Article

Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology

2022-07-16

Abstract excerpt

Trust and transparency are critical for deploying deep learning (DL) models into the clinic. DL application poses generalisation obstacles since training/development datasets often have different data distributions to clinical/production datasets that can lead to incorrect predictions with underestimated uncertainty. To investigate this pitfall, we benchmarked one pointwise and three approximate Bayesian DL models...

Topics

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

Identifiers and source

Literature Corpus work: b9cd9b39-0676-511b-961a-b58174d7c3ee
DOI: 10.1101/2022.07.14.500142

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncologyDOI 10.1101/2022.07.14.500142Read

Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncologySemantic proximity Read

High-Sensitivity Pan-Cancer AI Assessment of Lymph Node Metastasis via Uncertainty QuantificationSemantic proximity Read

Uncertainty-Aware Deep Learning for Segmentation of Primary Tumour and Pathologic Lymph Nodes in Oropharyngeal Cancer: Insights from a Multi-Centre CohortSemantic proximity Read

Advancing oncology with federated learning: transcending boundaries in breast, lung, and prostate cancer. A systematic reviewSemantic proximity Read

Reliable machine learning models in genomic medicine using conformal predictionSemantic proximity Read

Experimental Design Dominates Model Architecture in Multi-Model Cancer Classification: A Translational Bioinformatics Analysis Across Small-n and Large-n RegimesSemantic proximity Read

Established Machine Learning Matches Tabular Foundation Models in Clinical PredictionsSemantic proximity Read

Predicting IDH Mutation in Glioma Patients Using Deep Learning Algorithms with Conformal Prediction.Semantic proximity Read

Cooperative Modular Representation Learning for Lung Adenocarcinoma Survival Prediction from Transcriptomic and Clinical DataSemantic proximity Read

Data Farming to Table: Combined Use of a Learning Health System Infrastructure, Statistical Profiling, and Artificial Intelligence for Automating Toxicity and 3-year Survival for Quantified Predictive Feature Discovery from Real-World Data for Patients Having Head and Neck CancersSemantic proximity Read

Large-Scale Deep Learning for Metastasis Detection in Pathology ReportsSemantic proximity Read

Machine Unlearning for GDPR Right-to-Erasure in Antimicrobial Resistance Prediction ModelsSemantic proximity Read