-
Je něco špatně v tomto záznamu ?
Large-scale pancreatic cancer detection via non-contrast CT and deep learning
K. Cao, Y. Xia, J. Yao, X. Han, L. Lambert, T. Zhang, W. Tang, G. Jin, H. Jiang, X. Fang, I. Nogues, X. Li, W. Guo, Y. Wang, W. Fang, M. Qiu, Y. Hou, T. Kovarnik, M. Vocka, Y. Lu, Y. Chen, X. Chen, Z. Liu, J. Zhou, C. Xie, R. Zhang, H. Lu, GD....
Jazyk angličtina Země Spojené státy americké
Typ dokumentu multicentrická studie, časopisecké články
Grantová podpora
82372045
National Natural Science Foundation of China (National Science Foundation of China)
NLK
ProQuest Central
od 2000-01-01 do Před 1 rokem
Health & Medicine (ProQuest)
od 2000-01-01 do Před 1 rokem
- MeSH
- deep learning * MeSH
- duktální karcinom slinivky břišní * diagnostické zobrazování patologie MeSH
- lidé MeSH
- nádory slinivky břišní * diagnostické zobrazování patologie MeSH
- pankreas diagnostické zobrazování patologie MeSH
- počítačová rentgenová tomografie MeSH
- retrospektivní studie MeSH
- umělá inteligence MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- multicentrická studie MeSH
Pancreatic ductal adenocarcinoma (PDAC), the most deadly solid malignancy, is typically detected late and at an inoperable stage. Early or incidental detection is associated with prolonged survival, but screening asymptomatic individuals for PDAC using a single test remains unfeasible due to the low prevalence and potential harms of false positives. Non-contrast computed tomography (CT), routinely performed for clinical indications, offers the potential for large-scale screening, however, identification of PDAC using non-contrast CT has long been considered impossible. Here, we develop a deep learning approach, pancreatic cancer detection with artificial intelligence (PANDA), that can detect and classify pancreatic lesions with high accuracy via non-contrast CT. PANDA is trained on a dataset of 3,208 patients from a single center. PANDA achieves an area under the receiver operating characteristic curve (AUC) of 0.986-0.996 for lesion detection in a multicenter validation involving 6,239 patients across 10 centers, outperforms the mean radiologist performance by 34.1% in sensitivity and 6.3% in specificity for PDAC identification, and achieves a sensitivity of 92.9% and specificity of 99.9% for lesion detection in a real-world multi-scenario validation consisting of 20,530 consecutive patients. Notably, PANDA utilized with non-contrast CT shows non-inferiority to radiology reports (using contrast-enhanced CT) in the differentiation of common pancreatic lesion subtypes. PANDA could potentially serve as a new tool for large-scale pancreatic cancer screening.
Damo Academy Alibaba Group Hangzhou China
DAMO Academy Alibaba Group New York NY USA
Department of Biostatistics Harvard University T H Chan School of Public Health Cambridge MA USA
Department of Computer Science Johns Hopkins University Baltimore MD USA
Department of Pathology Shanghai Institution of Pancreatic Disease Shanghai China
Department of Radiology Fudan University Shanghai Cancer Center Shanghai China
Department of Radiology Guangdong Provincial People's Hospital Guangzhou China
Department of Radiology Shanghai Institution of Pancreatic Disease Shanghai China
Department of Radiology Shengjing Hospital of China Medical University Shenyang China
Department of Radiology Sun Yat Sen University Cancer Center Guangzhou China
Department of Radiology Tianjin Medical University Cancer Institute and Hospital Tianjin China
Department of Surgery Shanghai Institution of Pancreatic Disease Shanghai China
Citace poskytuje Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc24000348
- 003
- CZ-PrNML
- 005
- 20240213093125.0
- 007
- ta
- 008
- 240109s2023 xxu f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1038/s41591-023-02640-w $2 doi
- 035 __
- $a (PubMed)37985692
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a xxu
- 100 1_
- $a Cao, Kai $u Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China
- 245 10
- $a Large-scale pancreatic cancer detection via non-contrast CT and deep learning / $c K. Cao, Y. Xia, J. Yao, X. Han, L. Lambert, T. Zhang, W. Tang, G. Jin, H. Jiang, X. Fang, I. Nogues, X. Li, W. Guo, Y. Wang, W. Fang, M. Qiu, Y. Hou, T. Kovarnik, M. Vocka, Y. Lu, Y. Chen, X. Chen, Z. Liu, J. Zhou, C. Xie, R. Zhang, H. Lu, GD. Hager, AL. Yuille, L. Lu, C. Shao, Y. Shi, Q. Zhang, T. Liang, L. Zhang, J. Lu
- 520 9_
- $a Pancreatic ductal adenocarcinoma (PDAC), the most deadly solid malignancy, is typically detected late and at an inoperable stage. Early or incidental detection is associated with prolonged survival, but screening asymptomatic individuals for PDAC using a single test remains unfeasible due to the low prevalence and potential harms of false positives. Non-contrast computed tomography (CT), routinely performed for clinical indications, offers the potential for large-scale screening, however, identification of PDAC using non-contrast CT has long been considered impossible. Here, we develop a deep learning approach, pancreatic cancer detection with artificial intelligence (PANDA), that can detect and classify pancreatic lesions with high accuracy via non-contrast CT. PANDA is trained on a dataset of 3,208 patients from a single center. PANDA achieves an area under the receiver operating characteristic curve (AUC) of 0.986-0.996 for lesion detection in a multicenter validation involving 6,239 patients across 10 centers, outperforms the mean radiologist performance by 34.1% in sensitivity and 6.3% in specificity for PDAC identification, and achieves a sensitivity of 92.9% and specificity of 99.9% for lesion detection in a real-world multi-scenario validation consisting of 20,530 consecutive patients. Notably, PANDA utilized with non-contrast CT shows non-inferiority to radiology reports (using contrast-enhanced CT) in the differentiation of common pancreatic lesion subtypes. PANDA could potentially serve as a new tool for large-scale pancreatic cancer screening.
- 650 _2
- $a lidé $7 D006801
- 650 _2
- $a umělá inteligence $7 D001185
- 650 12
- $a deep learning $7 D000077321
- 650 12
- $a nádory slinivky břišní $x diagnostické zobrazování $x patologie $7 D010190
- 650 _2
- $a počítačová rentgenová tomografie $7 D014057
- 650 _2
- $a pankreas $x diagnostické zobrazování $x patologie $7 D010179
- 650 12
- $a duktální karcinom slinivky břišní $x diagnostické zobrazování $x patologie $7 D021441
- 650 _2
- $a retrospektivní studie $7 D012189
- 655 _2
- $a multicentrická studie $7 D016448
- 655 _2
- $a časopisecké články $7 D016428
- 700 1_
- $a Xia, Yingda $u DAMO Academy, Alibaba Group, New York, NY, USA $1 https://orcid.org/0000000274784392
- 700 1_
- $a Yao, Jiawen $u Hupan Laboratory, Hangzhou, China $u Damo Academy, Alibaba Group, Hangzhou, China $1 https://orcid.org/0000000174292964
- 700 1_
- $a Han, Xu $u Department of Hepatobiliary and Pancreatic Surgery, First Affiliated Hospital of Zhejiang University, Hangzhou, China
- 700 1_
- $a Lambert, Lukas $u Department of Radiology, First Faculty of Medicine, Charles University and General University Hospital in Prague, Prague, Czech Republic
- 700 1_
- $a Zhang, Tingting $u Department of Radiology, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- 700 1_
- $a Tang, Wei $u Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China
- 700 1_
- $a Jin, Gang $u Department of Surgery, Shanghai Institution of Pancreatic Disease, Shanghai, China
- 700 1_
- $a Jiang, Hui $u Department of Pathology, Shanghai Institution of Pancreatic Disease, Shanghai, China
- 700 1_
- $a Fang, Xu $u Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China
- 700 1_
- $a Nogues, Isabella $u Department of Biostatistics, Harvard University T.H. Chan School of Public Health, Cambridge, MA, USA
- 700 1_
- $a Li, Xuezhou $u Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China
- 700 1_
- $a Guo, Wenchao $u Hupan Laboratory, Hangzhou, China $u Damo Academy, Alibaba Group, Hangzhou, China $1 https://orcid.org/0000000204451859
- 700 1_
- $a Wang, Yu $u Hupan Laboratory, Hangzhou, China $u Damo Academy, Alibaba Group, Hangzhou, China
- 700 1_
- $a Fang, Wei $u Hupan Laboratory, Hangzhou, China $u Damo Academy, Alibaba Group, Hangzhou, China
- 700 1_
- $a Qiu, Mingyan $u Hupan Laboratory, Hangzhou, China $u Damo Academy, Alibaba Group, Hangzhou, China
- 700 1_
- $a Hou, Yang $u Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China
- 700 1_
- $a Kovarnik, Tomas $u Department of Invasive Cardiology, First Faculty of Medicine, Charles University and General University Hospital in Prague, Prague, Czech Republic
- 700 1_
- $a Vocka, Michal $u Department of Oncology, First Faculty of Medicine, Charles University and General University Hospital in Prague, Prague, Czech Republic $1 https://orcid.org/000000029386657X $7 xx0181880
- 700 1_
- $a Lu, Yimei $u Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China
- 700 1_
- $a Chen, Yingli $u Department of Surgery, Shanghai Institution of Pancreatic Disease, Shanghai, China
- 700 1_
- $a Chen, Xin $u Department of Radiology, Guangdong Provincial People's Hospital, Guangzhou, China
- 700 1_
- $a Liu, Zaiyi $u Department of Radiology, Guangdong Provincial People's Hospital, Guangzhou, China
- 700 1_
- $a Zhou, Jian $u Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, China $1 https://orcid.org/0000000268689866
- 700 1_
- $a Xie, Chuanmiao $u Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, China
- 700 1_
- $a Zhang, Rong $u Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, China
- 700 1_
- $a Lu, Hong $u Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China
- 700 1_
- $a Hager, Gregory D $u Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA $1 https://orcid.org/0000000266629763
- 700 1_
- $a Yuille, Alan L $u Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
- 700 1_
- $a Lu, Le $u DAMO Academy, Alibaba Group, New York, NY, USA $1 https://orcid.org/0000000267999416
- 700 1_
- $a Shao, Chengwei $u Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China. cwshao@sina.com $1 https://orcid.org/0000000293041252
- 700 1_
- $a Shi, Yu $u Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China. 18940259980@163.com $1 https://orcid.org/0000000319400074
- 700 1_
- $a Zhang, Qi $u Department of Hepatobiliary and Pancreatic Surgery, First Affiliated Hospital of Zhejiang University, Hangzhou, China. qi.zhang@zju.edu.cn $1 https://orcid.org/0000000260960690
- 700 1_
- $a Liang, Tingbo $u Department of Hepatobiliary and Pancreatic Surgery, First Affiliated Hospital of Zhejiang University, Hangzhou, China. liangtingbo@zju.edu.cn $1 https://orcid.org/0000000301433353
- 700 1_
- $a Zhang, Ling $u DAMO Academy, Alibaba Group, New York, NY, USA. ling.z@alibaba-inc.com $1 https://orcid.org/0000000183715252
- 700 1_
- $a Lu, Jianping $u Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China. cjr.lujianping@vip.163.com $1 https://orcid.org/0000000203807470
- 773 0_
- $w MED00003459 $t Nature medicine $x 1546-170X $g Roč. 29, č. 12 (2023), s. 3033-3043
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/37985692 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y - $z 0
- 990 __
- $a 20240109 $b ABA008
- 991 __
- $a 20240213093122 $b ABA008
- 999 __
- $a ok $b bmc $g 2049173 $s 1210042
- BAS __
- $a 3
- BAS __
- $a PreBMC-MEDLINE
- BMC __
- $a 2023 $b 29 $c 12 $d 3033-3043 $e 20231120 $i 1546-170X $m Nature medicine $n Nat Med $x MED00003459
- GRA __
- $a 82372045 $p National Natural Science Foundation of China (National Science Foundation of China)
- LZP __
- $a Pubmed-20240109
