English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Malignant melanoma (MM) is one of the deadliest types of skin cancer.Analysing dermatoscopic images plays an important role in the early detectionof MM and other pigmented skin lesions. Among different computer-based methods,deep learning-based approaches and in particular convolutional neural networkshave shown excellent classification and segmentation performances fordermatoscopic skin lesion images. These models can be trained end-to-endwithout requiring any hand-crafted features. However, the effect of usinglesion segmentation information on classification performance has remained anopen question. In this study, we explicitly investigated the impact of usingskin lesion segmentation masks on the performance of dermatoscopic imageclassification. To do this, first, we developed a baseline classifier as thereference model without using any segmentation masks. Then, we used eithermanually or automatically created segmentation masks in both training and testphases in different scenarios and investigated the classification performances.Evaluated on the ISIC 2017 challenge dataset which contained two binaryclassification tasks (i.e. MM vs. all and seborrheic keratosis (SK) vs. all)and based on the derived area under the receiver operating characteristic curvescores, we observed four main outcomes. Our results show that 1) usingsegmentation masks did not significantly improve the MM classificationperformance in any scenario, 2) in one of the scenarios (using segmentationmasks for dilated cropping), SK classification performance was significantlyimproved, 3) removing all background information by the segmentation maskssignificantly degraded the overall classification performance, and 4) in caseof using the appropriate scenario (using segmentation for dilated cropping),there is no significant difference of using manually or automatically createdsegmentation masks.

The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification