Curated_Br35H_MRI_Subset

Read full text
Authors: Yasser Nizamli
Cited by: 0

Abstract

A cleaned subset of 840 brain MRI images (350 normal / 490 tumor) from the original Br35H dataset. Near-duplicates and mislabeled samples were removed through automated ORB matching and manual verification. Created for the study "On the Validity of Public MRI Datasets for Neuro-Oncological Abnormality Detection and Classification" (Nizamli & Filatov, 2025) to serve as a quality-controlled benchmark for brain tumor detection models.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
2 January 2026
Document type
Dataset