컨볼루션 신경망 모델을 이용한 분류에서 입력 영상의 종류가 정확도에 미치는 영향 = The Effect of Type of Input Image on Accuracy in Classification Using Convolutional Neural Network Model

다국어 초록 (Multilingual Abstract)

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

참고문헌 (Reference)

1 양성희, "좌심실비대 진단에서 심장초음파와 심전도검사의 정확성" 한국콘텐츠학회 16 (16): 666-672, 2016

2 송하연, "인공지능과 헬스 커뮤니케이션" 언론정보연구소 57 (57): 196-238, 2020

3 Zagoruyko S, "Wide residual networks"

4 Simonyan K, "Very deep convolutional networks for large-scale image recognition"

5 Tschandl P, "The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions" 5 (5): 1-9, 2018

6 Kabachinski J, "TIFF, GIF, and PNG : get the picture?" 41 (41): 297-300, 2007

7 Alghamdi SS, "Study of cardiomegaly using chest x-ray" 13 (13): 460-467, 2020

8 Szegedy C, "Rethinking the inception architecture for computer vision" 2818-2826, 2016

9 권순무, "PACS에서 JPEG2000을 이용한 AAPM CT Performance Phantom영상의 압축에 따른 화질변화" 한국방사선학회 6 (6): 217-226, 2012

10 Frohlich, ED, "Left ventricular hypertrophy as a risk factor" 4 (4): 137-144, 1986

11 Krizhevsky A, "Imagenet classification with deep convolutional neural networks" 25 : 1097-1105, 2012

12 Huang Y, "Gpipe : Efficient training of giant neural networks using pipeline parallelism" 32 : 103-112, 2019

13 Japkowicz N, "Evaluating learning algorithms: a classification perspective" Cambridge University Press 2011

14 Yap MH, "End-to-end breast ultrasound lesions recognition with a deep learning approach" International Society for Optics and Photonics 10578 : 1057819-, 2018

15 Tan M, "Efficientnet: Rethinking model scaling for convolutional neural networks" PMLR 6105-6144, 2019

16 Huang G, "Densely connected convolutional networks" 4700-4708, 2017

17 He K, "Deep residual learning for image recognition" 770-778, 2016

18 Sahiner B, "Deep learning in medical imaging and radiation therapy" 46 (46): e1-e36, 2019

19 LeCun Y, "Deep learning" 521 (521): 436-444, 2015

20 고성진, "DICOM 영상과 다양한 형식의 영상 비교" 한국융합신호처리학회 18 (18): 76-83, 2017

21 Wang X, "Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases" 2097-2106, 2017

22 Amin H, "Cardiomegaly"

23 Han S, "A deep learning framework for supporting the classification of breast lesions in ultrasound images" 62 (62): 7714-, 2017