Bibliographic record
Abstract
The objective of this thesis is to detect the tumor in the brain images.It presents a new method of brain tumor detection and localization by using image segmentation and convolution neural network.Compared with the artificial neural network, this approach reduces the complexity of the learning model and has robustness to the noise within the image.In order to ensure the quality of the medical images, there are several image preprocessing techniques applied before tumor recognition, which include the procedure of removing the noise and non-brain tissue from the image and enhancing the contrast.By using active contour for image segmentation, the tumor area is separated from the image as its energy appears different in pixels and the feature extraction reveals the mathematical properties of the tumor.After the tumor localization, the target regions are imported into to the CNN as inputs and CNN classifies them into different categories based on the training results from the learning procedure.This thesis uses the 4-fold cross validation for result testing.With over 80% accuracy, the CNN shows great potential in tumor detection.In addition, this thesis covers the section of how parameter settings influencing the CNN performance.Another improvement in the thesis is to replace the ReLU function with ELU function within the non-linear layer.With the introduction of two hyperparameters, which controls the saturation for the negative value and the exponential decay, the vanishing gradient problem is alleviated and the learning speed is accelerated.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".