Automatically Detecting Rotation in Chest Radiographs Using Principal Rib-Orientation Measure for Quality Control

Santosh, K. C.; Candemir, Sema; Jaeger, Stefan; Karargyris, Alexandros; Thoma, George R.; Folio, Les

doi:10.1142/s0218001415570013

Cited by 21 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a distorted appearance can distract the algorithm and lead to inaccurate segmentation. Although there are articles recognize the importance of such distortions [ 61 , 63 , 64 ], to our knowledge, there is not any methodical inclusion of these challenges into a lung segmentation algorithm that is robust to such real-world image artifacts.…”

Section: Lungs With Deformed Appearancementioning

confidence: 99%

A review on lung boundary detection in chest X-rays

2019

Self Cite

View full text Add to dashboard Cite

PurposeChest radiography is the most common imaging modality for pulmonary diseases. Due to its wide usage, there is a rich literature addressing automated detection of cardiopulmonary diseases in digital chest X-rays (CXRs). One of the essential steps for automated analysis of CXRs is localizing the relevant region of interest, i.e., isolating lung region from other less relevant parts, for applying decision-making algorithms there. This article provides an overview of the recent literature on lung boundary detection in CXR images.MethodsWe review the leading lung segmentation algorithms proposed in period 2006–2017. First, we present a review of articles for posterior–anterior view CXRs. Then, we mention studies which operate on lateral views. We pay particular attention to works that focus their efforts on deformed lungs and pediatric cases. We also highlight the radiographic measures extracted from lung boundary and their use in automatically detecting cardiopulmonary abnormalities. Finally, we identify challenges in dataset curation and expert delineation process, and we listed publicly available CXR datasets.Results(1) We classified algorithms into four categories: rule-based, pixel classification-based, model-based, hybrid, and deep learning-based algorithms. Based on the reviewed articles, hybrid methods and deep learning-based methods surpass the algorithms in other classes and have segmentation performance as good as inter-observer performance. However, they require long training process and pose high computational complexity. (2) We found that most of the algorithms in the literature are evaluated on posterior–anterior view adult CXRs with a healthy lung anatomy appearance without considering challenges in abnormal CXRs. (3) We also found that there are limited studies for pediatric CXRs. The lung appearance in pediatrics, especially in infant cases, deviates from adult lung appearance due to the pediatric development stages. Moreover, pediatric CXRs are noisier than adult CXRs due to interference by other objects, such as someone holding the child’s arms or the child’s body, and irregular body pose. Therefore, lung boundary detection algorithms developed on adult CXRs may not perform accurately in pediatric cases and need additional constraints suitable for pediatric CXR imaging characteristics. (4) We have also stated that one of the main challenges in medical image analysis is accessing the suitable datasets. We listed benchmark CXR datasets for developing and evaluating the lung boundary algorithms. However, the number of CXR images with reference boundaries is limited due to the cumbersome but necessary process of expert boundary delineation.ConclusionsA reliable computer-aided diagnosis system would need to support a greater variety of lung and background appearance. To our knowledge, algorithms in the literature are evaluated on posterior–anterior view adult CXRs with a healthy lung anatomy appearance, without considering ambiguous lung silhouettes due to pathological deformities, anatomical alte...

show abstract

Section: Lungs With Deformed Appearancementioning

confidence: 99%

A review on lung boundary detection in chest X-rays

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…4 The rotation of the human lungs is measured by line histogram technique in range of 0°to 180°angle (K. C. Santosh et al, 2015). 5 The bad quality X-ray image can be filtered with the help of computer aided screening diagnosis. The screening approach outperformed the state of art methods by giving least processing time (K. C. Santosh et al, 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

The quantification of percentage filling of gutta-percha in obturated root canal using image processing and analysis

Lokhande

Balaguru

2020

Journal of Oral Biology and Craniofacial Research

View full text Add to dashboard Cite

To quantify the percentage filling of the gutta-percha in obturated root canal cavity using image processing and analysis. Methodology: The image processing and analysis using the X-ray radiographs is commonly being used by medical practitioners for easy and speedy diagnosis of patient health. But these methods are qualitative and assessment depends upon dentist's own experience and perception. Fifteen patients were randomly assigned to fifteen Dentists to perform the root canal treatment using warm vertical condensation. X-ray radiographs of pre and post obturation were obtained to carry image processing and analysis. Image enhancement, low pass filtering, kmeans clustering algorithm and edge detection technique were applied to get results. Percentage filling of the obturated root canal using X-ray radiography (Dentist's prediction) and proposed algorithm results of the present study were compared. Out of fifteen Dentists, the prediction of twelve Dentists were close in range of percentage filling quantified using proposed algorithm of the present study. When investigated it was found that three discrepancies found due to lack of sufficient experience of the respective Dentist. The proposed algorithm not only helps to overcome this false assessment but also helps to quantify accurate percentage filling of gutta-percha and outlines unfilled cavity gap of root canal. Results: The proposed algorithm of present study provides accurate percentage filling of gutta-percha in the obturated root canal up to two decimal points. The present study used gutta-percha as obturation material but the study can be implemented for any obturation material. Conclusion: The proposed algorithm of present study accurately quantified the percentage filling of root canal cavity using image processing. It also locates and outlines the unfilled root canal cavity.

show abstract

“…1 a ). Many CADx systems use bones (mainly the ribs and the clavicles) as markers to automatically detect rotations in CXRs [22, 23], to accurately register temporal CXRs [24], and to assess the level of inspiration in a CXR. Bones in a CXR can be segmented by using dual‐energy subtraction radiography [25] or by using the software methods described in [26–30].…”

Section: Chest Anatomymentioning

confidence: 99%

“…The images have a size varying from 1024 to 4248 pixels along each dimension, are in Digital Imaging and Communications in Medicine (DICOM) format, and cover a wide range of lung abnormalities. It has been used by USNLM researchers for CXR view classification [45], detecting rotations in CXRs [23], and foreign object detection [46]. It is not yet placed in public domain. Korean Institute of TB (KIT) dataset : This dataset consists of 10,848 PA CXR images in DICOM format.…”

Section: Datasetsmentioning

confidence: 99%