Development of an Image Classification Pipeline for Atherosclerotic Plaques Assessment using Supervised Machine Learning
Bibliographic record
Abstract
Abstract Background: Atherosclerosis, an underlying cause of cardiovascular diseases, is achronic inflammatory condition resulting in the accumulation of plaque composedof lipids and other bio compounds within artery walls. Thus, narrowing thearterial lumen and leading to the blockage of blood flow, and rupture of thearteries. Atherosclerosis is known to be an inevitably progressive disease, resultingin an increase in inflammation and lipid accumulation with age. Through thecombination of coherent anti-stokes Raman Scattering (CARS) microscopy, anon-linear optical microscopy modality, and an automated pipeline for plaqueclassification; the stages of plaque progression can be assessed in a label-freemanner. The pipeline provides a basis for recognizing changes in the progressionand/or stabilization of atherosclerotic lesions. Results: The use of machine learning in microscopy has been increasinglyallowing the classification of large amounts of images based on specific featuresrelevant to different applications. Based on a set of label-free CARS images ofatherosclerotic plaques (i.e. foam cell clusters) from a rabbit model, wedeveloped an automated pipeline to classify lesions based on their majormorphological features. Through the combination of image preprocessing andsegmentation, feature extraction and supervised machine learning algorithms, theclassification pipeline showcased the ability to exploit relevant plaquemorphological features to accurately classify 3 pre-defined stages ofatherosclerosis: early fatty streak development (EFS), early fibroatheroma (EF)and advancing atheroma (AA), greater than 85% class accuracy. Conclusions: Minute changes in the morphology of plaque can often beoverlooked. Through the combination of CARS microscopy and computationalmethods, a powerful classification tool was developed to identify the progressionof atherosclerotic plaque in an automated manner. The ability to differentiateamongst EFS, EF and AA present the opportunity to classify the onset ofatherosclerosis at an earlier stage of development, as well as greatly improvingthe potential of tracking effectiveness of novel therapeutic interventions
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.007 |
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".