Urine Dataset having eight particles classes
Taner Tuncer, Merve Erku\c{s}, Ahmet \c{C}{\i}nar, Hakan, Ayy{\i}ld{\i}z, Seda Arslan Tuncer

TL;DR
This paper introduces a comprehensive dataset of urine sediment particle images across eight classes to facilitate the development of AI-based automatic identification methods, aiming to improve diagnostic accuracy and efficiency.
Contribution
It provides a new, publicly available dataset of 8509 urine sediment particle images across eight classes for AI research in medical diagnostics.
Findings
Dataset contains 8509 images from 409 patients.
Includes 8 particle classes relevant to medical diagnosis.
Aims to support AI development for urine sediment analysis.
Abstract
Urine sediment examination (USE) is one of the main tests used in the evaluation of diseases such as kidney, urinary, metabolic, and diabetes and to determine the density and number of various cells in the urine. USE's manual microscopy is a labor-intensive and time-consuming, imprecise, subjective process. Recently, automatic analysis of urine sediment has become inevitable in the medical field. In this study, we propose a dataset that can be used by artificial intelligence techniques to automatically identify particles in urine sediment images. The data set consists of 8509 particle images obtained by examining the particles in the urine sediment obtained from 409 patients from the Biochemistry Clinics of Elazig Fethi Sekin Central Hospital. Particle images are collected in 8 classes in total and these are Erythrocyte, Leukocyte, Epithelial, Bacteria, Yeast, Cylinders, Crystals, and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsUrinary Tract Infections Management
