Intelligent Neurodiagnostic Platform for Brain Tumor and Alzheimer's Detection Using Deep Learning Models

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autori principali: Mr.Gulve Rushikesh Somnath, Mr.Hase Onkar Balasaheb, Mr.Jadhav Pranav Prashant, Mr.Warghude Rushikesh Sudhakar, Ms.K. T. Bhandwalkar
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866902168590614528
author Mr.Gulve Rushikesh Somnath
Mr.Hase Onkar Balasaheb
Mr.Jadhav Pranav Prashant
Mr.Warghude Rushikesh Sudhakar
Ms.K. T. Bhandwalkar
author_facet Mr.Gulve Rushikesh Somnath
Mr.Hase Onkar Balasaheb
Mr.Jadhav Pranav Prashant
Mr.Warghude Rushikesh Sudhakar
Ms.K. T. Bhandwalkar
contents <p class="MsoNormal"><em><span>The timely and precise identification of neurological conditions such as brain tumors and Alzheimer’s disease carries profound implications for patient survival, treatment efficacy, and long-term quality of life. This paper introduces NeuroDetect AI, a web-deployable Intelligent Neurodiagnostic Platform that automates MRI-based brain scan classification across brain-tumor-positive,<span> </span>Alzheimer’s-positive,<span> </span>and<span> </span>neurologically<span> </span>normal<span> </span>categories.<span> </span>The<span> </span>system<span> </span>adopts<span> </span>a dual deep learning strategy:<span> </span>a custom Modified Convolutional Neural Network<span> </span>for brain tumor classification and an EfficientNetB0 transfer-learning model for Alzheimer’s detection. A standardized preprocessing pipeline consisting of grayscale conversion, CLAHE, intensity normalization, and augmentation feeds both models. The platform uses a Flask REST API for inference<span> </span>and<span> </span>real-time<span> </span>doctor-patient<span> </span>communication,<span> </span>while<span> </span>a<span> </span>Django-backed<span> </span>module<span> </span>manages authentication, patient records, appointment scheduling, and role-based access control. Evaluation<span> </span>on<span> </span>6,500<span> </span>combined<span> </span>MRI<span> </span>scans<span> </span>from<span> </span>the<span> </span>Kaggle<span> </span>Brain<span> </span>Tumor<span> </span>MRI<span> </span>Dataset<span> </span>and<span> </span>ADNI yielded<span> </span>96.9%<span> </span>accuracy<span> </span>for<span> </span>tumor<span> </span>detection<span> </span>and<span> </span>95.8%<span> </span>for<span> </span>Alzheimer’s<span> </span>staging,<span> </span>with<span> </span>an<span> </span>average inference latency of 1.3 seconds per scan. The platform integrates confidence-based clinical triage, physician override, PDF report generation, and real-time consultation within a single deployable web application.</span></em></p> <p class="MsoBodyText"><em><span> </span></em></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_20201511
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Intelligent Neurodiagnostic Platform for Brain Tumor and Alzheimer's Detection Using Deep Learning Models
Mr.Gulve Rushikesh Somnath
Mr.Hase Onkar Balasaheb
Mr.Jadhav Pranav Prashant
Mr.Warghude Rushikesh Sudhakar
Ms.K. T. Bhandwalkar
brain tumor detection, Alzheimer's disease classification, Modified CNN, EfficientNetB0, transfer learning, MRI analysis, Flask, Django, deep learning, clinical decision support, neurodiagnostics
<p class="MsoNormal"><em><span>The timely and precise identification of neurological conditions such as brain tumors and Alzheimer’s disease carries profound implications for patient survival, treatment efficacy, and long-term quality of life. This paper introduces NeuroDetect AI, a web-deployable Intelligent Neurodiagnostic Platform that automates MRI-based brain scan classification across brain-tumor-positive,<span> </span>Alzheimer’s-positive,<span> </span>and<span> </span>neurologically<span> </span>normal<span> </span>categories.<span> </span>The<span> </span>system<span> </span>adopts<span> </span>a dual deep learning strategy:<span> </span>a custom Modified Convolutional Neural Network<span> </span>for brain tumor classification and an EfficientNetB0 transfer-learning model for Alzheimer’s detection. A standardized preprocessing pipeline consisting of grayscale conversion, CLAHE, intensity normalization, and augmentation feeds both models. The platform uses a Flask REST API for inference<span> </span>and<span> </span>real-time<span> </span>doctor-patient<span> </span>communication,<span> </span>while<span> </span>a<span> </span>Django-backed<span> </span>module<span> </span>manages authentication, patient records, appointment scheduling, and role-based access control. Evaluation<span> </span>on<span> </span>6,500<span> </span>combined<span> </span>MRI<span> </span>scans<span> </span>from<span> </span>the<span> </span>Kaggle<span> </span>Brain<span> </span>Tumor<span> </span>MRI<span> </span>Dataset<span> </span>and<span> </span>ADNI yielded<span> </span>96.9%<span> </span>accuracy<span> </span>for<span> </span>tumor<span> </span>detection<span> </span>and<span> </span>95.8%<span> </span>for<span> </span>Alzheimer’s<span> </span>staging,<span> </span>with<span> </span>an<span> </span>average inference latency of 1.3 seconds per scan. The platform integrates confidence-based clinical triage, physician override, PDF report generation, and real-time consultation within a single deployable web application.</span></em></p> <p class="MsoBodyText"><em><span> </span></em></p>
title Intelligent Neurodiagnostic Platform for Brain Tumor and Alzheimer's Detection Using Deep Learning Models
topic brain tumor detection, Alzheimer's disease classification, Modified CNN, EfficientNetB0, transfer learning, MRI analysis, Flask, Django, deep learning, clinical decision support, neurodiagnostics
url https://doi.org/10.5281/zenodo.20201511