HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Multi-tasking Siamese networks for breast mass detection using dual-view mammogram matching

Yutong Yan 1, 2 Pierre-Henri Conze 3, 1 Mathieu Lamard 2, 1 Gwenolé Quellec 4, 1 Béatrice Cochener 2, 5, 1 Gouenou Coatrieux 3, 1
1 LaTIM - Laboratoire de Traitement de l'Information Medicale
2 UBO - Université de Brest
3 IMT Atlantique - ITI - Département lmage et Traitement Information
4 INSERM - Institut National de la Santé et de la Recherche Médicale
5 CHRU Brest - Centre Hospitalier Régional Universitaire de Brest
Abstract : In clinical practice, radiologists use multiple views of routine mammograms for breast cancer screening. Similarly, computer-aided diagnosis (CAD) systems could be enhanced by integrating information arising from pairs of views. In this work, we present a new multi-tasking framework that combines craniocaudal (CC) and mediolateral-oblique (MLO) mammograms. We exploit multi-tasking properties of deep networks to jointly learn mass matching and classification, towards better detection performance. A combined Siamese model that includes patch-level mass classification and dual-view mass matching is used to take full advantage of multi-view information. This network is exploited in a full image detection pipeline based on You-Only-Look-Once (YOLO) region proposals. Experiments highlight the benefits of dual-view analysis for both patch-level classification and examination-level detection scenarios. Our pipeline outperforms conventional single-task deep models with 94.78% as Area Under the Curve (AUC) score and a classification accuracy of 0.8791. Additionally to these gains, our method further guides clinicians by providing accurate multi-view mass correspondences. This suggests that it could act as a relevant automatic second opinion for mammogram interpretation and breast cancer diagnosis.
Keywords : breast cancer mass detection dual-view mammogram matching information fusion deep learning computer-aided diagnosis
Document type :
Conference papers
Complete list of metadata
https://hal-imt-atlantique.archives-ouvertes.fr/hal-02913535
Contributor : Pierre-Henri Conze Connect in order to contact the contributor
Submitted on : Sunday, August 9, 2020 - 8:43:15 PM
Last modification on : Monday, April 4, 2022 - 9:28:21 AM

Identifiers

Collections

IMT-ATLANTIQUE | UNIV-BREST | LATIM | IBSAM | INSTITUT-TELECOM

Citation

Yutong Yan, Pierre-Henri Conze, Mathieu Lamard, Gwenolé Quellec, Béatrice Cochener, et al.. Multi-tasking Siamese networks for breast mass detection using dual-view mammogram matching. MLMI 2020 : International Workshop on Machine Learning in Medical Imaging, Oct 2020, Lima, Peru. pp.312-321, ⟨10.1007/978-3-030-59861-7_32⟩. ⟨hal-02913535⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

70