Memory-Augmented Capsule Network for Adaptable Lung Nodule Classification

A semantic fidelity interpretable-assisted decision model for lung nodule classification

PURPOSE

Early diagnosis of lung nodules is important for the treatment of lung cancer patients, existing capsule network-based assisted diagnostic models for lung nodule classification have shown promising prospects in terms of interpretability. However, these models lack the ability to draw features robustly at shallow networks, which in turn limits the performance of the models. Therefore, we propose a semantic fidelity capsule encoding and interpretable (SFCEI)-assisted decision model for lung nodule multi-class classification.

METHODS

First, we propose multilevel receptive field feature encoding block to capture multi-scale features of lung nodules of different sizes. Second, we embed multilevel receptive field feature encoding blocks in the residual code-and-decode attention layer to extract fine-grained context features. Integrating multi-scale features and contextual features to form semantic fidelity lung nodule attribute capsule representations, which consequently enhances the performance of the model.

RESULTS

We implemented comprehensive experiments on the dataset (LIDC-IDRI) to validate the superiority of the model. The stratified fivefold cross-validation results show that the accuracy (94.17%) of our method exceeds existing advanced approaches in the multi-class classification of malignancy scores for lung nodules.

CONCLUSION

The experiments confirm that the methodology proposed can effectively capture the multi-scale features and contextual features of lung nodules. It enhances the capability of shallow structure drawing features in capsule networks, which in turn improves the classification performance of malignancy scores. The interpretable model can support the physicians' confidence in clinical decision-making.

Classification of stages in cervical cancer MRI by customized CNN and transfer learning

Cervical cancer is the common cancer among women, where early-stage diagnoses of cervical cancer lead to recovery from the deadly cervical cancer. Correct cervical cancer staging is predominant to decide the treatment. Hence, cervical cancer staging is an important problem in designing automatic detection and diagnosing applications of the medical field. Convolutional Neural Networks (CNNs) often plays a greater role in object identification and classification. The performance of CNN in medical image classification can already compete with radiologists. In this paper, we planned to build a deep Capsule Network (CapsNet) for medical image classification that can achieve high accuracy using cervical cancer Magnetic Resonance (MR) images. In this study, a customized deep CNN model is developed using CapsNet to automatically predict the cervical cancer from MR images. In CapsNet, each layer receives input from all preceding layers, which helps to classify the features. The hyper parameters are estimated and it controls the backpropagation gradient at the initial learning. To improve the CapsNet performance, residual blocks are included between dense layers. Training and testing are performed with around 12,771 T2-weighted MR images of the TCGA-CESC dataset publicly available for research work. The results show that the accuracy of Customized CNN using CapsNetis higher and behaves well in classifying the cervical cancer. Thus, it is evident that CNN models can be used in developing automatic image analysis tools in the medical field.

A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images

OBJECTIVES

Both radiomics and deep learning methods have shown great promise in predicting lesion malignancy in various image-based oncology studies. However, it is still unclear which method to choose for a specific clinical problem given the access to the same amount of training data. In this study, we try to compare the performance of a series of carefully selected conventional radiomics methods, end-to-end deep learning models, and deep-feature based radiomics pipelines for pulmonary nodule malignancy prediction on an open database that consists of 1297 manually delineated lung nodules.

METHODS

Conventional radiomics analysis was conducted by extracting standard handcrafted features from target nodule images. Several end-to-end deep classifier networks, including VGG, ResNet, DenseNet, and EfficientNet were employed to identify lung nodule malignancy as well. In addition to the baseline implementations, we also investigated the importance of feature selection and class balancing, as well as separating the features learned in the nodule target region and the background/context region. By pooling the radiomics and deep features together in a hybrid feature set, we investigated the compatibility of these two sets with respect to malignancy prediction.

RESULTS

The best baseline conventional radiomics model, deep learning model, and deep-feature based radiomics model achieved AUROC values (mean ± standard deviations) of 0.792 ± 0.025, 0.801 ± 0.018, and 0.817 ± 0.032, respectively through 5-fold cross-validation analyses. However, after trying out several optimization techniques, such as feature selection and data balancing, as well as adding context features, the corresponding best radiomics, end-to-end deep learning, and deep-feature based models achieved AUROC values of 0.921 ± 0.010, 0.824 ± 0.021, and 0.936 ± 0.011, respectively. We achieved the best prediction accuracy from the hybrid feature set (AUROC: 0.938 ± 0.010).

CONCLUSION

The end-to-end deep-learning model outperforms conventional radiomics out of the box without much fine-tuning. On the other hand, fine-tuning the models lead to significant improvements in the prediction performance where the conventional and deep-feature based radiomics models achieved comparable results. The hybrid radiomics method seems to be the most promising model for lung nodule malignancy prediction in this comparative study.

DropConnect is effective in modeling uncertainty of Bayesian deep networks

Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art.