Enhancing Nipple Positioning Accuracy in Chest Reconstruction Surgery: An Automated Machine Learning Approach
Bibliographic record
Abstract
Accurate placement of the Nipple-Areola Complex (NAC) is critical for the aesthetic success of chest reconstruction surgery. Traditional methods rely on the surgeon's experience and subjective judgment, presenting a need for a more objective and reliable approach. This study introduces a machine learning solution to estimate the NAC position on a male chest wall. In this study, we feed a dataset composed of 102 images of 34 male subjects of different ages and body types into an open-source pose estimation algorithm to detect upper body key points that are common to both biological sexes such as shoulders and elbows. A selected subset of those key points is then used to form a normalized feature set which was fed into six regression models; Decision Tree Regressor, Random Forest Regressor, CatBoost Regressor, Multilayer Perceptron Regressor, Linear Regressor, and Support Vector Regressor to predict the NAC position. The lowest mean absolute percentage error(MAPE) between the real and predicted normalized body ratios (0.69%) was achieved with Linear Regression. Subsequently, the chosen model was used to predict the positions of both nipples. A tilt-correction mechanism was introduced to improve accuracy when patient posture was misaligned. Without tilt correction, the MAPE for right and left NAC positions was 1.2% and 0.99%, respectively, which was reduced to 0.75% and 0.63% after correction. Our results suggest that machine learning can be used to assist surgeons performing chest reconstruction surgeries.
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 | 0.001 | 0.003 |
| 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 | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".