Deep learning based on dynamic susceptibility contrast MR imaging for prediction of local progression in adult-type diffuse glioma (grade 4)

• Published in: Scientific reports 2023-08, Vol.13 (1), p.13864-13864, Article 13864
• Main Authors: Heo, Donggeon, Lee, Jisoo, Yoo, Roh-Eul, Choi, Seung Hong, Kim, Tae Min, Park, Chul-Kee, Park, Sung-Hye, Won, Jae-Kyung, Lee, Joo Ho, Lee, Soon Tae, Choi, Kyu Sung, Lee, Ji Ye, Hwang, Inpyeong, Kang, Koung Mi, Yun, Tae Jin
• Format: Article
• Language: English
• Subjects: 692/4028; 692/698/1688; Brain tumors; Cerebral blood flow; Deep learning; Glioma; Humanities and Social Sciences; Lesions; Magnetic resonance imaging; multidisciplinary; Radiation therapy; Science; Science (multidisciplinary)
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-41171-9

Adult-type diffuse glioma (grade 4) has infiltrating nature, and therefore local progression is likely to occur within surrounding non-enhancing T2 hyperintense areas even after gross total resection of contrast-enhancing lesions. Cerebral blood volume (CBV) obtained from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) is a parameter that is well-known to be a surrogate marker of both histologic and angiographic vascularity in tumors. We built two nnU-Net deep learning models for prediction of early local progression in adult-type diffuse glioma (grade 4), one using conventional MRI alone and one using multiparametric MRI, including conventional MRI and DSC-PWI. Local progression areas were annotated in a non-enhancing T2 hyperintense lesion on preoperative T2 FLAIR images, using the follow-up contrast-enhanced (CE) T1-weighted (T1W) images as the reference standard. The sensitivity was doubled with the addition of nCBV (80% vs. 40%, P  = 0.02) while the specificity was decreased nonsignificantly (29% vs. 48%, P  = 0.39), suggesting that fewer cases of early local progression would be missed with the addition of nCBV. While the diagnostic performance of CBV model is still poor and needs improving, the multiparametric deep learning model, which presumably learned from the subtle difference in vascularity between early local progression and non-progression voxels within perilesional T2 hyperintensity, may facilitate risk-adapted radiotherapy planning in adult-type diffuse glioma (grade 4) patients.