Bibliographic record
Abstract
According to the World Health Organization, breast cancer is a leading cause of death among middle-aged women. Precise diagnosis and correct treatment significantly reduces the high number of deaths caused by breast cancer. Being successful in the treatment strictly relies on the diagnosis. Specifically, the accuracy of the diagnosis and the stage at which a cancer was diagnosed. Precise and early diagnosis has a major impact on the survival rate, which indicates how many patients will live after the treatment. For many years researchers in medical and computer science fields have been working together to find the approach for precise diagnosis. For this thesis, precise diagnosis means finding a cancer at as early a stage as possible by developing new computer aided diagnostic tools. These tools differ depending on the type of cancer and the type of the examination that is used for diagnosis. This work concentrates on cytological images of breast cancer that are produced during fine needle aspiration biopsy examination. This kind of examination allows pathologists to estimate the malignancy of the cancer with very high accuracy. Malignancy estimation is very important when assessing a patients survival rate and the type of treatment. To achieve precise malignancy estimation, a classification framework is presented. This framework is able to classify breast cancer malignancy into two malignancy classes and is based on features calculated according to the Bloom-Richardson grading scheme. This scheme is commonly used by pathologists when grading breast cancer tissue. In Bloom-Richardson scheme two types of features are assessed depending on the magnification. Low magnification images are used for examining the dispersion of the cells in the image while the high magnification images are used for precise analysis of the cells' nuclear features. In this thesis, different types of segmentation algorithms were compared to estimate the algorithm that allows for relatively fast and accurate nuclear segmentation. Based on that segmentation a set of 34 features was extracted for further malignancy classification. For classification purposes 6 different classifiers were compared. From all of the tests a set of the best preforming features were chosen. The presented system is able to classify images of fine needle aspiration biopsy slides with high accuracy
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".