EP24.18: A novel machine learning model for automatic assessment of quality of transvaginal ultrasound images
Bibliographic record
Abstract
Accurate diagnosis of endometriosis from transvaginal ultrasound (TVUS) images is reliant upon images of a suitable diagnostic quality being acquired. This study aimed to create a novel machine learning model to automatically assess TVUS image quality. Six imaging professionals (two sonographers, two gynecological sonologists and two radiologists) assigned a quality score to 150 TVUS images from 50 cases (50 uterus images and 100 ovary images). Images were given a score of 1-4 (1- reject/ image inaccurate, 2- poor quality, 3- suboptimal quality or 4- optimal quality). As variation existed between the scores assigned by the raters, we treated this problem as a multi-rater noisy label problem. Using these scores, a new machine learning architecture was created. We used majority-voting to process multi-annotations into a single annotation by assessing label consistency to train the relabelling model. We then re-labelled the dataset with Crowdlab before finetuning a pretrained ViT model on the generated labels. A multi-axis vision transformer was then trained to further improve the image quality assessment process. Forty cases (120 images with various quality scores) were used to train the model. The remaining 10 cases (30 images with various quality scores) were reserved, for evaluation of the model. This novel machine learning architecture was able to successfully determine image quality. Our best model (weighted ensemble) produced an accuracy of 80% and 0.77 on Macro Average R-squared. Our novel machine learning model offers an automated method of assessing the quality of TVUS images. With further refinement, accuracy may be improved, and this tool could be used to provide feedback to those learning to perform TVUS. Potential also exists for this tool to provide quality thresholding for TVUS images which may be used in AI models for the purpose of image interpretation for the diagnosis of endometriosis and other gynecological pathologies.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".