SILP: Enhancing Skin Lesion Classification using Swin Transformer with Spatial Interaction and Local Perception Modules

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/93060

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/93060

Title:	SILP: Enhancing Skin Lesion Classification using Swin Transformer with Spatial Interaction and Local Perception Modules
Authors:	周裕惠;Zhou, Yu-Hui
Contributors:	資訊工程學系
Keywords:	皮膚癌;醫學影像;影像分類;視覺轉換器;skin lesion;medical imaging;image classification;vision transformer
Date:	2023-07-13
Issue Date:	2024-09-19 16:40:08 (UTC+8)
Publisher:	國立中央大學
Abstract:	由於紫外線和全球環境因素的變化，全球各地患有皮膚病的病患數量有日益增加的情況。在某些地區，因為其相對來說有限的醫療資源，因此，對於各項皮膚病的診斷仍是一大未知的挑戰。然而，未經正確醫治的皮膚病可能會發展為皮膚癌，所以，在此情況下，則迫切需要一個高效、準確且易於使用的系統來識別可疑病變。儘管目前存在許多皮膚病分類模型，但在準確性等評估指標上仍有改進的空間。為了提高皮膚病分類的準確性，本研究提出了名為SILP的新分類系統，該影像分類系統引入了兩個模塊：本地感知模塊和空間交互模塊。除此之外，我們也對激活函數進行了修改，以改進訓練時間和準確性。在實驗方面，主要通過在兩個公開的皮膚病資料及上進行實驗，以此來評估了SILP的性能。根據實驗結果顯示，SILP不僅在準確性方面比最先進的皮膚病分類模型還要好之外，在其他評估指標上也表現的十分亮眼。;Because of the harmful effects of ultraviolet rays and global environmental factors, the number of patients with skin lesions is increasing. If left untreated, skin lesions may lead to skin cancer. However, limited access to specialized medical care remains a challenge in certain regions. Therefore, there is an urgent need for an efficient, accurate, and accessible tool to identify suspicious lesions. Although there are many classification models for skin lesions, there is still room for improvement in terms of accuracy. To enhance the accuracy of skin lesion classification, a novel system named SILP is proposed in this study. There are two modules in SILP: the Local Perception Module and the Spatial Interaction Module. Additionally, we have modified the activation function to improve both training time and accuracy. SILP, along with several other models, has been tested on two public skin lesion datasets. The results demonstrate that our proposed system outperforms the state-of-the-art skin lesion classification model, not only in terms of accuracy but also in various other evaluation metrics.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	11	View/Open

社群 sharing

Loading...