Fully end-to-end deep-learning-based diagnosis of pancreatic tumors
| Autor: | Ying Xue, Tingbo Liang, Xiazhen Yu, Ke Si, Qinghai Li, Xinpei Zhu, Wei Gong, Shumin Duan |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Adult
Male medicine.medical_specialty tumor Medicine (miscellaneous) computed tomography (CT) artificial intelligence (AI) 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Pancreatic tumor medicine Image Processing Computer-Assisted Preprocessor Humans Segmentation Medical diagnosis Pharmacology Toxicology and Pharmaceutics (miscellaneous) Aged Aged 80 and over convolutional neural network (CNN) Intraductal papillary mucinous neoplasm business.industry deep learning Middle Aged medicine.disease Pancreatic Neoplasms medicine.anatomical_structure ROC Curve 030220 oncology & carcinogenesis Abdomen Female Radiology Pancreas F1 score business Tomography X-Ray Computed Algorithms Carcinoma Pancreatic Ductal Research Paper |
| Zdroj: | Theranostics |
| ISSN: | 1838-7640 |
| Popis: | Artificial intelligence can facilitate clinical decision making by considering massive amounts of medical imaging data. Various algorithms have been implemented for different clinical applications. Accurate diagnosis and treatment require reliable and interpretable data. For pancreatic tumor diagnosis, only 58.5% of images from the First Affiliated Hospital and the Second Affiliated Hospital, Zhejiang University School of Medicine are used, increasing labor and time costs to manually filter out images not directly used by the diagnostic model. Methods: This study used a training dataset of 143,945 dynamic contrast-enhanced CT images of the abdomen from 319 patients. The proposed model contained four stages: image screening, pancreas location, pancreas segmentation, and pancreatic tumor diagnosis. Results: We established a fully end-to-end deep-learning model for diagnosing pancreatic tumors and proposing treatment. The model considers original abdominal CT images without any manual preprocessing. Our artificial-intelligence-based system achieved an area under the curve of 0.871 and a F1 score of 88.5% using an independent testing dataset containing 107,036 clinical CT images from 347 patients. The average accuracy for all tumor types was 82.7%, and the independent accuracies of identifying intraductal papillary mucinous neoplasm and pancreatic ductal adenocarcinoma were 100% and 87.6%, respectively. The average test time per patient was 18.6 s, compared with at least 8 min for manual reviewing. Furthermore, the model provided a transparent and interpretable diagnosis by producing saliency maps highlighting the regions relevant to its decision. Conclusions: The proposed model can potentially deliver efficient and accurate preoperative diagnoses that could aid the surgical management of pancreatic tumor. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|