Rib suppression in frontal chest radiographs: A blind source separation approach

Rasheed, Tahir; Ahmed, Bilal; Khan, Md. Ashfaquzzaman; Bettayeb, Maâmar; Lee, Sungyoung; Kim, Tae‐Seong

doi:10.1109/isspa.2007.4555516

Cited by 12 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[18] proposed a clavicle suppression algorithm which works by first generating a bone image from a gradient map modified along the bone border direction and then creating a soft-tissue image by subtraction of the bone image from the standard image. Later, [19,20] proposed blind-source signal separation algorithms for suppression of bone structures in standard chest radiography. [4] presented a ribcage segmentation algorithm based on Active Appearance Model that can accurately estimate the rib border and suppress the bone signal from standard radiography based on this prediction.…”

Section: Related Workmentioning

confidence: 99%

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

Zhou

Lin

Eck

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Zhou

Lin

Eck

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

show abstract

“…Malah ia masih digunakan secara meluas kerana kos yang rendah, penggunaan yang mudah dan radiasi yang rendah, dianggarkan 100 kali lebih rendah daripada CT (Rasheed et al 2007). Kajian awal telah dibangunkan menggunakan 60 imej x-ray yang terdiri daripada lima bahagian anggota badan yang berlainan iaitu dada, abdomen, pinggul, lutut dan pergelangan kaki, seperti yang ditunjukkan dalam Rajah 2.…”

Section: Pangkalan Data Imejunclassified

Content-based Image Retrieval for Medical Application

Zaki¹,

Ahmad²,

Hussain³

et al. 2018

JKUKM

View full text Add to dashboard Cite

ABSTRAK Dapatan semula imej (DSI) adalah sistem pencarian imej yang menggunakan ciri-ciri tertentu atau konteks khusus Kata kunci: Imej perubatan; sistem dapatan semula imej; aplikasi perubatan; modaliti x-ray; TBIRS ABSTRACT Image retrieval is an image searching system that uses certain characteristics or context in an image. In a medical field, image retrieval system has been used to provide the needed correct images to the physicians while the diagnosis and treatment process is being conducted. The earlier image retrieval system was a text-based image retrieval system (TBIRS) which using keyword for the image context and it requires human's help to manually make text annotation on the images. This system is still being widely used in the hospitals nowadays. The text annotation process is a laborious task especially when dealing with a huge database and is prone to human errors. To overcome the aforementioned issues, the approach of a content-based image retrieval system (CBIRS) with automatic indexing using visual features such as color

show abstract

“…The unsupervised method finds bone targets and then removes them from CXR [6], [7]. Clavicle and ribs can be modeled as the elongated structures and high gradient edges [2], [12]. Blind source separation techniques or gradient modification are used to remove the bone structures from CXRs [2], [6], [12].…”

Section: Introductionmentioning

confidence: 99%

Bone Suppression of Chest Radiographs With Cascaded Convolutional Networks in Wavelet Domain

et al. 2019

View full text Add to dashboard Cite

Bone suppression of chest radiographs (CXRs) is potentially useful for diagnosing lung diseases for radiologists and computer-aided diagnosis. This paper presents a cascaded convolutional network model in wavelet domain (Wavelet-CCN) for bone suppression in single conventional CXR. Wavelet coefficients are sparse and suitable as the output of convolutional network. The convolutional networks are trained to predict the wavelet coefficients of bone images from the wavelet coefficients of CXRs, using real two-exposure dual energy subtraction (DES) CXRs as training data. By combining the multilevel wavelet decomposition and a cascaded refinement framework, the Wavelet-CCN model can work automatically with a multi-scale approach and progressively refine the prediction in terms of accuracy and spatial resolution. Compared with previous work of CamsNet model which preforms bone prediction in gradient domain, the Wavelet-CCN model predicts the wavelet coefficients to reconstruct bone images and can avoid the inconsistent background intensity caused by 2D integration of gradients. The predicted bone image is subtracted from the original CXR to produce a soft-tissue image. The Wavelet-CCN model and its variants with different wavelet basis are evaluated on a dataset that consists of 504 cases of real two-exposure DES CXRs (404 cases for training and 100 cases for test). Experimental results show that among all the variants and different wavelet bases, the Wavelet-CCN model with Haar wavelet performs best. The average peak signal-to-noise ratio and structural similarity index of the soft-tissue images produced by the proposed Wavelet-CCN model are both higher than those of the previous CamsNet model in gradient domain, reaching values of 39.4 (±0.94) dB and 0.977 (±0.004), respectively. The results also demonstrate that the Wavelet-CCN model can process the CXRs acquired by four types of X-ray machines. INDEX TERMS Bone suppression, convolutional networks, chest radiographs, wavelet transform.

show abstract

Rib suppression in frontal chest radiographs: A blind source separation approach

Abstract: ABSTRACT

Cited by 12 publications

References 14 publications

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

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

Content-based Image Retrieval for Medical Application

Bone Suppression of Chest Radiographs With Cascaded Convolutional Networks in Wavelet Domain

Contact Info

Product

Resources

About