breast Cancer Patients

Breast cancer prognosis through the use of multi-modal classifiers: current state of the art and the way forward

We present a survey of the current state-of-the-art in breast cancer detection and prognosis. We analyze the evolution of Artificial Intelligence-based approaches from using just uni-modal information to multi-modality for detection and how such paradigm shift facilitates the efficacy of detection, consistent with clinical observations. We conclude that interpretable AI-based predictions and ability to handle class imbalance should be considered priority.

MMGCN: Multi-modal multi-view graph convolutional networks for cancer prognosis prediction

BACKGROUND AND OBJECTIVE

Accurate prognosis prediction for cancer patients plays a significant role in the formulation of treatment strategies, considerably impacting personalized medicine. Recent advancements in this field indicate that integrating information from various modalities, such as genetic and clinical data, and developing multi-modal deep learning models can enhance prediction accuracy. However, most existing multi-modal deep learning methods either overlook patient similarities that benefit prognosis prediction or fail to effectively capture diverse information due to measuring patient similarities from a single perspective. To address these issues, a novel framework called multi-modal multi-view graph convolutional networks (MMGCN) is proposed for cancer prognosis prediction.

METHODS

Initially, we utilize the similarity network fusion (SNF) algorithm to merge patient similarity networks (PSNs), individually constructed using gene expression, copy number alteration, and clinical data, into a fused PSN for integrating multi-modal information. To capture diverse perspectives of patient similarities, we treat the fused PSN as a multi-view graph by considering each single-edge-type subgraph as a view graph, and propose multi-view graph convolutional networks (GCNs) with a view-level attention mechanism. Moreover, an edge homophily prediction module is designed to alleviate the adverse effects of heterophilic edges on the representation power of GCNs. Finally, comprehensive representations of patient nodes are obtained to predict cancer prognosis.

RESULTS

Experimental results demonstrate that MMGCN outperforms state-of-the-art baselines on four public datasets, including METABRIC, TCGA-BRCA, TCGA-LGG, and TCGA-LUSC, with the area under the receiver operating characteristic curve achieving 0.827 ± 0.005, 0.805 ± 0.014, 0.925 ± 0.007, and 0.746 ± 0.013, respectively.

CONCLUSIONS

Our study reveals the effectiveness of the proposed MMGCN, which deeply explores patient similarities related to different modalities from a broad perspective, in enhancing the performance of multi-modal cancer prognosis prediction. The source code is publicly available at https://github.com/ping-y/MMGCN.

SAGL: A self-attention-based graph learning framework for predicting survival of colorectal cancer patients

BACKGROUND AND OBJECTIVE

Colorectal cancer (CRC) is one of the most commonly diagnosed cancers worldwide. The accurate survival prediction for CRC patients plays a significant role in the formulation of treatment strategies. Recently, machine learning and deep learning approaches have been increasingly applied in cancer survival prediction. However, most existing methods inadequately represent and leverage the dependencies among features and fail to sufficiently mine and utilize the comorbidity patterns of CRC. To address these issues, we propose a self-attention-based graph learning (SAGL) framework to improve the postoperative cancer-specific survival prediction for CRC patients.

METHODS

We present a novel method for constructing dependency graph (DG) to reflect two types of dependencies including comorbidity-comorbidity dependencies and the dependencies between features related to patient characteristics and cancer treatments. This graph is subsequently refined by a disease comorbidity network, which offers a holistic view of comorbidity patterns of CRC. A DG-guided self-attention mechanism is proposed to unearth novel dependencies beyond what DG offers, thus augmenting CRC survival prediction. Finally, each patient will be represented, and these representations will be used for survival prediction.

RESULTS

The experimental results show that SAGL outperforms state-of-the-art methods on a real-world dataset, with the receiver operating characteristic curve for 3- and 5-year survival prediction achieving 0.849±0.002 and 0.895±0.005, respectively. In addition, the comparison results with different graph neural network-based variants demonstrate the advantages of our DG-guided self-attention graph learning framework.

CONCLUSIONS

Our study reveals that the potential of the DG-guided self-attention in optimizing feature graph learning which can improve the performance of CRC survival prediction.

Unsupervised Learning Based on Multiple Descriptors for WSIs Diagnosis

An automatic pathological diagnosis is a challenging task because histopathological images with different cellular heterogeneity representations are sometimes limited. To overcome this, we investigated how the holistic and local appearance features with limited information can be fused to enhance the analysis performance. We propose an unsupervised deep learning model for whole-slide image diagnosis, which uses stacked autoencoders simultaneously feeding multiple-image descriptors such as the histogram of oriented gradients and local binary patterns along with the original image to fuse the heterogeneous features. The pre-trained latent vectors are extracted from each autoencoder, and these fused feature representations are utilized for classification. We observed that training with additional descriptors helps the model to overcome the limitations of multiple variants and the intricate cellular structure of histopathology data by various experiments. Our model outperforms existing state-of-the-art approaches by achieving the highest accuracies of 87.2 for ICIAR2018, 94.6 for Dartmouth, and other significant metrics for public benchmark datasets. Our model does not rely on a specific set of pre-trained features based on classifiers to achieve high performance. Unsupervised spaces are learned from the number of independent multiple descriptors and can be used with different variants of classifiers to classify cancer diseases from whole-slide images. Furthermore, we found that the proposed model classifies the types of breast and lung cancer similar to the viewpoint of pathologists by visualization. We also designed our whole-slide image processing toolbox to extract and process the patches from whole-slide images.

Computer-Aided Diagnosis of Spinal Tuberculosis From CT Images Based on Deep Learning With Multimodal Feature Fusion

Background

Spinal tuberculosis (TB) has the highest incidence in remote plateau areas, particularly in Tibet, China, due to inadequate local healthcare services, which not only facilitates the transmission of TB bacteria but also increases the burden on grassroots hospitals. Computer-aided diagnosis (CAD) is urgently required to improve the efficiency of clinical diagnosis of TB using computed tomography (CT) images. However, classical machine learning with handcrafted features generally has low accuracy, and deep learning with self-extracting features relies heavily on the size of medical datasets. Therefore, CAD, which effectively fuses multimodal features, is an alternative solution for spinal TB detection.

Methods

A new deep learning method is proposed that fuses four elaborate image features, specifically three handcrafted features and one convolutional neural network (CNN) feature. Spinal TB CT images were collected from 197 patients with spinal TB, from 2013 to 2020, in the People’s Hospital of Tibet Autonomous Region, China; 3,000 effective lumbar spine CT images were randomly screened to our dataset, from which two sets of 1,500 images each were classified as tuberculosis (positive) and health (negative). In addition, virtual data augmentation is proposed to enlarge the handcrafted features of the TB dataset. Essentially, the proposed multimodal feature fusion CNN consists of four main sections: matching network, backbone (ResNet-18/50, VGG-11/16, DenseNet-121/161), fallen network, and gated information fusion network. Detailed performance analyses were conducted based on the multimodal features, proposed augmentation, model stability, and model-focused heatmap.

Results

Experimental results showed that the proposed model with VGG-11 and virtual data augmentation exhibited optimal performance in terms of accuracy, specificity, sensitivity, and area under curve. In addition, an inverse relationship existed between the model size and test accuracy. The model-focused heatmap also shifted from the irrelevant region to the bone destruction caused by TB.

Conclusion

The proposed augmentation effectively simulated the real data distribution in the feature space. More importantly, all the evaluation metrics and analyses demonstrated that the proposed deep learning model exhibits efficient feature fusion for multimodal features. Our study provides a profound insight into the preliminary auxiliary diagnosis of spinal TB from CT images applicable to the Tibetan area.