# PRISM-DR: Per-lesion Retinal Inference with Specialist Models for Diabetic Retinopathy

arXiv: https://arxiv.org/abs/2607.19864 · HTML: https://mlsanity.com/paper/2607.19864/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 71 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection](https://mlsanity.com/paper/2202.06934/) (2022)
- [A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability](https://mlsanity.com/paper/2008.09772/) (2020)
- [Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy](https://mlsanity.com/paper/1710.01711/) (2017)
- [CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading](https://mlsanity.com/paper/1911.01376/) (2019)
- [DRvertGRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images](https://mlsanity.com/paper/1910.11777/) (2019)
- [Deep Learning based Computer-Aided Diagnosis Systems for Diabetic Retinopathy: A Survey](https://mlsanity.com/paper/1811.01238/) (2018)
- [Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading](https://mlsanity.com/paper/1904.08764/) (2019)
- [Microaneurysm Detection in Fundus Images Using a Two-step Convolutional Neural Networks](https://mlsanity.com/paper/1710.05191/) (2017)
- [BezierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Images](https://mlsanity.com/paper/2108.00760/) (2021)
- [DRDrV3: Complete Lesion Detection in Fundus Images Using Mask R-CNN, Transfer Learning, and LSTM](https://mlsanity.com/paper/2108.08095/) (2021)
- [TJDR: A High-Quality Diabetic Retinopathy Pixel-Level Annotation Dataset](https://mlsanity.com/paper/2312.15389/) (2023)
- [Diabetic Retinopathy Lesion Segmentation through Attention Mechanisms](https://mlsanity.com/paper/2602.07301/) (2026)
- [A Deep Learning-Based Unified Framework for Red Lesions Detection on Retinal Fundus Images](https://mlsanity.com/paper/2109.05021/) (2021)

## Abstract (arXiv)

Diabetic retinopathy is a leading cause of preventable blindness; its early lesions are small, low contrast, and easily missed in manual screening. Most automated detectors handle the four non-proliferative DR lesions: microaneurysms, hemorrhages, hard exudates, and soft exudates, with a single multi-class model, even though these lesions differ sharply in size, color, morphology, and prevalence, so a shared model favors common, easy classes over rare, difficult ones. We present PRISM-DR, a lesion-specific pipeline that trains one single-class detector per lesion, each with its own configuration. From a raw fundus image, the pipeline applies region of interest cropping, fundus-specific preprocessing, four parallel YOLO detectors, tiling, per-lesion ensembling of five cross-validation folds, and an inter-lesion suppression step that resolves overlaps by physical lesion size and clinical priority rather than confidence. Per lesion, the best of five YOLO generations is selected, and augmentation is tuned by Bayesian optimization. Trained on IDRiD with stratified five-fold cross-validation, the system reaches a test mAP50 of 0.527 and F1 of 0.529, highest AP50 on hard exudates with 0.561. Without fine-tuning, the models transfer well where the imaging scale is close to IDRiD and degrade as field of view and resolution depart. These modest absolute results reflect a small single-source training set and a difficult task; however, treating each lesion as a separate detection problem is a practical alternative to a single multi-class model.