Brain tumor detection and segmentation - Interactive framework with a visual interface and feedback facility for dynamically improved accuracy and trust

Sep 24, 2026

Uploaded by Ivy

Brain cancers caused by malignant brain tumors remain among the most fatal cancer types, largely due to challenges in early detection. The work addresses this by targeting tumor detection and segmentation from 2D and 3D brain MRI scans using an automated system with a web-based user interface. The approach aims for over 90% detection accuracy and reports Dice-score based segmentation quality. It supports user uploads or hospital database access and includes a feedback mechanism to refine model training for improved future predictions.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages47

Reading Time1 h 58 min

AccessFree to download

Abstract

Introduction

Brain anatomy and tumor basics

Types of brain tumors and clinical impact

Imaging-based diagnosis context

PLOS ONE OPEN ACCESS Citation: Sailunaz K, Bestepe D, Alhajj S, ¨Ozyer T, Rokne J, Alhajj R (2023) Brain tumor detection and segmentation: Interactive framework with a visual interface and feedback facility for dynamically improved accuracy and trust. PLoS ONE 18(4): e0284418 . [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pone.0284418 Editor: Gulistan Raja, University of Engineering & Technology, Taxila, PAKISTAN Received: January 2, 2023 Accepted: March 30, 2023 Published: April 17, 2023 Copyright: © 2023 Sailunaz et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: Experiment data files. 2022. Available from: [https://www.kaggle.com/](https://www.kaggle.com/)[ ](https://www.kaggle.com/)[datasets/navoneel/brain-mri-images-for-brain-](datasets/navoneel/brain-mri-images-for-brain-)tumor-detection [https://figshare.com/articles/](https://figshare.com/articles/)[ ](https://figshare.com/articles/)dataset/brain_tumor_dataset/1512427 [https://](https://)[ ](https://)[www.kaggle.com/datasets/sanglequang/](www.kaggle.com/datasets/sanglequang/)[ ](www.kaggle.com/datasets/sanglequang/)[brats2018?select=MICCAI_BraTS_2018_Data_](brats2018?select=MICCAI_BraTS_2018_Data_)[Training](Training.)[.](Training.) Funding: The authors received no specific funding for this work. RESEARCH ARTICLE Brain tumor detection and segmentation: Interactive framework with a visual interface and feedback facility for dynamically improved accuracy and trust Kashfia Sailunaz1, Deniz Bestepe2, Sleiman Alhajj3 *, Tansel ¨Ozyer4, Jon Rokne1, Reda Alhajj1,2,5 1 Department of Computer Science, University of Calgary, Alberta, Canada, 2 Department of Computer Engineering, Istanbul Medipol University, Istanbul, Turkey, 3 International School of Medicine, Istanbul Medipol University, Istanbul, Turkey, 4 Department of Computer Engineering, Ankara Medipol University, Ankara, Turkey, 5 Department of Health Informatics, University of Southern Denmark, Odense, Denmark * alhajj@ucalgary.ca Abstract Brain cancers caused by malignant brain tumors are one of the most fatal cancer types with a low survival rate mostly due to the difficulties in early detection. Medical professionals therefore use various invasive and non-invasive methods for detecting and treating brain tumors at the earlier stages thus enabling early treatment. The main non-invasive methods for brain tumor diagnosis and assessment are brain imaging like computed tomography (CT), positron emission tomography (PET) and magnetic resonance imaging (MRI) scans. In this paper, the focus is on detection and segmentation of brain tumors from 2D and 3D brain MRIs. For this purpose, a complete automated system with a web application user interface is described which detects and segments brain tumors with more than 90% accuracy and Dice scores. The user can upload brain MRIs or can access brain images from hospital databases to check presence or absence of brain tumor, to check the existence of brain tumor from brain MRI features and to extract the tumor region precisely from the brain MRI using deep neural networks like CNN, U-Net and U-Net++ . The web application also provides an option for entering feedbacks on the results of the detection and segmentation to allow healthcare professionals to add more precise information on the results that can be used to train the model for better future predictions and segmentations. Introduction The brain is one of the major organs of human body. It controls most ofthe nervous system and it is responsible for managing most of the functions ofour body [ 1] . The brain weighs about 3 pounds and it contains soft tissues, fat, protein, carbohydrate, water and salts [2] . The soft tissues (i.e. gray matter and whi

FAQs

Why is early brain tumor detection important?

Early detection improves the ability to begin treatment sooner. The document notes low survival rates due to difficulties in early detection, motivating non-invasive diagnostic approaches.

What data modalities does the proposed system use?

The focus is on detecting and segmenting brain tumors from 2D and 3D brain MRIs.

How does the system improve accuracy over time?

A web application allows users to enter feedback on detection and segmentation results, which can be used to train the model for better future predictions and segmentations.

Sep 24, 2026

Uploaded by Ivy