Clinical Implementation of DeepVoxNet for Auto-Delineation of Organs at Risk in Head and Neck Cancer Patients in Radiotherapy

被引：16

作者：

Willems, Siri ^{[1
]}

Crijns, Wouter ^{[3
]}

Saint-Esteven, Agustina La Greca ^{[1
]}

Van der Veen, Julie ^{[2
]}

Robben, David ^{[1
]}

Depuydt, Tom ^{[2
,3
]}

Nuyts, Sandra ^{[2
,3
]}

Haustermans, Karin ^{[2
,3
]}

Maes, Frederik ^{[1
]}

机构：

[1] Katholieke Univ Leuven, Med Image Comp ESAT PSI, Leuven, Belgium

[2] KU Leuven Univ Leuven, Dept Oncol, Lab Expt Radiotherapy, Herestr 49, B-3000 Leuven, Belgium

[3] Univ Hosp Leuven, Dept Radiat Oncol, Herestr 49, B-3000 Leuven, Belgium

来源：

OR 2.0 CONTEXT-AWARE OPERATING THEATERS, COMPUTER ASSISTED ROBOTIC ENDOSCOPY, CLINICAL IMAGE-BASED PROCEDURES, AND SKIN IMAGE ANALYSIS, OR 2.0 2018 | 2018年 / 11041卷

关键词：

Auto-delineation; Deep convolutional neural network; Deep learning; Organs at risk; Radiotherapy; SEGMENTATION; CT;

D O I：

10.1007/978-3-030-01201-4_24

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Delineation of organs at risk (OAR) on CT images is a crucial step in the planning of radiotherapy treatment. Manual delineation is time-consuming and high interrater variability is observed within and across radiotherapy centers. Automated delineation of OAR is fast and can lead to more consistent treatment plans. We developed an auto-delineation tool based on a 3D convolutional neural network (CNN) to automatically delineate 16 OAR structures in head and neck cancer (HNC) patients. The CNN was trained off-line using 70 previously collected patient datasets and implemented to be available on-line in clinical routine practice. The tool was applied prospectively for delineation of 20 consecutive new HNC cases within the department of Radiation Oncology, with subsequent manual editing and approval of the contours by the clinical expert. Validation based on the automatically proposed and edited contours shows that the auto-delineation tool is able to achieve highly accurate segmentation results for most OAR. As a result, 3D delineation time is reduced to less than 19 min on average (about 1min/structure), compared to usually 1 h or more without auto-delineation tool.

引用

页码：223 / 232

页数：10

共 20 条

[1] How many new cancer patients in Europe will require radiotherapy by 2025? An ESTRO-HERO analysis [J].

Borras, Josep M. ;

Lievens, Yolande ;

Barton, Michael ;

Corral, Julieta ;

Ferlay, Jacques ;

Bray, Freddie ;

Grau, Cai .

RADIOTHERAPY AND ONCOLOGY, 2016, 119 (01) :5-11

[2]

Brouwer C.L., 2012, RADIAT ONCOL, P7

[3] Deep Learning Algorithm for Auto-Delineation of High-Risk Oropharyngeal Clinical Target Volumes With Built-In Dice Similarity Coefficient Parameter Optimization Function [J].

Cardenas, Carlos E. ;

McCarroll, Rachel E. ;

Court, Laurence E. ;

Elgohari, Baher A. ;

Elhalawani, Hesham ;

Fuller, Clifton D. ;

Kamal, Mona J. ;

Meheissen, Mohamed A. M. ;

Mohamed, Abdallah S. R. ;

Rao, Arvind ;

Williams, Bowman ;

Wong, Andrew ;

Yang, Jinzhong ;

Aristophanous, Michalis .

INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2018, 101 (02) :468-478

[4] Tissue segmentation of head and neck CT images for treatment planning: A multiatlas approach combined with intensity modeling [J].

Fortunati, Valerio ;

Verhaart, Rene F. ;

van der Lijn, Fedde ;

Niessen, Wiro J. ;

Veenland, Jifke F. ;

Paulides, Margarethus M. .

MEDICAL PHYSICS, 2013, 40 (07)

[5]

Girshick R., 2014, P IEEE C COMP VIS PA, DOI [10.1109/CVPR.2014.81, DOI 10.1109/CVPR.2014.81, 10.1109/cvpr.2014.81]

[6] Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks [J].

Ibragimov, Bulat ;

Xing, Lei .

MEDICAL PHYSICS, 2017, 44 (02) :547-557

[7] Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation [J].

Kamnitsas, Konstantinos ;

Ledig, Christian ;

Newcombe, Virginia F. J. ;

Sirnpson, Joanna P. ;

Kane, Andrew D. ;

Menon, David K. ;

Rueckert, Daniel ;

Glocker, Ben .

MEDICAL IMAGE ANALYSIS, 2017, 36 :61-78

[8] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[9] Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck, prostate and pleural cancer [J].

La Macchia, Mariangela ;

Fellin, Francesco ;

Amichetti, Maurizio ;

Cianchetti, Marco ;

Gianolini, Stefano ;

Paola, Vitali ;

Lomax, Antony J. ;

Widesott, Lamberto .

RADIATION ONCOLOGY, 2012, 7

[10] A survey on deep learning in medical image analysis [J].

Litjens, Geert ;

Kooi, Thijs ;

Bejnordi, Babak Ehteshami ;

Setio, Arnaud Arindra Adiyoso ;

Ciompi, Francesco ;

Ghafoorian, Mohsen ;

van der Laak, Jeroen A. W. M. ;

van Ginneken, Bram ;

Sanchez, Clara I. .

MEDICAL IMAGE ANALYSIS, 2017, 42 :60-88

← 1 2 →