Formulae Evaluation for Estimating Body Surface Area of Korean Children

Application of multiple deep learning models for automatic burn wound assessment

PURPOSE

Accurate assessment of the percentage of total body surface area (%TBSA) burned is crucial in managing burn injuries. It is difficult to estimate the size of an irregular shape by inspection. Many articles reported the discrepancy of estimating %TBSA burned by different doctors. We set up a system with multiple deep learning (DL) models for %TBSA estimation, as well as the segmentation of possibly poor-perfused deep burn regions from the entire wound.

METHODS

We proposed boundary-based labeling for datasets of total burn wound and palm, whereas region-based labeling for the dataset of deep burn wound. Several powerful DL models (U-Net, PSPNet, DeeplabV3+, Mask R-CNN) with encoders ResNet101 had been trained and tested from the above datasets. With the subject distances, the %TBSA burned could be calculated by the segmentation of total burn wound area with respect to the palm size. The percentage of deep burn area could be obtained from the segmentation of deep burn area from the entire wound.

RESULTS

A total of 4991 images of early burn wounds and 1050 images of palms were boundary-based labeled. 1565 out of 4994 images with deep burn were preprocessed with superpixel segmentation into small regions before labeling. DeeplabV3+ had slightly better performance in three tasks with precision: 0.90767, recall: 0.90065 for total burn wound segmentation; precision: 0.98987, recall: 0.99036 for palm segmentation; and precision: 0.90152, recall: 0.90219 for deep burn segmentation.

CONCLUSION

Combining the segmentation results and clinical data, %TBSA burned, the volume of fluid for resuscitation, and the percentage of deep burn area can be automatically diagnosed by DL models with a pixel-to-pixel method. Artificial intelligence provides consistent, accurate and rapid assessments of burn wounds.

Six commonly used empirical body surface area formulas disagreed in young children undergoing corrective heart surgery

AIM

Formulas for empirical body surface area (BSA), which is used to estimate body size and standardise physiological parameters, may disagree in children. We compared six commonly used BSA formulas-Du Bois, Boyd, Costeff, Haycock, Meban and Mosteller-in a surgical cohort.

METHODS

This retrospective single-centre cohort study comprised 68 children who had corrective heart surgery at Skåne University Children's Hospital, Lund, Sweden, from February 2010 to March 2017.

RESULTS

The children (51% female) underwent surgery at a mean weight of 7.0 kilograms (range 2.7-14.1 kg) and a mean age 11 months (range 0-43 months). All the BSA formulas showed good correlation with mean BSA, but there were considerable variations between them. Mosteller's formula was exactly the same as the mean BSA (bias 0.000). The Du Bois and Boyd formulas had the largest mean BSA deviations (bias -0.012 and 0.015). Costeff's formula showed good agreement with mean BSA, Haycock's formula showed minimal overestimation and Meban's formula demonstrated a systemic error in older children.

CONCLUSION

Commonly used BSA formulas did not agree in young children undergoing heart surgery, but they were all close to the overall mean of the six formulas, with the Mosteller formula producing the same value.