Name
Title | ||
|---|---|---|
Learning From Weakly-Labeled Clinical Data For Automatic Thyroid Nodule Classification In Ultrasound Images |
Abstract | ||
|---|---|---|
This paper proposes a semi-supervised learning method based on weakly-labeled data to automatically classify ultrasound (US) thyroid nodules. Key to our new approach is the unification of multi-instance learning (MIL) with deep learning. Benefiting from that, our method can directly use off-the-shelf clinical data, which involves no labels to indicate nodule classes. To this end, we take the US images of a patient as a bag, and take the corresponding pathology report as the bag label. Specifically, we first propose a bag generating method, wherein the detected thyroid nodules are considered as instances corresponding to certain bag. After that, we design an effective EM algorithm to train a convolutional neural network (CNN) for nodule classification. We conduct extensive experiments and comprehensive evaluations on different datasets, and all the experiments confirm that, our method significantly outperforms state-of-the-art MIL algorithms, which exhibits great potential in clinical applications. |
Year | Venue | Keywords |
|---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Weakly-labeled data, Multi-instance learning (MIL), Convolutional neural network (CNN), Thyroid ultrasound image, Automatic nodule classification |
Field | DocType | ISSN |
Pattern recognition,Computer science,Convolutional neural network,Expectation–maximization algorithm,Medical imaging,Feature extraction,Artificial intelligence,Deep learning,Thyroid nodules,Ultrasonic imaging,Ultrasound | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jianxiong Wang | 1 | 0 | 0.34 |
| Shuai Li | 2 | 175 | 31.37 |
| Wenfeng Song | 3 | 9 | 5.22 |
| Hong Qin | 4 | 2120 | 184.31 |
| Bo Zhang | 5 | 0 | 0.34 |
| Aimin Hao | 6 | 183 | 40.57 |