Computed Diffusion‐Weighted Images of Rectal Cancer: Image Quality, Restaging, and Treatment Response after Neoadjuvant Therapy

• Published in: Journal of magnetic resonance imaging 2024-01, Vol.59 (1), p.297-308
• Main Authors: Xia, Yihan, Zhu, Lan, Cai, Gang, Du, Lianjun, Wang, Lingyun, Feng, Weiming, Fu, Caixia, Ma, Qianchen, Dong, Yihan, Pan, Zilai, Yan, Fuhua, Shen, Hailin, Li, Weiguang, Zhang, Huan
• Format: Article
• Language: English
• Subjects: Cancer; Cancer therapies; Colorectal cancer; Computation; Correlation coefficient; Correlation coefficients; Diffusion; Diffusion Magnetic Resonance Imaging - methods; diffusion‐weighted imaging; Field strength; Humans; Image acquisition; Image quality; locally advanced rectal cancer (LARC); Magnetic resonance imaging; Medical imaging; Neoadjuvant Therapy; neoadjuvant therapy (NT); Population studies; Rectal Neoplasms - diagnostic imaging; Rectal Neoplasms - therapy; Rectum; Rectum - pathology; restaging; Retrospective Studies; Sensitivity; Statistical analysis; Statistical tests; treatment response; Tumors
• ISSN: 1053-1807; 1522-2586
• DOI: 10.1002/jmri.28766

Background Computed diffusion‐weighted images (cDWI) of random b value could be derived from acquired DWI (aDWI) with at least two different b values. However, its comparison between aDWI and cDWI images in locally advanced rectal cancer (LARC) patients after neoadjuvant therapy (NT) is needed. Purpose To compare the cDWI and aDWI in image quality, restaging, and treatment response of LARC after NT. Study Type Retrospective. Population Eighty‐seven consecutive patients. Field Strength/Sequence 3.0 T/DWI. Assessment All patients underwent two DWI sequences, including conventional acquisition with b = 0 and 1000 s/mm2 (aDWIb1000) and another with b = 0 and 700 s/mm2 on a 3.0‐T MR scanner. The images of the latter were used to compute the diffusion images with b = 1000 s/mm2 (cDWIb1000). Four radiologists with 3, 4, 14, and 25 years of experience evaluated the images to compare the image quality, TN restaging performance, and treatment response between aDWIb1000 and cDWIb1000. Statistical Tests Interclass correlation coefficients, weighted κ coefficient, paired Wilcoxon, and McNemar or Fisher test were used. A significance level of 0.05 was used. Results The cDWIb1000 images were superior to the aDWIb1000 ones in both subjective and objective image quality. In T restaging, the overall diagnostic accuracy of cDWIb1000 images was higher than that of aDWIb1000 images (57.47% vs. 49.43%, P = 0.289 for the inexperienced radiologist; 77.01% vs. 63.22%, significant for the experienced radiologist), with better sensitivity in determining ypT0‐Tis tumors. Additionally, it increased the sensitivity in detecting ypT2 tumors for the inexperienced radiologist and ypT3 tumors for the experienced radiologist. N restaging and treatment response were found to be similar between two sequences for both radiologists. Data Conclusion Compared to aDWIb1000 images, the computed ones might serve as a wise approach, providing comparable or better image quality, restaging performance, and treatment response assessment for LARC after NT. Level of Evidence 3 Technical Efficacy Stage 2