Deep neural networks show a superior performance to all 42 dermatologists in onychomycosis diagnosis
2018.01.08 17:13
Deep neural networks show a superior performance to all 42 dermatologists in onychomycosis diagnosis
We created datasets of standardized nail images using a region-based convolutional neural network (R-CNN) trained to distinguish a nail from a background. We used R-CNN to generate training datasets of 49,567 images, which were then used to fine-tune the ResNet-152 and VGG-19 models.
The validation datasets comprised 100 and 194 images from Inje University (B1 and B2 datasets, respectively), 125 images from Hallym University (C dataset), and 939 images from Seoul National University (D dataset).
The results from the AI ensemble model (ResNet-152 + VGG-19 + feedforward neural networks) showed the test sensitivity/specificity/ area under the curve values of (96.0 / 94.7 / 0.98), (82.7 / 96.7 / 0.95), (92.3 / 79.3 / 0.93), (87.7 / 69.3 / 0.82) for the B1, B2, C, and D datasets, respectively.
With the combination of the B1 and C datasets, the AI Youden index was significantly higher than that of 42 dermatologists who performed the same assessment manually (p = 0.01). For the combinations of B1+C and B2+D dataset, almost none of the dermatologists performed as well as the AI.
The deep learning model trained with the dataset comprising 49,567 images, achieved a diagnostic accuracy for the classification of onychomycosis, which was superior to that of most of the dermatologists who participated in this study.
댓글 0
번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
---|---|---|---|---|
304 | nvidia dali [1] | WHRIA | 2020.08.01 | 334 |
303 | % 빼고 center crop | WHRIA | 2016.10.22 | 330 |
302 | 민원24 프린터제한을 우회하거나 PDF 로 저장하는 방법 | WHRIA | 2015.07.12 | 323 |
301 | good luck ! | WHRIA | 2019.03.21 | 316 |
300 | asyncio | WHRIA | 2020.07.23 | 309 |
299 | 계속 실행시키기 nohup & | WHRIA | 2017.05.29 | 283 |
298 | mariaDB cache 설정 | WHRIA | 2019.08.04 | 283 |
297 | ambient-light-sensor | WHRIA | 2018.09.29 | 280 |
296 | naver rexnet clova AI [1] | WHRIA | 2020.07.04 | 274 |
295 | GPT2 [1] | WHRIA | 2020.08.03 | 263 |
294 | R graph | WHRIA | 2019.12.29 | 244 |
293 | FTC [1] | WHRIA | 2020.07.28 | 243 |
292 | 32 bit UEFI [6] | WHRIA | 2020.12.24 | 237 |
291 | 시거잭 퓨즈 교체 [2] | WHRIA | 2016.01.14 | 229 |
290 | pytorch object detect / retinanet | WHRIA | 2019.12.22 | 226 |