Deep learning for autosegmentation for radiotherapy treatment planning: State-of-the-art and novel perspectives

被引：16

作者：

Erdur, Ayhan Can ^{[1
,2
]}

Rusche, Daniel ^{[2
]}

Scholz, Daniel ^{[1
,3
]}

Kiechle, Johannes ^{[2
,4
,5
,6
]}

Fischer, Stefan ^{[2
,4
,5
]}

Llorian-Salvador, Oscar ^{[2
,7
,8
]}

Buchner, Josef A. ^{[2
]}

Nguyen, Mai Q. ^{[2
]}

Etzel, Lucas ^{[2
,9
]}

Weidner, Jonas ^{[1
,3
]}

Metz, Marie-Christin ^{[3
]}

Wiestler, Benedikt ^{[3
]}

Schnabel, Julia ^{[4
,5
,6
,11
,12
]}

Rueckert, Daniel ^{[1
,13
]}

Combs, Stephanie E. ^{[2
,9
,10
]}

Peeken, Jan C. ^{[2
,9
,10
]}

机构：

[1] Tech Univ Munich, Inst Artificial Intelligence & Informat Med, Klinikum Rechts Isar, Ismaninger Str, D-81675 Munich, Bavaria, Germany

[2] Tech Univ Munich, TUM Sch Med & Hlth, Dept Radiat Oncol, Klinikum rechts Isar, Ismaninger Str, D-81675 Munich, Bavaria, Germany

[3] Tech Univ Munich, TUM Sch Med & Hlth, Dept Neuroradiol, Klinikum rechts Isar, Ismaninger Str, D-81675 Munich, Bavaria, Germany

[4] Tech Univ Munich, Inst Computat Imaging & Med, Lichtenberg Str 2a, D-85748 Garching, Bavaria, Germany

[5] Tech Univ Munich, Munich Ctr Machine Learning MCML, Arcisstr 21, D-80333 Munich, Bavaria, Germany

[6] Tech Univ Munich, Konrad Zuse Sch Excellence Reliable relAI, Walther-von-Dyck-Str 10, D-85748 Garching, Bavaria, Germany

[7] Tech Univ Munich, Dept Bioinformat & Computat Biol i12, Boltzmannstr 3, D-85748 Garching, Bavaria, Germany

[8] Johannes Gutenberg Univ Mainz JGU, Inst Organism & Mol Evolut, Husch-Weg 15, D-55128 Mainz, Rhineland Palat, Germany

[9] Helmholtz Zentrum, Inst Radiat Med IRM, Ingolstadter Landstr 1, D-85764 Oberschleissheim, Bavaria, Germany

[10] German Consortium Translat Canc Res DKTK, Partner Site Munich, Munich, Bavaria, Germany

[11] Helmholtz Munich, Inst Machine Learning Biomed Imaging, Ingolstadter Landstr 1, D-85764 Neuherberg, Bavaria, Germany

[12] Kings Coll London, Sch Biomed Engn & Imaging Sci, Strand, London WC2R 2LS, England

[13] Imperial Coll London, Fac Engn, Dept Comp, Exhibit Rd, London SW7 2BX, England

来源：

STRAHLENTHERAPIE UND ONKOLOGIE | 2025年 / 201卷 / 03期

关键词：

Deep learning; Automatic segmentation; Radiotherapy planning; Radiation oncology; CLINICAL TARGET VOLUME; MEDICAL IMAGE SEGMENTATION; LYMPH-NODE STATUS; RADIATION-THERAPY; AUTO-SEGMENTATION; INTEROBSERVER VARIABILITY; AUTOMATIC SEGMENTATION; STATISTICAL SHAPE; RADIOMICS MODEL; NEURAL-NETWORK;

D O I：

10.1007/s00066-024-02262-2

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

The rapid development of artificial intelligence (AI) has gained importance, with many tools already entering our daily lives. The medical field of radiation oncology is also subject to this development, with AI entering all steps of the patient journey. In this review article, we summarize contemporary AI techniques and explore the clinical applications of AI-based automated segmentation models in radiotherapy planning, focusing on delineation of organs at risk (OARs), the gross tumor volume (GTV), and the clinical target volume (CTV). Emphasizing the need for precise and individualized plans, we review various commercial and freeware segmentation tools and also state-of-the-art approaches. Through our own findings and based on the literature, we demonstrate improved efficiency and consistency as well as time savings in different clinical scenarios. Despite challenges in clinical implementation such as domain shifts, the potential benefits for personalized treatment planning are substantial. The integration of mathematical tumor growth models and AI-based tumor detection further enhances the possibilities for refining target volumes. As advancements continue, the prospect of one-stop-shop segmentation and radiotherapy planning represents an exciting frontier in radiotherapy, potentially enabling fast treatment with enhanced precision and individualization.

引用

页码：236 / 254

页数：19

共 171 条

[1] Labels4Free: Unsupervised Segmentation using StyleGAN [J].