Skin Lesion Segmentation in Dermoscopic Images with Noisy Data.
We propose a deep learning approach to segment the skin lesion in dermoscopic images. The proposed network architecture uses a pretrained EfficientNet model in the encoder and squeeze-and-excitation residual structures in the decoder. We applied this approach on the publicly available International...
| Publicado en: | Journal of Digital Imaging Vol. 36; no. 4; pp. 1712 - 1723 |
|---|---|
| Autores principales: | , , , , |
| Formato: | pictorial research tables/charts Journal Article |
| Publicado: |
Springer Nature
Aug2023
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=169808814&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 169808814 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Aug2023 vid: 36 iid: 4 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 169808814 162913086 169808814 169808814 10.1007/s10278-023-00819-8 169808814 ppf: 1712 ppct: 11 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Skin Lesion Segmentation in Dermoscopic Images with Noisy Data. aug: au: Lama, Norsang Hagerty, Jason Nambisan, Anand Stanley, Ronald Joe Van Stoecker, William affil: Missouri University of Science &Technology, 65409, Rolla, MO, USA sug: subj: Skin Neoplasms Pathology Dermoscopy Methods Image Processing, Computer Assisted Methods Melanoma Pathology Human Algorithms Deep Learning Methods Noise Sensitivity and Specificity Skin Pathology Neural Networks (Computer) Benchmarking ab: We propose a deep learning approach to segment the skin lesion in dermoscopic images. The proposed network architecture uses a pretrained EfficientNet model in the encoder and squeeze-and-excitation residual structures in the decoder. We applied this approach on the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset. This benchmark dataset has been widely used in previous studies. We observed many inaccurate or noisy ground truth labels. To reduce noisy data, we manually sorted all ground truth labels into three categories — good, mildly noisy, and noisy labels. Furthermore, we investigated the effect of such noisy labels in training and test sets. Our test results show that the proposed method achieved Jaccard scores of 0.807 on the official ISIC 2017 test set and 0.832 on the curated ISIC 2017 test set, exhibiting better performance than previously reported methods. Furthermore, the experimental results showed that the noisy labels in the training set did not lower the segmentation performance. However, the noisy labels in the test set adversely affected the evaluation scores. We recommend that the noisy labels should be avoided in the test set in future studies for accurate evaluation of the segmentation algorithms. pubtype: Academic Journal doctype: pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|