IJRTI
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)

Call For Paper

For Authors

Forms / Download

Published Issue Details

Editorial Board

Other IMP Links

Facts & Figure

Impact Factor : 8.14

Issue per Year : 12

Volume Published : 11

Issue Published : 120

Article Submitted : 24205

Article Published : 9239

Total Authors : 24597

Total Reviewer : 847

Total Countries : 165

Indexing Partner

Licence

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Published Paper Details
Paper Title: NeuroSight - Automated Brain Tumor Radiology Report Generation Using 3D U-Net Segmentation, and Vision-Language Models
Authors Name: Geet Kale , Anish Godse , Shardul Sant , Alok Mistry , Sujata Deshmukh
Download E-Certificate: Download
Author Reg. ID:
IJRTI_212093
Published Paper Id: IJRTI2604310
Published In: Volume 11 Issue 4, April-2026
DOI:
Abstract: The process of diagnosing brain tumors by analyzing MRI images is quite tedious and requires great knowledge. In this paper, we introduce a system that automates the whole process of brain tumor analysis and report generation. Our system takes T1-weighted and T2-weighted MRIs from the BraTS dataset. Firstly, the inputs go through multiple preprocessing steps, namely, normalization of intensity, resizing, skull stripping, and contrast enhancement. After the preprocess step, a brain tumor segmentation model with 3D U-Net structure is applied to segment out the tumors. Our model obtains 0.88 Dice Similarity Coefficient (Dice Score). Then the segmented outputs will be fed into a two-pipeline framework. On one hand, our system adopts a modified EfficientNet-B3 architecture that is capable of tumor classification in four classes with an accuracy rate of 89.95%. On the other hand, the atlas-based region mapping technique, together with the Harvard Brain Atlas, is used to determine the location of brain tumors in cortical, subcortical, and cerebellar regions. Then the system extracts some important clinical features, i.e., hemisphere, lobes involved, size of the tumor, and spread method. In addition, the information extracted from visualized MRI images is also considered when feeding the input to a fine-tuned Qwen2-VL-7B vision-language model to generate reports automatically. ROUGE and BERTScore evaluation is performed, which shows that our model achieves a 0.845 BERTScore F1.
Keywords: Brain MRI, Radiology Report Generation, 3D U-Net, Tumor Segmentation, EfficientNet-B3, Atlas-Based Region Mapping, Vision-Language Model, Qwen2-VL, BraTS Dataset, Deep Learning.
Cite Article: "NeuroSight - Automated Brain Tumor Radiology Report Generation Using 3D U-Net Segmentation, and Vision-Language Models", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 4, page no.c307-c312, April-2026, Available :http://www.ijrti.org/papers/IJRTI2604310.pdf
Downloads: 000205514
ISSN: 2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publication Details: Published Paper ID: IJRTI2604310
Registration ID:212093
Published In: Volume 11 Issue 4, April-2026
DOI (Digital Object Identifier):
Page No: c307-c312
Country: Mumbai, Maharashtra, India
Research Area: Computer Engineering 
Publisher : IJ Publication
Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2604310
Published Paper PDF: https://www.ijrti.org/papers/IJRTI2604310
Share Article:

Share Facebook Twitter Google+ Pinterest LinkedIn Email Tumblr WhatsApp Google Gmail

Click Here to Download This Article

Article Preview
Click Here to Download This Article
Major Indexing from www.ijrti.org
Google Scholar ResearcherID Thomson Reuters Mendeley : reference manager Academia.edu
arXiv.org : cornell university library Research Gate CiteSeerX DOAJ : Directory of Open Access Journals
DRJI Index Copernicus International Scribd DocStoc

ISSN Details

ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED, Journal Starting Year (ESTD) : 2016

DOI (A digital object identifier)


Providing A digital object identifier by DOI.ONE
How to Get DOI?

Conference

Open Access License Policy

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Creative Commons License This material is Open Knowledge This material is Open Data This material is Open Content

Important Details

Join RMS/Earn 300
IJRTI

WhatsApp
Click Here

Indexing Partner
Copyright © 2026 - All Rights Reserved - IJRTI