Sökning: onr:"swepub:oai:lup.lub.lu.se:907410b6-33f1-4174-950a-29df64749d30" > Deep Learning-Based...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 06284naa a2200757 4500 | |
001 | oai:lup.lub.lu.se:907410b6-33f1-4174-950a-29df64749d30 | |
003 | SwePub | |
008 | 220223s2022 | |||||||||||000 ||eng| | |
024 | 7 | a https://lup.lub.lu.se/record/907410b6-33f1-4174-950a-29df64749d302 URI |
024 | 7 | a https://doi.org/10.3389/fonc.2022.8215942 DOI |
040 | a (SwePub)lu | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a art2 swepub-publicationtype |
072 | 7 | a ref2 swepub-contenttype |
100 | 1 | a Yu, Wenjinu Northwest University (China)4 aut |
245 | 1 0 | a Deep Learning-Based Classification of Cancer Cell in Leptomeningeal Metastasis on Cytomorphologic Features of Cerebrospinal Fluid |
264 | c 2022-02-22 | |
264 | 1 | b Frontiers Media SA,c 2022 |
520 | a Background: It is a critical challenge to diagnose leptomeningeal metastasis (LM), given its technical difficulty and the lack of typical symptoms. The existing gold standard of diagnosing LM is to use positive cerebrospinal fluid (CSF) cytology, which consumes significantly more time to classify cells under a microscope.Objective: This study aims to establish a deep learning model to classify cancer cells in CSF, thus facilitating doctors to achieve an accurate and fast diagnosis of LM in an early stage.Method: The cerebrospinal fluid laboratory of Xijing Hospital provides 53,255 cells from 90 LM patients in the research. We used two deep convolutional neural networks (CNN) models to classify cells in the CSF. A five-way cell classification model (CNN1) consists of lymphocytes, monocytes, neutrophils, erythrocytes, and cancer cells. A four-way cancer cell classification model (CNN2) consists of lung cancer cells, gastric cancer cells, breast cancer cells, and pancreatic cancer cells. Here, the CNN models were constructed by Resnet-inception-V2. We evaluated the performance of the proposed models on two external datasets and compared them with the results from 42 doctors of various levels of experience in the human-machine tests. Furthermore, we develop a computer-aided diagnosis (CAD) software to generate cytology diagnosis reports in the research rapidly.Results: With respect to the validation set, the mean average precision (mAP) of CNN1 is over 95% and that of CNN2 is close to 80%. Hence, the proposed deep learning model effectively classifies cells in CSF to facilitate the screening of cancer cells. In the human-machine tests, the accuracy of CNN1 is similar to the results from experts, with higher accuracy than doctors in other levels. Moreover, the overall accuracy of CNN2 is 10% higher than that of experts, with a time consumption of only one-third of that consumed by an expert. Using the CAD software saves 90% working time of cytologists.Conclusion: A deep learning method has been developed to assist the LM diagnosis with high accuracy and low time consumption effectively. Thanks to labeled data and step-by-step training, our proposed method can successfully classify cancer cells in the CSF to assist LM diagnosis early. In addition, this unique research can predict cancer’s primary source of LM, which relies on cytomorphologic features without immunohistochemistry. Our results show that deep learning can be widely used in medical images to classify cerebrospinal fluid cells. For complex cancer classification tasks, the accuracy of the proposed method is significantly higher than that of specialist doctors, and its performance is better than that of junior doctors and interns. The application of CNNs and CAD software may ultimately aid in expediting the diagnosis and overcoming the shortage of experienced cytologists, thereby facilitating earlier treatment and improving the prognosis of LM. | |
650 | 7 | a MEDICIN OCH HÄLSOVETENSKAPx Medicinska och farmaceutiska grundvetenskaperx Neurovetenskaper0 (SwePub)301052 hsv//swe |
650 | 7 | a MEDICAL AND HEALTH SCIENCESx Basic Medicinex Neurosciences0 (SwePub)301052 hsv//eng |
650 | 7 | a MEDICIN OCH HÄLSOVETENSKAPx Klinisk medicinx Neurologi0 (SwePub)302072 hsv//swe |
650 | 7 | a MEDICAL AND HEALTH SCIENCESx Clinical Medicinex Neurology0 (SwePub)302072 hsv//eng |
700 | 1 | a Liu, Yangyangu Xi'an Jiaotong University4 aut |
700 | 1 | a Zhao, Yunsongu Fourth Military Medical University4 aut |
700 | 1 | a Huang, Haofanu Shenzhen University4 aut |
700 | 1 | a Liu, Jiahaou Yan'an University4 aut |
700 | 1 | a Yao, Xiaofengu Yan'an University4 aut |
700 | 1 | a Li, Jingwenu Xiamen University4 aut |
700 | 1 | a Xie, Zhenu Northwest University (China)4 aut |
700 | 1 | a Jiang, Luyueu Xi'an Jiaotong University4 aut |
700 | 1 | a Wu, Hepingu Xi'an Jiaotong University4 aut |
700 | 1 | a Cao, Xinhao4 aut |
700 | 1 | a Zhou, Jiamingu Lund University,Lunds universitet,Oftalmologi, Lund,Sektion IV,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Ophthalmology, Lund,Section IV,Department of Clinical Sciences, Lund,Faculty of Medicine4 aut0 (Swepub:lu)ji6872zh |
700 | 1 | a Guo, Yuting4 aut |
700 | 1 | a Li, Gaoyang4 aut |
700 | 1 | a Ren, Matthew Xinhu4 aut |
700 | 1 | a Yi, Quan4 aut |
700 | 1 | a Mu, Tingmin4 aut |
700 | 1 | a Izquierdo11, Guillermo Ayuso4 aut |
700 | 1 | a Zhang, Guoxun4 aut |
700 | 1 | a Zhao, Runze4 aut |
700 | 1 | a Zhao, Di4 aut |
700 | 1 | a Yan, Jiangyun4 aut |
700 | 1 | a Zhang, Haijun4 aut |
700 | 1 | a Lv, Junchao4 aut |
700 | 1 | a Yao, Qian4 aut |
700 | 1 | a Duan, Yan4 aut |
700 | 1 | a Zhou, Huimin4 aut |
700 | 1 | a Liu, Tingting4 aut |
700 | 1 | a He, Ying4 aut |
700 | 1 | a Bian, Ting4 aut |
700 | 1 | a Dai, Wen4 aut |
700 | 1 | a Huai, Jiahui4 aut |
700 | 1 | a He, Qian4 aut |
700 | 1 | a Gao, Yi4 aut |
700 | 1 | a Ren, Wei4 aut |
700 | 1 | a Niu, Gang4 aut |
700 | 1 | a Zhao, Gang4 aut |
710 | 2 | a Northwest University (China)b Xi'an Jiaotong University4 org |
773 | 0 | t Frontiers in Oncologyd : Frontiers Media SAg 12, s. 1-11q 12<1-11x 2234-943X |
856 | 4 | u http://dx.doi.org/10.3389/fonc.2022.821594x freey FULLTEXT |
856 | 4 | u https://www.frontiersin.org/articles/10.3389/fonc.2022.821594/pdf |
856 | 4 8 | u https://lup.lub.lu.se/record/907410b6-33f1-4174-950a-29df64749d30 |
856 | 4 8 | u https://doi.org/10.3389/fonc.2022.821594 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
Kopiera och spara länken för att återkomma till aktuell vy