Deep-Learning Detection of Cancer Metastases to the Brain on MRI

被引:79
作者
Zhang, Min [1 ]
Young, Geoffrey S. [1 ]
Chen, Huai [1 ,2 ]
Li, Jing [1 ,3 ]
Qin, Lei [4 ]
McFaline-Figueroa, J. Ricardo [5 ]
Reardon, David A. [4 ]
Cao, Xinhua [6 ]
Wu, Xian [7 ]
Xu, Xiaoyin [1 ]
机构
[1] Harvard Med Sch, Brigham & Womens Hosp, Dept Radiol, 75 Francis St, Boston, MA 02115 USA
[2] Guangzhou Med Univ, Affiliated Hosp 1, Dept Radiol, Guangzhou, Guangdong, Peoples R China
[3] Zhengzhou Univ, Henan Canc Hosp, Affiliated Hosp, Dept Radiol, Zhengzhou, Henan, Peoples R China
[4] Harvard Med Sch, Dana Farber Canc Inst, Dept Radiol, Boston, MA 02115 USA
[5] Harvard Med Sch, Dana Farber Canc Inst, Ctr Neurooncol, Boston, MA 02115 USA
[6] Harvard Med Sch, Boston Childrens Hosp, Dept Radiol, Boston, MA 02115 USA
[7] Tsinghua Univ, Dept Comp Sci & Technol, Beijing, Peoples R China
基金
美国国家卫生研究院;
关键词
brain metastases; deep learning; Faster R-CNN; RUSBoost; COMPUTER-AIDED DETECTION; STEREOTACTIC RADIOSURGERY; WHOLE-BRAIN; TUMORS; MANAGEMENT; CLASSIFICATION; SINGLE; IMAGES; CNN;
D O I
10.1002/jmri.27129
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Background Approximately one-fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective. Purpose To develop a deep-learning-based approach for finding brain metastasis on MRI. Study Type Retrospective. Sequence Axial postcontrast 3D T-1-weighted imaging. Field Strength 1.5T and 3T. Population A total of 361 scans of 121 patients were used to train and test the Faster region-based convolutional neural network (Faster R-CNN): 1565 lesions in 270 scans of 73 patients for training; 488 lesions in 91 scans of 48 patients for testing. From the 48 outputs of Faster R-CNN, 212 lesions in 46 scans of 18 patients were used for training the RUSBoost algorithm (MatLab) and 276 lesions in 45 scans of 30 patients for testing. Assessment Two radiologists diagnosed and supervised annotation of metastases on brain MRI as ground truth. This data were used to produce a 2-step pipeline consisting of a Faster R-CNN for detecting abnormal hyperintensity that may represent brain metastasis and a RUSBoost classifier to reduce the number of false-positive foci detected. Statistical Tests The performance of the algorithm was evaluated by using sensitivity, false-positive rate, and receiver's operating characteristic (ROC) curves. The detection performance was assessed both per-metastases and per-slice. Results Testing on held-out brain MRI data demonstrated 96% sensitivity and 20 false-positive metastases per scan. The results showed an 87.1% sensitivity and 0.24 false-positive metastases per slice. The area under the ROC curve was 0.79. Conclusion Our results showed that deep-learning-based computer-aided detection (CAD) had the potential of detecting brain metastases with high sensitivity and reasonable specificity. Level of Evidence 3 Technical Efficacy Stage 2
引用
收藏
页码:1227 / 1236
页数:10
相关论文
共 50 条
  • [41] Deep-learning single-shot detector for automatic detection of brain metastases with the combined use of contrast-enhanced and non-enhanced computed tomography images
    Takao, Hidemasa
    Amemiya, Shiori
    Kato, Shimpei
    Yamashita, Hiroshi
    Sakamoto, Naoya
    Abe, Osamu
    EUROPEAN JOURNAL OF RADIOLOGY, 2021, 144
  • [42] Deep learning for lungs cancer detection: a review
    Javed, Rabia
    Abbas, Tahir
    Khan, Ali Haider
    Daud, Ali
    Bukhari, Amal
    Alharbey, Riad
    ARTIFICIAL INTELLIGENCE REVIEW, 2024, 57 (08)
  • [43] Mammography with deep learning for breast cancer detection
    Wang, Lulu
    FRONTIERS IN ONCOLOGY, 2024, 14
  • [44] Automated Detection and Segmentation of Brain Metastases in Malignant Melanoma: Evaluation of a Dedicated Deep Learning Model
    Pennig, L.
    Shahzad, R.
    Caldeira, L.
    Lennartz, S.
    Thiele, F.
    Goertz, L.
    Zopfs, D.
    Meissner, A-K
    Fuertjes, G.
    Perkuhn, M.
    Kabbasch, C.
    Grau, S.
    Borggrefe, J.
    Laukamp, K. R.
    AMERICAN JOURNAL OF NEURORADIOLOGY, 2021, 42 (04) : 655 - 662
  • [45] Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions
    Akkus, Zeynettin
    Galimzianova, Alfiia
    Hoogi, Assaf
    Rubin, Daniel L.
    Erickson, Bradley J.
    JOURNAL OF DIGITAL IMAGING, 2017, 30 (04) : 449 - 459
  • [46] Early cancer detection using deep learning and medical imaging: A survey
    Ahmad, Istiak
    Alqurashi, Fahad
    CRITICAL REVIEWS IN ONCOLOGY HEMATOLOGY, 2024, 204
  • [47] MRI pulse sequence integration for deep-learning-based brain metastases segmentation
    Yi, Darvin
    Grovik, Endre
    Tong, Elizabeth
    Iv, Michael
    Emblem, Kyrre Eeg
    Nilsen, Line Brennhaug
    Saxhaug, Cathrine
    Latysheva, Anna
    Jacobsen, Kari Dolven
    Helland, Aslaug
    Zaharchuk, Greg
    Rubin, Daniel
    MEDICAL PHYSICS, 2021, 48 (10) : 6020 - 6035
  • [48] Predicting survival after radiosurgery in patients with lung cancer brain metastases using deep learning of radiomics and EGFR status
    Liao, Chien-Yi
    Lee, Cheng-Chia
    Yang, Huai-Che
    Chen, Ching-Jen
    Chung, Wen-Yuh
    Wu, Hsiu-Mei
    Guo, Wan-Yuo
    Liu, Ren-Shyan
    Lu, Chia-Feng
    PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE, 2023, 46 (02) : 585 - 596
  • [49] Annotation-free deep-learning framework for microcalcifications detection on mammograms
    Terrassin, Paul
    Tardy, Mickael
    Lauzeral, Nathan
    Normand, Nicolas
    COMPUTER-AIDED DIAGNOSIS, MEDICAL IMAGING 2024, 2024, 12927
  • [50] A lightweight deep-learning model for parasite egg detection in microscopy images
    Xu, Wenbin
    Zhai, Qiang
    Liu, Jizhong
    Xu, Xingyu
    Hua, Jing
    PARASITES & VECTORS, 2024, 17 (01):