To develop a convolutional neural network (CNN) algorithm that can predict the molecular subtype of a breast cancer based on MRI features. An IRB-approved study was performed in 216 patients with available pre-treatment MRIs and immunohistochemical staining pathology data. First post-contrast MRI images were used for 3D segmentation using 3D slicer. A CNN architecture was designed with 14 layers. Residual connections were used in the earlier layers to allow stabilization of gradients during backpropagation. Inception style layers were utilized deeper in the network to allow learned segregation of more complex feature mappings. Extensive regularization was utilized including dropout, L2, feature map dropout, and transition layers. The class imbalance was addressed by doubling the input of underrepresented classes and utilizing a class sensitive cost function. Parameters were tuned based on a 20% validation group. A class balanced holdout set of 40 patients was utilized as the testing set. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. Seventy-four luminal A, 106 luminal B, 13 HER2+, and 23 basal breast tumors were evaluated. Testing set accuracy was measured at 70%. The class normalized macro area under receiver operating curve (ROC) was measured at 0.853. Non-normalized microaggregated AUC was measured at 0.871, representing improved discriminatory power for the highly represented Luminal A and Luminal B subtypes. Aggregate sensitivity and specificity was measured at 0.603 and 0.958. MRI analysis of breast cancers utilizing a novel CNN can predict the molecular subtype of breast cancers. Larger data sets will likely improve our model.
Objective Cochlear implantation is associated with poor music perception and enjoyment. Reducing music complexity has been shown to enhance music enjoyment in cochlear implant (CI) recipients. In this study, we assess the impact of harmonic series reduction on music enjoyment. Study Design Prospective analysis of music enjoyment in normal-hearing (NH) individuals and CI recipients. Setting Single tertiary academic medical center. Patients NH adults (N=20) and CI users (N=8) rated the Happy Birthday song on three validated enjoyment modalities–musicality, pleasantness, and naturalness. Intervention Subjective rating of music excerpts. Main outcome measures Participants listened to seven different instruments play the melody, each with five levels of harmonic reduction (Full|F3+F2+F1+F0|F2+F1+F0|F1+F0|F0). NH participants listened to the segments both with and without CI simulation. Linear mixed effect models (LME) and likelihood ratio tests were used to assess the impact of harmonic reduction on enjoyment. Results NH listeners without simulation rated segments with the first four harmonics (F3+F2+F1+F0) most pleasant and natural (p<0.001|p=0.004). NH listeners with simulation rated the first harmonic alone (F0) most pleasant and natural (p<0.001|p=0.003). Their ratings demonstrated a positive linear relationship between harmonic reduction and both pleasantness (slope estimate=0.030|SE=0.004|p<0.001|LME) and naturalness (slope estimate=0.012|SE=0.003|p=0.003|LME). CI recipients also found the first harmonic alone (F0) to be most pleasant (p=0.003), with a positive linear relationship between harmonic reduction and pleasantness (slope estimate=0.029|SE=0.008|p<0.001|LME). Conclusions Harmonic series reduction increases music enjoyment in CI and NH individuals with or without CI simulation. Therefore, minimization of the harmonics may be a useful strategy for enhancing musical enjoyment among both NH and CI listeners.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.