Densemask RCNN: A Hybrid Model for Skin Burn Image Classification and Severity Grading

In the medical image processing, automatic segmentation of burn images is one of the critical tasks in the classification of skin burn into normal and burn area. Traditional models identify the burns from the image and distinguish the region as burn and non-burn regions. However, the earlier models cannot accurately classify the wound region and also requires more time in the prediction of burns. Also, the burn depth analysis is an important factor for the calculation of the percentage of burn depth i.e. degree of severity is analyzed by Total body surface area (TBSA). For those issues, we design a hybrid approach named DenseMask Regional convolutional neural network (RCNN) approach for segmenting the skin burn region based on the various degrees of burn severity. In this, hybrid integration of Mask-region based convolution neural network CNN (Mask R-CNN) and dense pose estimation are integrated into DenseMask RCNN that calculate the full-body human pose and performs semantic segmentation. At first, we use the Residual Network with a dilated convolution using a weighted mapping model to generate the dense feature map. Then the feature map is fed into the Region proposal network (RPN) which utilizes a Feature pyramid network (FPN) to detect the objects at different scales of location and pyramid level from the input images. For the accurate alignment of pixel-to-pixel labels, we introduce a Region of interest (RoI)-pose align module that properly aligns the objects based on the human pose with the characteristics of scale, right-left, translation, and left–right flip to a standard scale. After the alignment task, a cascaded fully convolutional architecture is employed on the top of the RoI module that performs mask segmentation and dense pose regression task simultaneously. Finally, the transfer learning model classifies the detected burn regions into three classes of wound depths. Experimental analysis is performed on the burn dataset and the result obtained shows better accuracy than the state-of-art approaches.