MRI-based radiomics to predict response in locally advanced rectal cancer: comparison of manual and automatic segmentation on external validation in a multicentre study.
Artificial intelligence
Machine learning
Multiparametric magnetic resonance imaging
Neoadjuvant therapy
Rectal neoplasms
Journal
European radiology experimental
ISSN: 2509-9280
Titre abrégé: Eur Radiol Exp
Pays: England
ID NLM: 101721752
Informations de publication
Date de publication:
03 05 2022
03 05 2022
Historique:
received:
14
12
2021
accepted:
23
03
2022
entrez:
2
5
2022
pubmed:
3
5
2022
medline:
6
5
2022
Statut:
epublish
Résumé
Pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer (LARC) is achieved in 15-30% of cases. Our aim was to implement and externally validate a magnetic resonance imaging (MRI)-based radiomics pipeline to predict response to treatment and to investigate the impact of manual and automatic segmentations on the radiomics models. Ninety-five patients with stage II/III LARC who underwent multiparametric MRI before chemoradiotherapy and surgical treatment were enrolled from three institutions. Patients were classified as responders if tumour regression grade was 1 or 2 and nonresponders otherwise. Sixty-seven patients composed the construction dataset, while 28 the external validation. Tumour volumes were manually and automatically segmented using a U-net algorithm. Three approaches for feature selection were tested and combined with four machine learning classifiers. Using manual segmentation, the best result reached an accuracy of 68% on the validation set, with sensitivity 60%, specificity 77%, negative predictive value (NPV) 63%, and positive predictive value (PPV) 75%. The automatic segmentation achieved an accuracy of 75% on the validation set, with sensitivity 80%, specificity 69%, and both NPV and PPV 75%. Sensitivity and NPV on the validation set were significantly higher (p = 0.047) for the automatic versus manual segmentation. Our study showed that radiomics models can pave the way to help clinicians in the prediction of tumour response to chemoradiotherapy of LARC and to personalise per-patient treatment. The results from the external validation dataset are promising for further research into radiomics approaches using both manual and automatic segmentations.
Sections du résumé
BACKGROUND
Pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer (LARC) is achieved in 15-30% of cases. Our aim was to implement and externally validate a magnetic resonance imaging (MRI)-based radiomics pipeline to predict response to treatment and to investigate the impact of manual and automatic segmentations on the radiomics models.
METHODS
Ninety-five patients with stage II/III LARC who underwent multiparametric MRI before chemoradiotherapy and surgical treatment were enrolled from three institutions. Patients were classified as responders if tumour regression grade was 1 or 2 and nonresponders otherwise. Sixty-seven patients composed the construction dataset, while 28 the external validation. Tumour volumes were manually and automatically segmented using a U-net algorithm. Three approaches for feature selection were tested and combined with four machine learning classifiers.
RESULTS
Using manual segmentation, the best result reached an accuracy of 68% on the validation set, with sensitivity 60%, specificity 77%, negative predictive value (NPV) 63%, and positive predictive value (PPV) 75%. The automatic segmentation achieved an accuracy of 75% on the validation set, with sensitivity 80%, specificity 69%, and both NPV and PPV 75%. Sensitivity and NPV on the validation set were significantly higher (p = 0.047) for the automatic versus manual segmentation.
CONCLUSION
Our study showed that radiomics models can pave the way to help clinicians in the prediction of tumour response to chemoradiotherapy of LARC and to personalise per-patient treatment. The results from the external validation dataset are promising for further research into radiomics approaches using both manual and automatic segmentations.
Identifiants
pubmed: 35501512
doi: 10.1186/s41747-022-00272-2
pii: 10.1186/s41747-022-00272-2
pmc: PMC9061921
doi:
Types de publication
Journal Article
Multicenter Study
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
19Informations de copyright
© 2022. The Author(s) under exclusive licence to European Society of Radiology.
Références
Sung H, Ferlay J, Siegel RL, et al (2021) Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209–249. https://doi.org/10.3322/caac.21660
doi: 10.3322/caac.21660
pubmed: 33538338
Ali F, Keshinro A, Weiser MR (2020) Advances in the treatment of locally advanced rectal cancer. Ann Gastroenterol Surg 5:32–38. https://doi.org/10.1002/ags3.12389
doi: 10.1002/ags3.12389
pubmed: 33532678
pmcid: 7832958
Lee M, Gibbs P, Wong R (2015) Multidisciplinary management of locally advanced rectal cancer--an evolving landscape? Clin Colorectal Cancer 14:251–261. https://doi.org/10.1016/j.clcc.2015.06.002
doi: 10.1016/j.clcc.2015.06.002
pubmed: 26210575
Nacion AJD, Park YY, Kim NK (2018) Contemporary management of locally advanced rectal cancer: resolving issues, controversies and shifting paradigms. Chin J Cancer Res 30:131–146. doi: https://doi.org/10.21147/j.issn.1000-9604.2018.01.14
Hoendervangers S, Burbach JPM, Lacle MM, et al (2020) Pathological complete response following different neoadjuvant treatment strategies for locally advanced rectal cancer: a systematic review and meta-analysis. Ann Surg Oncol 27:4319–4336. https://doi.org/10.1245/s10434-020-08615-2
doi: 10.1245/s10434-020-08615-2
pubmed: 32524461
pmcid: 7497700
Habr-Gama A, Gama-Rodrigues J, São Julião GP, et al (2014) Local recurrence after complete clinical response and watch and wait in rectal cancer after neoadjuvant chemoradiation: impact of salvage therapy on local disease control. Int J Radiat Oncol Biol Phy. 88:822–828. https://doi.org/10.1016/j.ijrobp.2013.12.012
doi: 10.1016/j.ijrobp.2013.12.012
Hupkens BJP, Maas M, Martens MH, et al (2018) Organ preservation in rectal cancer after chemoradiation: should we extend the observation period in patients with a clinical near-complete response? Ann Surg Oncol 25:197–203. https://doi.org/10.1245/s10434-017-6213-8
doi: 10.1245/s10434-017-6213-8
pubmed: 29134378
Dresen RC, Beets GL, Rutten HJ et al (2009) Locally advanced rectal cancer: MR imaging for restaging after neoadjuvant radiation therapy with concomitant chemotherapy. Part I. Are we able to predict tumor confined to the rectal wall? Radiology 252:71–80. https://doi.org/10.1148/radiol.2521081200
doi: 10.1148/radiol.2521081200
pubmed: 19403847
Liu M, Lv H, Liu LH, Yang ZH, Jin EH, Wang ZC (2017) Locally advanced rectal cancer: predicting non-responders to neoadjuvant chemoradiotherapy using apparent diffusion coefficient textures. Int J Colorectal Dis 32:1009–1012. https://doi.org/10.1007/s00384-017-2835-3
doi: 10.1007/s00384-017-2835-3
pubmed: 28497403
Song J, Yin Y, Wang H, Chang Z, Liu Z, Cui L (2020) A review of original articles published in the emerging field of radiomics. Eur J Radiol 127:108991. https://doi.org/10.1016/j.ejrad.2020.108991
doi: 10.1016/j.ejrad.2020.108991
pubmed: 32334372
Shaish H, Aukerman A, Vanguri R, et al (2020) Radiomics of MRI for pretreatment prediction of pathologic complete response, tumor regression grade, and neoadjuvant rectal score in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiation: an international multicenter study. Eur Radiol 30:6263–6273. https://doi.org/10.1007/s00330-020-06968-6
doi: 10.1007/s00330-020-06968-6
pubmed: 32500192
Liu L, Liu Y, Xu L, et al (2017) Application of texture analysis based on apparent diffusion coefficient maps in discriminating different stages of rectal cancer. J Magn Reson Imaging 45:1798–1808. https://doi.org/10.1002/jmri.25460
doi: 10.1002/jmri.25460
pubmed: 27654307
Cui Y, Yang X, Shi Z, et al (2019) Radiomics analysis of multiparametric MRI for prediction of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Eur Radiol 29:1211–1220. https://doi.org/10.1007/s00330-018-5683-9
doi: 10.1007/s00330-018-5683-9
pubmed: 30128616
Petresc B, Lebovici A, Caraiani C, Feier DS, Graur F, Buruian MM (2020) Pre-treatment T2-WI based radiomics features for prediction of locally advanced rectal cancer non-response to neoadjuvant chemoradiotherapy: a preliminary study. Cancers (Basel) 12:1894. https://doi.org/10.3390/cancers12071894
doi: 10.3390/cancers12071894
Zhang S, Yu M, Chen D, Li P, Tang B, Li J (2022) Role of MRI-based radiomics in locally advanced rectal cancer (review). Oncol Rep 47:34. https://doi.org/10.3892/or.2021.8245
doi: 10.3892/or.2021.8245
pubmed: 34935061
Giannini V, Mazzetti S, Bertotto I, et al (2019) Predicting locally advanced rectal cancer response to neoadjuvant therapy with
doi: 10.1007/s00259-018-4250-6
pubmed: 30637502
Coppola F, Giannini V, Gabelloni M, et al (2021) Radiomics and magnetic resonance imaging of rectal cancer: from engineering to clinical practice. Diagnostics (Basel) 11:756. https://doi.org/10.3390/diagnostics11050756
doi: 10.3390/diagnostics11050756
Rizzo S, Botta F, Raimondi S, et al (2018) Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp 2:36. https://doi.org/10.1186/s41747-018-0068-z
doi: 10.1186/s41747-018-0068-z
pubmed: 30426318
pmcid: 6234198
van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B (2020) Radiomics in medical imaging-“how-to” guide and critical reflection. Insights Imaging 11:91. https://doi.org/10.1186/s13244-020-00887-2
doi: 10.1186/s13244-020-00887-2
pubmed: 32785796
pmcid: 7423816
Liu R, Elhalawani H, Radwan Mohamed AS, et al (2019) Stability analysis of CT radiomic features with respect to segmentation variation in oropharyngeal cancer. Clin Transl Radiat Oncol 21:11–18. https://doi.org/10.1016/j.ctro.2019.11.005
doi: 10.1016/j.ctro.2019.11.005
pubmed: 31886423
pmcid: 6920497
Zhu HT, Zhang XY, Shi YJ, Li XT, Sun YS (2021) Automatic segmentation of rectal tumor on diffusion-weighted images by deep learning with U-Net. J Appl Clin Med Phys 22:324–331. https://doi.org/10.1002/acm2.13381
doi: 10.1002/acm2.13381
pubmed: 34343402
pmcid: 8425941
Mandard AM, Dalibard F, Mandard JC, et al (1994) Pathologic assessment of tumor regression after preoperative chemoradiotherapy of esophageal carcinoma. Clinicopathologic correlations. Cancer 73:2680–2686. https://doi.org/10.1002/1097-0142(19940601)73:11<2680::aid-cncr2820731105>3.0.co;2-c
doi: 10.1002/1097-0142(19940601)73:11<2680::aid-cncr2820731105>3.0.co;2-c
pubmed: 8194005
Beets-Tan RGH, Lambregts DMJ, Maas M, et al (2018) Magnetic resonance imaging for clinical management of rectal cancer: updated recommendations from the 2016 European society of gastrointestinal and abdominal radiology (ESGAR) consensus meeting. Eur Radiol 28:1465–1475. https://doi.org/10.1007/s00330-017-5026-2PMC5834554
doi: 10.1007/s00330-017-5026-2PMC5834554
pubmed: 29043428
Zwanenburg A, Vallières M, Abdalah MA, et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338. https://doi.org/10.1148/radiol.2020191145
doi: 10.1148/radiol.2020191145
Zwanenburg A, Leger S, Agolli L, et al (2019) Assessing robustness of radiomic features by image perturbation. Sci Rep 9:614. https://doi.org/10.1038/s41598-018-36938-4
doi: 10.1038/s41598-018-36938-4
pubmed: 30679599
pmcid: 6345842
Qin L, Li A, Qu J et al (2018) Normalization of ADC does not improve correlation with overall survival in patients with high-grade glioma (HGG). J Neurooncol 137:313–319. https://doi.org/10.1007/s11060-017-2719-y
doi: 10.1007/s11060-017-2719-y
pubmed: 29383647
pmcid: 6071871
Rosati S, Cm G, Balesta G, Giannini V, Mazzetti S, Regge D (2018) Radiomics to predict response to neoadjuvant chemotherapy in rectal cancer: influence of simultaneous feature selection and classifier optimization. IEEE Life Sciences Conference:65–68. https://doi.org/10.1109/LSC.2018.8572194
Wang K, Zhang J, Li D, Zhang X, Guo T (2007) Adaptive affinity propagation clustering. Acta Automatica Sinica 33:1242–1246. https://doi.org/10.1360/aas-007-1242
doi: 10.1360/aas-007-1242
Kirkwood BR, Sterne JAC (2003) Essential medical statistics, 2nd edn. Blackwell Science, Oxford
Nie K, Shi L, Chen Q, et al (2016) Rectal cancer: assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI. Clin Cancer Res 22:5256–5264. https://doi.org/10.1158/1078-0432.CCR-15-2997
doi: 10.1158/1078-0432.CCR-15-2997
pubmed: 27185368
Horvat N, Veeraraghavan H, Khan M, et al (2018) MR imaging of rectal cancer: radiomics analysis to assess treatment response after neoadjuvant therapy. Radiology 287:833–843. https://doi.org/10.1148/radiol.2018172300
doi: 10.1148/radiol.2018172300
pubmed: 29514017
Petkovska I, Tixier F, Ortiz EJ, et al (2020) Clinical utility of radiomics at baseline rectal MRI to predict complete response of rectal cancer after chemoradiation therapy. Abdom Radiol (NY) 5:3608–3617. https://doi.org/10.1007/s00261-020-02502-w
doi: 10.1007/s00261-020-02502-w
Liu Z, Zhang XY, Shi YJ, et al (2017) Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res 23:7253–7262. https://doi.org/10.1158/1078-0432.CCR-17-1038
doi: 10.1158/1078-0432.CCR-17-1038
pubmed: 28939744
Delli Pizzi A, Chiarelli AM, Chiacchiaretta P, et al (2021) MRI-based clinical-radiomics model predicts tumor response before treatment in locally advanced rectal cancer. Sci Rep 11:5379. https://doi.org/10.1038/s41598-021-84816-3
doi: 10.1038/s41598-021-84816-3
pubmed: 33686147
pmcid: 7940398
Li Y, Liu W, Pei Q, et al (2019) Predicting pathological complete response by comparing MRI-based radiomics pre- and postneoadjuvant radiotherapy for locally advanced rectal cancer. Cancer Med 8:7244–7252. https://doi.org/10.1002/cam4.2636
doi: 10.1002/cam4.2636
pubmed: 31642204
pmcid: 6885895
Bulens P, Couwenberg A, Intven M, et al (2020) Predicting the tumor response to chemoradiotherapy for rectal cancer: model development and external validation using MRI radiomics. Radiother Oncol 142:246–252. https://doi.org/10.1016/j.radonc.2019.07.033
doi: 10.1016/j.radonc.2019.07.033
pubmed: 31431368
Horvat N, Bates DDB, Petkovska I (2019) Novel imaging techniques of rectal cancer: what do radiomics and radiogenomics have to offer? A literature review. Abdom Radio (NY) 44:3764–3774. https://doi.org/10.1007/s00261-019-02042-y
doi: 10.1007/s00261-019-02042-y
Alvarez-Jimenez C, Sandino AA, Prasanna P, Gupta A, Viswanath SE, Romero E (2020) Identifying cross-scale associations between radiomic and pathomic signatures of non-small cell lung cancer subtypes: preliminary results. Cancers 12:3663. https://doi.org/10.3390/cancers1212366
doi: 10.3390/cancers1212366
pmcid: 7762258