0 51

Cited 0 times in

Deep Learning-Based Classification of Korean Basal Cell Carcinoma Using Convolutional Neural Network

Authors
 Chung, Hyun Jung  ;  Kim, Yoon Jae  ;  Song, Howon  ;  Ahn, Sung Ku  ;  Kim, Hyunggun  ;  Hwang, Heon 
Citation
 JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, Vol.9(1) : 195-201, 2019-01 
Journal Title
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS
ISSN
 2156-7018 
Issue Date
2019-01
Keywords
Basal Cell Carcinoma ; Deep Learning ; Convolution Neural Network ; Skin Cancer ; Segmentation
Abstract
A steady increase in incidence of basal cell carcinoma and other skin cancers has been reported in a number of epidemiologic studies conducted in Korea. In this study, we demonstrated a pipelined deep neural network-based model classifying the Korean basal cell carcinoma vs. normal nevus, using photographic images taken in various lighting, angles, and zoom to develop an early-detection diagnosis kits for malignant skin lesions. The original data set consisted of 1,200 photographic images-600 of basal cell carcinoma and 600 of normal nevus. Our study focused on the effectiveness of pipelining two different DNN-based models for this classification task. The performance of the pipeline was compared to the classification-only method based on four metrics: sensitivity, specificity, AUC, and accuracy. Various sizes of the training set were evaluated (n = 50, 100, 300, 600, 840) to assess the performance of each method. The classification-only model reached an AUC of .93. Closer inspection on the incorrectly-classified test points revealed that the model tended to mislabel noisy images. With the segmentation-classification model, the segmentation step allowed tighter cropping around the lesions, cutting out the distractions. Consequently, we found that for a given small dataset, the segmentation-classification model performed better than the classification-only model. This is a pioneering research in examining a deep learning system for the Korean-specific photographic images. While our study focused primarily on the Korean basal cell carcinoma, our data demonstrated the potential in cancer detection in the clinic where a sufficient number of quality training data are not available. Although we utilized noisy images in low resolution as input data, our findings demonstrated that the pipelining procedures can provide a promising system to deal with data having such limitations.
Full Text
https://www.ingentaconnect.com/content/asp/jmihi/2019/00000009/00000001/art00030;jsessionid=1ekib452uqoul.x-ic-live-03
DOI
10.1166/jmihi.2019.2560
Appears in Collections:
1. College of Medicine (의과대학) > Others (기타) > 1. Journal Papers
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/189178
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links