Non-invasive detection of anemia using lip mucosa images transfer learning convolutional neural networks

被引:1
作者
Mansour, Mohammed [1 ]
Donmez, Turker Berk [2 ]
Kutlu, Mustafa [1 ]
Mahmud, Shekhar [3 ]
机构
[1] Sakarya Univ Appl Sci, Mechatron Engn Dept, Serdivan, Sakarya, Turkiye
[2] Sakarya Univ Appl Sci, Biomed Engn Dept, Serdivan, Sakarya, Turkiye
[3] Mil Technol Coll, Dept Syst Engn, Muscat, Oman
来源
FRONTIERS IN BIG DATA | 2023年 / 6卷
关键词
anemia; image processing; deep learning; classification; convolutional neural network (CNN); DIAGNOSIS;
D O I
10.3389/fdata.2023.1291329
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Anemia is defined as a drop in the number of erythrocytes or hemoglobin concentration below normal levels in healthy people. The increase in paleness of the skin might vary based on the color of the skin, although there is currently no quantifiable measurement. The pallor of the skin is best visible in locations where the cuticle is thin, such as the interior of the mouth, lips, or conjunctiva. This work focuses on anemia-related pallors and their relationship to blood count values and artificial intelligence. In this study, a deep learning approach using transfer learning and Convolutional Neural Networks (CNN) was implemented in which VGG16, Xception, MobileNet, and ResNet50 architectures, were pre-trained to predict anemia using lip mucous images. A total of 138 volunteers (100 women and 38 men) participated in the work to develop the dataset that contains two image classes: healthy and anemic. Image processing was first performed on a single frame with only the mouth area visible, data argumentation was preformed, and then CNN models were applied to classify the dataset lip images. Statistical metrics were employed to discriminate the performance of the models in terms of Accuracy, Precision, Recal, and F1 Score. Among the CNN algorithms used, Xception was found to categorize the lip images with 99.28% accuracy, providing the best results. The other CNN architectures had accuracies of 96.38% for MobileNet, 95.65% for ResNet %, and 92.39% for VGG16. Our findings show that anemia may be diagnosed using deep learning approaches from a single lip image. This data set will be enhanced in the future to allow for real-time classification.
引用
收藏
页数:10
相关论文
共 56 条
  • [1] Age, anemia, and fatigue
    Aapro, MS
    Cella, D
    Zagari, M
    [J]. SEMINARS IN ONCOLOGY, 2002, 29 (03) : 55 - 59
  • [2] Random forest method for the recognition of susceptibility and resistance patterns in antibiograms
    Ayala-Aldana, Nicolas
    Gonzalez-Valdes, Leticia
    [J]. REVISTA CHILENA DE INFECTOLOGIA, 2023, 40 (01): : 76 - 77
  • [3] Resume Classification System using Natural Language Processing and Machine Learning Techniques
    Ali, Irfan
    Mughal, Nimra
    Khand, Zahid Hussain
    Ahmed, Javed
    Mujtaba, Ghulam
    [J]. MEHRAN UNIVERSITY RESEARCH JOURNAL OF ENGINEERING AND TECHNOLOGY, 2022, 41 (01) : 65 - 79
  • [4] Aloysius N, 2017, 2017 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), P588, DOI 10.1109/ICCSP.2017.8286426
  • [5] Emerging point-of-care technologies for anemia detection
    An, Ran
    Huang, Yuning
    Man, Yuncheng
    Valentine, Russell W.
    Kucukal, Erdem
    Goreke, Utku
    Sekyonda, Zoe
    Piccone, Connie
    Owusu-Ansah, Amma
    Ahuja, Sanjay
    Little, Jane A.
    Gurkan, Umut A.
    [J]. LAB ON A CHIP, 2021, 21 (10) : 1843 - 1865
  • [6] Anemia during pregnancy and treatment with intravenous iron: review of the literature
    Bashiri, A
    Burstein, E
    Sheiner, E
    Mazor, M
    [J]. EUROPEAN JOURNAL OF OBSTETRICS & GYNECOLOGY AND REPRODUCTIVE BIOLOGY, 2003, 110 (01) : 2 - 7
  • [7] BROWN RG, 1991, POSTGRAD MED, V89, P161
  • [8] A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models
    Christodoulou, Evangelia
    Ma, Jie
    Collins, Gary S.
    Steyerberg, Ewout W.
    Verbakel, Jan Y.
    Van Calster, Ben
    [J]. JOURNAL OF CLINICAL EPIDEMIOLOGY, 2019, 110 : 12 - 22
  • [9] Conrad M. E., 2011, Anemia
  • [10] A Systematic Mapping Study on Research in Anemia Assessment with Non-Invasive Devices
    Dimauro, Giovanni
    Caivano, Danilo
    Di Pilato, Pierangelo
    Dipalma, Alessandro
    Camporeale, Mauro Giuseppe
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (14):