Abstract
Eye diseases can have highly adverse outcomes without an early diagnosis and correct monitoring. Retinopathy of Prematurity (ROP) Plus Form, in particular, is a disease that can lead to childhood blindness, and its diagnosis requires medical experts to examine the retinal condition manually. Although developments in screening equipment have helped, this is still a time-consuming and subjective task. The development of automatic tools for Retinal Blood Vessel Segmentation allows the extraction of blood vessels from fundus images, which healthcare experts can then use to perform the diagnosis, monitoring, and prognosis of eye diseases. Thus, developing such a segmentation tool is a widely explored task with different methodologies that can be followed. However, many studies try to segment all the blood vessels rather than only the most important ones. In this work, we present a segmentation pipeline to segment only the main vessels whose characteristics can be used to assess ROP Plus Form disease. This pipeline uses different operations and filters, including CIELAB Enhancement, Background Normalization, Bell-Shaped Gaussian Matched Filtering, Modified Top-Hat operation, and Frangi Filtering. The final segmentation is done by determining a threshold value using the Triangle Threshold algorithm. The pipeline was tested in the well-known DRIVE Database, achieving an Accuracy of 0.949, Specificity of 0.963, and Sensitivity of 0.756. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Background: ROP Plus Form is an eye disease that can lead to blindness, and diagnosing it requires medical experts to manually examine the retinal condition. This task is challenging due to its subjective nature and poor image quality. Therefore, developing automatic tools for Retinal Blood Vessel Segmentation in fundus images could assist healthcare experts in diagnosing, monitoring, and prognosing the disease. Objective: This study focuses on developing a novel pipeline for automatically segmenting retinal blood vessels. The main requirements are that it can correctly identify the blood vessels in fundus images and perform well on different systems used for newborn evaluation. Methods: The pipeline uses different methods, including CIELAB Enhancement, Background Normalization, BellShaped Gaussian Matched Filtering, Modified Top-Hat operation, and a combination of vesselness filtering composed of Frangi and Jerman Filters. The segmentation is done by determining a threshold using the Triangle Threshold algorithm. A novel filter is also proposed to remove the Optical Disc artifacts from the primary segmentation based on the Circular Hough Transform. The segmentation pipeline is combined with different pretrained Convolution Neural Network architectures to evaluate its automatic classification capabilities. Results: The pipeline was tested with newborn fundus images acquired with Clarity RetCam3 and Phoenix ICON systems. The results were compared against annotations from three ophthalmologic experts. Clarity RetCam3 images achieved an accuracy of 0.94, specificity of 0.95, and sensitivity of 0.81, while Phoenix ICON images achieved an accuracy of 0.94, specificity of 0.97, and sensitivity of 0.83. The pipeline was also tested for the DRIVE Database, achieving an accuracy of 0.95, specificity of 0.97, and sensitivity of 0.82. For the classification task, the best results were achieved with the DenseNet121 architecture with an accuracy of 0.946. Conclusion: The segmentation scores were auspicious and confirmed the clinical relevance of the proposed pipeline. It has also proven to have a good generalization performance, essential for easier clinic integration. Finally, preliminary results on using CNNs showed how our work can be used to develop fully automatic tools for diagnosing ROP Plus form disease.