Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis

Accurately diagnosing skin lesion disease is a challenging task. Although present methods often use the multi-branch structure to get more clues, the rigescent methods of cropping zone and fusing branch results fail to handle the instability of the disease zone and the difference in branch results,...

Full description

Saved in:
Bibliographic Details
Main Authors: Gaoshuai Wang, Linrunjia Liu, Fabrice Lauri, Amir HAJJAM El Hassani
Format: Article
Language:English
Published: Tsinghua University Press 2024-12-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2024.9020038
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846100791775985664
author Gaoshuai Wang
Linrunjia Liu
Fabrice Lauri
Amir HAJJAM El Hassani
author_facet Gaoshuai Wang
Linrunjia Liu
Fabrice Lauri
Amir HAJJAM El Hassani
author_sort Gaoshuai Wang
collection DOAJ
description Accurately diagnosing skin lesion disease is a challenging task. Although present methods often use the multi-branch structure to get more clues, the rigescent methods of cropping zone and fusing branch results fail to handle the instability of the disease zone and the difference in branch results, which leads to improper cropping and degrades Deep Convolutional Neural Networks (DCNN)’s performance. To address these problems, we propose a Multi-scale DCNN with Dynamic weight and Part cross-entropy loss model (namely MDP-DCNN) to bootstrap skin lesion diagnosis. Inspired by the object detection method, the multi-scale structure adjusts the cropping position based on the Gradient-weighted Class Activation Mapping (Grad-CAM) center. It enables the model to adapt to the disease zone variety in position and size. The dynamic weight structure alleviates the negative influence of branch differences by comparing the grey-cropped zone and its CAM. Moreover, we also propose the part cross-entropy loss to deal with the over-fitting problem. This optimizes the non-targeted label to decrease the influence on other labels’ stability when the prediction is wrong. We conduct our model on the ISIC-2017 and ISIC-2018 datasets. Experiments demonstrate that MDP-DCNN achieves excellent results in skin lesion classification without external data. Multi-scale DCNN with dynamic weight and part loss function verifies its advantages in enhancing diagnosis accuracy.
format Article
id doaj-art-e0307d3fb37445808f52a943d40c9a6e
institution Kabale University
issn 2096-0654
language English
publishDate 2024-12-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-e0307d3fb37445808f52a943d40c9a6e2024-12-29T15:36:22ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-12-01741347136110.26599/BDMA.2024.9020038Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion DiagnosisGaoshuai Wang0Linrunjia Liu1Fabrice Lauri2Amir HAJJAM El Hassani3Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDepartment of Computer Science, Xidian University, Xi’an 710071, ChinaDepartment of Computer Science, Université de Technologie de Belfort-Montbéliard, Belfort 90000, FranceDepartment of Computer Science, Université de Technologie de Belfort-Montbéliard, Belfort 90000, FranceAccurately diagnosing skin lesion disease is a challenging task. Although present methods often use the multi-branch structure to get more clues, the rigescent methods of cropping zone and fusing branch results fail to handle the instability of the disease zone and the difference in branch results, which leads to improper cropping and degrades Deep Convolutional Neural Networks (DCNN)’s performance. To address these problems, we propose a Multi-scale DCNN with Dynamic weight and Part cross-entropy loss model (namely MDP-DCNN) to bootstrap skin lesion diagnosis. Inspired by the object detection method, the multi-scale structure adjusts the cropping position based on the Gradient-weighted Class Activation Mapping (Grad-CAM) center. It enables the model to adapt to the disease zone variety in position and size. The dynamic weight structure alleviates the negative influence of branch differences by comparing the grey-cropped zone and its CAM. Moreover, we also propose the part cross-entropy loss to deal with the over-fitting problem. This optimizes the non-targeted label to decrease the influence on other labels’ stability when the prediction is wrong. We conduct our model on the ISIC-2017 and ISIC-2018 datasets. Experiments demonstrate that MDP-DCNN achieves excellent results in skin lesion classification without external data. Multi-scale DCNN with dynamic weight and part loss function verifies its advantages in enhancing diagnosis accuracy.https://www.sciopen.com/article/10.26599/BDMA.2024.9020038skin lesiondynamic weightdynamic croppingpart cross-entropy loss
spellingShingle Gaoshuai Wang
Linrunjia Liu
Fabrice Lauri
Amir HAJJAM El Hassani
Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis
Big Data Mining and Analytics
skin lesion
dynamic weight
dynamic cropping
part cross-entropy loss
title Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis
title_full Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis
title_fullStr Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis
title_full_unstemmed Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis
title_short Multi-Scale DCNN with Dynamic Weight and Part Cross-Entropy Loss for Skin Lesion Diagnosis
title_sort multi scale dcnn with dynamic weight and part cross entropy loss for skin lesion diagnosis
topic skin lesion
dynamic weight
dynamic cropping
part cross-entropy loss
url https://www.sciopen.com/article/10.26599/BDMA.2024.9020038
work_keys_str_mv AT gaoshuaiwang multiscaledcnnwithdynamicweightandpartcrossentropylossforskinlesiondiagnosis
AT linrunjialiu multiscaledcnnwithdynamicweightandpartcrossentropylossforskinlesiondiagnosis
AT fabricelauri multiscaledcnnwithdynamicweightandpartcrossentropylossforskinlesiondiagnosis
AT amirhajjamelhassani multiscaledcnnwithdynamicweightandpartcrossentropylossforskinlesiondiagnosis