mlsanityData to 7 Oct 2026

Combining 3D Image and Tabular Data via the Dynamic Affine Feature Map Transform

arXiv 2107.05990 ↗First posted 13 Jul 2021eess.IV cs.CV cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

Prior work on diagnosing Alzheimer's disease from magnetic resonance images of the brain established that convolutional neural networks (CNNs) can leverage the high-dimensional image information for classifying patients. However, little research focused on how these models can utilize the usually low-dimensional tabular information, such as patient demographics or laboratory measurements. We introduce the Dynamic Affine Feature Map Transform (DAFT), a general-purpose module for CNNs that dynamically rescales and shifts the feature maps of a convolutional layer, conditional on a patient's tabular clinical information. We show that DAFT is highly effective in combining 3D image and tabular information for diagnosis and time-to-dementia prediction, where it outperforms competing CNNs with a mean balanced accuracy of 0.622 and mean c-index of 0.748, respectively. Our extensive ablation study provides valuable insights into the architectural properties of DAFT. Our implementation is available at https://github.com/ai-med/DAFT.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 8 of its 32 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

8 of 32 references.

References · 8

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  4. 2019Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluationcited by 106
  5. 2020Semi-Structured Deep Piecewise Exponential Modelscited by 13
  6. 2018End-To-End Alzheimer's Disease Diagnosis and Biomarker Identificationcited by 12
  7. 2019A Wide and Deep Neural Network for Survival Analysis from Anatomical Shape and Tabular Clinical Datacited by 12
  8. 2020INSIDE: Steering Spatial Attention with Non-Imaging Information in CNNscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 6; 2024: 8; 2025: 8; 2026: 10.

38 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2022MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray imagescited by 53
  3. 2024DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistencycited by 51
  4. 2022Deep Multi-modal Fusion of Image and Non-image Data in Disease Diagnosis and Prognosis: A Reviewcited by 37
  5. 2024TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Datacited by 32
  6. 2024Review of multimodal machine learning approaches in healthcarecited by 30
  7. 2023Dynamic Multimodal Information Bottleneck for Multimodality Classificationcited by 14
  8. 2023Multimodal Contrastive Learning and Tabular Attention for Automated Alzheimer's Disease Predictioncited by 12
  9. 2025STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classificationcited by 12
  10. 2023GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Datacited by 10
  11. 2022A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI imagescited by 6
  12. 2024Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generationcited by 6
26 more
  1. 2024CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysiscited by 6
  2. 2022Medical Diagnosis with Large Scale Multimodal Transformers: Leveraging Diverse Data for More Accurate Diagnosiscited by 5
  3. 2023Treatment Outcome Prediction for Intracerebral Hemorrhage via Generative Prognostic Model with Imaging and Tabular Datacited by 5
  4. 2023RegBN: Batch Normalization of Multimodal Data with Regularizationcited by 5
  5. 2023Visual-Attribute Prompt Learning for Progressive Mild Cognitive Impairment Predictioncited by 5
  6. 2025Learning Contrastive Multimodal Fusion with Improved Modality Dropout for Disease Detection and Predictioncited by 5
  7. 2024A Progressive Single-Modality to Multi-Modality Classification Framework for Alzheimer's Disease Sub-type Diagnosiscited by 3
  8. 2026VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learningcited by 3
  9. 2022Survival Analysis for Idiopathic Pulmonary Fibrosis using CT Images and Incomplete Clinical Datacited by 2
  10. 2024Automatic Prediction of Stroke Treatment Outcomes: Latest Advances and Perspectivescited by 2
  11. 2025Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnosticscited by 2
  12. 2024TabMixer: Noninvasive Estimation of the Mean Pulmonary Artery Pressure via Imaging and Tabular Data Mixingcited by 1
  13. 2025PHGNN: A Novel Prompted Hypergraph Neural Network to Diagnose Alzheimer's Diseasecited by 1
  14. 2025Small Lesions-aware Bidirectional Multimodal Multiscale Fusion Network for Lung Disease Classificationcited by 1
  15. 2025AMF-MedIT: An Efficient Align-Modulation-Fusion Framework for Medical Image-Tabular Datacited by 0
  16. 2025Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Processcited by 0
  17. 2025Cross-Modal Alignment via Variational Copula Modellingcited by 0
  18. 2026When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusioncited by 0
  19. 2026Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classificationcited by 0
  20. 2026KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learningcited by 0
  21. 2026Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patientscited by 0
  22. 2026Whole-Body MRI Classification via Prompt-Based Clinical Conditioningcited by 0
  23. 2026Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRIcited by 0
  24. 2026M2PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Diseasecited by 0
  25. 2026Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Modelcited by 0
  26. 2026CAMOS: Coupled Oscillatory State-Space Model for Multimodal Clinical Time-Seriescited by 0