Urine Microscopic Image Dataset

TL;DR

This paper introduces the Urine Microscopic Image Dataset (UMID), a publicly available collection of around 3700 annotated urine sediment images for advancing deep learning in urinalysis.

Contribution

The paper presents a new, publicly accessible urine sediment microscopic image dataset with detailed annotations, addressing the lack of available datasets for urinalysis research.

Findings

Dataset contains 3700+ cell annotations

Includes three cell categories: RBC, pus, epithelial cells

Facilitates deep learning research in urinalysis

Abstract

Urinalysis is a standard diagnostic test to detect urinary system related problems. The automation of urinalysis will reduce the overall diagnostic time. Recent studies used urine microscopic datasets for designing deep learning based algorithms to classify and detect urine cells. But these datasets are not publicly available for further research. To alleviate the need for urine datsets, we prepare our urine sediment microscopic image (UMID) dataset comprising of around 3700 cell annotations and 3 categories of cells namely RBC, pus and epithelial cells. We discuss the several challenges involved in preparing the dataset and the annotations. We make the dataset publicly available.