https://www.ncbi.nlm.nih.gov/pubmed/30069585
Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability.
Author information
- 1
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA. shahein@stajmir.com.
- 2
- Harvard Medical School, Boston, MA, USA. shahein@stajmir.com.
- 3
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
- 4
- Harvard John A. Paulson School of Engineering and Applied Sciences, Cambridge, MA, USA.
- 5
- Harvard Medical School, Boston, MA, USA.
- 6
- The Billings Clinic, Billings, MT, USA.
- 7
- Children's Hospital of Philadelphia, Philadelphia, PA, USA.
Abstract
OBJECTIVE:
Radiographic bone age assessment (BAA) is used in the evaluation of pediatric endocrine and metabolic disorders. We previously developed an automated artificial intelligence (AI) deep learning algorithm to perform BAA using convolutional neural networks. We compared the BAA performance of a cohort of pediatric radiologists with and without AI assistance.
MATERIALS AND METHODS:
Six board-certified, subspecialty trained pediatric radiologists interpreted 280 age- and gender-matched bone age radiographs ranging from 5 to 18 years. Three of those radiologists then performed BAA with AI assistance. Bone age accuracy and root mean squared error (RMSE) were used as measures of accuracy. Intraclass correlation coefficient evaluated inter-rater variation.
RESULTS:
AI BAA accuracy was 68.2% overall and 98.6% within 1 year, and the mean six-reader cohort accuracy was 63.6 and 97.4% within 1 year. AI RMSE was 0.601 years, while mean single-reader RMSE was 0.661 years. Pooled RMSE decreased from 0.661 to 0.508 years, all individually decreasing with AI assistance. ICC without AI was 0.9914 and with AI was 0.9951.
CONCLUSIONS:
AI improves radiologist's bone age assessment by increasing accuracy and decreasing variability and RMSE. The utilization of AI by radiologists improves performance compared to AI alone, a radiologist alone, or a pooled cohort of experts. This suggests that AI may optimally be utilized as an adjunct to radiologist interpretation of imaging studies to improve performance.
KEYWORDS:
Augmented intelligence; Bone age; Machine learning; Pediatric; Radiographs
- PMID:
- 30069585
- DOI:
- 10.1007/s00256-018-3033-2
미국 보스턴, 하버드 메사추세츠 병원
AI 이용하면 골연령 판별에 도움이 된다.
6명의 영상의학과 소아파트 전문의
280장을 해석.
AI 보조시 정확성 root mean squared error (RMSE) : 0.601
한명의 사람 판독시 root mean squared error (RMSE) : 0.661
Method : "The classification CNN is based on an ImageNet pre-trained GoogLeNet fine-tuned on our train dataset by applying data augmentation with geometric (rotation, resizing, and shearing) and photometric (contrast and brightness) transformations to avoid overfitting."
PACS 에 embeded 되어 사용가능.
(국내에는 VUNO. 식약청 허가 + . )
논문은, AI 보조시 더 정확하다고 표현하지만 (의사를 배제 또는 대체 하지 않는다는 표현),
AI 단독만으로도 거의 영상전문의 수준만큼 판독해 내는 것 아닌가 싶다...
2018 Skeletal Rad - Artificial intelligence-assisted interpretation of bone age radiographs.pdf
