Computer aided prognosis for cell death categorization and prediction<i>in vivo</i>using quantitative ultrasound and machine learning techniques
Bibliographic record
Abstract
PURPOSE: At present, a one-size-fits-all approach is typically used for cancer therapy in patients. This is mainly because there is no current imaging-based clinical standard for the early assessment and monitoring of cancer treatment response. Here, the authors have developed, for the first time, a complete computer-aided-prognosis (CAP) system based on multiparametric quantitative ultrasound (QUS) spectroscopy methods in association with texture descriptors and advanced machine learning techniques. This system was used to noninvasively categorize and predict cell death levels in fibrosarcoma mouse tumors treated using ultrasound-stimulated microbubbles as novel endothelial-cell radiosensitizers. METHODS: Sarcoma xenograft tumor-bearing mice were treated using ultrasound-stimulated microbubbles, alone or in combination with x-ray radiation therapy, as a new antivascular treatment. Therapy effects were assessed at 2-3, 24, and 72 h after treatment using a high-frequency ultrasound. Two-dimensional spectral parametric maps were generated using the power spectra of the raw radiofrequency echo signal. Subsequently, the distances between "pretreatment" and "post-treatment" scans were computed as an indication of treatment efficacy, using a kernel-based metric on textural features extracted from 2D parametric maps. A supervised learning paradigm was used to either categorize cell death levels as low, medium, or high using a classifier, or to "continuously" predict the levels of cell death using a regressor. RESULTS: The developed CAP system performed at a high level for the classification of cell death levels. The area under curve of the receiver operating characteristic was 0.87 for the classification of cell death levels to both low/medium and medium/high levels. Moreover, the prediction of cell death levels using the proposed CAP system achieved a good correlation (r = 0.68, p < 0.001) with histological cell death levels as the ground truth. A statistical test of significance between individual treatment groups with the corresponding control group demonstrated that the predicted levels indicated the same significant changes in cell death as those indicated by the ground-truth levels. CONCLUSIONS: The technology developed in this study addresses a gap in the current standard of care by introducing a quality control step that generates potentially actionable metrics needed to enhance treatment decision-making. The study establishes a noninvasive framework for quantifying levels of cancer treatment response developed preclinically in tumors using QUS imaging in conjunction with machine learning techniques. The framework can potentially facilitate the detection of refractory responses in patients to a certain cancer treatment early on in the course of therapy to enable switching to more efficacious treatments.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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 teacher head, 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".