Artificial intelligence (AI)-based decision support improves reproducibility of tumor response assessment in neuro-oncology: An international multi-reader study

被引：30

作者：

Vollmuth, Philipp ^{[1
]}

Foltyn, Martha ^{[1
]}

Huang, Raymond Y. ^{[2
]}

Galldiks, Norbert ^{[3
,4
,5
,6
,7
,8
]}

Petersen, Jens ^{[9
]}

Isensee, Fabian ^{[9
]}

van den Bent, Martin J. ^{[10
]}

Barkhof, Frederik ^{[11
,12
,13
]}

Park, Ji Eun ^{[14
,15
]}

Park, Yae Won ^{[16
,17
,18
]}

Ahn, Sung Soo ^{[16
,17
,18
]}

Brugnara, Gianluca ^{[1
]}

Meredig, Hagen ^{[1
]}

Jain, Rajan ^{[19
]}

Smits, Marion ^{[20
]}

Pope, Whitney B. ^{[21
]}

Maier-Hein, Klaus ^{[9
]}

Weller, Michael ^{[22
,23
]}

Wen, Patrick Y. ^{[24
]}

Wick, Wolfgang ^{[25
,26
]}

Bendszus, Martin ^{[1
]}

机构：

[1] Heidelberg Univ Hosp, Dept Neuroradiol, Neuenheimer Feld 400, D-69120 Heidelberg, Germany

[2] Brigham & Womens Hosp, Dept Radiol, 75 Francis St, Boston, MA 02115 USA

[3] Univ Cologne, Univ Hosp Cologne, Fac Med, Dept Neurol, Cologne, Germany

[4] Res Ctr Juelich, Inst Neurosci & Med INM 3 4, Julich, Germany

[5] Univ Aachen, Ctr Integrated Oncol CIO, Aachen, Germany

[6] Univ Bonn, Ctr Integrated Oncol CIO, Bonn, Germany

[7] Univ Cologne, Ctr Integrated Oncol CIO, Cologne, Germany

[8] Univ Duesseldorf, Ctr Integrated Oncol CIO, Dusseldorf, Germany

[9] German Canc Res Ctr, Dept Med Image Comp MIC, Heidelberg, Germany

[10] Erasmus MC, Brain Tumor Ctr, Canc Inst, Rotterdam, Netherlands

[11] Vrije Univ, Dept Radiol & Nucl Med, Amsterdam UMC, Amsterdam, Netherlands

[12] UCL, Inst Neurol, London, England

[13] UCL, Ctr Med Image Comp, London, England

[14] Univ Ulsan, Asan Med Ctr, Dept Radiol, Coll Med, Seoul, South Korea

[15] Univ Ulsan, Coll Med, Asan Med Ctr, Res Inst Radiol, Seoul, South Korea

[16] Yonsei Univ, Dept Radiol, Coll Med, Seoul, South Korea

[17] Yonsei Univ, Res Inst Radiol Sci, Coll Med, Seoul, South Korea

[18] Yonsei Univ, Ctr Clin Imaging Data Sci, Coll Med, Seoul, South Korea

[19] NYU, Dept Radiol, Sch Med, New York, NY USA

[20] Erasmus MC, Dept Radiol & Nucl Med, Rotterdam, Netherlands

[21] Univ Calif Los Angeles, David Geffen Sch Med, Dept Radiol Sci, Los Angeles, CA 90095 USA

[22] Univ Hosp, Dept Neurol, Zurich, Switzerland

[23] Univ Zurich, Zurich, Switzerland

[24] Dana Farber Canc Inst, Ctr Neurooncol, Boston, MA 02115 USA

[25] Heidelberg Univ Hosp, Neurol Clin, Heidelberg, Germany

[26] German Canc Res Ctr, Clin Cooperat Unit Neurooncol, German Canc Consortium DKTK, Heidelberg, Germany

来源：

NEURO-ONCOLOGY | 2023年 / 25卷 / 03期

关键词：

Artificial intelligence (AI)-based decision support; RANO; tumor response assessment; tumor volumetry; HIGH-GRADE GLIOMAS; CRITERIA;

D O I：

10.1093/neuonc/noac189

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Background. To assess whether artificial intelligence (AI)-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the Response Assessment in Neuro-Oncology (RANO) criteria. Methods. A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds. In the first round the TTP was evaluated based on the RANO criteria, whereas in the second round the TTP was evaluated by incorporating additional information from AI-enhanced MRI sequences depicting the longitudinal changes in tumor volumes. The agreement of the TTP measurements between investigators was evaluated using concordance correlation coefficients (CCC) with confidence intervals (CI) and P-values obtained using bootstrap resampling. Results. The CCC of TTP-measurements between investigators was 0.77 (95% CI = 0.69,0.88) with RANO alone and increased to 0.91 (95% CI = 0.82,0.95) with AI-based decision support (P = .005). This effect was significantly greater (P = .008) for patients with lower-grade gliomas (CCC = 0.70 [95% CI = 0.56,0.85] without vs. 0.90 [95% CI = 0.76,0.95] with AI-based decision support) as compared to glioblastoma (CCC = 0.83 [95% CI = 0.75,0.92] without vs. 0.86 [95% CI = 0.78,0.93] with AI-based decision support). Investigators with less years of experience judged the AI-based decision as more helpful (P = .02). Conclusions. AI-based decision support has the potential to yield more reproducible and standardized assessment of treatment response in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden, particularly in patients with lower-grade gliomas. A fully-functional version of this AI-based processing pipeline is provided as open-source (https://github.com/NeuroAI-HD/HD-GLIO-XNAT).

引用

页码：533 / 543

页数：11

共 24 条

[1]

Baid U., ARXIV

[2] Data Descriptor: Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features [J].

Bakas, Spyridon ;

Akbari, Hamed ;

Sotiras, Aristeidis ;

Bilello, Michel ;

Rozycki, Martin ;

Kirby, Justin S. ;

Freymann, John B. ;

Farahani, Keyvan ;

Davatzikos, Christos .

SCIENTIFIC DATA, 2017, 4

[3] Automatic assessment of glioma burden: a deep learning algorithm for fully automated volumetric and bidimensional measurement [J].

Chang, Ken ;

Beers, Andrew L. ;

Bai, Harrison X. ;

Brown, James M. ;

Ly, K. Ina ;

Li, Xuejun ;

Senders, Joeky T. ;

Kavouridis, Vasileios K. ;

Boaro, Alessandro ;

Su, Chang ;

Bi, Wenya Linda ;

Rapalino, Otto ;

Liao, Weihua ;

Shen, Qin ;

Zhou, Hao ;

Xiao, Bo ;

Wang, Yinyan ;

Zhang, Paul J. ;

Pinho, Marco C. ;

Wen, Patrick Y. ;

Batchelor, Tracy T. ;

Boxerman, Jerrold L. ;

Arnaout, Omar ;

Rosen, Bruce R. ;

Gerstner, Elizabeth R. ;

Yang, Li ;

Huang, Raymond Y. ;

Kalpathy-Cramer, Jayashree .

NEURO-ONCOLOGY, 2019, 21 (11) :1412-1422

[4] Modified Criteria for Radiographic Response Assessment in Glioblastoma Clinical Trials [J].

Ellingson, Benjamin M. ;

Wen, Patrick Y. ;

Cloughesy, Timothy F. .

NEUROTHERAPEUTICS, 2017, 14 (02) :307-320

[5] Consensus recommendations for a standardized Brain Tumor Imaging Protocol in clinical trials [J].

Ellingson, Benjamin M. ;

Bendszus, Martin ;

Boxerman, Jerrold ;

Barboriak, Daniel ;

Erickson, Bradley J. ;

Smits, Marion ;

Nelson, Sarah J. ;

Gerstner, Elizabeth ;

Alexander, Brian ;

Goldmacher, Gregory ;

Wick, Wolfgang ;

Vogelbaum, Michael ;

Weller, Michael ;

Galanis, Evanthia ;

Kalpathy-Cramer, Jayashree ;

Shankar, Lalitha ;

Jacobs, Paula ;

Pope, Whitney B. ;

Yang, Dewen ;

Chung, Caroline ;

Knopp, Michael V. ;

Cha, Soonme ;

van den Bent, Martin J. ;

Chang, Susan ;

Al Yung, W. K. ;

Cloughesy, Timothy F. ;

Wen, Patrick Y. ;

Gilbert, Mark R. .

NEURO-ONCOLOGY, 2015, 17 (09) :1188-1198

[6]

Food U., 2007, FED REGISTER, P72

[7] Lessons learned from independent central renew [J].

Ford, R. ;

Schwartz, L. ;

Dancey, J. ;

Dodd, L. E. ;

Eisenhauer, E. A. ;

Gwyther, S. ;

Rubinstein, L. ;

Sargent, D. ;

Shankar, L. ;

Therasse, P. ;

Verweij, J. .

EUROPEAN JOURNAL OF CANCER, 2009, 45 (02) :268-274

[8] Current status of PET imaging in neuro-oncology [J].

Galldiks, Norbert ;

Lohmann, Philipp ;

Albert, Nathalie L. ;

Tonn, Joerg C. ;

Langen, Karl-Josef .

NEURO-ONCOLOGY ADVANCES, 2019, 1 (01)

[9] Automated brain extraction of multisequence MRI using artificial neural networks [J].

Isensee, Fabian ;

Schell, Marianne ;

Pflueger, Irada ;

Brugnara, Gianluca ;

Bonekamp, David ;

Neuberger, Ulf ;

Wick, Antje ;

Schlemmer, Heinz-Peter ;

Heiland, Sabine ;

Wick, Wolfgang ;

Bendszus, Martin ;

Maier-Hein, Klaus H. ;

Kickingereder, Philipp .

HUMAN BRAIN MAPPING, 2019, 40 (17) :4952-4964

[10]

Kickingereder P, 2020, GLIOMA IMAGING: PHYSIOLOGIC, METABOLIC, AND MOLECULAR APPROACHES, P61, DOI 10.1007/978-3-030-27359-0_5

← 1 2 3 →