ABSTRACT
Purpose: To predict the corresponding age of myelin maturation from brain MRI scans in infants and young children by using a deep learning algorithm and to build upon previously published models. Materials and Methods: Brain MRI scans acquired between January 1, 2011, and March 17, 2021, in our institution in patients aged 0-3 years were retrospectively retrieved from the archive. An ensemble of two-dimensional (2D) and three-dimensional (3D) convolutional neural network models was trained and internally validated in 710 patients to predict myelin maturation age on the basis of radiologist-generated labels. The model ensemble was tested on an internal dataset of 123 patients and two external datasets of 226 (0-25 months of age) and 383 (0-2 months of age) healthy children and infants, respectively. Mean absolute error (MAE) and Pearson correlation coefficients were used to assess model performance. Results: The 2D, 3D, and 2D-plus-3D ensemble models showed MAE values of 1.43, 2.55, and 1.77 months, respectively, on the internal test set, values of 2.26, 2.27, and 1.22 months on the first external test set, and values of 0.44, 0.27, and 0.31 months on the second external test set. The ensemble model outperformed the previous state-of-the-art model on the same external test set (MAE = 1.22 vs 2.09 months). Conclusion: The proposed deep learning model accurately predicted myelin maturation age using pediatric brain MRI scans and may help reduce the time needed to complete this task, as well as interobserver variability in radiologist predictions.Keywords: Pediatrics, MR Imaging, CNS, Brain/Brain Stem, Convolutional Neural Network (CNN), Artificial Intelligence, Pediatric Imaging, Myelin Maturation, Brain MRI, Neuroradiology Supplemental material is available for this article. © RSNA, 2023.
ABSTRACT
BACKGROUND: The prognostic role of tumor-related parameters in diffuse large B cell lymphoma (DLBCL) is a matter of controversy. METHODS: We investigated the prognostic value of phenotypic and genotypic profiles in DLBCL in clinical trial (NCT00544219) patients homogenously treated with six cycles of rituximab, cyclophosphamide, hydroxydaunorubicin, vincristine, prednisone (R-CHOP), followed by two cycles of R (R-CHOP-14). The primary endpoint was event-free survival at 2 years (EFS). Secondary endpoints were progression-free (PFS) and overall survival (OS). Immunohistochemical (bcl2, bcl6, CD5, CD10, CD20, CD95, CD168, cyclin E, FOXP1, GCET, Ki-67, LMO2, MUM1p, pSTAT3) and in situ hybridization analyses (BCL2 break apart probe, C-MYC break apart probe and C-MYC/IGH double-fusion probe, and Epstein-Barr virus probe) were performed and correlated with the endpoints. RESULTS: One hundred twenty-three patients (median age 58 years) were evaluable. Immunohistochemical assessment succeeded in all cases. Fluorescence in situ hybridization was successful in 82 instances. According to the Tally algorithm, 81 cases (66%) were classified as non-germinal center (GC) DLBCL, while 42 cases (34%) were GC DLBCL. BCL2 gene breaks were observed in 7/82 cases (9%) and C-MYC breaks in 6/82 cases (8%). "Double-hit" cases with BCL2 and C-MYC rearrangements were not observed. Within the median follow-up of 53 months, there were 51 events, including 16 lethal events and 12 relapses. Factors able to predict worse EFS in univariable models were failure to achieve response according to international criteria, failure to achieve positron emission tomography response (p < 0.005), expression of CD5 (p = 0.02), and higher stage (p = 0.021). Factors predicting inferior PFS were failure to achieve response according to international criteria (p < 0.005), higher stage (p = 0.005), higher International Prognostic Index (IPI; p = 0.006), and presence of either C-MYC or BCL2 gene rearrangements (p = 0.033). Factors predicting inferior OS were failure to achieve response according to international criteria and expression of FOXP1 (p < 0.005), cyclin E, CD5, bcl2, CD95, and pSTAT3 (p = 0.005, 0.007, 0.016, and 0.025, respectively). Multivariable analyses revealed that expression of CD5 (p = 0.044) and FOXP1 (p = 0.004) are independent prognostic factors for EFS and OS, respectively. CONCLUSION: Phenotypic studies with carefully selected biomarkers like CD5 and FOXP1 are able to prognosticate DLBCL course at diagnosis, independent of stage and IPI and independent of response to R-CHOP.
