An approach for reducing the error rate in automated lung segmentation

Robust lung segmentation is challenging, especially when tens of thousands of lung CT scans need to be processed, as required by large multi-center studies. The goal of this work was to develop and assess a method for the fusion of segmentation results from two different methods to generate lung segmentations that have a lower failure rate than individual input segmentations. As basis for the fusion approach, lung segmentations generated with a region growing and model-based approach were utilized. The fusion result was generated by comparing input segmentations and selectively combining them using a trained classification system. The method was evaluated on a diverse set of 204 CT scans of normal and diseased lungs. The fusion approach resulted in a Dice coefficient of 0.9855±0.0106 and showed a statistically significant improvement compared to both input segmentation methods. In addition, the failure rate at different segmentation accuracy levels was assessed. For example, when requiring that lung segmentations must have a Dice coefficient of better than 0.97, the fusion approach had a failure rate of 6.13%. In contrast, the failure rate for region growing and model-based methods was 18.14% and 15.69%, respectively. Therefore, the proposed method improves the quality of the lung segmentations, which is important for subsequent quantitative analysis of lungs. Also, to enable a comparison with other methods, results on the LOLA11 challenge test set are reported.

[1]  Jayaram K. Udupa,et al.  A Generic Approach to Pathological Lung Segmentation , 2014, IEEE Transactions on Medical Imaging.

[2]  Timo Kohlberger,et al.  Multi-stage Learning for Robust Lung Segmentation in Challenging CT Volumes , 2011, MICCAI.

[3]  Filip Malmberg,et al.  SmartPaint: a tool for interactive segmentation of medical volume images , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[4]  Reinhard Beichel,et al.  Segmentation of Lungs with Interstitial Lung Disease in CT Scans: A TV-L1 Based Texture Analysis Approach , 2014, ISVC.

[5]  David Gur,et al.  Automated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme. , 2003, Academic radiology.

[6]  Bram van Ginneken,et al.  Automated segmentation of pulmonary structures in thoracic computed tomography scans: a review , 2013 .

[7]  Qiang Li,et al.  Automated segmentation of lungs with severe interstitial lung disease in CT. , 2009, Medical physics.

[8]  Reinhard Beichel,et al.  Automated 3-D Segmentation of Lungs With Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach , 2012, IEEE Transactions on Medical Imaging.

[9]  Gurman Gill,et al.  A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes. , 2014, Medical physics.

[10]  N. Simanovsky,et al.  Pleural effusion: characterization with CT attenuation values and CT appearance. , 2009, AJR. American journal of roentgenology.

[11]  B. van Ginneken,et al.  Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection. , 2009, Medical physics.

[12]  Matthew Toews,et al.  Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach , 2014, Int. J. Biomed. Imaging.

[13]  Bram van Ginneken,et al.  Toward automated segmentation of the pathological lung in CT , 2005, IEEE Transactions on Medical Imaging.

[14]  R. Blair,et al.  An alternative method for significance testing of waveform difference potentials. , 1993, Psychophysiology.

[15]  H. Peitgen,et al.  Informatics in radiology (infoRAD): new tools for computer assistance in thoracic CT. Part 1. Functional analysis of lungs, lung lobes, and bronchopulmonary segments. , 2005, Radiographics : a review publication of the Radiological Society of North America, Inc.

[16]  Jonathan R. M. Hosking,et al.  Partitioning Nominal Attributes in Decision Trees , 1999, Data Mining and Knowledge Discovery.

[17]  Reinhard Beichel,et al.  Graph-Based Airway Tree Reconstruction From Chest CT Scans: Evaluation of Different Features on Five Cohorts , 2015, IEEE Transactions on Medical Imaging.

[18]  Daniel Cremers,et al.  Fast and exact solution of Total Variation models on the GPU , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[19]  M. Levandowsky,et al.  Distance between Sets , 1971, Nature.

[20]  Xin Meng,et al.  Shape “Break-and-Repair” Strategy and Its Application to Automated Medical Image Segmentation , 2011, IEEE Transactions on Visualization and Computer Graphics.