A new preprocessing approach to improve the performance of CNN-based skin lesion classification

被引:0
|
作者
Hadi Zanddizari
Nam Nguyen
Behnam Zeinali
J. Morris Chang
机构
[1] University of South Florida,Department of Electrical Engineering
关键词
Region of interest; Segmentation; Convolutional neural network; Skin lesion;
D O I
暂无
中图分类号
学科分类号
摘要
Skin lesion is one of the severe diseases which in many cases endanger the lives of patients on a worldwide extent. Early detection of disease in dermoscopy images can significantly increase the survival rate. However, the accurate detection of disease is highly challenging due to the following reasons: e.g., visual similarity between different classes of disease (e.g., melanoma and non-melanoma lesions), low contrast between lesions and skin, background noise, and artifacts. Machine learning models based on convolutional neural networks (CNN) have been widely used for automatic recognition of lesion diseases with high accuracy in comparison to conventional machine learning methods. In this research, we proposed a new preprocessing technique in order to extract the region of interest (RoI) of skin lesion dataset. We compare the performance of the most state-of-the-art CNN classifiers with two datasets which contain (1) raw, and (2) RoI extracted images. Our experiment results show that training CNN models by RoI extracted dataset can improve the accuracy of the prediction (e.g., InceptionResNetV2, 2.18% improvement). Moreover, it significantly decreases the evaluation (inference) and training time of classifiers as well.
引用
收藏
页码:1123 / 1131
页数:8
相关论文
共 50 条
  • [1] A new preprocessing approach to improve the performance of CNN-based skin lesion classification
    Zanddizari, Hadi
    Nguyen, Nam
    Zeinali, Behnam
    Chang, J. Morris
    [J]. MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2021, 59 (05) : 1123 - 1131
  • [2] Vision transformer and CNN-based skin lesion analysis: classification of monkeypox
    Yolcu Oztel, Gozde
    [J]. Multimedia Tools and Applications, 2024, 83 (28) : 71909 - 71923
  • [3] Skin Lesion Classification Using CNN-based Transfer Learning Model
    Dimililer, Kamil
    Sekeroglu, Boran
    [J]. GAZI UNIVERSITY JOURNAL OF SCIENCE, 2023, 36 (02): : 660 - 673
  • [4] Approach to Bearing Fault Diagnosis: CNN-Based Classification Across Different Preprocessing Techniquese
    Jachymczyk, Urszula
    Knap, Pawel
    Balazy, Patryk
    Podlasek, Szymon
    Lalik, Krzysztof
    [J]. 2024 25TH INTERNATIONAL CARPATHIAN CONTROL CONFERENCE, ICCC 2024, 2024,
  • [5] CNN-Based Model for Skin Diseases Classification
    Altimimi, Asmaa S. Zamil
    Abdulkader, Hasan
    [J]. ARTIFICIAL INTELLIGENCE FOR INTERNET OF THINGS (IOT) AND HEALTH SYSTEMS OPERABILITY, IOTHIC 2023, 2024, 8 : 28 - 38
  • [6] An interpretable CNN-based CAD system for skin lesion diagnosis
    Lopez-Labraca, Javier
    Gonzalez-Diaz, Ivan
    Diaz-de-Maria, Fernando
    Fueyo-Casado, Alejandro
    [J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2022, 132
  • [7] Automatic Stones Classification through a CNN-Based Approach
    Tropea, Mauro
    Fedele, Giuseppe
    De Luca, Raffaella
    Miriello, Domenico
    De Rango, Floriano
    [J]. SENSORS, 2022, 22 (16)
  • [8] Skin Microstructure Segmentation and Aging Classification Using CNN-Based Models
    Moon, Cho-, I
    Lee, Onseok
    [J]. IEEE ACCESS, 2022, 10 : 4948 - 4956
  • [9] A DenseNet CNN-based liver lesion prediction and classification for future medical diagnosis
    Prakash, N. Nanda
    Rajesh, V
    Namakhwa, Dumisani Lickson
    Pande, Sandeep Dwarkanath
    Ahammad, Sk Hasane
    [J]. SCIENTIFIC AFRICAN, 2023, 20
  • [10] A novel CNN-based approach for detection and classification of DDoS attacks
    Najar, Ashfaq Ahmad
    Sugali, Manohar Naik
    Lone, Faisal Rasheed
    Nazir, Azra
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2024, 36 (19):