Assessing the Impact of Image Reconstruction and Acquisition Parameters on the Reproducibility of Radiomic Features
Bibliographic record
Abstract
Colorectal cancer is the third most commonly diagnosed cancer in the United States, with approximately 152,000 new cases per year. Roughly one-quarter of these patients will develop colorectal liver metastases, characterized by the spread of the primary cancer to the liver and associated with a three-year survival rate of less than 10%. Complex treatment decisions are often made with incomplete knowledge of how an individual’s disease will behave. However, radiomics models trained on quantitative imaging features extracted from contrast-enhanced computed tomography (CECT) scans have the potential to pre-operatively predict an individual’s risk of recurrence and response to chemotherapy. Image variation across CT image acquisition and reconstruction parameters is a major bottleneck preventing clinical translation. We prospectively and systematically varied the CT parameters slice thickness, Adaptive Statistical Iterative Reconstruction (ASiR), and contrast timing to quantify their impact on 105 commonly used radiomic features. ComBat’s feature correction was assessed on reproducibility. 143 CRLM patients were prospectively enrolled from Memorial Sloan Kettering Cancer Center (n = 70) and University of Texas MD Anderson Cancer Center (n = 73), and radiomic features were extracted from the liver parenchyma and the largest metastasis separately. Differences in feature distribution across institution and region of interest were analyzed. Between MD Anderson and Memorial Sloan Kettering, differences in feature distribution, mean Hounsfield value with respect to time and reproducibility were identified. Changes in all imaging parameters greatly impacted feature reproducibility with 30% and 13.3% of features extracted from the largest tumour and liver parenchyma, respectively, maintaining a CCC with a lower 95% confidence limit of above 0.9 across all main phases of reproducibility analysis. Features extracted from the liver parenchyma were consistently less reproducible than those extracted from the largest tumour. This was shown to be a result of the relatively tight distribution of features extracted from patients’ liver parenchymas. Batch harmonization using ComBat was shown to greatly improve the reproducibility of features across reconstruction.
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 | 0.008 | 0.032 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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 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".