Ultra-high b-value DWI in rectal cancer: image quality assessment and regional lymph node prediction based on radiomics

Objectives This study aims to evaluate image quality and regional lymph node metastasis (LNM) in patients with rectal cancer (RC) on multi- b -value diffusion-weighted imaging (DWI). Methods This retrospective study included 199 patients with RC who had undergone multi- b -value DWI. Subjective (five-point Likert scale) and objective assessments of quality images were performed on DWI b1000 , DWI b2000, and DWI b3000 . Patients were randomly divided into a training ( n = 140) or validation cohort ( n = 59). Radiomics features were extracted within the whole volume tumor on ADC maps ( b = 0, 1000 s/mm 2 ), DWI b1000 , DWI b2000 , and DWI b3000 , respectively. Five prediction models based on selected features were developed using logistic regression analysis. The performance of radiomics models was evaluated with a receiver operating characteristic curve, calibration, and decision curve analysis (DCA). Results The mean signal intensity of the tumor (SI tumor ), signal-to-noise ratio (SNR), and artifact and anatomic differentiability score gradually were decreased as the b -value increased. However, the contrast-to-noise (CNR) on DWI b2000 was superior to those of DWI b1000 and DWI b3000 (4.58 ± 0.86, 3.82 ± 0.77, 4.18 ± 0.84, p