A fast and accurate automatic lung segmentation and volumetry method for MR data used in epidemiological studies

Ivanovska, Tetyana; Hegenscheid, Katrin; Laqua, René; Kühn, Jens‐Peter; Gläser, Sven; Ewert, Ralf; Hosten, Norbert; Puls, Ralf; Völzke, Henry

doi:10.1016/j.compmedimag.2011.10.001

Cited by 18 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The disadvantage of this approach is that it requires expert knowledge, and there is always a risk of human error. Human fallibility is apparent in the fact that different experts give different outlines of the same lungs [ 10 ]. However, our method uses 12,816 images in total.…”

Section: Discussionmentioning

confidence: 99%

Novel method of lung area extraction in chest perfusion computed tomography

Kalicka

Lipiński

Browarczyk

2013

Biomedizinische Technik/Biomedical Engineering

View full text Add to dashboard Cite

Chest perfusion computed tomography (pCT) is a useful technique in the medical diagnosis of how organs function. Perfusion CT scans are used to calculate perfusion parameters. In the case of automated methods of lung perfusion parameters calculation, the prior extraction of the lung area is desired to avoid unnecessary calculation in an area outside the lung cross-section and to avoid wasting time on processing signals of no diagnostic importance. Our new method is designed to extract a lung cross-section from a whole series of chest pCT images. It uses a complete sequence of pCT scans to extract the rough lung contour. Next each scan is processed individually, within the rough contour, to obtain a detailed, individual outline of the lungs. The proposed method and obtained results are presented and compared with methods known in literature.

show abstract

Section: Discussionmentioning

confidence: 99%

Novel method of lung area extraction in chest perfusion computed tomography

Kalicka

Lipiński

Browarczyk

2013

Biomedizinische Technik/Biomedical Engineering

View full text Add to dashboard Cite

show abstract

“…1(b)) enables limiting the search space during fissure detection, thereby improving computational efficiency and eliminating the possibility of erroneous (false positive) fissure detections outside the actual lung regions [27–28]. In this study, we use an automated lung segmentation approach proposed in [26], namely Adaptive Border Marching Algorithm (ABMA), to segment the lung volume depicted on CT images.…”

Section: Methodsmentioning

confidence: 99%

Identification of pulmonary fissures using a piecewise plane fitting algorithm

Wilson

Wang

et al. 2012

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

We describe an automated computerized scheme to identify pulmonary fissures depicted in chest computed tomography (CT) examinations from a novel perspective. Whereas CT images can be regarded as a cloud of points, the underlying idea is to search for surface-like structures in the three dimensional (3D) Euclidean space by using an efficient plane fitting algorithm. The proposed plane fitting operation is performed in a number of small spherical lung sub-volumes to detect small planar patches. Using a simple clustering criterion based on their spatial coherence and surface area, the identified planar patches, assumed to represent fissures, are classified into different types of fissures, namely left oblique, right oblique and right horizontal fissures. The performance of the developed scheme was assessed by comparing with a manually created “reference standard” and the results obtained by a previously developed approach on a dataset of 30 lung CT examinations. The experiments show that the average discrepancy is around 1.0 mm in comparison with the reference standard, while the corresponding maximum discrepancy is 20.5 mm. In addition, 94% of the fissure voxels identified by the computerized scheme are within 3 mm of the fissures in the reference standard. As compared to a previously developed approach, we also found that the newly developed scheme had a smaller discrepancy with the standard reference. In efficiency, it takes approximately 8 minutes to identify the fissures in a chest CT examination on a typical PC. The developed scheme demonstrates a reasonable performance in terms of accuracy, robustness, and computational efficiency.

show abstract

“…Başarı oranı daha karmaşık algoritma ve kısıtlı sayıda verinin kullanıldığı [9]'den daha fazladır. Geliştirilen algoritma, akciğer bölgesinin bilgisayar destekli çeşitli analiz işlemlerinde ilk adım olarak önerilebilir.…”

Section: Sonuçlarunclassified

“…Tıp alanında görüntü bölütlenmesinde k-means algoritmasını kullanan çeşitli çalışmalar [1] - [9] gerçekleştirilmiştir. Lee et al [1], beyin tomografisi görüntülerini k-means algoritması ile kümelenerek normal ve normal olmayan bölgeler için ilk ayrımı gerçekleşmiştir.…”

Section: Introductionunclassified

“…MR görüntüleri üzerinden sağlıklı beyin dokusu için parametre tahmini yapmayı amaçlayan bir çalışmada [8], histogram tabanlı kmeans algoritmasından ara işlem olarak yararlanılmıştır. Ivanovska et al'ın [9] geliştirdiği çalışmada MR görüntüleri üzerinden otomatik akciğer bölütlemesi yapılmış ve bölütleme işleminde klasik k-means algoritmasından yararlanılmıştır. Çalışmanın dezavantajı veri setinin 10 ile sınırlı olması ve bölütleme için daha karmaşık algoritmaya ihtiyaç duyulmuş olmasıdır.…”

Section: Introductionunclassified

See 1 more Smart Citation

Automatic lung segmentation by using histogram based k-means algorithm

Dinçer

Duru

2016

2016 Electric Electronics, Computer Science, Biomedical Engineerings' Meeting (EBBT)

View full text Add to dashboard Cite

Özetçe Bu çalışmada bütün akciğer bölgesini otomatik olarak bölütlemek için bölgenin özellikleri dikkate alınarak histogram tabanlı k-means algoritması geliştirilmiştir. Bölütleme sonunda akciğer lobları çevre dokulardan ayrı olarak elde edilmiştir. Bu yöntem akciğer bölgesinin bilgisayar destekli çeşitli analiz işlemlerinde ilk adım olarak kullanılabilir. Çalışmada üç farklı tomografi cihazından alınan toplam 34 kesit seti işlenmiştir. Yöntemin sağladığı kolaylıkla normalizasyon işlemi uygulanmadan görüntüler %96 başarı oranıyla bölütlenebilmiştir. Noktalar arası uzaklıkları hesaplamak için geleneksel k-means yöntemindeki kartezyen sistem yerine histogram değerleri kullanılmıştır. Böylece aralarında bağlantı olmayan ve farklı yerlerde olan aynı tür dokuların aynı kümeye dahil olması sağlanmıştır. Histogram tabanlı kmeans algoritması, Fuzzy C-means (FCM) ve optimal eşikleme yöntemleriyle karşılaştırıldığında iterasyon sayısı ve bölütleme doğruluğu açısından daha verimli bulunmuştur. AbstractIn this study, it was developed an histogram based kmeans algorithm by considering the region features in order to segment whole lung region automatically. After the segmentation the lung lobes are extracted from the surrounding tissue. This method could be used as a first step of various computer aided analysis of lungs. In the study, 34 cases which were scanned by the three different tomography systems, the processed. The method provides 96% segmentation success rate without performing normalization process. The histogram values have been used to calculate the distance between the points instead of using the cartesian system of the traditional k-means method. Thus, similar tissues which are not connected and far from each other, were included in the same set. The histogram based k-means algorithm was compared with Fuzzy C-means (FCM) and optimal thresholding method, found more efficient for the iteration number and segmentation accuracy.

show abstract

A fast and accurate automatic lung segmentation and volumetry method for MR data used in epidemiological studies

Cited by 18 publications

References 16 publications

Novel method of lung area extraction in chest perfusion computed tomography

Novel method of lung area extraction in chest perfusion computed tomography

Identification of pulmonary fissures using a piecewise plane fitting algorithm

Automatic lung segmentation by using histogram based k-means algorithm

Contact Info

Product

Resources

About