The effects of skin lesion segmentation on the performance of dermatoscopic image classification. (December 2020)

• Record Type: Journal Article
• Authors: Mahbod, Amirreza; Tschandl, Philipp; Langs, Georg; Ecker, Rupert; Ellinger, Isabella
• Is Part Of: Computer methods and programs in biomedicine. Volume 197(2020)
• Publication Date: 2020-12
• Subjects: Skin cancer -- dermatoscopy -- medical image analysis -- deep learning -- effect of segmentation on classification; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105725
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Using segmentation masks did not significantly improve malignant melanoma classification performance. Using segmentation masks for dilated cropping of skin lesion images significantly improved seborrheic keratosis classification performance. Removing all background information by the segmentation masks significantly degraded the overall skin lesion classification performance. Using automatically instead of manually created segmentation masks for dilated cropping, did not significantly change the overall classification performance. Abstract: Background and Objective: Malignant melanoma (MM) is one of the deadliest types of skin cancer. Analysing dermatoscopic images plays an important role in the early detection of MM and other pigmented skin lesions. Among different computer-based methods, deep learning-based approaches and in particular convolutional neural networks have shown excellent classification and segmentation performances for dermatoscopic skin lesion images. These models can be trained end-to-end without requiring any hand-crafted features. However, the effect of using lesion segmentation information on classification performance has remained an open question. Methods: In this study, we explicitly investigated the impact of using skin lesion segmentation masks on the performance of dermatoscopic image classification. To do this, first, we developed a baseline classifier as the reference model without using any segmentation masks. Then, we used either manually or automatically created segmentation masks in both training and test phases in different scenarios and investigated the classification performances. The different scenarios included approaches that exploited the segmentation masks either for cropping of skin lesion images or removing the surrounding background or using the segmentation masks as an additional input channel for model training. Results: Evaluated on the ISIC 2017 challenge dataset which contained two binary classification tasks (i.e. MM vs. all and seborrheic keratosis (SK) vs. all) and based on the derived area under the receiver operating characteristic curve scores, we observed four main outcomes. Our results show that 1) using segmentation masks did not significantly improve the MM classification performance in any scenario, 2) in one of the scenarios (using segmentation masks for dilated cropping), SK classification performance was significantly improved, 3) removing all background information by the segmentation masks significantly degraded the overall classification performance, and 4) in case of using the appropriate scenario (using segmentation for dilated cropping), there is no significant difference of using manually or automatically created segmentation masks. Conclusions: We systematically explored the effects of using image segmentation on the performance of dermatoscopic skin lesion classification.