Hybrid Elmann-BiLSTM Based Brain Tumor Classification on Augmented Data with Combination of Variational Auto-Encoders and Generative Adversarial Network
Bibliographic record
Abstract
For detecting and classifying brain tumors, clinicians use Magnetic Resonance Imaging (MRI) data.Automated AI-powered tools accelerate the diagnostic process for clinicians.However, large amounts of data are needed for these models to achieve high accuracy.Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN) architecture are combined for dataset expansion.The accuracy was improved with the artificial image set created in all tested models.However, since the accuracy rate remained at 92,960% using Long Short Term Memory Algorithm, it was observed that a hybrid method was also needed, and hybrid Elmann Bidirectional Long Short Memory Algorithm (Elmann-BiLSTM) was developed.In this proposed approach based on deep learning, a Guided Bilateral Filter is used to separate skull from images after VAE-GAN structure.The thresholding scheme extracts tumour regions from the original image in parts.Edge features and major texture data are collected from these tumor images produced using the Improved Gabor Wavelet Transform.Random Forest-based feature selection algorithm will select optimal features that increase accuracy from extracted features.These features feed the Elmann-BiLSTM algorithm used as a two-step classifier.The accuracy rate was 98.897% in the one-step classification approach and 100% and 99.313% in the two-step classifier approach, respectively.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".