Abstract
Purpose
To distinguish malignant and benign bowel wall thickening (BWT) by using computed tomography (CT) texture features based on machine learning (ML) models and to compare its success with the clinical model and combined model.
Methods
One hundred twenty-two patients with BWT identified on contrast-enhanced abdominal CT and underwent colonoscopy were included in this retrospective study. Texture features were extracted from CT images using LifeX software. Feature selection and reduction were performed using the Least Absolute Shrinkage and Selection Operator (LASSO). Six radiomic features were selected with LASSO. In the clinical model, six features (age, gender, thickness, fat stranding, symmetry, and lymph node) were included. Six radiomic and six clinical features were used in the combined model. Classification was done using two machine learning algorithms: Support Vector Machine (SVM) and Logistic Regression (LR). The data sets were divided into 80% training set and 20% test set. Then, training took place with all three datasets. The model’s success was tested with the test set consisting of features not used during training.
Results
In the training set, the combined model had the best performance with the area under the curve (AUC) value of 0.99 for SVM and 0.95 for LR. In the radiomic-derived model, the AUC value is 0.87 in SVM and 0.79 in LR. In the clinical model, SVM made this distinction with 0.95 AUC and LR with 0.92 AUC value. In the test set, the classifier with the highest success distinguishing malignant wall thickening is SVM in the radiomic-derived model with an AUC value of 0.90. In other models, the AUC value is in the range of 0.75–0.86, and the accuracy values are in the range of 0.72–0.84.
Conclusion
In conclusion, radiomic-based machine learning has shown high success in distinguishing malignant and benign BWT and may improve diagnostic accuracy compared to clinical features only. The results of our study may help ensure early diagnosis and treatment of colorectal cancers by facilitating the recognition of malignant BWT.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Uzzaman MM, Alam A, Nair MS, Borgstein R, Meleagros L. Computed tomography findings of bowel wall thickening: its significance and relationship to endoscopic abnormalities. Ann R Coll Surg Engl. 2012;94(1):23–7.
Chandrapalan S, Tahir F, Kimani P, Sinha R, Arasaradnam R. Systematic review and meta-analysis: does colonic mural thickening on CT correlate with endoscopic findings at colonoscopy? Frontline Gastroenterol. 2018;9:278–84.
Nicholson BD, Hyland R, Rembacken BJ, Denyer M, Hull MA, Tolan DJM. Colonoscopy for colonic wall thickening at computed tomography: a worthwhile pursuit? Surg Endosc. 2011;25:2586–91.
Moraitis D, Singh P, Jayadevan R, Cayten CG. Colonic wall thickening on computed tomography scan and clinical correlation. Does it suggest the presence of an underlying neoplasia? Am Surg. 2006;72(3):269–71.
Thomson CS, Forman D. Cancer survival in England and the influence of early diagnosis: what can we learn from recent EUROCARE results? Br J Cancer. 2009;101(Suppl 2):S102–9.
Al-Khowaiter SS, Brahmania M, Kim E, Madden M, Harris A, Yoshida EM, et al. Clinical and endoscopic significance of bowel-wall thickening reported on abdominal computed tomographies in symptomatic patients with no history of gastrointestinal disease. Can Assoc Radiol J. 2014;65(1):67–70.
Wang X, Yuan M, Mi H, Suo S, Eteer K, Li S, et al. The feasibility of differentiating colorectal cancer from normal and inflammatory thickening colon wall using CT texture analysis. Sci Rep. 2020;10(1):6346.
Sandrasegaran K, Lin Y, Asare-Sawiri M, Taiyini T, Tann M. CT texture analysis of pancreatic cancer. Eur Radiol. 2019;29(3):1067–73.
Aide N, Fruchart C, Nganoa C, Gac AC, Lasnon C. Baseline 18F-FDG PET radiomic features as predictors of 2-year event-free survival in diffuse large B cell lymphomas treated with immunochemotherapy. Eur Radiol. 2020;30(8):4623–32.
Wolff JH, Rubin A, Potter JD, Lattimore W, Resnick MB, Murphy BL, et al. Clinical significance of colonoscopic findings associated with colonic thickening on computed tomography: is colonoscopy warranted when thickening is detected? J Clin Gastroenterol. 2008;42(5):472–5.
Nioche C, Orlhac F, Boughdad S, Reuzé S, Goya-Outi J, Robert C, et al. LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res. 2018;78(16):4786–9.
Kang J, Choi YJ, Kim IK, Lee HS, Kim H, Baik SH, et al. LASSO-based machine learning algorithm for prediction of lymph node metastasis in T1 colorectal cancer. Cancer Res Treat. 2021;53(3):773–83.
Tellez-Avila FI, García-Osogobio S, Chavez-Tapia NC, Ramirez-Luna MA, Franco-Guzman A, Sosa-Lozano A, et al. Utility of endoscopy in patients with incidental gastrointestinal luminal wall thickening detected with CT. Surg Endosc. 2009;23(10):2191–6.
Rizzo S, Botta F, Raimondi S, Origgi D, Fanciullo C, Morganti AG, et al. Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp. 2018;2(1):36.
Li Z, Mao Y, Huang W, Li H, Zhu J, Li W, et al. Texture-based classification of different single liver lesion based on SPAIR T2W MRI images. BMC Med Imaging. 2017;17(1):42.
Stoecker WV, Chiang CS, Moss RH. Texture in skin images: comparison of three methods to determine smoothness. Comput Med Imaging Graph. 1992;16:179–90.
Pooler BD, Lubner MG, Theis JR, Halberg RB, Liang Z, Pickhardt PJ. Volumetric textural analysis of colorectal masses at CT colonography: differentiating benign versus malignant pathology and comparison with human reader performance. Acad Radiol. 2019;26(1):30–7.
Funding
The authors declared that this study has received no financial support.
Author information
Authors and Affiliations
Contributions
HMB was involved in data curation, formal analysis, methodology, statistical analysis, writing original draft, and writing, review & editing. GB was involved in data curation, methodology, visualization, and writing, review & editing. UK was involved in data curation, formal analysis, methodology, writing—original draft, and writing, review & editing. EK was involved in conceptualization, data curation, statistical analysis, supervision, and writing, review & editing.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant conflicts of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Bülbül, H.M., Burakgazi, G., Kesimal, U. et al. Radiomics-based machine learning in the differentiation of benign and malignant bowel wall thickening radiomics in bowel wall thickening. Jpn J Radiol (2024). https://doi.org/10.1007/s11604-024-01558-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11604-024-01558-8