Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximization
Explore this paper's citation graph
Summary
This work proposes a novel decision explanation scheme based on CycleGAN activation maximization which generates high-quality visualizations of classifier decisions even in smaller data sets and conducts a user study in which this scheme significantly outperformed existing methods on the LIDC dataset for lung lesion malignancy classification.
- Type
- preprint
- Published
- 2020-10-09
- Cited by
- 30
- References
- 72
- Access
- Open access
- OpenAlex
- https://openalex.org/W3092090468
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:222290876
Keywords
Computer science, Artificial intelligence, Machine learning, Decision support system, Classifier (UML)
References
- Multiscale structural similarity for image quality assessment
- Learning Deconvolution Network for Semantic Segmentation
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
- The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.
- A second generation little jiffy
- When is a correlation matrix appropriate for factor analysis? Some decision rules.
- Ammonia as a case study for the spontaneous ionization of a simple hydrogen-bonded compound
- The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository
- QIN “Radiomics: The Process and the Challenges”
- Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
- The measurement of observer agreement for categorical data.
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Explaining nonlinear classification decisions with deep Taylor decomposition
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier
- Learning Deep Features for Discriminative Localization
- Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- HIPSTR and thousands of lncRNAs are heterogeneously expressed in human embryos, primordial germ cells and stable cell lines
- Image-to-Image Translation with Conditional Adversarial Networks
- A survey on deep learning in medical image analysis
Cited by
- Cluster Data Analysis with a Fuzzy Equivalence Relation to Substantiate a Medical Diagnosis
- Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods
- A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database
- Output-targeted baseline for neuron attribution calculation
- Explainable fuzzy cluster-based regression algorithm with gradient descent learning
- Reconnoitering the class distinguishing abilities of the features, to know them better
- Interpretability of Clinical Decision Support Systems Based on Artificial Intelligence from Technological and Medical Perspective: A Systematic Review
- Visualizing Global Explanations of Point Cloud DNNs
- DR-CIML: Few-shot Object Detection via Base Data Resampling and Cross-iteration Metric Learning
- Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks
- Few-Shot Object Detection: A Comprehensive Survey
- Deep Learning and Neural Networks: Decision-Making Implications
- Leveraging Activation Maximization and Generative Adversarial Training to Recognize and Explain Patterns in Natural Areas in Satellite Imagery
- TIDE: Test-Time Few-Shot Object Detection
- Flow AM: Generating Point Cloud Global Explanations by Latent Alignment
- DP-ProtoNet: An interpretable dual path prototype network for medical image diagnosis
- Enhancing Deep Learning Model Explainability in Brain Tumor Datasets Using Post-Heuristic Approaches
- Multi-View Part-Based Few-Shot Object Detection
- Few-shot learning for novel object detection in autonomous driving
- Towards a transparent and interpretable AI model for medical image classifications
Related papers
- Improving Interpretability of Deep Neural Networks in Medical Diagnosis by Investigating the Individual Units
- WHEN MULTIVARIATE FORECASTING MEETS UNSUPERVISED FEATURE LEARNING - TOWARDS A NOVEL ANOMALY DETECTION FRAMEWORK FOR DECISION SUPPORT Research-in-Progress
- PatternNet and PatternLRP - Improving the interpretability of neural networks
- Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
- Health Risk Prediction Using Big Medical Data - a Collaborative Filtering-Enhanced Deep Learning Approach
- Context-based image explanations for deep neural networks