A deep learning-based illumination transform for devignetting photographs of dermatological lesions

Venugopal, V and Nath, MK and Joseph, J and Das, MV (2024) A deep learning-based illumination transform for devignetting photographs of dermatological lesions. In: Image and Vision Computing, 142 .

PDF ima_vis_com_142_2024.pdf - Published Version Restricted to Registered users only Download (27MB) | Request a copy

Abstract

Photographs of skin lesions taken with standard digital cameras (macroscopic images) have gained wide acceptance in dermatology. However, uneven background lighting caused by nonstandard image acquisition negatively impacts lesion segmentation and diagnosis. To address this, we propose an automated illumination equalization method based on a counter exponential transform (IECET). A modified residual network (ResNet) regressor is used to automate the selection of the operational parameter of the IECET. The regressor is designed by modifying the final fully-connected layer of the baseline ResNet-50 model. The modified fully-connected layer is coupled to a regression layer in the modified ResNet regressor. A prior knowledge base is created to train the modified ResNet regressor. For this, a set of corrupted images are generated by simulating uneven background illumination on pristine images. The knowledge base is created by including pairs of value components obtained from the HSV color space version of the corrupted macroscopic images and ideal operational parameter values that maximize the peak signal-to-noise ratio (PSNR) between the pristine images and the IECET outputs. We evaluated segmentation accuracies of the deep threshold prediction network (DTP-Net), DeepLabV3 +, fully convolutional network (FCN), and U-Net on the corrupted macroscopic images and output images of the IECET. The DTP-Net, DeepLabV3 +, FCN, and U-Net exhibited Dice similarity coefficient (DSC) of 0.71 ± 0.26, 0.85 ± 0.15, 0.75 ± 0.22, and 0.66 ± 0.28 on corrupted images and 0.81 ± 0.17, 0.87 ± 0.12, 0.79 ± 0.18, and 0.79 ± 0.15, on the outputs of the IECET. Increase in DSC proves the ability of the IECET to improve the performance of deep learning models used to segment skin lesions on macroscopic images. © 2024 Elsevier B.V.

Item Type:	Journal Article
Publication:	Image and Vision Computing
Publisher:	Elsevier Ltd
Additional Information:	The copyright for this article belongs to Elsevier Ltd.
Keywords:	Convolution; Convolutional neural networks; Dermatology; Image enhancement; Image segmentation; Knowledge based systems; Photography; Signal to noise ratio, Convolutional networks; Convolutional neural network; Corrupted images; Counter exponential transform; Deep learning; Exponential transforms; Illumination correction; Lesion segmentations; Similarity coefficients; Skin lesion, Deep learning
Department/Centre:	Autonomous Societies / Centres > Centre for Brain Research
Date Deposited:	04 Apr 2024 11:39
Last Modified:	04 Apr 2024 11:39
URI:	https://eprints.iisc.ac.in/id/eprint/84715

Actions (login required)

View Item