Abstract PO-034: The prediction of mandibular osteoradionecrosis in head and neck cancer patients using CT-derived radiomics features
Bibliographic record
Abstract
Abstract Osteoradionecrosis (ORN), or bone death, is a multifactorial late complication caused by radiotherapy (RT), that diminishes the bone’s ability to withstand trauma and avoid infection. In head and neck cancer (HNC), ORN most commonly manifests in the mandible. It is influenced by RT-induced factors and patient-related parameters. The most effective way to limit RT-induced ORN is to reduce mandibular volumes receiving high RT doses. However, this strategy may also result in a reduced dose to the tumor due to its proximity to the mandible, and therefore must be restricted to only the patients deemed most vulnerable to mandibular ORN. The objective of this study was to design a prognostic model based on RT-planning CT-derived radiomic features extracted from mandible contours along with the patient’s clinical features to predict the probability of mandibular ORN from the end of RT to the onset of ORN in HNC patients. We hypothesized that these features are related to mandibular ORN and that incorporating them into a prediction model will help to identify patients at risk of mandibular ORN after HNC RT. Patient data was retrospectively collected from the Princess Margaret Cancer Centre, University Health Network and based on the following inclusion criteria: patients had (1) had status regarding radiation-induced bone toxicity, (2) the time to the toxicity event was recorded, and (3) head RT-planning CT images in addition to mandible contours. Then, the patient’s history was reviewed by radiation oncologists to collect clinical features. Quantitative image features were then extracted from the segmented mandible for each patient. Finally, multivariable models, a binary classifier, and a regressor were independently trained on three sets of features (radiomic, demo-clinical, and both) to predict the patient’s risk of ORN and the time between the end of RT and the start of ORN respectively. In total, we analyzed CT images from 92 OPC patients with known ORN status (55 positive, 37 negative). We extracted a total of 1877 radiomic features from the manually-segmented Mandible from each patient. Initially, cases were labelled with their status regarding presence and time to radiation toxicity. Top 50, most relevant and least redundant, features were with mRMRe were used for both binary classification and regression models to predict time to the mandibular ORN. Model training upon radiomics and clinical features resulted in the higher accuracy value of 0.93 (AUCROC) compared to the only radiomics features (0.92) and clinical model (0.74). The distribution of AUC values was significantly wider in models trained on clinical features than radiomics or radiomics plus clinical features. Citation Format: Reza Reiazi, Mattea Welch, Scott V. Bratman, Andrew J. Hope, Benjamin Haibe-Kains. The prediction of mandibular osteoradionecrosis in head and neck cancer patients using CT-derived radiomics features [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-034.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".