Article

Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs Improves Generalization

2022-07-14

Abstract excerpt

Adopting Convolutional Neural Networks (CNNs) in the daily routine of pathological diagnosis requires not only near-perfect precision, but also sufficient generalization to data shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model. Building on top of successfully existing techniques such as multi-task learning, doma...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: f517512c-e014-572a-9bc2-a23b213a0e4a
DOI: 10.21203/rs.3.rs-744740/v3

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs Improves GeneralizationDOI 10.21203/rs.3.rs-744740/v3Read

Contrastive Deep Encoding Enables Uncertainty-aware Machine-learning-assisted HistopathologySemantic proximity Read

Histopathological Domain Adaptation with Generative Adversarial Networks Bridging the Domain Gap Between Thyroid Cancer Histopathology DatasetsSemantic proximity Read

iMDPath: Interpretable Multi-task Digital Pathology Model for Clinical Pathological Image Prediction and InterpretationSemantic proximity Read

Adversarial Robustness of Capsule Networks for Medical Image ClassificationSemantic proximity Read

Using Progressive Context Encoders for Anomaly Detection in Digital Pathology ImagesSemantic proximity Read

Synthesis of diagnostic quality cancer pathology imagesSemantic proximity Read

Enhancing Histological Cancer Cell Detection: Integrating XAI with Deep Learning for Improved Accuracy, Interpretability, and Clinical TrustSemantic proximity Read

Multiple instance learning on tile level-pathology images provides accurate and interpretable classification for breast cancer molecular subtypesSemantic proximity Read

Quantifying Interpretation Reproducibility in Vision Transformer Models with TAVACSemantic proximity Read

Benchmarking Vision Encoders for Survival Analysis using Histopathological ImagesSemantic proximity Read

Towards Explainable Breast Cancer Classification Using SimCLR-Based Self-Supervised Representation LearningSemantic proximity Read

Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offsSemantic proximity Read