Eliminating rib shadows in chest radiographic images providing diagnostic assistance

Ogul, Hasan; Oğul, Burçin Buket; Ağıldere, Ahmet Muhteşem; Bayrak, Tuncay; Sümer, Emre

doi:10.1016/j.cmpb.2015.12.006

Cited by 13 publications

(16 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The general approach is first extracting the rib pixels using an edge detection algorithm [25]. Then, the candidate rib pixels/lines are grouped into a complete rib boundary by applying a curve fitting technique [26], using a voting approach such as Hough transform [10, 27], or applying a geometric model such as parabolas [28, 29, 30, 7] or ellipses [31]. Although extracting the rib borders with an edge detection algorithm is a well-known approach, these algorithms produce spurious edges at the apex of the lung due to overlapping bone structures.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In [9] the bone-like structures are extracted by applying regression filters learned from the training data. In [7], authors first delineate the rib-bone candidates with parabola curve fitting, and then the delineated ribs are suppressed using an unsupervised regression model which also takes into account the proximal thickness of bone.…”

Section: Literature Reviewmentioning

confidence: 99%

“…On a typical CXR, the bone structures overlap with the lung tissue due to the 2D projection of the chest. The ribcage causes a cross-hatching pattern on the lung region, which misleads the texture analysis [4, 5, 6, 7]. A straightforward solution to this problem would be to extract textures only from the inter-costal regions.…”

Section: Introductionmentioning

confidence: 99%

“…This strategy indeed increases the accuracy of normal/abnormal lung classification [5]. Another way to improve the texture analysis is to suppress the rib-bone by reducing the intensities for rib regions, and to work on soft-tissue-like images [8, 9, 7]. The soft-tissue-like images can be obtained by subtracting the rib region from the input X-ray.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Atlas-based rib-bone detection in chest X-rays

Candemir

Jaeger

Bağcı

et al. 2016

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

This paper investigates using rib-bone atlases for automatic detection of rib-bones in chest X-rays (CXRs). We built a system that takes patient X-ray and model atlases as input and automatically computes the posterior rib borders with high accuracy and efficiency. In addition to conventional atlas, we propose two alternative atlases: (i) automatically computed rib bone models using Computed Tomography (CT) scans, and (ii) dual energy CXRs. We test the proposed approach with each model on 25 CXRs from the Japanese Society of Radiological Technology (JSRT) dataset and another 25 CXRs from the National Library of Medicine CXR dataset. We achieve an area under the ROC curve (AUC) of about 95% for Montgomery and 91% for JSRT datasets. Using the optimal operating point of the ROC curve, we achieve a segmentation accuracy of 88.91 ± 1.8 % for Montgomery and 85.48 ± 3.3 % for JSRT datasets. Our method produces comparable results with the state-of-the-art algorithms. The performance of our method is also excellent on challenging X-rays as it successfully addressed the rib-shape variance between patients and number of visible rib-bones due to patient respiration.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Atlas-based rib-bone detection in chest X-rays

Candemir

Jaeger

Bağcı

et al. 2016

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

show abstract

“…Akciğer dokusu ile üst üste binen kaburgaların etkisini azaltmak amacıyla daha önce yapılan çalışmalar, tespit edilen kemik bölgelerinin de bir öznitelik olarak ayırt edici modele dâhil edilmesi veya bu bölgeler baskılandıktan sonra modelin öğrenilmesi şeklinde görülmektedir [14]. Baskılama sonrası öğrenme yanlış pozitifleri azaltmada etkili olmakla birlikte normal dokuda bozulmalara neden olduğundan tahmin duyarlılığında da düşmeye neden olmaktadır.…”

Section: Introductionunclassified

Context-sensitive model learning for lung nodule detection

Oğul¹,

Ogul

Sümer

2016

2016 24th Signal Processing and Communication Application Conference (SIU)

View full text Add to dashboard Cite

Özetçe -Akciğer radyografilerinde nodül tespiti Bilgisayar Destekli Tanı (BDT) sistemlerinin temel bileşenlerinden biridir. Problem çoğunlukla x-ray görüntüsü üzerinde bulunan aday bölgelerinin gözetimli yöntemlerle sınıflandırılması şeklinde ele alınmıştır. Bu amaçla önceden belirlenmiş öznitelikler kullanılarak ayırt edici bir model öğrenilir. Bu modellerin temel problemi, grafilerde normal akciğer organ dokusu yanında pek çok diğer anatomik bölgelerin de görüntülenmesi ve bu bölgelerin organ dokusu ile üst üste binmesidir. Bu çakışma, çıkarılan özniteliklerin ayırt ediciliğini azaltmakta ve farklı anatomik bölgelerin çakıştığı noktalarda yanlış pozitiflerin raporlanmasına neden olmaktadır. Bu çalışmada, yanlış pozitiflerin en önemli nedeni olan kemik bölgelerinin bir ön işlem olarak bölütlenmesi sonrasında, kemik ve normal doku bölgeleri için farklı modeller öğrenilmesi önerilmektedir. Böylece kemik bölgesi ve normal doku bölgesinde bulunan nodül adayları bağlam-duyarlı olarak değerlendirilmektedir. Bilinen bir kıyaslama veri kümesi üzerinde yapılan testler önerilen yaklaşımın duyarlılığı azaltmadan yanlış pozitifleri önemli ölçüde azalttığını açıkça göstermiştir. Anahtar Kelimeler -Bilgisayar Destekli Tanı (BDT); Akciğer radiografisi; Akciğer kanseri; Kemik baskılama; Sınıflandırma. Abstract -Nodule detection in chest radiographs is a main component of current Computer Aided Diagnosis (CAD) systems. The problem is usually approached as a supervised classification task of candidate nodule segments.To this end, a discriminative model is learnt from predefined set of features. A key concern with this approach is the fact that some normal tissues are also imaged and these regions can overlap with the lung tissue as to hide the nodules. These overlaps may reduce the discriminative ability of extracted features and increase the number of false positives accordingly. In this study, we offer to learn distinct models for bone and normal tissue regions following to the segmentation of ribs, which are often the major reason for false positives. Thus, the nodule candidates in bone and normal tissue regions can be assessed in context-sensitive way. The experiments on a common benchmark set determine that the proposed approach can significantly recue the false positives while preserving the sensitivity of detections.

show abstract

Dilated conditional GAN for bone suppression in chest radiographs with enforced semantic features

Zhou

Shen³

2020

Medical Physics

View full text Add to dashboard Cite

Purpose The purpose of this essay is to improve computer‐aided diagnosis of lung diseases by the removal of bone structures imagery such as ribs and clavicles, which may shadow a clinical view of lesions. This paper aims to develop an algorithm to suppress the imaging of bone structures within clinical x‐ray images, leaving a residual portrayal of lung tissue; such that these images can be used to better serve applications, such as lung nodule detection or pathology based on the radiological reading of chest x rays. Methods We propose a conditional Adversarial Generative Network (cGAN) (Mirza and Osindero, Conditional generative adversarial nets, 2014.) model, consisting of a generator and a discriminator, for the task of bone shadow suppression. The proposed model utilizes convolutional operations to expand the size of the receptive field of the generator without losing contextual information while downsampling the image. It is trained by enforcing both the pixel‐wise intensity similarity and the semantic‐level visual similarity between the generated x‐ray images and the ground truth, via optimizing an L‐1 loss of the pixel intensity values on the generator side and a feature matching loss on the discriminator side, respectively. Results The framework we propose is trained and tested on an open‐access chest radiograph dataset for benchmark. Results show that our model is capable of generating bone‐suppressed images of outstanding quality with a limited number of training samples (N = 272). Conclusions Our approach outperforms current state‐of‐the‐art bone suppression methods using x‐ray images. Instead of simply downsampling images at different scales, our proposed method mitigates the loss of contextual information by utilizing dilated convolutions, which gains a noticeable quality improvement for the outputs. On the other hand, our experiment shows that enforcing the semantic similarity between the generated and the ground truth images assists the adversarial training process and achieves better perceptual quality.

show abstract

Eliminating rib shadows in chest radiographic images providing diagnostic assistance

Cited by 13 publications

References 15 publications

Atlas-based rib-bone detection in chest X-rays

Atlas-based rib-bone detection in chest X-rays

Context-sensitive model learning for lung nodule detection

Dilated conditional GAN for bone suppression in chest radiographs with enforced semantic features

Contact Info

Product

Resources

About