One way to achieve eXplainable artificial intelligence (XAI) is through the use of post-hoc analysis methods. In particular, methods that generate heatmaps have been used to explain black-box models, such as deep neural network. In some cases, heatmaps are appealing due to the intuitive and visual ways to understand them. However, quantitative analysis that demonstrates the actual potential of heatmaps have been lacking, and comparison between different methods are not standardized as well. In this paper, we introduce a synthetic data that can be generated adhoc along with the ground-truth heatmaps for better quantitative assessment. Each sample data is an image of a cell with easily distinguishable features, facilitating a more transparent assessment of different XAI methods. Comparison and recommendations are made, shortcomings are clarified along with suggestions for future research directions to handle the finer details of select post-hoc analysis methods.

Quantifying Explainability of Saliency Methods in Deep Neural Networks

Purpose The purpose of this study was to design an automated algorithm that can detect fluorescence leakage accurately and quickly without the use of a large amount of labeled data. Methods A weakly supervised learning-based method was proposed to detect fluorescein leakage without the need for manual annotation of leakage areas. To enhance the representation of the network, a residual attention module (RAM) was designed as the core component of the proposed generator. Moreover, class activation maps (CAMs) were used to define a novel anomaly mask loss to facilitate more accurate learning of leakage areas. In addition, sensitivity, specificity, accuracy, area under the curve (AUC), and dice coefficient (DC) were used to evaluate the performance of the methods. Results The proposed method reached a sensitivity of 0.73 ± 0.04, a specificity of 0.97 ± 0.03, an accuracy of 0.95 ± 0.05, an AUC of 0.86 ± 0.04, and a DC of 0.87 ± 0.01 on the HRA data set; a sensitivity of 0.91 ± 0.02, a specificity of 0.97 ± 0.02, an accuracy of 0.96 ± 0.03, an AUC of 0.94 ± 0.02, and a DC of 0.85 ± 0.03 on Zhao's publicly available data set; and a sensitivity of 0.71 ± 0.04, a specificity of 0.99 ± 0.06, an accuracy of 0.87 ± 0.06, an AUC of 0.85 ± 0.02, and a DC of 0.78 ± 0.04 on Rabbani's publicly available data set. Conclusions The experimental results showed that the proposed method achieves better performance on fluorescence leakage detection and can detect one image within 1 second and thus has great potential value for clinical diagnosis and treatment of retina-related diseases, such as diabetic retinopathy and malarial retinopathy. Translational Relevance The proposed weakly supervised learning-based method that automates the detection of fluorescence leakage can facilitate the assessment of retinal-related diseases.

A Weakly Supervised Deep Learning Approach for Leakage Detection in Fluorescein Angiography Images

In recent years, brain–machine interface (BMI) technology has made great progress in controlling external devices and restoring motor function for people with disabilities. To better optimize BMI system performance, in this article, we summarize and describe a universal closed-loop BMI system framework and review the latest developments over the past ten years from a control perspective. First, the basic BMI systems with open-loop and closed-loop structures are introduced in chronological order. Second, the units of the universal closed-loop BMI system, i.e., the decoder, encoder, and auxiliary controller, are reviewed and summarized in terms of principles, categories, and algorithms. Finally, from research and practical perspectives, the importance of biomimetic brain models, great challenges, and future developments are discussed based on current progress. With this analysis of the universal closed-loop framework, this review can provide necessary theoretical guidance for the research and development of BMI systems.

Review of Closed-Loop Brain–Machine Interface Systems From a Control Perspective

In recent years, brain–machine interface (BMI) technology has made great progress in controlling external devices and restoring motor function for people with disabilities. To better optimize BMI system performance, in this article, we summarize and describe a universal closed-loop BMI system framework and review the latest developments over the past ten years from a control perspective. First, the basic BMI systems with open-loop and closed-loop structures are introduced in chronological order. Second, the units of the universal closed-loop BMI system, i.e., the decoder, encoder, and auxiliary controller, are reviewed and summarized in terms of principles, categories, and algorithms. Finally, from research and practical perspectives, the importance of biomimetic brain models, great challenges, and future developments are discussed based on current progress. With this analysis of the universal closed-loop framework, this review can provide necessary theoretical guidance for the research and development of BMI systems. 

A weakly supervised deep active contour model for nodule segmentation in thyroid ultrasound images

Fully supervised methods with numerous dense-labeled training data have achieved accurate localization results for anatomical structures. However, obtaining such a dedicated dataset usually requires clinical expertise and time-consuming annotation process. In this work, we tackle the organ localization problem under the setting of image-level annotations. Previous Class Activation Map (CAM) and its derivatives have proved that discriminative regions of images can be located with basic classification networks. To improve the representative capacity of attention maps generated by CAMs, a novel learning-based Local Area Reconstruction (LAR) method is proposed. Our weakly supervised organ localization network, namely OLNet, can generate high-resolution attention maps that preserve fine-detailed target anatomical structures. Online generated pseudo ground-truth is utilized to impose geometric constraints on attention maps. Extensive experiments on In-house Chest CT Dataset and Kidney Tumor Segmentation Benchmark (KiTS19) show that our approach can provide promising localization results both in saliency map and semantic segmentation perspectives.

Weakly Supervised Organ Localization with Attention Maps Regularized by Local Area Reconstruction

We implement a visual interpretability method Layer-wise Relevance Propagation (LRP) on top of 3D U-Net trained to perform lesion segmentation on the small dataset of multi-modal images provided by ISLES 2017 competition. We demonstrate that LRP modifications could provide more sensible visual explanations to an otherwise highly noise-skewed saliency map. We also link amplitude of modified signals to useful information content. High amplitude localized signals appear to constitute the noise that undermines the interpretability capacity of LRP. Furthermore, mathematical framework for possible analysis of function approximation is developed by analogy.

Enhancing the Extraction of Interpretable Information for Ischemic Stroke Imaging from Deep Neural Networks.

Steady-State Visual Evoked Potential (SSVEP) BCI brings high accuracy and consistent performance across subjects at the expense of a long stimulus presentation time window. Several recent methods exploited subject-specific features to improve SSVEP recognition performance in a short time window less than 1s. Although the calibration process is tedious and causes inconvenience, small calibration data with short duration resulting in higher performance gains are worth considering. So we propose a method by optimizing Filter-Bank Canonical Correlation Analysis (FBCCA) with subjects’ calibrated templates, subject-specific weights and multiple reference types. The proposed method, subject-calibration extended FBCCA (SCEF) leverages independent and distinct discrimination characteristics of multiple references with subject-specific weight-adjusted features to improve SSVEP recognition performance. We tested the proposed method with different parameters compared with FBCCA baseline and state-of-the-art calibration methods on forty targets SSVEP dataset using 0.2s to 4s time windows. Our evaluation results show SCEF with three reference templates and subject-specific weighted features perform significantly better than all FBCCA variants in 0.2 s to 1 s time window (p < 0.001). SCEF performs marginally, not statistically significant, better than existing methods about 2.69 ± 2.32% mean accuracy across time windows. Including multiple templates and subject-specific weight increases 15.73 ± 5.34% and 8.06± 2.06% in mean accuracy resulting the overall performance improvements in short time window. The proposed optimization only requires prior calibration data to create subject-specific templates and weights instead of learning features from calibration data every time. This enables not requiring to repeat the calibration step in every SSVEP session for the same subject while still maintaining accuracy similar to state-of-the-art calibration methods.

/pdf/optimizing-filter-bank-canonical-correlation-analysis-for-3f5nksaazl.pdf

Optimizing Filter-bank Canonical Correlation Analysis for fast response SSVEP Brain-Computer Interface (BCI)

Steady-state visual evoked potentials (SSVEP) brain-computer interface (BCI) provides reliable responses leading to high accuracy and information throughput. But achieving high accuracy typically requires a relatively long time window of one second or more. Various methods were proposed to improve sub-second response accuracy through subject-specific training and calibration. Substantial performance improvements were achieved with tedious calibration and subject-specific training; resulting in the user's discomfort. So, we propose a training-free method by combining spatial-filtering and temporal alignment (CSTA) to recognize SSVEP responses in sub-second response time. CSTA exploits linear correlation and non-linear similarity between steady-state responses and stimulus templates with complementary fusion to achieve desirable performance improvements. We evaluated the performance of CSTA in terms of accuracy and Information Transfer Rate (ITR) in comparison with both training-based and training-free methods using two SSVEP data-sets. We observed that CSTA achieves the maximum mean accuracy of 97.43$\pm$2.26 % and 85.71$\pm$13.41 % with four-class and forty-class SSVEP data-sets respectively in sub-second response time in offline analysis. CSTA yields significantly higher mean performance (p<0.001) than the training-free method on both data-sets. Compared with training-based methods, CSTA shows 29.33$\pm$19.65 % higher mean accuracy with statistically significant differences in time window less than 0.5 s. In longer time windows, CSTA exhibits either better or comparable performance though not statistically significantly better than training-based methods. We show that the proposed method brings advantages of subject-independent SSVEP classification without requiring training while enabling high target recognition performance in sub-second response time.

Towards a Fast Steady-State Visual Evoked Potentials (SSVEP) Brain-Computer Interface (BCI)

The invention discloses a coronary artery calcification lesion full-automatic segmentation method based on chest flat scanning CT, and the method comprises the following steps: carrying out the preprocessing of an original chest flat scanning CT image, and obtaining preprocessing data; inputting the preprocessed data into a heart segmentation model, and segmenting a heart region in the original chest flat-scanning CT image to obtain a heart segmentation image which corresponds to the original chest flat-scanning CT image and contains the heart region; screening suspected coronary artery calcification lesions in the heart area; extracting a plurality of candidate sample blocks from the screened suspected coronary artery calcification lesions; and based on the plurality of candidate sample blocks and the corresponding coordinates of the candidate sample blocks in the coordinate system corresponding to the original chest horizontal scanning CT image, obtaining coronary artery calcification focus segmentation results of the candidate sample blocks by using a calcification focus segmentation model. According to the method, a coarse-to-fine strategy is adopted, a two-stage deep neural network is used for achieving full-automatic coronary artery calcification focus segmentation based on chest flat scanning CT, and a good segmentation result can also be obtained for data with large noise.

Heng Guo

Papers

Weakly Supervised Organ Localization with Attention Maps Regularized by Local Area Reconstruction

Enhancing the Extraction of Interpretable Information for Ischemic Stroke Imaging from Deep Neural Networks.

Optimizing Filter-bank Canonical Correlation Analysis for fast response SSVEP Brain-Computer Interface (BCI)

Towards a Fast Steady-State Visual Evoked Potentials (SSVEP) Brain-Computer Interface (BCI)

Coronary artery calcification lesion full-automatic segmentation method based on chest flat scanning CT