@inproceedings{479340f1e8674d72965133bd5ced6e75,
title = "Multimodal deep learning for cervical dysplasia diagnosis",
abstract = "To improve the diagnostic accuracy of cervical dysplasia,it is important to fuse multimodal information collected during a patient{\textquoteright}s screening visit. However,current multimodal frameworks suffer from low sensitivity at high specificity levels,due to their limitations in learning correlations among highly heterogeneous modalities. In this paper,we design a deep learning framework for cervical dysplasia diagnosis by leveraging multimodal information. We first employ the convolutional neural network (CNN) to convert the low-level image data into a feature vector fusible with other non-image modalities. We then jointly learn the non-linear correlations among all modalities in a deep neural network. Our multimodal framework is an end-to-end deep network which can learn better complementary features from the image and non-image modalities. It automatically gives the final diagnosis for cervical dysplasia with 87.83% sensitivity at 90% specificity on a large dataset,which significantly outperforms methods using any single source of information alone and previous multimodal frameworks.",
author = "Tao Xu and Han Zhang and Xiaolei Huang and Shaoting Zhang and Metaxas, {Dimitris N.}",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.",
year = "2016",
doi = "10.1007/978-3-319-46723-8_14",
language = "English (US)",
isbn = "9783319467221",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "115--123",
editor = "Gozde Unal and Sebastian Ourselin and Leo Joskowicz and Sabuncu, {Mert R.} and William Wells",
booktitle = "Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016 - 19th International Conference, Proceedings",
address = "Germany",
}