Filtering normal papanicolaou smear with multi-instance learning

Filtering normal papanicolaou smear using computer-aided system can help clinical doctors to detect cervical cancer. In this paper, we propose a scheme to classify cervical cells as normal or abnormal. The pipeline includes preprocessing, perinuclear area extraction, feature extraction and multi-ins...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2016 IEEE International Conference on Signal and Image Processing (ICSIP) S. 113 - 117
Hauptverfasser: Jie Wang, Xun Liu, Yunjie Chen, Yuan Liu, Lei Pan, Huijuan Zhang, Xiang Ji, Su Zhang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.08.2016
Schlagworte:
Cervical cancer
Classification algorithms
Feature extraction
Manuals
multi-instance learning(MIL)
papanicolaou smear
Pathology
Pipelines
stacked sparse autoencoder(SSAE)
textural features
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Filtering normal papanicolaou smear using computer-aided system can help clinical doctors to detect cervical cancer. In this paper, we propose a scheme to classify cervical cells as normal or abnormal. The pipeline includes preprocessing, perinuclear area extraction, feature extraction and multi-instance learning (MIL). We tried and compared several feature extraction methods, including textural features, manual features and Stacked sparse autoencoder(SSAE) self-learned features. In multi-instance learning, we modify softmax classifier to be adequate for our problem besides some classic MIL algorithms. The results show that manual features or SSAE with modified softmax achieve the best performance and are recognized by clinical pathology doctors.
DOI:10.1109/SIPROCESS.2016.7888234