A Sisters Similarity Neural Network SSNN Model for Generalization and Detection of Mammographic Breast Cancer Lesion Abnormalities
Bibliographic record
Abstract
Breast cancer remains one of the leading causes of mortality among women worldwide. Early detection through mammography significantly enhances survival rates, particularly when abnormalities are identified before metastasis. However, challenges such as tissue density, image noise, variability across mammogram devices hinder consistent diagnosis. The study proposes a robust deep learning framework to automate the detection classification of Breast abnormalities- specifically masses and calcifications. In this research a patch based preprocessing pipeline, involving articraft removal, thresholding, contrast enhancement and dynamic patch extraction resulting high quality and diverse dataset to create thousands of patches. A Novel deep Neural architecture the sisters neural network inspired by Sisters NN is designed to learn discriminative similarity features between image pairs. This approach enhances generalization performance, particular under limited data and high intraclass variability. The network achieves a validation accuracy and testing accuracy of 86.01%, with notable AUC of 0.936. The frame work has integrated an advanced model that allows to predict the unknown lesion in a unseen full scan with mAP of 0.70 and IoU of 84.5%. Additionally, segmentation is done in an enhanced way by Fuzzy c-means and Distance Transform FCDT method which has improved clustering accuracy and lesion localization even in very noisy images or ambiguous tissue regions. The Proposed model demonstrates a superior generalization performance with an accuracy of 92.3%, outperforming with existing models on mAP and AUC metrics. The Framework proposed established a foundation for scalable, best early breast cancer diagnostic tool for generalization.
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 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".