Improving The Accuracy Of Computer-Aided Diagnosis (Cad)For Breast Mri By Differentiating Between Mass And NonmassLesions.
Bibliographic record
Abstract
Purpose: To determine suitable features and optimal classifier design for a computer-aided diagnosis (CAD) system to differentiate among mass and non-mass enhancements during dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. Materials and Methods: Histology-proven 280 mass lesions and 129 non-mass lesions from MRI studies were retrospectively collected. The institutional research ethics board (REB) approved this study and waived informed consent. BIRADS classification of mass and non-mass enhancements was obtained from radiology reports. Image data from DCE-MRI was extracted and analyzed using feature selection techniques and binary, multiclass and cascade classifiers. Performance differences among classifiers were assessed by area under the receiver operating characteristic curve (AUC), Sensitivity (Se) and Specificity (Sp). Bootstrap cross-validation was used to predict the feature sets and the classifier choices with the best discrimination power for the classification task of mass and nonmass benign and malignant breast lesions. Results: A total of 176 features were extracted from the lesion ROI. Feature relevance ranking indicated unequal importance of kinetic, texture and morphology features for mass and non-mass lesions. Best classifier performance was a 2-stage cascade classifier (mass vs. non-mass followed by malignant vs. benign classification), with 0.91 AUC, 95%CI: [0.88-0.94] in comparison to one-shot (i.e. all benign vs. malignant classifier) with 0.89 AUC, 95%CI: [0.85-0.92]. The AUC was 2% higher for cascade (median % difference obtained using paired bootstrapped samples) and this was statistically significant (pvalue= 0.0027). Our proposed 2-stage cascade classifier decreases the overall misclassification rate by 12%, (72/409) missed diagnoses by cascade versus (82/409) missed by one-shot. Conclusion: Optimizing feature selection and training classifiers for mass and non-mass lesions separately improves the accuracy of a CAD for breast MRI. By cascading classifiers we obtained a significant improvement in performance with respect to a one-shot classifier. Our cascaded classifier may provide an advantage for screening of women at high-risk, where the ability to diagnose cancers at an early-stage is of primary importance. This record was migrated from the OpenDepot repository service in June, 2017 before shutting down.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".