Display options
Cite
Ningrum DNA, Yuan SP, Kung WM, et al. Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection. J Multidiscip Healthc. 2021;14:877-885doi: 10.2147/JMDH.S306284.
Ningrum, D. N. A., Yuan, S. P., Kung, W. M., Wu, C. C., Tzeng, I. S., Huang, C. Y., Li, J. Y., & Wang, Y. C. (2021). Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection. Journal of multidisciplinary healthcare, 14877-885. https://doi.org/10.2147/JMDH.S306284
Ningrum, Dina Nur Anggraini, et al. "Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection." Journal of multidisciplinary healthcare vol. 14 (2021): 877-885. doi: https://doi.org/10.2147/JMDH.S306284
Ningrum DNA, Yuan SP, Kung WM, Wu CC, Tzeng IS, Huang CY, Li JY, Wang YC. Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection. J Multidiscip Healthc. 2021 Apr 21;14:877-885. doi: 10.2147/JMDH.S306284. eCollection 2021. PMID: 33907414; PMCID: PMC8071207.
Copy Download .nbib Format: NLM
Share it on

J Multidiscip Healthc. 2021 Apr 21;14:877-885. doi: 10.2147/JMDH.S306284. eCollection 2021.

Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection.

Journal of multidisciplinary healthcare

Dina Nur Anggraini Ningrum, Sheng-Po Yuan, Woon-Man Kung, Chieh-Chen Wu, I-Shiang Tzeng, Chu-Ya Huang, Jack Yu-Chuan Li, Yao-Chin Wang

Affiliations

  1. Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.
  2. Public Health Department, Universitas Negeri Semarang, Semarang City, Indonesia.
  3. Department of Otorhinolaryngology, Shuang-Ho Hospital, Taipei Medical University, New Taipei City, Taiwan.
  4. Department of Exercise and Health Promotion, College of Kinesiology and Health, Chinese Culture University, Taipei, Taiwan.
  5. Department of Research, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan.
  6. Department of Statistics, National Taipei University, Taipei, Taiwan.
  7. Taiwan College of Healthcare Executives, Taipei, Taiwan.
  8. Department Dermatology, Wan Fang Hospital, Taipei, Taiwan.
  9. Taipei Medical University Research Center of Cancer Translational Medicine, Taipei, Taiwan.
  10. Graduate Institute of Injury Prevention and Control, College of Public Health, Taipei Medical University, Taipei, Taiwan.
  11. Department of Emergency Medicine, Min-Sheng General Hospital, Taoyuan, Taiwan.

PMID: 33907414 PMCID: PMC8071207 DOI: 10.2147/JMDH.S306284

Abstract

BACKGROUND: Incidence of skin cancer is one of the global burdens of malignancies that increase each year, with melanoma being the deadliest one. Imaging-based automated skin cancer detection still remains challenging owing to variability in the skin lesions and limited standard dataset availability. Recent research indicates the potential of deep convolutional neural networks (CNN) in predicting outcomes from simple as well as highly complicated images. However, its implementation requires high-class computational facility, that is not feasible in low resource and remote areas of health care. There is potential in combining image and patient's metadata, but the study is still lacking.

OBJECTIVE: We want to develop malignant melanoma detection based on dermoscopic images and patient's metadata using an artificial intelligence (AI) model that will work on low-resource devices.

METHODS: We used an open-access dermatology repository of International Skin Imaging Collaboration (ISIC) Archive dataset consist of 23,801 biopsy-proven dermoscopic images. We tested performance for binary classification malignant melanomas vs nonmalignant melanomas. From 1200 sample images, we split the data for training (72%), validation (18%), and testing (10%). We compared CNN with image data only (CNN model) vs CNN for image data combined with an artificial neural network (ANN) for patient's metadata (CNN+ANN model).

RESULTS: The balanced accuracy for CNN+ANN model was higher (92.34%) than the CNN model (73.69%). Combination of the patient's metadata using ANN prevents the overfitting that occurs in the CNN model using dermoscopic images only. This small size (24 MB) of this model made it possible to run on a medium class computer without the need of cloud computing, suitable for deployment on devices with limited resources.

CONCLUSION: The CNN+ANN model can increase the accuracy of classification in malignant melanoma detection even with limited data and is promising for development as a screening device in remote and low resources health care.

© 2021 Ningrum et al.

Keywords: artificial neural network; convolutional neural network; embedded artificial intelligence; skin cancer

Conflict of interest statement

The authors report no conflicts of interest in this work.

References

  1. J Med Syst. 2018 Mar 26;42(5):85 - PubMed
  2. J Natl Cancer Inst. 2015 Nov 07;108(2): - PubMed
  3. Exp Dermatol. 2018 Nov;27(11):1261-1267 - PubMed
  4. JAMA Oncol. 2018 Nov 1;4(11):1553-1568 - PubMed
  5. Sensors (Basel). 2018 Feb 11;18(2): - PubMed
  6. IEEE Trans Med Imaging. 2019 Sep;38(9):2092-2103 - PubMed
  7. Tissue Cell. 2019 Jun;58:76-83 - PubMed
  8. J Am Acad Dermatol. 2017 Jan;76(1):129-139.e10 - PubMed
  9. Eur J Cancer. 2016 Jan;53:33-41 - PubMed
  10. IEEE Rev Biomed Eng. 2015;8:98-113 - PubMed
  11. EBioMedicine. 2019 May;43:107-113 - PubMed
  12. J Med Syst. 2016 Apr;40(4):96 - PubMed
  13. Diagnostics (Basel). 2020 Aug 09;10(8): - PubMed
  14. Eur J Cancer. 2020 Mar;127:21-29 - PubMed
  15. Sci Data. 2018 Aug 14;5:180161 - PubMed
  16. J Med Syst. 2018 Jan 09;42(2):33 - PubMed

Publication Types