Minimizing False Negatives in Metastasis Prediction for Breast Cancer Patients Through a Deep Stacked Ensemble Analysis of Whole Slide Images
Bibliographic record
Abstract
Accurate metastasis prediction in breast cancer (BC) patients is crucial for timely treatment, thereby reducing life-threatening risks.Traditional methods involve manual observation of whole slide images (WSIs) to identify tumor cells, necessitating extensive expertise and resulting in a time-consuming process.Recently, deep learning techniques have been employed for precise tumor cell detection.However, automatic detection methods face challenges such as limited availability of large datasets and the ambiguity between cancer cell structures and normal tissue.This paper proposes a novel deep stacked ensemble architecture to address these challenges.The proposed model incorporates three pre-trained models, namely RESNET50, EfficientNet B3, and DenseNet121, with single, double, and triple fully connected layers for each architecture, yielding nine models.Among these, three heterogeneous models were selected for the stacking ensemble.The performance of these models and the deep stacked ensemble was investigated and compared using the CAMELYON 17 challenge dataset, which contains lymph node WSIs of BC patients.Results demonstrate that the deep stacked ensemble outperforms individual models.In this prediction task, recall is more critical than precision; thus, the trade-off between recall and precision was also examined.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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".