Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction

• URL: http://arxiv.org/abs/2604.16955v2
• Date: Sat, 25 Apr 2026 21:59:12 GMT
• Title: Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction
• Abstract summary: Recent methods have moved toward increasing generative complexity, but the conditions under which this complexity is necessary remain unclear.<n>We propose that generative complexity should match the entropy of a predictable task's conditional posterior component, with training-inference input alignment required in all regimes.<n>We validated this framework on a fundus autofluorescence dataset by contrasting five configurations.
• Score: 3.0602131532925436
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting disease progression from longitudinal imaging is useful for clinical decision making and trial design. Recent methods have moved toward increasing generative complexity, but the conditions under which this complexity is necessary remain unclear. We propose that generative complexity should match the entropy of the predictable component of a task's conditional posterior, with training-inference input alignment required in all regimes. Two model-light measurements, a task-entropy analysis on raw image pairs and a posterior-concentration analysis on a stochastic model, let practitioners assess the complexity a task warrants before committing to a modeling framework. We validated this framework on a fundus autofluorescence (FAF) dataset by contrasting five conditioning configurations, sharing one architecture and training set, spanning standard conditional diffusion, inference-aligned stochastic training, and deterministic regression. Training-inference alignment produced large gains (delta-SSIM +0.082, SSIM +0.086, both p < 0.001), while the choice among aligned frameworks produced no clinically meaningful difference across evaluated metrics. Across two FAF platforms, inter-visit change was dominated by time-invariant acquisition variability rather than disease progression, and the stochastic models' posteriors collapsed to an effective point, explaining the framework equivalence. We trained a deterministic Temporal Retinal U-Net (TRU) and evaluated it on 28,899 eyes across three manufacturers and two modalities (two FAF platforms and en-face SLO), with three independent cohorts evaluated zero-shot. TRU matched or exceeded three published baselines on delta-SSIM, SSIM, and PSNR. These findings show that when disease progression is slow compared with acquisition variability, a deterministic regression model matches or outperforms more complex stochastic alternatives.

Related papers

• Toward Personalized Digital Twins for Cognitive Decline Assessment: A Multimodal, Uncertainty-Aware Framework [0.2566571621858396]
  The PCD-DT framework provides a principled starting point for personalized in silico modeling in neurodegenerative disease.<n>This work positions PCD-DT as a foundational step toward clinically deployable, uncertainty-aware digital twin systems.
  arXiv  Detail & Related papers  (2026-04-29T21:40:55Z)
• Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images [47.944896477309555]
  We propose a robust alignment technique for Standard Fundus Images (SFIs) and Ultra-Widefield Fundus Images (UWFIs)<n>Our method, termed Particle Diffusion Matching (PDM), performs alignment through an iterative Random Walk Correspondence Search (RWCS) guided by a diffusion model.<n>PDM achieves state-of-the-art performance across multiple retinal image alignment benchmarks.
  arXiv  Detail & Related papers  (2026-04-11T08:09:53Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis [1.8747639074211104]
  We present the first comprehensive validation of hyperbolic representation learning for medical image analysis.<n>We demonstrate statistically significant gains across eleven in-distribution datasets and three ViT models.<n>Our proposed method promotes domain-invariant features and outperforms state-of-the-art Euclidean methods by an average of $+2.1%$ AUC.
  arXiv  Detail & Related papers  (2026-02-03T08:50:24Z)
• POWDR: Pathology-preserving Outpainting with Wavelet Diffusion for 3D MRI [7.901173149711112]
  POWDR is a pathology-preserving outpainting framework for 3D MRI based on a conditioned wavelet diffusion model.<n>Our approach leverages wavelet-domain conditioning to enhance high-frequency detail and blurring common in latent diffusion models.
  arXiv  Detail & Related papers  (2026-01-14T00:20:13Z)
• Controllable Probabilistic Forecasting with Stochastic Decomposition Layers [1.3995263206621]
  We introduce Decomposition Layers (SDL) for converting deterministic machine learning weather models into ensemble systems.<n>SDL applies learned perturbations at three decoder scales through latent-driven modulation, per-pixel noise, and channel scaling.<n>When applied to WXFormer via transfer learning, SDL requires less than 2% of the computational cost needed to train the baseline model.
  arXiv  Detail & Related papers  (2025-12-21T17:10:00Z)
• Functional Localization Enforced Deep Anomaly Detection Using Fundus Images [3.0606378255830253]
  Diabetic retinopathy and age-related macular degeneration were detected reliably, whereas glaucoma remained the most frequently misclassified disease.<n>We developed a GANomaly-based anomaly detector, achieving an AUC of 0.76 while providing inherent reconstruction-based explainability and robust generalization to unseen data.
  arXiv  Detail & Related papers  (2025-11-23T21:56:40Z)
• Stage-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI [1.1458853556386799]
  We present the first stage-specific, cross-sectional benchmarking of deep learning models for follow-up MRI.<n>We analyze different post-RT scans independently to test whether architecture performance depends on time-point.<n>These results establish a stage-aware benchmark and motivate future work incorporating longitudinal modeling, multi-sequence MRI, and larger multi-center cohorts.
  arXiv  Detail & Related papers  (2025-11-23T19:38:03Z)
• T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis [15.624549727053475]
  Existing model-merging techniques fail to deliver consistent gains across diverse medical modalities.<n>We introduce Test-Time Task adaptive merging (T3), a backpropagation-free framework that computes per-sample coefficients.<n>We present a rigorous cross-evaluation protocol spanning in-domain, base-to-novel, and corruptions across four modalities.
  arXiv  Detail & Related papers  (2025-10-31T08:05:40Z)
• AttentiveGRUAE: An Attention-Based GRU Autoencoder for Temporal Clustering and Behavioral Characterization of Depression from Wearable Data [46.262619407930266]
  We present AttentiveGRUAE, a novel attention-based gated recurrent unit (GRU) autoencoder designed for temporal clustering and prediction of outcome from longitudinal wearable data.<n>We evaluate AttentiveGRUAE on longitudinal sleep data from 372 participants (GLOBEM 2018-2019)<n>It demonstrates superior performance over baseline clustering, domain-aligned self-supervised, and ablated models in both clustering quality and depression classification.
  arXiv  Detail & Related papers  (2025-10-02T20:52:16Z)
• MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation [55.37355146924576]
  MedSeqFT is a sequential fine-tuning framework for medical image analysis.<n>It adapts pre-trained models to new tasks while refining their representational capacity.<n>It consistently outperforms state-of-the-art fine-tuning strategies.
  arXiv  Detail & Related papers  (2025-09-07T15:22:53Z)
• Enhancing ALS Progression Tracking with Semi-Supervised ALSFRS-R Scores Estimated from Ambient Home Health Monitoring [3.210027230758067]
  Self-attention achieved the lowest prediction error for subscale-level models.<n>We identified distinct homogeneity-hegeneity profiles across functional domains.
  arXiv  Detail & Related papers  (2025-07-13T02:56:40Z)
• Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates [27.933665582178115]
  Foundation medical segmentation models, with MedSAM being the most popular, have achieved promising performance across organs and lesions.<n>MedSAM still suffers from compromised performance on specific lesions with intricate structures and appearance, as well as bounding box prompt-induced perturbations.<n>We propose to encourage maximizing factorized conditional probabilities of the posterior prediction probability using a proposed distribution-approxd latent conditional random field loss combined with an entropy minimization loss.
  arXiv  Detail & Related papers  (2025-04-02T03:03:34Z)
• Multi-scale Spatio-temporal Transformer-based Imbalanced Longitudinal Learning for Glaucoma Forecasting from Irregular Time Series Images [45.894671834869975]
  Glaucoma is one of the major eye diseases that leads to progressive optic nerve fiber damage and irreversible blindness. We introduce the Multi-scale Spatio-temporal Transformer Network (MST-former) based on the transformer architecture tailored for sequential image inputs. Our method shows excellent generalization capability on the Alzheimer's Disease Neuroimaging Initiative (ADNI) MRI dataset, with an accuracy of 90.3% for mild cognitive impairment and Alzheimer's disease prediction.
  arXiv  Detail & Related papers  (2024-02-21T02:16:59Z)
• The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease detection [51.697248252191265]
  This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation. We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare. Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
  arXiv  Detail & Related papers  (2023-09-13T10:40:41Z)
• Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations [84.42837346400151]
  Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare. Existing causal inference approaches consider regular, discrete-time intervals between observations and treatment decisions. We propose a controllable simulation environment based on a model of tumor growth for a range of scenarios.
  arXiv  Detail & Related papers  (2022-06-16T17:15:15Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation [56.622832383316215]
  We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans. Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our empirical results show that CyTran outperforms all competing methods.
  arXiv  Detail & Related papers  (2021-10-12T23:25:03Z)
• Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation [64.59521853145368]
  Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features.
  arXiv  Detail & Related papers  (2021-09-08T07:56:51Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)
• Consistency Guided Scene Flow Estimation [159.24395181068218]
  CGSF is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. We show that the proposed model can reliably predict disparity and scene flow in challenging imagery. It achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.
  arXiv  Detail & Related papers  (2020-06-19T17:28:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.