Efficient Deep Learning Fusion-Based Approach for Brain Tumor Diagnosis
Bibliographic record
Abstract
Technology has advanced to the point where it can influence every facet of human existence.Here, we look at how technology can help treat brain tumors, one of the most frequent malignancies and a leading cause of death.Many people lose their lives each year because of brain tumors.In the United States, roughly 85,000 new cases are diagnosed each year, bringing the total number of people with primary brain tumors to an estimated 700,000.Artificial intelligence has helped medicine and people overcome this challenge.Most brain cancers are detected via magnetic resonance imaging.Medical imaging and image processing make extensive use of magnetic resonance imaging for diagnosing anatomical differences.In this paper, we investigate the performance of various convolutional neural network (CNN) models like AlexNet, GoogleNet, VGGnet11, VGGnet13, VGGnet16, VGGnet19, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, DenseNet121, DenseNet161, DenseNet169, and DenseNet201 for brain tumor diagnosis tasks.On a dataset of 3264 MRI images, we perform experiments for healthy meningioma, glioma, and pituitary brain tumor classification.Our tests reveal that the ResNet and DenseNet models yield the highest accuracy (82%).Furthermore, we investigate the potential of a fusionbased approach where we test for different combinations of fusion of CNN models.The results show that fusing many CNN features improves accuracy even more.Classification accuracy is improved to 86% when ResNet50 and ResNet101 are fused and improves to 84% when DenseNet161 and DenseNet169 are fused.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".