Deep Video Analysis Methods for Surgical Skills Assessment in Cataract Surgery
Bibliographic record
Abstract
It is important for a graduate surgical trainee in ophthalmology to have a strong understanding of how to proficiently perform cataract surgery. The surgical training curriculum should incorporate methodical assessments of surgical skills and improve trainee surgeons' expertise to maintain patient safety. Prior rating scales for cataract surgery are highly dependant on the subjective opinion of the observing grader and are time consuming. This project is intended to develop a deep learning model for skill evaluation in cataract surgery using raw surgery videos that can supplement human review. An advanced convolutional neural network model is leveraged in this work and was evaluated using a large custom dataset. Videos from four phases in cataract surgery were used to quantify the model performance. Our model yielded an average accuracy of 82% for all four phases of cataract surgery. iii 7.3 Real time prediction of the model on all the 16-second video snippets representing a never seen before video sample (Model identifies novice). Video clip duration (e.g. clip 1 : 0-16 seconds, clip 2: 17-32 seconds) for all 16 second clips are plotted along x axis. . . . . . . . . . . . . . 62 7.4 Real time prediction of the model on all the 16-second video snippets representing a never seen before video sample (Model identifies expert). 63 x
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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 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".