Early Diagnosis of Mammogram Images Using Hybird Deep and Machine Learning Algorithm
Bibliographic record
Abstract
Automated early detection of breast cancer using Computer Aided Diagnosis (CAD) is the most important step in extending the cancer patient's lifetime.However, achieving this with the CAD model, high accuracy in mammogram image analysis remains a challenge with the numerous machine learning (ML) algorithms.Sometimes, the medical practitioner needs a second opinion with this automated result.This motivated me to find a robust and reliable disease classification model to enhance the classification performance.Deep learners (DL) are the most powerful tool in extracting complex features, such as subtle abnormalities in complex images.The machine learning algorithm will classify the images with the optimal feature set to overcome the overfitting problem, and in this way, it achieves a higher accuracy than the existing traditional and other machine learning algorithms.This paper presents a new framework that integrates AdaBoost (ML) with two popular CNNs: AlexNet and ResNet (DL).AlexNet is used for feature extraction, and ResNet approaches vanishing gradient issues with a residual learning framework.The proposed model is a hybrid DL combination integrated with features coming from the CNN, which captures inherent characteristics of mammogram images to be exploited by AdaBoost acknowledged for its strong classification power.The proposed hybrid model is trained and tested on a wide publicly available mammogram dataset and achieves a high classification rate in terms of sensitivity (90 %) and specificity (92.8 %) in testing.
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".