Advanced Segmentation Techniques for Lung Nodules, Liver Metastases, and Enlarged Lymph Nodes in CT Scans

被引：123

作者：

Moltz, Jan Hendrik ^{[1
]}

Bornemann, Lars ^{[1
]}

Kuhnigk, Jan-Martin ^{[1
]}

Dicken, Volker ^{[1
]}

Peitgen, Elena ^{[2
]}

Meier, Stephan ^{[3
]}

Bolte, Hendrik ^{[4
]}

Fabel, Michael ^{[4
]}

Bauknecht, Hans-Christian ^{[5
]}

Hittinger, Markus ^{[6
]}

Kiessling, Andreas ^{[7
]}

Puesken, Michael ^{[8
]}

Peitgen, Heinz-Otto ^{[1
]}

机构：

[1] Fraunhofer MEVIS, Inst Med Image Comp, D-28359 Bremen, Germany

[2] Hosp Bremen E, Dept Radiol, D-28325 Bremen, Germany

[3] Univ Hosp Mainz, Dept Diagnost & Intervent Radiol, D-55131 Mainz, Germany

[4] Univ Hosp Schleswig Holstein, Dept Diagnost Radiol, D-24105 Kiel, Germany

[5] Charite, Inst Radiol, D-10117 Berlin, Germany

[6] Univ Hosp Munich, Inst Clin Radiol, D-81377 Munich, Germany

[7] Univ Hosp Giessen & Marburg, Dept Diagnost Radiol, D-35043 Marburg, Germany

[8] Univ Hosp Munster, Inst Clin Radiol, D-48149 Munster, Germany

来源：

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING | 2009年 / 3卷 / 01期

关键词：

Biomedical image processing; computed tomography; image segmentation; liver; respiratory system; tumors; PULMONARY NODULES; AUTOMATIC SEGMENTATION; VOLUMETRY; ALGORITHM; ACCURACY; LESIONS; CAD;

D O I：

10.1109/JSTSP.2008.2011107

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This article presents advanced algorithms for segmenting lung nodules, liver metastases, and enlarged lymph nodes in CT scans. Segmentation and volumetry are essential tasks of a software assistant for oncological therapy monitoring. Our methods are based on a hybrid algorithm originally developed for lung nodules that combines a threshold-based approach with model-based morphological processing. We propose extensions that deal with particular challenges of each lesion type: lung nodules that are attached to non-convex parts of the pleura, rim-enhancing and peripheral liver metastases and lymph nodes with an extensive contact to structures of similar density. We evaluated our methods on several hundred lesions in clinical datasets and the quality of segmentations was rated by radiologists. The results were classified as acceptable or better in 81% to 92% of the cases for the different algorithms and readers.

引用

页码：122 / 134

页数：13

共 31 条

[1]

[Anonymous], P MICCAI WORKSH 3 D

[2] OncoTREAT: a software assistant for cancer therapy monitoring [J].

Bornemann, Lars ;

Dicken, Volker ;

Kuhnigk, Jan-Martin ;

Wormanns, Dag ;

Shin, Hoen-Oh ;

Bauknecht, Hans-Christian ;

Diehl, Volker ;

Fabel, Michael ;

Meier, Stefan ;

Kress, Oliver ;

Krass, Stefan ;

Peitgen, Heinz-Otto .

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2007, 1 (05) :231-242

[3]

Ciecholewski M, 2007, LECT NOTES COMPUT SC, V4528, P63

[4] Segmentation of pulmonary nodules in thoracic CT scans: A region growing approach [J].

Dehmeshi, Jamshid ;

Amin, Hamdan ;

Valdivieso, Manlio ;

Ye, Xujiong .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2008, 27 (04) :467-480

[5]

DENG X, 2008, P MICCAI WORKSH 3 D

[6]

DORNHEIM J, 2006, P MICCAI, P904

[7] Semi-automated volumetric analysis of lymph node metastases in patients with malignant melanoma stage III/IV-A feasibility study [J].

Fabel, M. ;

von Tengg-Kobligk, H. ;

Giesel, F. L. ;

Bornemann, L. ;

Dicken, V. ;

Kopp-Schneider, A. ;

Moser, C. ;

Delorme, S. ;

Kauczor, H. -U. .

EUROPEAN RADIOLOGY, 2008, 18 (06) :1114-1122

[8] Automatic segmentation of pulmonary nodules by using dynamic 3D cross-correlation for interactive CAD systems [J].

Fan, L ;

Qian, JZ ;

Odry, B ;

Shen, H ;

Naidich, D ;

Kohl, G ;

Klotz, E .

MEDICAL IMAGING 2002: IMAGE PROCESSING, VOL 1-3, 2002, 4684 :1362-1369

[9]

Fetita CI, 2003, LECT NOTES COMPUT SC, V2878, P626

[10] Head detection and tracking by 2-D and 3-D ellipsoid fitting. [J].

Grammalidis, N ;

Strintzis, MG .

COMPUTER GRAPHICS INTERNATIONAL 2000, PROCEEDINGS, 2000, :221-226

← 1 2 3 4 →