Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography

Abstract 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 unnec...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kwang-Hyun Uhm, Seung-Won Jung, Moon Hyung Choi, Hong-Kyu Shin, Jae-Ik Yoo, Se Won Oh, Jee Young Kim, Hyun Gi Kim, Young Joon Lee, Seo Yeon Youn, Sung-Hoo Hong, Sung-Jea Ko
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/b233852307e7463aa595188f0f21eff1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b233852307e7463aa595188f0f21eff1
record_format	dspace
spelling	oai:doaj.org-article:b233852307e7463aa595188f0f21eff12021-12-02T17:40:41ZDeep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography10.1038/s41698-021-00195-y2397-768Xhttps://doaj.org/article/b233852307e7463aa595188f0f21eff12021-06-01T00:00:00Zhttps://doi.org/10.1038/s41698-021-00195-yhttps://doaj.org/toc/2397-768XAbstract 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.Kwang-Hyun UhmSeung-Won JungMoon Hyung ChoiHong-Kyu ShinJae-Ik YooSe Won OhJee Young KimHyun Gi KimYoung Joon LeeSeo Yeon YounSung-Hoo HongSung-Jea KoNature PortfolioarticleNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENnpj Precision Oncology, Vol 5, Iss 1, Pp 1-6 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Kwang-Hyun Uhm Seung-Won Jung Moon Hyung Choi Hong-Kyu Shin Jae-Ik Yoo Se Won Oh Jee Young Kim Hyun Gi Kim Young Joon Lee Seo Yeon Youn Sung-Hoo Hong Sung-Jea Ko Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
description	Abstract 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.
format	article
author	Kwang-Hyun Uhm Seung-Won Jung Moon Hyung Choi Hong-Kyu Shin Jae-Ik Yoo Se Won Oh Jee Young Kim Hyun Gi Kim Young Joon Lee Seo Yeon Youn Sung-Hoo Hong Sung-Jea Ko
author_facet	Kwang-Hyun Uhm Seung-Won Jung Moon Hyung Choi Hong-Kyu Shin Jae-Ik Yoo Se Won Oh Jee Young Kim Hyun Gi Kim Young Joon Lee Seo Yeon Youn Sung-Hoo Hong Sung-Jea Ko
author_sort	Kwang-Hyun Uhm
title	Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
title_short	Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
title_full	Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
title_fullStr	Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
title_full_unstemmed	Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
title_sort	deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b233852307e7463aa595188f0f21eff1
work_keys_str_mv	AT kwanghyunuhm deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT seungwonjung deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT moonhyungchoi deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT hongkyushin deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT jaeikyoo deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT sewonoh deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT jeeyoungkim deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT hyungikim deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT youngjoonlee deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT seoyeonyoun deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT sunghoohong deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography AT sungjeako deeplearningforendtoendkidneycancerdiagnosisonmultiphaseabdominalcomputedtomography
_version_	1718379783940734976

Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography

Ejemplares similares