Visualizing surrogate decision trees of convolutional neural networks

Jia, Shichao; Lin, Pei‐Wen; Li, Zeyu; Zhang, Jiawan; Liu, Shixia

doi:10.1007/s12650-019-00607-z

Cited by 28 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, a new generation of AI which has better reliability, interpretability, accountability, and transparency than black-box AI is worth investing in to overcome the "black box" dilemma. For example, Jia et al created visualizing surrogate decision trees of convolutional neural networks with python (161).…”

Section: Limitations and Future Considerationsmentioning

confidence: 99%

See 1 more Smart Citation

Applications of Artificial Intelligence Based on Medical Imaging in Glioma: Current State and Future Challenges

Meng

Qiu

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

Glioma is one of the most fatal primary brain tumors, and it is well-known for its difficulty in diagnosis and management. Medical imaging techniques such as magnetic resonance imaging (MRI), positron emission tomography (PET), and spectral imaging can efficiently aid physicians in diagnosing, treating, and evaluating patients with gliomas. With the increasing clinical records and digital images, the application of artificial intelligence (AI) based on medical imaging has reduced the burden on physicians treating gliomas even further. This review will classify AI technologies and procedures used in medical imaging analysis. Additionally, we will discuss the applications of AI in glioma, including tumor segmentation and classification, prediction of genetic markers, and prediction of treatment response and prognosis, using MRI, PET, and spectral imaging. Despite the benefits of AI in clinical applications, several issues such as data management, incomprehension, safety, clinical efficacy evaluation, and ethical or legal considerations, remain to be solved. In the future, doctors and researchers should collaborate to solve these issues, with a particular emphasis on interdisciplinary teamwork.

show abstract

Section: Limitations and Future Considerationsmentioning

confidence: 99%

“…For example, Jia et al. created visualizing surrogate decision trees of convolutional neural networks with python ( 161 ).…”

Section: Limitations and Future Considerationsmentioning

confidence: 99%

Applications of Artificial Intelligence Based on Medical Imaging in Glioma: Current State and Future Challenges

Meng

Qiu

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Visualizing (deep) neural networks has become a popular research focus in recent years. However, in most cases the approaches focus on explaining and debugging the models, for instance, visualizing which pixel regions are most supportive for the prediction [64], explaining predictions of convolutional neural networks with surrogate decision trees [26], or visualizing activation patterns to understand deep learning models [29]. Liu et al [33] provide an overview of visual analytic approaches for understanding, debugging and refining machine learning models, Choo et al [12] for explainable deep learning, and recently Sacha et al [47] for assisting machine learning.…”

Section: Related Workmentioning

confidence: 99%

Visual Neural Decomposition to Explain Multivariate Data Sets

Knittel

Lalama

Koch

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Our technique contributes to another way of interpretable machine learning [13,31]. Previous works either open the black boxes [40,41,43,45,62,68] which need analysts to have machine learning knowledge or explain the black boxes using surrogate models [33,46], which adds another layer of uncertainty.…”

Section: Interactive Classificationmentioning

confidence: 99%

Towards Visual Explainable Active Learning for Zero-Shot Classification

Jia

Zhang

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fig. 1. Semantic navigator is a mixed-initiative visual analytics system for zero-shot classification. (a) The machine asks contrastive questions to guide analysts to come up with new attributes. (b) The semantic map explains the machine's status and presents the label recommendations (striped contours). Analysts select partial classes as positive (solid red contours) or negative (solid blue contours) to adjust the label recommendations ((c) and (d)). (e) The line chart monitors the training accuracy for seen classes and testing accuracy for unseen classes. (f) The class-attribute matrix is built interactively via collaboration between analysts and the machine.

show abstract

Visualizing surrogate decision trees of convolutional neural networks

Cited by 28 publications

References 27 publications

Applications of Artificial Intelligence Based on Medical Imaging in Glioma: Current State and Future Challenges

Applications of Artificial Intelligence Based on Medical Imaging in Glioma: Current State and Future Challenges

Visual Neural Decomposition to Explain Multivariate Data Sets

Towards Visual Explainable Active Learning for Zero-Shot Classification

Contact Info

Product

Resources

About