Diagnostic and Prognostic DNA-Karyometry for Cancer Diagnostics
Bibliographic record
Abstract
Diagnostic and prognostic DNA-karyometry represents an automated computerized microscopical procedure, designed to improve cancer diagnostics at three different aspects: Screening for cancer cells, e.g. in body cavity effusions, urines or mucosal smears Specifying the risk of dysplasias or borderline lesions to progress to manifest cancer, e.g. of oral, bronchial or cervical mucosa, or the ovary. Grading the malignancy of certain tumors, like prostate cancer. It combines an automated diagnostic classification of Feulgen-stained nuclei with precise nuclear DNA-measurements. DNA-aneuploidy is used as a specific marker of malignancy and its degree for grading. All types of cytological specimens can be used after (re-)staining specific for DNA according to Feulgen. Histological specimens are subjected to enzymatic cell separation before Feulgen-staining. A video-slide scanner is used for automated scanning of microscopical slides. Diagnostic nuclear classifiers have tissue-specifically been trained by an expert-cytopathologist (A. B.), based on Random Forest Classifiers, applying 18 different morphometric features. They achieve an overall accuracy of 91.1% to differentiate 8 differents types of objects/nuclei. Nuclear DNA-measurements of diploid nuclei achieve a CV of <3%. DNA-stemline-aneuploidy, applied as a 100% specific marker for malignancy, is detected and quantified, using internationally accepted algorithms (ESACP 1995-2001). Suspicion of malignancy is raised in the absence of DNA-aneuploidy but presence of >1% morphometrically abnormal nuclei. Time needed for loading, scanning and validation of results per slide is about 10 minutes. Results of digital diagnostic nuclear classification can be verified by a cytopathologist, using image galleries. Likewise automated diagnostic interpretation of nuclear DNA-distributions can be checked on the monitor, before a pathologists validated diagnoses are issued. Screening-results are presented for body cavity effusions and urines. Evaluations of dysplasias are reported for oral, bronchial and cervical smears. Results of grading malignancy are shown for prostate cancers.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.025 | 0.020 |
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".