Detection of heterogeneity on multi-spectral transmission image based on multiple types of pseudo-color maps

Abstract In transmission imaging, there are many difficulties in identifying heterogeneity on multi-spectral transmission images due to the strong absorption and scattering of biological tissues. This paper combines the multi-wavelength fusion information with the Faster-RCNN model to achieve the heterogeneous detection on the multi-spectral fusion pseudo-color map. Firstly, the original multi-spectral transmission images of phantom are collected on the self-built experimental platform. Then, the gray-scale level of image is improved by modulation and frame accumulation technique. Thereby, fusion pseudo-color maps (fusion pseudo-color maps of original RGB and gradient image) with high quality are obtained. And by comparing the running time, mean average precision (mAP) and root mean square error (RMSE) of Faster-RCNN model, the optimal iteration times and learning rate of model are determined. Finally, the fusion pseudo-color maps used for testing are input into the best Faster-RCNN model to realize the heterogeneous detection. The results show that the Faster-RCNN model established in this paper can effectively identify 2, 4 and 7 different types of heterogeneity on multi-spectral images, respectively. And the best mAP detection results for 2, 4 and 7 heterogeneities are 97.65%, 96.78% and 97.04%, respectively. In conclusion, this paper achieves the detection of heterogeneity on multi-spectral transmission images by fusing high-quality multi-wavelength transmission images and the Faster-RCNN network model, which will promote the clinical application of transmission imaging in early screening of breast cancer.

[1]  Pengcheng Liu,et al.  Multilevel fusing paired visible light and near-infrared spectral images for face anti-spoofing , 2019, Pattern Recognit. Lett..

[2]  Ick Chan Kwon,et al.  Application of Near-Infrared Fluorescence Imaging Using a Polymeric Nanoparticle-Based Probe for the Diagnosis and Therapeutic Monitoring of Colon Cancer , 2011, Digestive Diseases and Sciences.

[3]  Roohie Naaz Mir,et al.  Saliency guided faster-RCNN (SGFr-RCNN) model for object detection and recognition , 2019, J. King Saud Univ. Comput. Inf. Sci..

[4]  Nikolaos C. Deliolanis,et al.  Multiparametric Cystoscopy for Detection of Bladder Cancer Using Real-time Multispectral Imaging. , 2020, European urology.

[5]  Xue Yang,et al.  Effect on measurement accuracy of transillumination using sawtooth-shaped-function optical signal. , 2016, The Review of scientific instruments.

[6]  Xue Yang,et al.  Assessment of spatial information for hyperspectral imaging of lesion , 2016, SPIE/COS Photonics Asia.

[7]  G. C. Langhout,et al.  Near-infrared fluorescence (NIRF) imaging in breast-conserving surgery: assessing intraoperative techniques in tissue-simulating breast phantoms. , 2011, European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology.

[8]  Woo Kyung Moon,et al.  Near-infrared photothermal therapy using EGFR-targeted gold nanoparticles increases autophagic cell death in breast cancer. , 2017, Journal of photochemistry and photobiology. B, Biology.

[9]  Yu-hong Zhang,et al.  Value of Ultrasonic Elastography and Conventional Ultrasonography in the Differential Diagnosis of Non-Mass-like Breast Lesions. , 2019, Ultrasound in medicine & biology.

[10]  Stephen Lin,et al.  Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning , 2014, IEEE Transactions on Biomedical Engineering.

[11]  E. Rutgers,et al.  Detection of extra-axillary lymph node involvement with FDG PET/CT in patients with stage II-III breast cancer. , 2010, European journal of cancer.

[12]  Jian Lian,et al.  Ocular multi-spectral imaging deblurring via regularization of mutual information , 2019, Pattern Recognit. Lett..

[13]  Shabana Urooj,et al.  Breast Cancer Detection Using PCPCET and ADEWNN: A Geometric Invariant Approach to Medical X-Ray Image Sensors , 2016, IEEE Sensors Journal.

[14]  Hao Chen,et al.  Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[15]  Gang Li,et al.  Optimum method of image acquisition using sawtooth-shaped-function optical signal to improve grey-scale resolution , 2016 .

[16]  Yuichi Motai,et al.  Elastographic Tomosynthesis From X-Ray Strain Imaging of Breast Cancer , 2019, IEEE Journal of Translational Engineering in Health and Medicine.

[17]  Ronald M. Summers,et al.  A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations , 2014, MICCAI.

[18]  Ling Lin,et al.  Employment of frame accumulation and shaped function for upgrading low-light-level image detection sensitivity. , 2012, Optics letters.

[19]  Y. Ueno,et al.  Enhancement of breast cancer on pre-treatment dynamic contrast-enhanced MRI using computer-aided detection is associated with response to neo-adjuvant chemotherapy. , 2018, Diagnostic and interventional imaging.

[20]  Juan Li,et al.  Clinicopathological and Ultrasonic Features of Triple-Negative Breast Cancers: A Comparison with Hormone Receptor-Positive/Human Epidermal Growth Factor Receptor-2-Negative Breast Cancers. , 2018, Ultrasound in medicine & biology.

[21]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[22]  K. S. Sim,et al.  Three-dimensional model reconstruction using surface interpolation with the interfacing of Hermite surface for breast cancer MRI imaging system , 2016, 2016 International Conference on Robotics, Automation and Sciences (ICORAS).

[23]  I. Olivotto,et al.  Diagnosis of Metachronous Contralateral Breast Cancer , 2001, The breast journal.

[24]  Steven C. H. Hoi,et al.  Face Detection using Deep Learning: An Improved Faster RCNN Approach , 2017, Neurocomputing.

[25]  Soumen Das,et al.  Near infra-red polymeric nanoparticle based optical imaging in Cancer diagnosis. , 2019, Journal of photochemistry and photobiology. B, Biology.

[26]  Nishchal K. Verma,et al.  Image Dehazing for Object Recognition using Faster RCNN , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[27]  B. Seo,et al.  Quantitative analysis of radiation dosage and image quality between digital breast tomosynthesis (DBT) with two-dimensional synthetic mammography and full-field digital mammography (FFDM). , 2019, Clinical imaging.

[28]  Mohamed Elhoseny,et al.  Multi-spectral and panchromatic image fusion approach using stationary wavelet transform and swarm flower pollination optimization for remote sensing applications , 2018, Future Gener. Comput. Syst..

[29]  R. Bosc,et al.  Impact of loco-regional treatment on metastatic breast cancer outcome: a review. , 2013, Critical reviews in oncology/hematology.

[30]  A. Arieno,et al.  Screening for dense breasts: digital breast tomosynthesis. , 2015, AJR. American journal of roentgenology.

[31]  Yang Yang,et al.  Fault point detection of IOT using multi-spectral image fusion based on deep learning , 2019, J. Vis. Commun. Image Represent..

[32]  Gang Li,et al.  Improving heterogeneous classification accuracy based on the MDFAT and the combination feature information of multi-spectral transmission images , 2019, Infrared Physics & Technology.

[33]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  William J. Phillips,et al.  Comparison of Framingham risk score and chest-CT identified coronary artery calcification in breast cancer patients to predict cardiovascular events. , 2019, International journal of cardiology.