Can MRI radiomics distinguish residual adenocarcinoma from acellular mucin in treated rectal cancer? Journal Article
| Authors: | Corines, M. J.; Ibrahim, A.; Baheti, A.; Gibbs, P.; Sheedy, S. P.; Lee, S.; Nougaret, S.; Ernst, R.; Moreno, C. C.; Korngold, E.; Fox, M.; Miranda, J.; Nahas, S. C.; Petkovska, I.; Zheng, J.; Sosa, R. E.; Gangai, N.; Zhao, B.; Schwartz, L. H.; Horvat, N.; Gollub, M. J. |
| Article Title: | Can MRI radiomics distinguish residual adenocarcinoma from acellular mucin in treated rectal cancer? |
| Abstract: | Background: We explored the use of MRI T2-weighted imaging (T2WI) radiomics to help distinguish acellular mucin from cellular mucin (residual tumor) to inform patient management. Methods: This retrospective, multi-institutional study included consecutive patients with rectal adenocarcinoma containing mucin on restaging MRI from March 2012–January 2020. Radiologists segmented 3-mm–thick T2WI. Data were split into training (n = 122), validation (n = 40), and test (n = 42) sets. Sensitivity, specificity, PPV, NPV, and AUC of the developed radiomic models were investigated on the test set. Histopathology was the reference standard. Two radiologists independently reviewed 42 patients using a unique five-point Likert scale for the probability of cellular mucin. DeLong-Delong or McNemar's test was used to compare the AUC and diagnostic performance, respectively, of the radiomics model to that of the human readers. Results: Of 204 patients (mean age, 56.6 ± 13.3 years; 129 men and 75 women), 39/204 (19 %) had acellular mucin whereas 165/204 (81 %) had cellular mucin. The radiomics model demonstrated a sensitivity of 90 % (27/30, 95 % CI: 74–97 %), specificity of 83 % (10/12, 95 % CI: 55–95 %), PPV of 93 % (27/29, 95 % CI: 78–98 %), NPV of 77 % (10/13, 95 % CI: 50–92 %), and AUC of 0.84 (95 % CI: 0.65–0.99), whereas the human readers showed inferior sensitivities of 47 % (14/30) (95 % CI: 28–66 %) and 50 % (15/30) (95 % CI: 31–69 %) and AUCs of 0.58 (95 % CI: 0.41–0.74) (DeLong's p = 0.06 [95 % CI: −0.55, 0.01]) and 0.73 (95 % CI: 0.57–0.88) (DeLong's p = 0.43 [95 % CI: −0.39, 0.16]). Conclusion: The developed MRI radiomics model predicts cellular mucin post neoadjuvant chemoradiation with higher sensitivity than human readers. © 2025 Elsevier B.V. |
| Keywords: | adult; human tissue; unclassified drug; major clinical study; histopathology; area under the curve; nuclear magnetic resonance imaging; magnetic resonance imaging; sensitivity and specificity; adenocarcinoma; accuracy; cohort analysis; retrospective study; neoplasm, residual; probability; rectal neoplasms; rectum cancer; receiver operating characteristic; mucin; mucins; machine learning; human; male; female; article; likert scale; radiomics; acellular mucin; t2 weighted imaging |
| Journal Title: | European Journal of Radiology |
| Volume: | 184 |
| ISSN: | 0720-048X |
| Publisher: | Elsevier B.V |
| Date Published: | 2025-03-01 |
| Start Page: | 111986 |
| Language: | English |
| DOI: | 10.1016/j.ejrad.2025.111986 |
| PROVIDER: | scopus |
| PUBMED: | 39923594 |
| PMCID: | PMC11892329 |
| DOI/URL: | |
| Notes: | The MSK Cancer Center Support Grant (P30 CA008748) is acknowledge in the PDF -- Corresponding authors is MSK author: Marc J. Gollub -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
Related MSK Work