Abstract P1-01-04: Early stage breast cancer prognostication using whole tumor or Ki67 heterogeneity-based digital imaging
Bibliographic record
Abstract
Abstract Introduction: Accurate prognosis of hormone-positive early stage breast cancer patients offers the opportunity to make more informed follow-up choices, for example the addition of adjuvant chemotherapy. More recently patient prognostication based on immunohistochemistry-scored protein expression (ER, PR, Her2 and Ki67) in the ATAC trial has been described as IHC4 (C-index of 0.78). However, IHC4 clinical translation has not occurred and may be hindered by the need for a clinically-validated standardized assay as well as pathologist scoring reproducibility. To address this idea, we employed a standardized assay system and automated scoring using digital image analysis to assess either whole tumor (WT) IHC expression values or Ki67 heterogeneity (Ki67H) quantification. The goals were to 1) establish a prognostic model based on and potentially improving the IHC4 concept and 2) improve pathologist scoring reproducibility. Material and Methods: A paraffin-embedded whole tissue cohort consisting of 120 cases of hormone-positive, HER2-negative, stage I and II, breast cancer patient samples were re-stained with standardized ER, PR, HER2, and Ki67 IHC assays. Three pathologists independently scored conventional glass slides microscopically (CM) and annotated WT on H&E and Ki67 heterogeneous regions on whole slide scanned images (WSI) for each case separately. The annotations were separately registered across serial stained slides and also scored via the digital pathology algorithm. Results: The mean patient age at the time of diagnosis is 63 years with a maximum follow-up of 18 years. Patients with regional and/or distal recurrence compose 26% of the cohort with a median recurrence free survival of 8.5 years. years. Clinical variables (CV) plus WT (C-index 0.74, r2 0.38) or Ki67H (C-index 0.77, r2 0.39) models improved on patient prognostication each as compared to the IHC4 plus CV (C-index 0.70, r2 0.19) in this cohort. High inter-pathologist reproducibility for the IHC score, as measured by concordance correlation coefficient was noted for Ki67H (0.90). Conclusions: Novel algorithmic scoring methodologies such as WT and Ki67H may improve on the IHC4 concept with high inter-pathology reproducibility. We are currently validating in a larger 600 patient cohort. Citation Format: Barnes M, Srinivas C, Xu C, Dean S, Singh S, Henricksen LA, Wik N, Morris D, Magliocco A, LaFleur B. Early stage breast cancer prognostication using whole tumor or Ki67 heterogeneity-based digital imaging. [abstract]. In: Proceedings of the Thirty-Eighth Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2015 Dec 8-12; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2016;76(4 Suppl):Abstract nr P1-01-04.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 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".