Deep Learning Classification of Breast Cancer Tissue from Terahertz Imaging Through Wavelet Synchro-Squeezed Transformation and Transfer Learning

Liu, Haoyan; Vohra, Nagma; Bailey, Keith; El-Shenawee, Magda; Nelson, Alexander

doi:10.1007/s10762-021-00839-x

Cited by 25 publications

(15 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of deep learning algorithms like the Convolutional Neural Networks (CNN) enables system complexity, robustness and multimodal capability [189]. The application of deep learning in this application has been explored in few studies such as [190] and [191]. The development of custom convolutional neural network (CNN) model and fine-tuned, pretrained CNN models capable of multimodal image classification have been proposed in our recent studies [189], [192].…”

Section: B Artificial Intelligence and Robotics In Thz Healthcarementioning

confidence: 99%

“…However, the accuracy and effectiveness of deep learning-based implementations in THz cancer imaging for these data driven explorations require huge datasets for training. Some challenges have already been faced in a deep learning study for THz breast cancer imaging by [190]. These challenges that caused erroneous classifications were found to be caused by pixels scattering near scan edges, lack of precise ground truth because of deformations during paraffin, formalin fixing.…”

Section: ) Challenges In Data Driven Thz Studiesmentioning

confidence: 99%

“…The overlapping electric properties in fat and muscle tissue as well as cancer and muscle make it difficult to differentiate the signals in THz scans and also it is a challenging task to classify artefacts that not related to tissue i.e. not part of the actual tissue [190].…”

Section: ) Challenges In Data Driven Thz Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Terahertz Imaging and Sensing for Healthcare: Current Status and Future Perspectives

Gezimati

Singh

2023

IEEE Access

View full text Add to dashboard Cite

There is a keen interest in the exploration of new generation emitters and detectors due to advancements in innovation of new materials and device processing technologies which have opened up new frontiers in the Terahertz (THz) spectrum. Therefore, it is necessary to review the developments in THz technology for healthcare applications, their impact, implications and prospects for ongoing research and development. This paper provides a broad overview of the current status and prospects of application of THz imaging and sensing for the healthcare domain. We present current knowledge, identify existing challenges for wide scale clinical adoption of THz systems and prospective opinions to facilitate research and development towards optimized and miniaturized THz systems and biosensors that provide real operational convenience through emerging trends. Firstly, we provide an overview of the THz imaging and sensing techniques that exploit properties of THz generation and detection with emphasis on terahertz time domain spectroscopy (THz-TDS) and THz Metamaterials. The mechanisms of tissue image contrast and the application of THz imaging and sensing for biomedical applications in particular, the cancer detection application is reported. Secondly, an outlook toward the advancements in THz technology in the interface of healthcare 4.0 and its enabling technologies is explored for next generation smart and connected healthcare systems. Third, we identify the merits and existing challenges in THz cancer imaging and sensing and suggest prospective opinions to pave way to ongoing and future research. Further, we discuss the recent advances in THz imaging development and the contribution of near-field techniques based on plasmonic, and resonance based metasurfaces, waveguides etc. for breaking the diffraction limit towards development of THz systems that are convenient for point of care. We bring researchers a roadmap for future research scope.

show abstract

Section: B Artificial Intelligence and Robotics In Thz Healthcarementioning

confidence: 99%

Section: ) Challenges In Data Driven Thz Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Terahertz Imaging and Sensing for Healthcare: Current Status and Future Perspectives

Gezimati

Singh

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2022.3174595, IEEE Access VOLUME XX, 2017 1`Transfer learning Classification of breast cancer tissue Liu et al[77]…”

mentioning

confidence: 99%

Machine Learning and Application in Terahertz Technology: A Review on Achievements and Future Challenges

Jiang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Terahertz (THz) radiation (0.1~10 THz) shows great potential in agricultural products detection, biomedical, and security inspection in recent years. Machine learning methods are widely used to support the user demand of higher efficiency and high prediction accuracy. The technological and key challenges of machine learning methods are for THz spectroscopy and image data preprocessing, reconstruction algorithms, and qualitative and quantitative analysis. In this paper, an exhaustive review of recent related works of THz detection and imaging techniques and machine learning methods are presented. The application of machine learning methods combined with THz technology in quality inspection of agricultural products, biomedical, security inspection, and materials science are highlighted. Challenges of machine learning methods for these applications are addressed. The development trend and future perspectives of THz technology are also discussed.INDEX TERMS terahertz spectrum, terahertz imaging, machine learning, agricultural products, detection application.

show abstract

“…Recently, deep learning has achieved impressive results in various fields, including THz imaging 30 . Deep learning has been applied to segmentation and classification tasks in THz images such as impurity detection in wheat 31,32 , breast cancer classification 33 , and heavy-metal detection in soils 34 . The low resolution problem of THz imaging can also be mitigated by deep learning based super-resolution techniques 35,36 .…”

mentioning

confidence: 99%

Deep learning for terahertz image denoising in nondestructive historical document analysis

Dutta

Root

Ullmann

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Historical documents contain essential information about the past, including places, people, or events. Many of these valuable cultural artifacts cannot be further examined due to aging or external influences, as they are too fragile to be opened or turned over, so their rich contents remain hidden. Terahertz (THz) imaging is a nondestructive 3D imaging technique that can be used to reveal the hidden contents without damaging the documents. As noise or imaging artifacts are predominantly present in reconstructed images processed by standard THz reconstruction algorithms, this work intends to improve THz image quality with deep learning. To overcome the data scarcity problem in training a supervised deep learning model, an unsupervised deep learning network (CycleGAN) is first applied to generate paired noisy THz images from clean images (clean images are generated by a handwriting generator). With such synthetic noisy-to-clean paired images, a supervised deep learning model using Pix2pixGAN is trained, which is effective to enhance real noisy THz images. After Pix2pixGAN denoising, 99% characters written on one-side of the Xuan paper can be clearly recognized, while 61% characters written on one-side of the standard paper are sufficiently recognized. The average perceptual indices of Pix2pixGAN processed images are 16.83, which is very close to the average perceptual index 16.19 of clean handwriting images. Our work has important value for THz-imaging-based nondestructive historical document analysis.

show abstract

Deep Learning Classification of Breast Cancer Tissue from Terahertz Imaging Through Wavelet Synchro-Squeezed Transformation and Transfer Learning

Cited by 25 publications

References 46 publications

Terahertz Imaging and Sensing for Healthcare: Current Status and Future Perspectives

Terahertz Imaging and Sensing for Healthcare: Current Status and Future Perspectives

Machine Learning and Application in Terahertz Technology: A Review on Achievements and Future Challenges

Deep learning for terahertz image denoising in nondestructive historical document analysis

Contact Info

Product

Resources

About