Your browser doesn't support javascript.
loading
Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography.
Uhm, Kwang-Hyun; Jung, Seung-Won; Choi, Moon Hyung; Shin, Hong-Kyu; Yoo, Jae-Ik; Oh, Se Won; Kim, Jee Young; Kim, Hyun Gi; Lee, Young Joon; Youn, Seo Yeon; Hong, Sung-Hoo; Ko, Sung-Jea.
Afiliación
  • Uhm KH; Department of Electrical Engineering, Korea University, Seoul, South Korea.
  • Jung SW; Department of Electrical Engineering, Korea University, Seoul, South Korea.
  • Choi MH; Department of Radiology, The Catholic University of Korea, Seoul, South Korea.
  • Shin HK; Department of Electrical Engineering, Korea University, Seoul, South Korea.
  • Yoo JI; Department of Electrical Engineering, Korea University, Seoul, South Korea.
  • Oh SW; Department of Radiology, The Catholic University of Korea, Seoul, South Korea.
  • Kim JY; Department of Radiology, The Catholic University of Korea, Seoul, South Korea.
  • Kim HG; Department of Radiology, The Catholic University of Korea, Seoul, South Korea.
  • Lee YJ; Department of Radiology, The Catholic University of Korea, Seoul, South Korea.
  • Youn SY; Department of Radiology, The Catholic University of Korea, Seoul, South Korea.
  • Hong SH; Department of Urology, The Catholic University of Korea, Seoul, South Korea. toomey@catholic.ac.kr.
  • Ko SJ; Department of Electrical Engineering, Korea University, Seoul, South Korea. sjko@korea.ac.kr.
NPJ Precis Oncol ; 5(1): 54, 2021 Jun 18.
Article en En | MEDLINE | ID: mdl-34145374
In 2020, it is estimated that 73,750 kidney cancer cases were diagnosed, and 14,830 people died from cancer in the United States. Preoperative multi-phase abdominal computed tomography (CT) is often used for detecting lesions and classifying histologic subtypes of renal tumor to avoid unnecessary biopsy or surgery. However, there exists inter-observer variability due to subtle differences in the imaging features of tumor subtypes, which makes decisions on treatment challenging. While deep learning has been recently applied to the automated diagnosis of renal tumor, classification of a wide range of subtype classes has not been sufficiently studied yet. In this paper, we propose an end-to-end deep learning model for the differential diagnosis of five major histologic subtypes of renal tumors including both benign and malignant tumors on multi-phase CT. Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention. We trained and tested the model using CT data from 308 patients who underwent nephrectomy for renal tumors. The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes. We further validated the model on an independent dataset of 184 patients from The Cancer Imaging Archive (TCIA). The AUC for this dataset was 0.855, and the model performed comparably to the radiologists. These results indicate that our model can achieve similar or better diagnostic performance than radiologists in differentiating a wide range of renal tumors on multi-phase CT.
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Diagnostic_studies / Guideline / Prognostic_studies Idioma: En Revista: NPJ Precis Oncol Año: 2021 Tipo del documento: Article País de afiliación: Corea del Sur Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Diagnostic_studies / Guideline / Prognostic_studies Idioma: En Revista: NPJ Precis Oncol Año: 2021 Tipo del documento: Article País de afiliación: Corea del Sur Pais de publicación: Reino Unido