AI-Based Cancer Detection Model for Contrast-Enhanced Mammography

被引:6
|
作者
Jailin, Clement [1 ]
Mohamed, Sara [1 ]
Iordache, Razvan [1 ]
De Carvalho, Pablo Milioni [1 ]
Ahmed, Salwa Yehia [2 ]
Sattar, Engy Abdullah Abdel [2 ]
Moustafa, Amr Farouk Ibrahim [2 ,3 ]
Gomaa, Mohammed Mohammed [2 ,3 ]
Kamal, Rashaa Mohammed [2 ,4 ]
Vancamberg, Laurence [1 ]
机构
[1] GE Healthcare, 283 Rue Miniere, F-78530 Buc, France
[2] Baheya Fdn Early Detect &Treatment Breast Canc, El Haram, Giza, Egypt
[3] Cairo Univ, NCI, 1 Kasr Elainy St Fom Elkalig, Cairo 11511, Egypt
[4] Cairo Univ, Kasr El Ainy Hosp, Radiol Dept, Cairo 11511, Egypt
来源
BIOENGINEERING-BASEL | 2023年 / 10卷 / 08期
关键词
contrast-enhanced mammography; breast cancer; cancer detection; deep learning; computer aided detection;
D O I
10.3390/bioengineering10080974
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Background: The recent development of deep neural network models for the analysis of breast images has been a breakthrough in computer-aided diagnostics (CAD). Contrast-enhanced mammography (CEM) is a recent mammography modality providing anatomical and functional imaging of the breast. Despite the clinical benefits it could bring, only a few research studies have been conducted around deep-learning (DL) based CAD for CEM, especially because the access to large databases is still limited. This study presents the development and evaluation of a CEM-CAD for enhancing lesion detection and breast classification. Materials & Methods: A deep learning enhanced cancer detection model based on a YOLO architecture has been optimized and trained on a large CEM dataset of 1673 patients (7443 images) with biopsy-proven lesions from various hospitals and acquisition systems. The evaluation was conducted using metrics derived from the free receiver operating characteristic (FROC) for the lesion detection and the receiver operating characteristic (ROC) to evaluate the overall breast classification performance. The performances were evaluated for different types of image input and for each patient background parenchymal enhancement (BPE) level. Results: The optimized model achieved an area under the curve (AUROC) of 0.964 for breast classification. Using both low-energy and recombined image as inputs for the DL model shows greater performance than using only the recombined image. For the lesion detection, the model was able to detect 90% of all cancers with a false positive (non-cancer) rate of 0.128 per image. This study demonstrates a high impact of BPE on classification and detection performance. Conclusion: The developed CEM CAD outperforms previously published papers and its performance is comparable to radiologist-reported classification and detection capability.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] Contrast-Enhanced Digital Mammography in the Surgical Management of Breast Cancer
    Ali-Mucheru, Mariam
    Patel, Bhavika
    Pockaj, Barbara
    Pizzitola, Victor
    Wasif, Nabil
    Stucky, Chee-Chee
    Gray, Richard
    ANNALS OF SURGICAL ONCOLOGY, 2016, 23 : 14 - 15
  • [22] Contrast-Enhanced Digital Mammography in the Surgical Management of Breast Cancer
    Ali-Mucheru, Mariam
    Pockaj, Barbara
    Patel, Bhavika
    Pizzitola, Victor
    Wasif, Nabil
    Stucky, Chee-Chee
    Gray, Richard
    ANNALS OF SURGICAL ONCOLOGY, 2016, 23 : S649 - S655
  • [23] Advancing radiomics from contrast-enhanced mammography in breast cancer
    Wu, Xuewei
    Ling, Ye
    Zhang, Shuixing
    Zhang, Bin
    BRITISH JOURNAL OF CANCER, 2025, 132 (02) : 154 - 155
  • [24] Contrast-Enhanced Digital Mammography in the Surgical Management of Breast Cancer
    Mariam Ali-Mucheru
    Barbara Pockaj
    Bhavika Patel
    Victor Pizzitola
    Nabil Wasif
    Chee-Chee Stucky
    Richard Gray
    Annals of Surgical Oncology, 2016, 23 : 649 - 655
  • [25] The feasibility of contrast-enhanced spectral mammography immediately after contrast-enhanced CT
    Okada, Nobuko
    Tatsugami, Fuminari
    Sugai, Mai
    Okita, Izumi
    Ito, Mitsuya
    Ohtani, Shoichiro
    Ichimura, Kouichi
    Urashima, Masaki
    Awai, Kazuo
    RADIOLOGICAL PHYSICS AND TECHNOLOGY, 2019, 12 (03) : 277 - 282
  • [26] The feasibility of contrast-enhanced spectral mammography immediately after contrast-enhanced CT
    Nobuko Okada
    Fuminari Tatsugami
    Mai Sugai
    Izumi Okita
    Mitsuya Ito
    Shoichiro Ohtani
    Kouichi Ichimura
    Masaki Urashima
    Kazuo Awai
    Radiological Physics and Technology, 2019, 12 : 277 - 282
  • [27] Contrast-Enhanced Mammography: A Scientific Review
    Lewin, John M.
    Patel, Bhavika K.
    Tanna, Aneri
    JOURNAL OF BREAST IMAGING, 2020, 2 (01) : 7 - 15
  • [28] Contrast-enhanced spectral mammography (CESM)
    James, J. J.
    Tennant, S. L.
    CLINICAL RADIOLOGY, 2018, 73 (08) : 715 - 723
  • [29] An Observer Model for Lesion Detectability in Contrast-Enhanced Digital Mammography
    Hill, Melissa L.
    Mainprize, James G.
    Yaffe, Martin J.
    DIGITAL MAMMOGRAPHY, 2010, 6136 : 720 - +
  • [30] Contrast-enhanced digital mammography and angiogenesis
    Rosado-Mendez, I.
    Palma, B. A.
    Villasenor, Y.
    Benitez-Bribiesca, L.
    Brandan, M. E.
    NUCLEAR PHYSICS METHODS AND ACCELERATORS IN BIOLOGY AND MEDICINE, 2007, 958 : 278 - +