Post

New research · Endocrinology
Journal of imaging informatics in medicine · 3h
AI / informaticsJournal of imaging informatics in medicine · 2026

Lightweight Transfer Learning Models for Multi-Class Brain Tumor Classification: Glioma, Meningioma, Pituitary Tumors, and No Tumor MRI Screening.

Alon Gorenshtein, Tom Liba, Avner Goren
Read paper
EndocrinologyAI / informatics

Transfer-learned artificial intelligence model perfectly classifies brain tumors from MRI scans.

Lightweight Transfer Learning Models for Multi-Class Brain Tumor Classification: Glioma, Meningioma, Pituitary Tumors, and No Tumor MRI Screening.

Alon Gorenshtein et al. · Journal of imaging informatics in medicine · 2026
Background

Glioma, pituitary tumors, and meningiomas constitute the major types of primary brain tumors.

Methods

We compared our models to SOTA methods such as SAlexNet and TumorGANet, highlighting computational efficiency and classification performance.

n = 7023 images
overall AUC of 1.0
Results
the artificial intelligence model perfectly distinguished between different brain tumor types and no tumor
n = 7023 images
More results

We developed multiple lightweight deep learning models ResNet-18 (both pretrained on ImageNet and trained from scratch), ResNet-34, ResNet-50, and a custom CNN to classify glioma, meningioma, pituitary tumor, and no tumor MRI scans.

A dataset of 7023 images was employed, split into 5712 for training and 1311 for validation.

More results

Learning rate optimization facilitated stable convergence, and loss metrics indicated effective generalization with minimal overfitting.

Our findings confirm that a moderately sized, transfer-learned network (ResNet-18) can deliver high diagnostic accuracy and robust performance for four-class brain tumor classification.

“
Conclusion

Future studies should incorporate multi-sequence MRI and extended patient cohorts to further validate these promising results.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Review
“This review highlights that migraines are associated with specific alterations in gut microbiota, including decreased microbial diversity and changes in the abundance of key taxa.”
Meta-analysis
RR 1.61
women have a higher risk of loss of smell in long COVID compared to men
Cohort Study
“BMI was not an independent predictor of survival outcomes in advanced NSCLC treated with ICI. Incorporating BMI with other patient-specific factors into personalized immunotherapy strategies highlights the importance of tailored approaches to improve patient care and clinical outcomes.”
AI / Informatics
32
studies exploring machine learning to predict cancer outcomes
AI / Informatics
P_adj = 0.038
early pregnancy ANGPTL4 levels were higher in women who developed gestational diabetes
Randomized Trial
HR 0·38
the drug combination significantly reduced the chance of cancer progression or death
Review
10-60 mGy
the range of radiation exposure to the baby from belly or pelvis CT scans
Cohort Study
16 min 08 s
PACScrawler was faster at getting medical images than manual methods