Multimodality deep learning radiomics predicts pathological response after neoadjuvant chemoradiotherapy for esophageal squamous cell carcinoma.

Publisher: Springer Country of Publication: Germany NLM ID: 101532453 Publication Model: Electronic Cited Medium: Print ISSN: 1869-4101 (Print) Linking ISSN: 18694101 NLM ISO Abbreviation: Insights Imaging Subsets: PubMed not MEDLINE

Original Publication: Berlin : Springer

Objectives: This study aimed to develop and validate a deep-learning radiomics model using CT, T2, and DWI images for predicting pathological complete response (pCR) in patients with esophageal squamous cell carcinoma (ESCC) undergoing neoadjuvant chemoradiotherapy (nCRT).
Materials and Methods: Patients with ESCC undergoing nCRT followed by surgery were retrospectively enrolled from three institutions and divided into training and testing cohorts. Both traditional and deep-learning radiomics features were extracted from pre-treatment CT, T2, and DWI. Multiple radiomics models were developed, both single modality and integrated, using machine learning algorithms. The models' performance was assessed using receiver operating characteristic curve analysis, with the area under the curve (AUC) as a primary metric, alongside sensitivity and specificity from the cut-off analysis.
Results: The study involved 151 patients, among whom 63 achieved pCR. The training cohort consisted of 89 patients from Institution 1 (median age 62, 73 males) and the testing cohort included 52 patients from Institution 2 (median age 62, 41 males), and 10 in a clinical trial from Institution 3 (median age 69, 9 males). The integrated model, combining traditional and deep learning radiomics features from CT, T2, and DWI, demonstrated the best performance with an AUC of 0.868 (95% CI: 0.766-0.959), sensitivity of 88% (95% CI: 73.9-100), and specificity of 78.4% (95% CI: 63.6-90.2) in the testing cohort. This model outperformed single-modality models and the clinical model.
Conclusion: A multimodality deep learning radiomics model, utilizing CT, T2, and DWI images, was developed and validated for accurately predicting pCR of ESCC following nCRT.
Critical Relevance Statement: Our research demonstrates the satisfactory predictive value of multimodality deep learning radiomics for the response of nCRT in ESCC and provides a potentially helpful tool for personalized treatment including organ preservation strategy.
Key Points: After neoadjuvant chemoradiotherapy, patients with ESCC have pCR rates of about 40%. The multimodality deep learning radiomics model, could predict pCR after nCRT with high accuracy. The multimodality radiomics can be helpful in personalized treatment of esophageal cancer.
Competing Interests: Declarations Ethics approval and consent to participate This study was approved by the institutional review boards and the patient informed consent was obtained from each participant enrolled prospectively. Consent for publication Not applicable. Competing interests The authors declare that they have no competing interests.
(© 2024. The Author(s).)

Dis Esophagus. 2018 Feb 1;31(2):. (PMID: 29036528)
Insights Imaging. 2023 May 4;14(1):75. (PMID: 37142815)
J Clin Oncol. 2005 Jul 1;23(19):4330-7. (PMID: 15781882)
Neuro Oncol. 2024 Mar 4;26(12 Suppl 2):S17-S25. (PMID: 38437666)
JAMA Netw Open. 2020 Sep 1;3(9):e2015927. (PMID: 32910196)
Eur Radiol. 2024 Jan;34(1):485-494. (PMID: 37540319)
Radiother Oncol. 2021 Jan;154:6-13. (PMID: 32941954)
Eur J Nucl Med Mol Imaging. 2022 Jul;49(8):2462-2481. (PMID: 34939174)
Eur Radiol Exp. 2023 Mar 15;7(1):11. (PMID: 36918479)
Ann Surg. 2022 Mar 1;275(3):467-476. (PMID: 34191461)
JAMA Surg. 2021 Aug 1;156(8):721-729. (PMID: 34160577)
In Vivo. 2021 May-Jun;35(3):1857-1863. (PMID: 33910873)
J Magn Reson Imaging. 2023 Sep;58(3):907-923. (PMID: 36527425)
Cancer. 1994 Jun 1;73(11):2680-6. (PMID: 8194005)
Br J Surg. 2019 Apr;106(5):596-605. (PMID: 30802305)
J Radiat Res. 2019 Jul 1;60(4):538-545. (PMID: 31111948)
Am J Surg. 2020 Jun;219(6):1024-1029. (PMID: 31387687)
Brief Bioinform. 2021 Jan 18;22(1):360-379. (PMID: 31950132)
Ann Oncol. 2022 Oct;33(10):992-1004. (PMID: 35914638)
J Clin Oncol. 2018 Sep 20;36(27):2796-2803. (PMID: 30089078)
IEEE Trans Med Imaging. 2010 Jun;29(6):1310-20. (PMID: 20378467)
Nat Rev Clin Oncol. 2022 Feb;19(2):132-146. (PMID: 34663898)
J Clin Oncol. 2021 Jun 20;39(18):1995-2004. (PMID: 33891478)
Radiother Oncol. 2024 May;194:110160. (PMID: 38369025)
N Engl J Med. 2021 Apr 1;384(13):1191-1203. (PMID: 33789008)
EClinicalMedicine. 2024 Jan 03;67:102385. (PMID: 38261897)
Eur Radiol Exp. 2018 Nov 14;2(1):36. (PMID: 30426318)
BMJ. 2024 Jun 3;385:e074962. (PMID: 38830686)
J Thorac Oncol. 2019 Jul;14(7):1156-1171. (PMID: 30999111)
Cancers (Basel). 2019 Oct 29;11(11):. (PMID: 31671766)
N Engl J Med. 2012 May 31;366(22):2074-84. (PMID: 22646630)
Nat Rev Clin Oncol. 2017 Dec;14(12):749-762. (PMID: 28975929)

2022YFC2705000, 2022YFC2705001 National Key Research and Development Program of China; LC2022R03 Beijing Hope Run Special Fund of Cancer Foundation of China; 2023-I2M-C&T-A-011 CAMS Innovation Fund for Medical Sciences (CIFMS)

Keywords: Deep learning; Esophageal neoplasms; Multimodal imaging; Neoadjuvant chemoradiotherapy; Treatment outcome

Date Created: 20241115 Latest Revision: 20241118

20241118

PMC11568088

10.1186/s13244-024-01851-0

39546168