EVET: Enhancing Visual Explanations of Deep Neural Networks Using Image Transformations

Oh, Youngrock; Jung, Hun Soon; Park, Jeonghyung; Kim, Min Soo

doi:10.1109/wacv48630.2021.00362

Cited by 9 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main reasons for having such expansive development and testing is because of the large amounts of open-source data present (including open accessing all research), which is generally absent for other diseases. Self-supervised learning approaches have proven to surpass the usual supervised deep learning methods in [ 134 , 135 ] and should be given more importance and consideration when topics of extension and challenges are brought upon. There is also a major gap in accounting for the research conducted in terms of prognosis for COVID-19.…”

Section: Related Reviews In the Fieldmentioning

confidence: 99%

“…Score-CAM eliminates the dependence on gradients (as seen in Grad-CAM) by securing the weight of individual activation maps, by virtue of its forward passing score on the aimed target class, which results in a linear combination of the activation maps and weights. EVET [ 135 ] proposes a heuristic pipeline for strengthening the visual explanations by applying image transformations. Explainability in segmentation tasks (primarily done by U-Nets) is a field that is still being heavily explored.…”

Section: Related Reviews In the Fieldmentioning

confidence: 99%

See 1 more Smart Citation

Radiological Analysis of COVID-19 Using Computational Intelligence: A Broad Gauge Study

Ligi

Kundu

Kumar

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Pulmonary medical image analysis using image processing and deep learning approaches has made remarkable achievements in the diagnosis, prognosis, and severity check of lung diseases. The epidemic of COVID-19 brought out by the novel coronavirus has triggered a critical need for artificial intelligence assistance in diagnosing and controlling the disease to reduce its effects on people and global economies. This study aimed at identifying the various COVID-19 medical imaging analysis models proposed by different researchers and featured their merits and demerits. It gives a detailed discussion on the existing COVID-19 detection methodologies (diagnosis, prognosis, and severity/risk detection) and the challenges encountered for the same. It also highlights the various preprocessing and post-processing methods involved to enhance the detection mechanism. This work also tries to bring out the different unexplored research areas that are available for medical image analysis and how the vast research done for COVID-19 can advance the field. Despite deep learning methods presenting high levels of efficiency, some limitations have been briefly described in the study. Hence, this review can help understand the utilization and pros and cons of deep learning in analyzing medical images.

show abstract

Section: Related Reviews In the Fieldmentioning

confidence: 99%

Section: Related Reviews In the Fieldmentioning

confidence: 99%

Radiological Analysis of COVID-19 Using Computational Intelligence: A Broad Gauge Study

Ligi

Kundu

Kumar

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…On the other hand, a few papers have proposed methods to enhance explanations of a given explainability method for CNNs [31,32]. In general, explanation enhancement methods make copies of the input image with a small perturbation and incorporate the explanations for them to give a better explanation for the target prediction.…”

Section: Related Workmentioning

confidence: 99%

“…For example, SmoothGrad [31] takes random samples in the neighborhood of the input and average the explanations of the samples. EVET [32] provides a visually clear explanation that takes into account geometric transformations of the input image. SEEN is similar to them in the way that we incorporate the auxiliary explanations to sharpen the target explanation.…”

Section: Related Workmentioning

confidence: 99%

SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods

Cho,

Oh,

Jeon

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Explaining the foundations for predictions obtained from graph neural networks (GNNs) is critical for credible use of GNN models for real-world problems. Owing to the rapid growth of GNN applications, recent progress in explaining predictions from GNNs, such as sensitivity analysis, perturbation methods, and attribution methods, showed great opportunities and possibilities for explaining GNN predictions. In this study, we propose a method to improve the explanation quality of node classification tasks that can be applied in a post hoc manner through aggregation of auxiliary explanations from important neighboring nodes, named SEEN. Applying SEEN does not require modification of a graph and can be used with diverse explainability techniques due to its independent mechanism. Experiments on matching motif-participating nodes from a given graph show great improvement in explanation accuracy of up to 12.71% and demonstrate the correlation between the auxiliary explanations and the enhanced explanation accuracy through leveraging their contributions. SEEN provides a simple but effective method to enhance the explanation quality of GNN model outputs, and this method is applicable in combination with most explainability techniques.

show abstract

“…We, therefore, developed an explainable AI system in a cloud framework, labeled the “COVLIAS 2.0-cXAI” system, which was our primary novelty [ 47 , 48 , 49 , 50 , 51 , 52 ]. The COVLIAS 2.0-cXAI design consisted of three stages ( Figure 1 ): (i) automated lung segmentation using the hybrid deep learning ResNet-UNet model using automatic adjustment of Hounsfield units [ 53 ], hyperparameter optimization [ 54 ], and the parallel and distributed nature of design during training; (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201) [ 55 , 56 , 57 , 58 ]; and (iii) scientific validation using four kinds of class activation mapping (CAM) visualization techniques: gradient-weighted class activation mapping (Grad-CAM) [ 59 , 60 , 61 , 62 , 63 ], Grad-CAM++ [ 64 , 65 , 66 , 67 ], score-weighted CAM (Score-CAM) [ 68 , 69 , 70 ], and FasterScore-CAM [ 71 , 72 ]. The COVLIAS 2.0-cXAI was validated by a trained senior radiologist for its stability and reliability.…”

Section: Introductionmentioning

confidence: 99%

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Suri¹,

Agarwal²,

Chabert

et al. 2022

Diagnostics

View full text Add to dashboard Cite

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

show abstract

EVET: Enhancing Visual Explanations of Deep Neural Networks Using Image Transformations

Cited by 9 publications

References 18 publications

Radiological Analysis of COVID-19 Using Computational Intelligence: A Broad Gauge Study

Radiological Analysis of COVID-19 Using Computational Intelligence: A Broad Gauge Study

SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Contact Info

Product

Resources

About