Lirot.ai: A Novel Platform for Crowd-Sourcing Retinal Image Segmentations

TL;DR

Lirot.ai is a new platform that streamlines crowd-sourced retinal image segmentation using iPadOS devices and Apple Pencil, aiming to efficiently create large annotated datasets for deep learning in medical imaging.

Contribution

The paper introduces Lirot.ai, a novel platform integrating hardware and software components to facilitate remote, crowd-sourced image segmentation with enhanced speed and accuracy.

Findings

Successfully created a retinal fundus dataset with segmentations

Demonstrated the platform's usability for medical image annotation

Proposed active learning to expand datasets efficiently

Abstract

Introduction: For supervised deep learning (DL) tasks, researchers need a large annotated dataset. In medical data science, one of the major limitations to develop DL models is the lack of annotated examples in large quantity. This is most often due to the time and expertise required to annotate. We introduce Lirot. ai, a novel platform for facilitating and crowd-sourcing image segmentations. Methods: Lirot. ai is composed of three components; an iPadOS client application named Lirot. ai-app, a backend server named Lirot. ai-server and a python API name Lirot. ai-API. Lirot. ai-app was developed in Swift 5.6 and Lirot. ai-server is a firebase backend. Lirot. ai-API allows the management of the database. Lirot. ai-app can be installed on as many iPadOS devices as needed so that annotators may be able to perform their segmentation simultaneously and remotely. We incorporate Apple Pencil compatibility, making the segmentation faster, more accurate, and more intuitive for the expert than any other computer-based alternative. Results: We demonstrate the usage of Lirot. ai for the creation of a retinal fundus dataset with reference vasculature segmentations. Discussion and future work: We will use active learning strategies to continue enlarging our retinal fundus dataset by including a more efficient process to select the images to be annotated and distribute them to annotators.