Towards Interpretability of Segmentation Networks by Analyzing DeepDreams

Couteaux, Vincent; Nempont, Olivier; Pizaine, Guillaume; Bloch, Isabelle

doi:10.1007/978-3-030-33850-3_7

Cited by 47 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A DeepDreams [ 45 ] inspired attribution method was presented in [ 46 ] for explaining the segmentation of tumor from liver CT images. This novel method formulated using the concepts of DeapDreams, an image generation algorithm can be applied to a black-box neural network like other attribution methods discussed in Section 3 .…”

Section: Applicationsmentioning

confidence: 99%

Explainable Deep Learning Models in Medical Image Analysis

2020

View full text Add to dashboard Cite

Deep learning methods have been very effective for a variety of medical diagnostic tasks and have even outperformed human experts on some of those. However, the black-box nature of the algorithms has restricted their clinical use. Recent explainability studies aim to show the features that influence the decision of a model the most. The majority of literature reviews of this area have focused on taxonomy, ethics, and the need for explanations. A review of the current applications of explainable deep learning for different medical imaging tasks is presented here. The various approaches, challenges for clinical deployment, and the areas requiring further research are discussed here from a practical standpoint of a deep learning researcher designing a system for the clinical end-users.

show abstract

Section: Applicationsmentioning

confidence: 99%

Explainable Deep Learning Models in Medical Image Analysis

2020

View full text Add to dashboard Cite

show abstract

“…If the model outcome has changed notably with perturbations, it shows us that the feature has a high contribution to the prediction. Couteaux et al [119] implemented an explanation method based on the DeepDreams concept for explaining the classification of tumors using data of liver computed tomography (CT). Their proposed method used SA of each feature by maximizing the neuron activation using gradient ascent.…”

Section: D) Local Interpretable Model-agnostic Explanations (Lime)mentioning

confidence: 99%

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

Rasheed¹,

Qayyum²,

Ghaly³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the advent of machine learning (ML) applications in daily life, the questions about liability, trust, and interpretability of their outputs are raising, especially for healthcare applications. The black-box nature of ML models is a roadblock for clinical utilization. Therefore, to gain the trust of clinicians and patients, researchers need to provide explanations of how and why the model is making a specific decision. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provide a comprehensive review of explainable and interpretable ML techniques implemented for providing the reasons behind their decisions for various healthcare applications. Along with highlighting various security, safety, and robustness challenges that hinder the trustworthiness of ML we also discussed the ethical issues of healthcare ML and describe how explainable and trustworthy ML can resolve these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

show abstract

“…Couteaux et al, using the LiTS CT liver tumour database, analysed not only the performance of DL liver tumour segmentations but also what influenced the output of the algorithm. They found the DL model was sensitive to focal liver density change and shape of the lesions [ 76 ].…”

Section: Future Perspectivesmentioning

confidence: 99%

An Overview of Artificial Intelligence Applications in Liver and Pancreatic Imaging

Cardobi

Palù

Pedrini

et al. 2021

Cancers

View full text Add to dashboard Cite

Artificial intelligence (AI) is one of the most promising fields of research in medical imaging so far. By means of specific algorithms, it can be used to help radiologists in their routine workflow. There are several papers that describe AI approaches to solve different problems in liver and pancreatic imaging. These problems may be summarized in four different categories: segmentation, quantification, characterization and image quality improvement. Segmentation is usually the first step of successive elaborations. If done manually, it is a time-consuming process. Therefore, the semi-automatic and automatic creation of a liver or a pancreatic mask may save time for other evaluations, such as quantification of various parameters, from organs volume to their textural features. The alterations of normal liver and pancreas structure may give a clue to the presence of a diffuse or focal pathology. AI can be trained to recognize these alterations and propose a diagnosis, which may then be confirmed or not by radiologists. Finally, AI may be applied in medical image reconstruction in order to increase image quality, decrease dose administration (referring to computed tomography) and reduce scan times. In this article, we report the state of the art of AI applications in these four main categories.

show abstract

Towards Interpretability of Segmentation Networks by Analyzing DeepDreams

Cited by 47 publications

References 10 publications

Explainable Deep Learning Models in Medical Image Analysis

Explainable Deep Learning Models in Medical Image Analysis

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

An Overview of Artificial Intelligence Applications in Liver and Pancreatic Imaging

Contact Info

Product

Resources

About