Deep learning classification of inverted papilloma malignant transformation using 3D convolutional neural networks and magnetic resonance imaging.
George S LiuAngela YangDayoung KimAndrew HojelDiana VoevodskyJulia WangCharles C L TongHeather UngererJames N PalmerMichael A KohanskiJayakar V NayakPeter H HwangNithin D AdappaZara M PatelPublished in: International forum of allergy & rhinology (2022)
A deep learning approach with 3-dimensional CNNs can distinguish IP and IP-SCC with moderate test classification performance. Although CNNs demonstrate promise to enhance the prediction of IP-SCC using MRIs, more data are needed before they can reach the predictive value already established by human MRI evaluation.