Article

Visual interpretability of image-based classification models by generative latent space disentanglement applied to in vitro fertilization

2023-11-17

Abstract excerpt

The success of deep learning in identifying complex patterns exceeding human intuition comes at the cost of interpretability. Non-linear entanglement of image features makes deep learning a “black box” lacking human meaningful explanations for the models’ decision. We present DISCOVER, a generative model designed to discover the underlying visual properties driving image-based classification models. DISCOVER learn...

Topics

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

Identifiers and source

Literature Corpus work: 5730004d-58b3-5410-bd97-807db1741e12
DOI: 10.1101/2023.11.15.566968

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Visual interpretability of image-based classification models by generative latent space disentanglement applied to in vitro fertilizationDOI 10.1101/2023.11.15.566968Read

<i>Delta Marches</i> : Generative AI based image synthesis to decode disease-driving morphologic transformationsSemantic proximity Read

Quantitative Attributions with CounterfactualsSemantic proximity Read

An artificial intelligence tool predicts blastocyst development from static images of fresh mature oocytesSemantic proximity Read

Comparing tangible retinal image characteristics with deep learning features reveals their complementarity for gene association and disease predictionSemantic proximity Read

An explainable deep learning-based algorithm with an attention mechanism for predicting the live birth potential of mouse embryosSemantic proximity Read

Quantifying Interpretation Reproducibility in Vision Transformer Models with TAVACSemantic proximity Read

Soft Optical Sensor for Embryo Quality Evaluation Based on Multi-Focal Image Fusion and RAG-Enhanced Vision TransformersSemantic proximity Read

Comparing tangible retinal image characteristics with deep learning features reveals their complementarity for gene association and disease predictionSemantic proximity Read

Expertise-informed Generative AI Enables Ultra-High Data Efficiency for Building Generalist Medical Foundation ModelSemantic proximity Read

Determination of nuclear position by the arrangement of actin filaments using deep generative networksSemantic proximity Read

Deep learning-based embryo assessment of static images can reduce the time to live birth in<i>in vitro</i>fertilizationSemantic proximity Read

Revealing invisible cell phenotypes with conditional generative modelingSemantic proximity Read