Generation of Virtual Dual Energy Images from Standard Single-Shot Radiographs Using Multi-scale and Conditional Adversarial Network

Abstract

Dual-energy (DE) chest radiographs provide greater diagnostic information than standard radiographs by separating the image into bone and soft tissue, revealing suspicious lesions which may otherwise be obstructed from view. However, acquisition of DE images requires two physical scans, necessitating specialized hardware and processing, and images are prone to motion artifact. Generation of virtual DE images from standard, single-shot chest radiographs would expand the diagnostic value of standard radiographs without changing the acquisition procedure. We present a Multi-scale Conditional Adversarial Network (MCA-Net) which produces high-resolution virtual DE bone images from standard, single-shot chest radiographs. Our proposed MCA-Net is trained using the adversarial network so that it learns sharp details for the production of high-quality bone images. Then, the virtual DE soft tissue image is generated by processing the standard radiograph with the virtual bone image using a cross projection transformation. Experimental results from 210 patient DE chest radiographs demonstrated that the algorithm can produce high-quality virtual DE chest radiographs. Important structures were preserved, such as coronary calcium in bone images and lung lesions in soft tissue images. The average structure similarity index and the peak signal to noise ratio of the produced bone images in testing data were 96.4 and 41.5, which are significantly better than results from previous methods. Furthermore, our clinical evaluation results performed on the publicly available dataset indicates the clinical values of our algorithms. Thus, our algorithm can produce high-quality DE images that are potentially useful for radiologists, computer-aided diagnostics, and other diagnostic tasks.

The detection of lung cancer using MTANN (Massive Training Artificial Neural Network) based soft tissue technique

“…However, there were problems such as high radiation dose and motion artifacts due to double exposure with different energies. This problem had been addressed by using deep learning [25] .Deep Learning has assumed that there was a nonlinear relationship between dual energy image. If the nonlinear relationship was deduced using deep learning, a dual energy image could be generated from single energy chest radiography without double exposures.…”

“…If the nonlinear relationship was deduced using deep learning, a dual energy image could be generated from single energy chest radiography without double exposures. They had utilized chest radiograms in training (lung image database consortium (LIDC-IDRI)) database [25]. Their training data utilized in this study were a single energy and dual energy chest radiogram pair.…”

“…The virtual dual energy [25] bone free chest radiogram was obtained by subtracting the predicted dual energy soft tissue free chest radiograms from the conventional single energy chest radiogram. Kenji Suzuki developed pixel based device mechanism using medical image processing which avoids error caused by inaccurate feature calculation and segmentation while classifying objects into certain classes [26].Takeshi Kobayashi, Xin-Wei Xu, Heber MacMahon, Charles E. Metz, Kunio Doi evaluate the consequence on nodule output by utilizing ROC analysis with two diverse techniques involved in computer aided diagnosis scheme [27].…”

Synthesizing Multi-Tracer PET Images for Alzheimer's Disease Patients using a 3D Unified Anatomy-aware Cyclic Adversarial Network

“…As 11 C-UCB-J reflects the neural synaptic density, 18 F-FDG reflects the cell metabolism (high activities at the neural synapse) and 11 C-PiB reflecting the neural growth/repair activities, the PET images from these three tracers are correlated which post the possibility to predict one tracer image from another tracer image. With the recent advances in deep learning based image translation techniques [9,10], these techniques have been widely utilized in medical imaging for translation between individual modalities and individual acquisition protocols, such as MR-PET [11], DR-DE [12], and PET-PET [13]. Even though similar strategies can be utilized for synthesizing multi-tracer PET images from single-tracer PET image, it will result in the need for training large amount of one-to-one domain translation model (A 2 n = n × (n − 1)) and leaving features learned from multiple domain under-utilized.…”

Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition

“…Existing approaches to X-ray image decomposition are supervised, requiring paired original and decomposed images in training. For example, the paired dual energy (DE) imaging is always needed for supervised bone suppression and serves as the learning targets of neural networks [8,10]. DE radiography provides bone-free CXR by capturing two radiographs at two energy levels.…”