Dermo-DOCTOR: A framework for concurrent skin lesion detection and recognition using a deep convolutional neural network with end-to-end dual encoders. (July 2021)

• Record Type: Journal Article
• Authors: Hasan, Md. Kamrul; Roy, Shidhartho; Mondal, Chayan; Alam, Md. Ashraful; E Elahi, Md. Toufick; Dutta, Aishwariya; Uddin Raju, S.M. Taslim; Jawad, Md. Tasnim; Ahmad, Mohiuddin
• Is Part Of: Biomedical signal processing and control. Volume 68(2021)
• Publication Date: 2021-07
• Subjects: Malignant melanoma -- Skin lesion detection and recognition -- Convolutional neural networks -- Dual encoder networks -- ISIC skin lesion datasets; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102661
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Development of an end-to-end ensembling model with dual encoders in the proposed Dermo-DOCTOR framework. Incorporation of segmented lesion ROIs for the recognition, enabling to learn the abstract lesion region and detailed structural description. Employment of image augmentations, class rebalancing, and transfer learning to build a generic diagnostic system. Demonstration of state-of-the-art lesion detection and recognition results on ISIC-2016 and ISIC-2017. Implementation of possible web application of our Dermo-DOCTOR, deploying its trained weights. Abstract: Background and objective: Automated skin lesion analysis for simultaneous detection and recognition is still challenging for inter-class homogeneity and intra-class heterogeneity, leading to low generic capability of a single convolutional neural network (CNN) with limited datasets. Methods: This article proposes an end-to-end deep CNN-based framework for simultaneous detection and recognition of the skin lesions, named Dermo-DOCTOR, consisting of two encoders. The feature maps from two encoders are fused channel-wise, called Fused Feature Map (FFM). The FFM is utilized for decoding in the detection sub-network, concatenating each stage of two encoders' outputs with corresponding decoder layers to retrieve the lost spatial information due to pooling in the encoders. For the recognition sub-network, the outputs of three fully connected layers, utilizing feature maps of two encoders and FFM, are aggregated to obtain a final lesion class. We train and evaluate the proposed Dermo-Doctor utilizing two publicly available benchmark datasets, such as ISIC-2016 and ISIC-2017. Results: The achieved segmentation results exhibit mean intersection over unions of 85.0% and 80.0% respectively for ISIC-2016 and ISIC-2017 test datasets. The proposed Dermo-DOCTOR also demonstrates praiseworthy success in lesion recognition, providing the areas under the receiver operating characteristic curves of 0.98 and 0.91 respectively for those two datasets. The experimental results show that the proposed Dermo-DOCTOR outperforms the alternative methods mentioned in the literature, designed for skin lesion detection and recognition. Conclusion: As the Dermo-DOCTOR provides better results on two different test datasets, even with limited training data, it can be an auspicious computer-aided assistive tool for dermatologists.