Authors :
Aditya Suyash; Ritik Raj; Dr. R. Thilagavathy
Volume/Issue :
Volume 9 - 2024, Issue 1 - January
Google Scholar :
http://tinyurl.com/zek5uvdx
Scribd :
http://tinyurl.com/653ucd3k
DOI :
https://doi.org/10.5281/zenodo.10618098
Abstract :
In order to improve brain tumour analysis,
our research uses MRI and CT data in a Flask-based
web application. Our research focuses on advancing
brain tumor analysis through a sophisticated approach
that integrates MRI and CT data within a user-friendly
Flask-based web application. The landmark-based
registration ensures precise alignment of diverse patient
images, establishing a standardized coordinate system
for meticulous anatomical comparisons. To enhance the
VGG-19 CNN architecture's analytical capabilities, we
employ transfer learning, enabling nuanced analysis.
The subsequent Image Fusion process optimizes tumor
segmentation accuracy by leveraging the complementary
strengths of CT and MRI data. The Watershed
transformation isolates regions of interest, facilitating a
more refined segmentation process. Additionally, a CNN
predicts the presence of brain tumors, streamlining
detection and prognosis, ultimately contributing to a
healthcare paradigm that is both efficient and patient-
centered. These advancements not only streamline the
intricate examination of brain tumors but also enhance
accessibility and accuracy in healthcare practices.
Keywords :
CNN, Flask, VGG -19, Image Fusion, Watershed Transformation.
In order to improve brain tumour analysis,
our research uses MRI and CT data in a Flask-based
web application. Our research focuses on advancing
brain tumor analysis through a sophisticated approach
that integrates MRI and CT data within a user-friendly
Flask-based web application. The landmark-based
registration ensures precise alignment of diverse patient
images, establishing a standardized coordinate system
for meticulous anatomical comparisons. To enhance the
VGG-19 CNN architecture's analytical capabilities, we
employ transfer learning, enabling nuanced analysis.
The subsequent Image Fusion process optimizes tumor
segmentation accuracy by leveraging the complementary
strengths of CT and MRI data. The Watershed
transformation isolates regions of interest, facilitating a
more refined segmentation process. Additionally, a CNN
predicts the presence of brain tumors, streamlining
detection and prognosis, ultimately contributing to a
healthcare paradigm that is both efficient and patient-
centered. These advancements not only streamline the
intricate examination of brain tumors but also enhance
accessibility and accuracy in healthcare practices.
Keywords :
CNN, Flask, VGG -19, Image Fusion, Watershed Transformation.
