How AI-based techniques for brain tumour diagnosis can address data variability.
- 1Faculty of Engineering, Free University of Bozen-Bolzano, Bolzano-Bozen, Italy.
- 2Technologies of Vision, Fondazione Bruno Kessler, Trento, Italy.
Abstract
Data variability in medical imaging of tumors refers to the inconsistencies in Magnetic Resonance Imaging and Computational Tomography scans caused by heterogeneous tumor biology, varying scanner hardware, and subjective human interpretation. This variability creates significant challenges for accurate diagnoses, treatment tracking, and AI model development. Although the variability in medical imaging data for diagnostic and prognostic purposes is a challenge for AI methods applied to other types of tumors as well, it is particularly problematic when the analysis involves gliomas and glioblastomas. Most gliomas are infiltrative and glioblastomas are highly infiltrative tumors with poorly defined margins. They exhibit significant regional variations, including cystic necrosis, localized hemorrhages, and complex microvascular proliferation. Addressing this variability requires a combination of algorithmic innovation, standardized datasets, and a leading-edge computational pipeline including traditional and AI-based data modelling methodologies to ensure diagnostic and prognostic models are robust. In this article, we will identify some AI methods that show promise in the analysis of brain tumor images and that must overcome the challenges posed by data availability. We will also offer some insights into how these challenges can be overcome and propose a possible computational pipeline that utilizes them.
Related
- Comparison of Four Yogic Breathing Techniques Regarding Their Impact on Heart-Rate Variability and Breathing Frequency
- AMF-U-Net: an adaptive multimodal fusion residual attention 3D U-Net for boundary-aware brain tumour segmentation
- Sertoli-Leydig Cell Tumour With Heterologous Elements Presenting as Hyperandrogenaemia and Markedly Elevated Alpha-Fetoprotein: A Challenging Diagnosis.
- Management of epilepsy in the brain tumour patient: Current concepts and practical approaches
- Combining Cognitive Training and Brain Stimulation: A Novel Approach to Address Disordered Eating and Antipsychotic‐Induced Weight Gain in People With Severe Mental Illness
BibTeX
@article{lecca2026aibased,
title = {{How AI-based techniques for brain tumour diagnosis can address data variability.}},
author = {Paola Lecca and Michela Lecca},
journal = {Frontiers in bioinformatics},
year = {2026},
month = oct,
doi = {10.3389/fbinf.2026.1916468},
url = {https://europepmc.org/article/MED/42898464},
note = {CC BY},
}
RIS
TY - JOUR
TI - How AI-based techniques for brain tumour diagnosis can address data variability.
AU - Paola Lecca
AU - Michela Lecca
PY - 2026
DA - 2026/10/05
JO - Frontiers in bioinformatics
DO - 10.3389/fbinf.2026.1916468
UR - https://europepmc.org/article/MED/42898464
AB - Data variability in medical imaging of tumors refers to the inconsistencies in Magnetic Resonance Imaging and Computational Tomography scans caused by heterogeneous tumor biology, varying scanner hardware, and subjective human interpretation. This variability creates significant challenges for accurate diagnoses, treatment tracking, and AI model development. Although the variability in medical imaging data for diagnostic and prognostic purposes is a challenge for AI methods applied to other types of tumors as well, it is particularly problematic when the analysis involves gliomas and glioblastomas. Most gliomas are infiltrative and glioblastomas are highly infiltrative tumors with poorly defined margins. They exhibit significant regional variations, including cystic necrosis, localized hemorrhages, and complex microvascular proliferation. Addressing this variability requires a combination of algorithmic innovation, standardized datasets, and a leading-edge computational pipeline including traditional and AI-based data modelling methodologies to ensure diagnostic and prognostic models are robust. In this article, we will identify some AI methods that show promise in the analysis of brain tumor images and that must overcome the challenges posed by data availability. We will also offer some insights into how these challenges can be overcome and propose a possible computational pipeline that utilizes them.
SN - 2673-7647
ER -