Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: JMIR Preprints

Date Submitted: Jun 3, 2026

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Artificial Intelligence and Deep Learning for Early Detection and Diagnosis of Brain Tumors in Neurosurgery Using CT Scan and Medical Imaging

  • Negin Mehdinejad; 
  • Cyrus Asadzadeh; 
  • Amir Salehi Farid; 
  • Mohamadreza Shabani; 
  • Azadeh Ahmadi; 
  • Ahmad Zahedi; 
  • Yaseen Padash; 
  • Sajad Khonche; 
  • Aliasghar Tabatabaei Mohammadi; 
  • Erfan Ghanbarzade; 
  • Vahid Carvani

ABSTRACT

Background:

Lung cancer remains a leading cause of mortality worldwide, with early detection significantly improving survival rates. Computed tomography (CT) scans are a primary imaging modality for identifying lung tumors, but manual interpretation can be time-consuming and prone to errors. Deep learning models offer promise for automating and enhancing detection accuracy.

Methods:

We developed a hybrid deep learning framework combining convolutional neural networks (CNNs) for classification and object detection models like YOLOv8 for localization. The model was trained on publicly available datasets, including the Lung-PET-CT-Dx and Kaggle Chest CT-Scan images, comprising over 20,000 CT images. Preprocessing involved image resizing, augmentation, and segmentation techniques such as Watershed and Otsu's thresholding. Hyperparameter tuning was performed using grid search, with evaluation on metrics like accuracy, precision, recall, F1-score, and Jaccard index.

Results:

Our model achieved 98.5% accuracy in classifying CT images as cancerous or non-cancerous, with 90.3% precision in tumor localization. This enabled detection of tumors at earlier stages compared to traditional methods, reducing false negatives by 15%.

Conclusions:

The integration of deep learning with CT imaging facilitates earlier tumor detection, potentially improving patient outcomes. Future work should focus on multi-center validation and real-time clinical integration.


 Citation

Please cite as:

Mehdinejad N, Asadzadeh C, Salehi Farid A, Shabani M, Ahmadi A, Zahedi A, Padash Y, Khonche S, Tabatabaei Mohammadi A, Ghanbarzade E, Carvani V

Artificial Intelligence and Deep Learning for Early Detection and Diagnosis of Brain Tumors in Neurosurgery Using CT Scan and Medical Imaging

JMIR Preprints. 03/06/2026:102766

DOI: 10.2196/preprints.102766

URL: https://preprints.jmir.org/preprint/102766

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.