Data Augmentation by Wavelet Transform for Breast Cancer Based on Deep Learning
Bibliographic record
Abstract
Automated diagnosis and evolving CNN architectures are improving diagnostic quality in digital breast cancer histopathology images.The study predominantly focuses on classifying the histopathological images of the BreakHis breast cancer dataset into distinct categories: benign and malignant.A primary challenge in this task is the uneven class distribution and limited training samples, which introduce bias and compromise the model's non-malignant classification accuracy.The study utilizes wavelet decomposition on benign images to address class imbalance and enhance the model's ability to accurately classify breast cancer histopathological images.This technique begins by filtering the image with high-pass and low-pass filters, followed by downsampling.The process is then repeated to generate four images representing different components of the original image, enabling precise localization of essential features and denoising.The DenseNet201 convolutional network is chosen for image classification due to its efficiency and accuracy.Our proposal involves concatenating features extracted from specific blocks of the pre-trained DenseNet201 model: pool3_pool, pool4_pool, and conv5_block32_conca.The proposed framework achieves an impressive overall accuracy in classifying both benign and malignant images, maintaining high accuracy rates of 99% in both multi-scale and magnification-independent classifications.These promising results indicate the potential clinical application of this approach in diagnosing diseases.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".