Biparametric magnetic resonance imaging-based radiomics features for prediction of lymphovascular invasion in rectal cancer

Abstract

Background Preoperative assessment of lymphovascular invasion(LVI) of rectal cancer has very important clinical significance. However, accurate preoperative imaging evaluation of LVI is highly challenging because the resolution of MRI is still limited. Relatively few studies have focused on prediction of LVI of rectal cancer with the tool of radiomics, especially in patients with negative statue of MRI-based extramural vascular invasion (mrEMVI).The purpose of this study was to explore the preoperative predictive value of biparametric MRI-based radiomics features for LVI of rectal cancer in patients with the negative statue of mrEMVI. Methods The data of 146 cases of rectal adenocarcinoma confirmed by postoperative pathology were retrospectively collected. In the cases, 38 had positive status of LVI. All patients were examined by MRI before the operation. The biparametric MRI protocols included T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). We used whole-volume three-dimensional method and two feature selection methods, minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO), to extract and select the features. Logistics regression was used to construct models. The area under the receiver operating characteristic curve (AUC) and DeLong’s test were used to evaluate the diagnostic performance of the radiomics based on T2WI and DWI and the combined models. Results Radiomics models based on T2WI and DWI had good predictive performance for LVI of rectal cancer in both the training cohort and the validation cohort. The AUCs of the T2WI model were 0.87 and 0.87, and the AUCs of the DWI model were 0.94 and 0.92. The combined model was better than the T2WI model, with AUCs of 0.97 and 0.95. The predictive performance of the DWI model was comparable to that of the combined model. Conclusions The radiomics model based on biparametric MRI, especially DWI, had good predictive value for LVI of rectal cancer. This model has the potential to facilitate the clinical recognition of LVI in rectal cancer preoperatively.

The correlation between time-intensity curve parameters of transrectal contrast-enhanced ultrasound and pathological prognostic factors in rectal adenocarcinoma

“…Tumor differentiation grading was assessed based on the 2019 WHO classification of tumors of the digestive system [15]. LVI in rectal cancer was defined as the invasion of carcinoma cells into lymphatic and/or blood vessel structures [16]. PNI in rectal cancer was characterized by the invasion of carcinoma cells into any layer of the nerve sheath or perineural space [17].…”

Prediction of Pathologic Complete Response for Rectal Cancer Based on Pre-treatment Factors Using Machine Learning

“…12,13 Recent work also suggests that it is possible to predict lymphovascular and perineural invasion from MRI, and, in the future, it may be feasible to capture this information without pathologic data. 47 Because model performance decreases significantly when excluding these variables, prospective analyses based on pretreatment data collection are needed to validate their predictive ability. More broadly, the use of the NCDB does carry major limitations regarding reliability and granularity compared with single-institution data sets.…”

Endoscopic ultrasonography-based intratumoral and peritumoral machine learning radiomics analyses for distinguishing insulinomas from non-functional pancreatic neuroendocrine tumors

“…Integrating radiomics and machine learning strategies has shown promising results in the differential diagnosis and prognosis prediction of various cancers ( 29 ). Radiomics facilitates extracting and analyzing numerous objective and internal image features using high-throughput techniques ( 30 ).…”