Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen

被引:9
作者
Meddeb, Aymen [1 ,2 ,3 ]
Kossen, Tabea [4 ]
Bressem, Keno K. [1 ,2 ,3 ,5 ]
Hamm, Bernd [1 ,2 ,3 ]
Nagel, Sebastian N. [1 ,2 ,3 ]
机构
[1] Charite Univ Med Berlin, Hindenburgdamm 30, D-12203 Berlin, Germany
[2] Free Univ Berlin, Hindenburgdamm 30, D-12203 Berlin, Germany
[3] Humboldt Univ, Radiol Klin, Hindenburgdamm 30, D-12203 Berlin, Germany
[4] Charite Univ Med Berlin, CLAIM Charite Lab Med, Augustenburger Pl 1, D-13353 Berlin, Germany
[5] Charite Univ Med Berlin, Berlin Inst Hlth, Charitepl 1, D-10117 Berlin, Germany
关键词
automated segmentation; deep learning; image processing; diagnostic techniques and procedures; diagnosis; LIVER;
D O I
10.3390/tomography7040078
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house dataset (n = 61) including diseases with and without splenic involvement (in-house U-Net), and an open-source dataset from the Medical Segmentation Decathlon (open dataset, n = 61) without splenic abnormalities (open U-Net). Both datasets were split into a training (n = 32.52%), a validation (n = 9.15%) and a testing dataset (n = 20.33%). The segmentation performances of the two models were measured using four established metrics, including the Dice Similarity Coefficient (DSC). On the open test dataset, the in-house and open U-Net achieved a mean DSC of 0.906 and 0.897 respectively (p = 0.526). On the in-house test dataset, the in-house U-Net achieved a mean DSC of 0.941, whereas the open U-Net obtained a mean DSC of 0.648 (p < 0.001), showing very poor segmentation results in patients with abnormalities in or surrounding the spleen. Thus, for reliable, fully automated spleen segmentation in clinical routine, the training dataset of a deep learning-based algorithm should include conditions that directly or indirectly affect the spleen.
引用
收藏
页码:950 / 960
页数:11
相关论文
共 42 条
[1]   Deep Learning Algorithm for Automated Segmentation and Volume Measurement of the Liver and Spleen Using Portal Venous Phase Computed Tomography Images [J].
Ahn, Yura ;
Yoon, Jee Seok ;
Lee, Seung Soo ;
Suk, Heung-Il ;
Son, Jung Hee ;
Sung, Yu Sub ;
Lee, Yedaun ;
Kang, Bo-Kyeong ;
Kim, Ho Sung .
KOREAN JOURNAL OF RADIOLOGY, 2020, 21 (08) :987-997
[2]   Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation [J].
Bobo, Meg F. ;
Bao, Shunxing ;
Huo, Yuankai ;
Yao, Yuang ;
Virostko, Jack ;
Plassard, Andrew J. ;
Lyu, Ilwoo ;
Assad, Albert ;
Abramson, Richard G. ;
Hilmes, Melissa A. ;
Landman, Bennett A. .
MEDICAL IMAGING 2018: IMAGE PROCESSING, 2018, 10574
[3]   VOLUME DETERMINATIONS USING COMPUTED-TOMOGRAPHY [J].
BREIMAN, RS ;
BECK, JW ;
KOROBKIN, M ;
GLENNY, R ;
AKWARI, OE ;
HEASTON, DK ;
MOORE, AV ;
RAM, PC .
AMERICAN JOURNAL OF ROENTGENOLOGY, 1982, 138 (02) :329-333
[4]   The Spleen in Local and Systemic Regulation of Immunity [J].
Bronte, Vincenzo ;
Pittet, Mikael J. .
IMMUNITY, 2013, 39 (05) :806-818
[5]  
Di Stasi M., 1995, EUR J ULTRASOUND, V2, P117, DOI [10.1016/0929-8266(95)00088-7, DOI 10.1016/0929-8266(95)00088-7]
[6]   U-Net: deep learning for cell counting, detection, and morphometry [J].
Falk, Thorsten ;
Mai, Dominic ;
Bensch, Robert ;
Cicek, Oezguen ;
Abdulkadir, Ahmed ;
Marrakchi, Yassine ;
Boehm, Anton ;
Deubner, Jan ;
Jaeckel, Zoe ;
Seiwald, Katharina ;
Dovzhenko, Alexander ;
Tietz, Olaf ;
Dal Bosco, Cristina ;
Walsh, Sean ;
Saltukoglu, Deniz ;
Tay, Tuan Leng ;
Prinz, Marco ;
Palme, Klaus ;
Simons, Matias ;
Diester, Ilka ;
Brox, Thomas ;
Ronneberger, Olaf .
NATURE METHODS, 2019, 16 (01) :67-+
[7]   3D Slicer as an image computing platform for the Quantitative Imaging Network [J].
Fedorov, Andriy ;
Beichel, Reinhard ;
Kalpathy-Cramer, Jayashree ;
Finet, Julien ;
Fillion-Robin, Jean-Christophe ;
Pujol, Sonia ;
Bauer, Christian ;
Jennings, Dominique ;
Fennessy, Fiona ;
Sonka, Milan ;
Buatti, John ;
Aylward, Stephen ;
Miller, James V. ;
Pieper, Steve ;
Kikinis, Ron .
MAGNETIC RESONANCE IMAGING, 2012, 30 (09) :1323-1341
[8]   Abdominal image segmentation using three-dimensional deformable models [J].
Gao, LM ;
Heath, DG ;
Fishman, EK .
INVESTIGATIVE RADIOLOGY, 1998, 33 (06) :348-355
[9]  
Gauriau R, 2015, I S BIOMED IMAGING, P359, DOI 10.1109/ISBI.2015.7163887
[10]   Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks [J].
Gibson, Eli ;
Giganti, Francesco ;
Hu, Yipeng ;
Bonmati, Ester ;
Bandula, Steve ;
Gurusamy, Kurinchi ;
Davidson, Brian ;
Pereira, Stephen P. ;
Clarkson, Matthew J. ;
Barratt, Dean C. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2018, 37 (08) :1822-1834