Breast lesion identification and categorization using mammography screening based on combined convolutional recursive neural network framework with parameters optimized using multi‐objective seagull optimization algorithm
Bibliographic record
Abstract
Summary In recent years, a number of learning methods have been adopted for classifying the mammogram images, which helps the early detection and diagnosis of breast cancer. The breast lesion identification and categorization using mammography screening based on combined convolutional neural network and recursive neural network (CRNN) framework with parameters optimized using multi‐objective seagull optimization algorithm (BLIC‐CRNN‐MOSOA) is proposed in this article. Initially, the unnecessary noise components are taken away from the mammogram images and the quality of the images are enhanced based on altered phase preserving dynamic range compression filtering approach. Then, the deep CRNN model with weight parameters optimized using multi‐objective seagull optimization algorithm is adopted for classifying the mammogram images into three categories: (i) normal, (ii) benign, and (iii) malignant masses. The proposed BLIC‐CRNN‐MOSOA approach is executed in MATLAB platform, and its performance is compared with other deep learning classification approaches. Then the simulation performance of the proposed BLIC‐CRNN‐MOSOA method attains higher accuracy 99.67%, 98.38%, and 97.45%, higher sensitivity 98.33%, 89.34%, and 88.96%, higher specificity 93.15%, 91.25%, and 92.88% compared with existing methods, like BLIC‐FrCN, BLIC‐ICS‐ELM, and BLIC‐DCNN‐BO. By this, the proposed method achieves higher classification accuracy with less misclassified error. Finally, the simulation results show that the proposed method is more efficient than the other classification methods.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".