Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT

A 3D image segmentation for lung cancer using V.Net architecture based deep convolutional networks

Lung segmentation of chest CT scan is utilised to identify lung cancer and this step is also critical in other diagnostic pathways. Therefore, powerful algorithms to accomplish this accurate segmentation task are highly needed in the medical imaging domain, where the tumours are required to be segmented with the lung parenchyma. Also, the lung parenchyma needs to be detached from the tumour regions that are often confused with the lung tissue. Recently, lung semantic segmentation is more suitable to allocate each pixel in the image to a predefined class based on fully convolutional networks (FCNs). In this paper, CT cancer scans from the Task06_Lung database were applied to FCN that was inspired by V.Net architecture for efficiently selecting a region of interest (ROI) using the 3D segmentation. This lung database is segregated into 64 training images and 32 testing images. The proposed system is generalised by three steps including data preprocessing, data augmentation and neural network based on the V-Net model. Then, it was evaluated by dice score coefficient (DSC) to calculate the ratio of the segmented image and the ground truth image. This proposed system outperformed other previous schemes for 3D lung segmentation with an average DCS of 80% for ROI and 98% for surrounding lung tissues. Moreover, this system demonstrated that 3D views of lung tumours in CT images precisely carried tumour estimation and robust lung segmentation.

Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem

BACKGROUND

Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exists, involving sophisticated pipelines trained and validated on different datasets. However, the clinical applicability of these approaches across diseases remains limited.

METHODS

We compared four generic deep learning approaches trained on various datasets and two readily available lung segmentation algorithms. We performed evaluation on routine imaging data with more than six different disease patterns and three published data sets.

RESULTS

Using different deep learning approaches, mean Dice similarity coefficients (DSCs) on test datasets varied not over 0.02. When trained on a diverse routine dataset (n = 36), a standard approach (U-net) yields a higher DSC (0.97 ± 0.05) compared to training on public datasets such as the Lung Tissue Research Consortium (0.94 ± 0.13, p = 0.024) or Anatomy 3 (0.92 ± 0.15, p = 0.001). Trained on routine data (n = 231) covering multiple diseases, U-net compared to reference methods yields a DSC of 0.98 ± 0.03 versus 0.94 ± 0.12 (p = 0.024).

CONCLUSIONS

The accuracy and reliability of lung segmentation algorithms on demanding cases primarily relies on the diversity of the training data, highlighting the importance of data diversity compared to model choice. Efforts in developing new datasets and providing trained models to the public are critical. By releasing the trained model under General Public License 3.0, we aim to foster research on lung diseases by providing a readily available tool for segmentation of pathological lungs.

Automated Lung Segmentation from HRCT Scans with Diffuse Parenchymal Lung Diseases

Performing accurate and fully automated lung segmentation of high-resolution computed tomography (HRCT) images affected by dense abnormalities is a challenging problem. This paper presents a novel algorithm for automated segmentation of lungs based on modified convex hull algorithm and mathematical morphology techniques. Sixty randomly selected lung HRCT scans with different abnormalities are used to test the proposed algorithm, and experimental results show that the proposed approach can accurately segment the lungs even in the presence of disease patterns, with some limitations in the apices and bases of lungs. The algorithm demonstrates a high segmentation accuracy (dice similarity coefficient = 98.62 and shape differentiation metrics dmean = 1.39 mm, and drms = 2.76 mm). Therefore, the developed automated lung segmentation algorithm is a good candidate for the first stage of a computer-aided diagnosis system for diffuse lung diseases.

Fuzzy-C-Means Clustering Based Segmentation and CNN-Classification for Accurate Segmentation of Lung Nodules

Objective: Accurate segmentation of abnormal and healthy lungs is very crucial for a steadfast computer-aided disease diagnostics. Methods: For this purpose a stack of chest CT scans are processed. In this paper, novel methods are proposed for segmentation of the multimodal grayscale lung CT scan. In the conventional methods using Markov–Gibbs Random Field (MGRF) model the required regions of interest (ROI) are identified. Result: The results of proposed FCM and CNN based process are compared with the results obtained from the conventional method using MGRF model. The results illustrate that the proposed method can able to segment the various kinds of complex multimodal medical images precisely. Conclusion: However, in this paper, to obtain an exact boundary of the regions, every empirical dispersion of the image is computed by Fuzzy C-Means Clustering segmentation. A classification process based on the Convolutional Neural Network (CNN) classifier is accomplished to distinguish the normal tissue and the abnormal tissue. The experimental evaluation is done using the Interstitial Lung Disease (ILD) database.

Accurate Lungs Segmentation on CT Chest Images by Adaptive Appearance-Guided Shape Modeling

To accurately segment pathological and healthy lungs for reliable computer-aided disease diagnostics, a stack of chest CT scans is modeled as a sample of a spatially inhomogeneous joint 3D Markov-Gibbs random field (MGRF) of voxel-wise lung and chest CT image signals (intensities). The proposed learnable MGRF integrates two visual appearance sub-models with an adaptive lung shape submodel. The first-order appearance submodel accounts for both the original CT image and its Gaussian scale space (GSS) filtered version to specify local and global signal properties, respectively. Each empirical marginal probability distribution of signals is closely approximated with a linear combination of discrete Gaussians (LCDG), containing two positive dominant and multiple sign-alternate subordinate DGs. The approximation is separated into two LCDGs to describe individually the lungs and their background, i.e., all other chest tissues. The second-order appearance submodel quantifies conditional pairwise intensity dependencies in the nearest voxel 26-neighborhood in both the original and GSS-filtered images. The shape submodel is built for a set of training data and is adapted during segmentation using both the lung and chest appearances. The accuracy of the proposed segmentation framework is quantitatively assessed using two public databases (ISBI VESSEL12 challenge and MICCAI LOLA11 challenge) and our own database with, respectively, 20, 55, and 30 CT images of various lung pathologies acquired with different scanners and protocols. Quantitative assessment of our framework in terms of Dice similarity coefficients, 95-percentile bidirectional Hausdorff distances, and percentage volume differences confirms the high accuracy of our model on both our database (98.4±1.0%, 2.2±1.0 mm, 0.42±0.10%) and the VESSEL12 database (99.0±0.5%, 2.1±1.6 mm, 0.39±0.20%), respectively. Similarly, the accuracy of our approach is further verified via a blind evaluation by the organizers of the LOLA11 competition, where an average overlap of 98.0% with the expert's segmentation is yielded on all 55 subjects with our framework being ranked first among all the state-of-the-art techniques compared.

Automatic multiorgan segmentation in CT images of the male pelvis using region-specific hierarchical appearance cluster models

PURPOSE

Accurate segmentation of pelvic organs in CT images is of great importance in external beam radiotherapy for prostate cancer. The aim of this studying is to develop a novel method for automatic, multiorgan segmentation of the male pelvis.

METHODS

The authors' segmentation method consists of several stages. First, a pretreatment includes parameterization, principal component analysis (PCA), and an established process of region-specific hierarchical appearance cluster (RSHAC) model which was executed on the training dataset. After the preprocessing, online automatic segmentation of new CT images is achieved by combining the RSHAC model with the PCA-based point distribution model. Fifty pelvic CT from eight prostate cancer patients were used as the training dataset. From another 20 prostate cancer patients, 210 CT images were used for independent validation of the segmentation method.

RESULTS

In the training dataset, 15 PCA modes were needed to represent 95% of shape variations of pelvic organs. When tested on the validation dataset, the authors' segmentation method had an average Dice similarity coefficient and mean absolute distance of 0.751 and 0.371 cm, 0.783 and 0.303 cm, 0.573 and 0.604 cm for prostate, bladder, and rectum, respectively. The automated segmentation process took on average 5 min on a personal computer equipped with Core 2 Duo CPU of 2.8 GHz and 8 GB RAM.

CONCLUSIONS

The authors have developed an efficient and reliable method for automatic segmentation of multiple organs in the male pelvis. This method should be useful for treatment planning and adaptive replanning for prostate cancer radiotherapy. With this method, the physicist can improve the work efficiency and stability.

Lung Segmentation in 4D CT Volumes Based on Robust Active Shape Model Matching

Dynamic and longitudinal lung CT imaging produce 4D lung image data sets, enabling applications like radiation treatment planning or assessment of response to treatment of lung diseases. In this paper, we present a 4D lung segmentation method that mutually utilizes all individual CT volumes to derive segmentations for each CT data set. Our approach is based on a 3D robust active shape model and extends it to fully utilize 4D lung image data sets. This yields an initial segmentation for the 4D volume, which is then refined by using a 4D optimal surface finding algorithm. The approach was evaluated on a diverse set of 152 CT scans of normal and diseased lungs, consisting of total lung capacity and functional residual capacity scan pairs. In addition, a comparison to a 3D segmentation method and a registration based 4D lung segmentation approach was performed. The proposed 4D method obtained an average Dice coefficient of 0.9773 ± 0.0254, which was statistically significantly better (p value ≪0.001) than the 3D method (0.9659 ± 0.0517). Compared to the registration based 4D method, our method obtained better or similar performance, but was 58.6% faster. Also, the method can be easily expanded to process 4D CT data sets consisting of several volumes.

Regression Segmentation for M³ Spinal Images

Clinical routine often requires to analyze spinal images of multiple anatomic structures in multiple anatomic planes from multiple imaging modalities (M(3)). Unfortunately, existing methods for segmenting spinal images are still limited to one specific structure, in one specific plane or from one specific modality (S(3)). In this paper, we propose a novel approach, Regression Segmentation, that is for the first time able to segment M(3) spinal images in one single unified framework. This approach formulates the segmentation task innovatively as a boundary regression problem: modeling a highly nonlinear mapping function from substantially diverse M(3) images directly to desired object boundaries. Leveraging the advancement of sparse kernel machines, regression segmentation is fulfilled by a multi-dimensional support vector regressor (MSVR) which operates in an implicit, high dimensional feature space where M(3) diversity and specificity can be systematically categorized, extracted, and handled. The proposed regression segmentation approach was thoroughly tested on images from 113 clinical subjects including both disc and vertebral structures, in both sagittal and axial planes, and from both MRI and CT modalities. The overall result reaches a high dice similarity index (DSI) 0.912 and a low boundary distance (BD) 0.928 mm. With our unified and expendable framework, an efficient clinical tool for M(3) spinal image segmentation can be easily achieved, and will substantially benefit the diagnosis and treatment of spinal diseases.

Registration of lung CT images acquired in different respiratory ranges with 4DCT and HRCT

Pulmonary image registration is challenging because of the unique structure of the lung, its high deformability and its non-uniform intensity change with breathing. In the present work we propose a new method for pulmonary image registration, based on the reconstruction and the combination of the main pulmonary structures to modify parenchyma intensity prior to the application of the registration algorithm. The algorithm has been applied to both four dimensional CT and multi-volume high resolution CT demonstrating an increased accuracy of the results with the application of the pulmonary structure enhancement, evaluated both on landmarks distance in 4DCT and structures' surface distance in HRCT.

Automated compromised right lung segmentation method using a robust atlas-based active volume model with sparse shape composition prior in CT

To resolve challenges in image segmentation in oncologic patients with severely compromised lung, we propose an automated right lung segmentation framework that uses a robust, atlas-based active volume model with a sparse shape composition prior. The robust atlas is achieved by combining the atlas with the output of sparse shape composition. Thoracic computed tomography images (n=38) from patients with lung tumors were collected. The right lung in each scan was manually segmented to build a reference training dataset against which the performance of the automated segmentation method was assessed. The quantitative results of this proposed segmentation method with sparse shape composition achieved mean Dice similarity coefficient (DSC) of (0.72, 0.81) with 95% CI, mean accuracy (ACC) of (0.97, 0.98) with 95% CI, and mean relative error (RE) of (0.46, 0.74) with 95% CI. Both qualitative and quantitative comparisons suggest that this proposed method can achieve better segmentation accuracy with less variance than other atlas-based segmentation methods in the compromised lung segmentation.

A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes

PURPOSE

The automated correct segmentation of left and right lungs is a nontrivial problem, because the tissue layer between both lungs can be quite thin. In the case of lung segmentation with left and right lung models, overlapping segmentations can occur. In this paper, the authors address this issue and propose a solution for a model-based lung segmentation method.

METHODS

The thin tissue layer between left and right lungs is detected by means of a classification approach and utilized to selectively modify the cost function of the lung segmentation method. The approach was evaluated on a diverse set of 212 CT scans of normal and diseased lungs. Performance was assessed by utilizing an independent reference standard and by means of comparison to the standard segmentation method without overlap avoidance.

RESULTS

For cases where the standard approach produced overlapping segmentations, the proposed method significantly (p = 1.65 × 10(-9)) reduced the overlap by 97.13% on average (median: 99.96%). In addition, segmentation accuracy assessed with the Dice coefficient showed a statistically significant improvement (p = 7.5 × 10(-5)) and was 0.9845 ± 0.0111. For cases where the standard approach did not produce an overlap, performance of the proposed method was not found to be significantly different.

CONCLUSIONS

The proposed method improves the quality of the lung segmentations, which is important for subsequent quantitative analysis steps.

Automated 3D ιnterstitial lung disease εxtent quantification: performance evaluation and correlation to PFTs

In this study, the performance of a recently proposed computer-aided diagnosis (CAD) scheme in detection and 3D quantification of reticular and ground glass pattern extent in chest computed tomography of interstitial lung disease (ILD) patients is evaluated. CAD scheme performance was evaluated on a dataset of 37 volumetric chest scans, considering five representative axial anatomical levels per scan. CAD scheme reliability analysis was performed by estimating agreement (intraclass correlation coefficient, ICC) of automatically derived ILD pattern extent to semi-quantitative disease extent assessment in terms of 29-point rating scale provided by two expert radiologists. Receiver operating characteristic (ROC) analysis was employed to assess CAD scheme accuracy in ILD pattern detection in terms of area under ROC curve (A z ). Correlation of reticular and ground glass volumetric pattern extent to pulmonary function tests (PFTs) was also investigated. CAD scheme reliability was substantial for ILD extent (ICC = 0.809) and distinct reticular pattern extent (0.806) and moderate for distinct ground glass pattern extent (0.543), performing within inter-observer agreement. CAD scheme demonstrated high accuracy in detecting total ILD (A z  = 0.950 ± 0.018), while accuracy in detecting distinct reticular and ground glass patterns was 0.920 ± 0.023 and 0.883 ± 0.024, respectively. Moderate and statistically significant negative correlation was found between reticular volumetric pattern extent and diffusing capacity, forced expiratory volume in 1 s, forced vital capacity, and total lung capacity (R = -0.581, -0.513, -0.494, and -0.446, respectively), similar to correlations found between radiologists' semi-quantitative ratings with PFTs. CAD-based quantification of disease extent is in agreement with radiologists' semi-quantitative assessment and correlates to specific PFTs, suggesting a potential imaging biomarker for ILD staging and management.

Objective CT-based quantification of lung sequelae in treated patients with paracoccidioidomycosis

This study presents methodology for objectively quantifying the pulmonary region affected by emphysemic and fibrotic sequelae in treated patients with paracoccidioidomycosis. This methodology may also be applied to any other disease that results in these sequelae in the lungs.Pulmonary high-resolution computed tomography examinations of 30 treated paracoccidioidomycosis patients were used in the study. The distribution of voxel attenuation coefficients was analyzed to determine the percentage of lung volume that consisted of emphysemic, fibrotic, and normal tissue. Algorithm outputs were compared with subjective evaluations by radiologists using a scale that is currently used for clinical diagnosis.Affected regions in the patient images were determined by computational analysis and compared with estimates by radiologists, revealing mean (± standard deviation) differences in the scores for fibrotic and emphysemic regions of 0.1% ± 1.2% and -0.2% ± 1.0%, respectively.The computational results showed a strong correlation with the radiologist estimates, but the computation results were more reproducible, objective, and reliable.

Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels

This work is focused on application of a new technique in the first steps of computer-aided detection (CAD) of lung nodules. The scheme includes segmenting the lung volume and detecting most of the nodules with a low number of false positive (FP) objects. The juxtapleural nodules were properly included and the airways excluded in the lung segmentation. Among the suspicious regions obtained from the multiscale dot enhancement filter, those containing the center of nodule candidates, were determined. These center points were achieved from a 3D blob detector based on Laplacian of Gaussian kernels. Then the volumetric shape index (SI) that encodes the 3D local shape information was calculated for voxels in the determined regions. The performance of the scheme was evaluated by using 42 CT images from the Lung Image Database Consortium (LIDC). The results show that the average number of FPs reaches to 38.8 per scan with the sensitivity of 95.9% in the initial detections. The scheme is adaptable to detect nodules with wide variations in size, shape, intensity and location. Comparison of results with previously reported ones indicates that the proposed scheme can be satisfactory applied for initial detection of lung nodules in the chest CT images.

Wavelet-based algorithm to the evaluation of contrasted hepatocellular carcinoma in CT-images after transarterial chemoembolization

Background

Hepatocellular carcinoma is a primary tumor of the liver and involves different treatment modalities according to the tumor stage. After local therapies, the tumor evaluation is based on the mRECIST criteria, which involves the measurement of the maximum diameter of the viable lesion. This paper describes a computed methodology to measure through the contrasted area of the lesions the maximum diameter of the tumor by a computational algorithm.

Methods

63 computed tomography (CT) slices from 23 patients were assessed. Non-contrasted liver and HCC typical nodules were evaluated, and a virtual phantom was developed for this purpose. Optimization of the algorithm detection and quantification was made using the virtual phantom. After that, we compared the algorithm findings of maximum diameter of the target lesions against radiologist measures.

Results

Computed results of the maximum diameter are in good agreement with the results obtained by radiologist evaluation, indicating that the algorithm was able to detect properly the tumor limits. A comparison of the estimated maximum diameter by radiologist versus the algorithm revealed differences on the order of 0.25 cm for large-sized tumors (diameter > 5 cm), whereas agreement lesser than 1.0 cm was found for small-sized tumors.

Conclusions

Differences between algorithm and radiologist measures were accurate for small-sized tumors with a trend to a small decrease for tumors greater than 5 cm. Therefore, traditional methods for measuring lesion diameter should be complemented non-subjective measurement methods, which would allow a more correct evaluation of the contrast-enhanced areas of HCC according to the mRECIST criteria.

Computer-aided diagnosis systems for lung cancer: challenges and methodologies

This paper overviews one of the most important, interesting, and challenging problems in oncology, the problem of lung cancer diagnosis. Developing an effective computer-aided diagnosis (CAD) system for lung cancer is of great clinical importance and can increase the patient's chance of survival. For this reason, CAD systems for lung cancer have been investigated in a huge number of research studies. A typical CAD system for lung cancer diagnosis is composed of four main processing steps: segmentation of the lung fields, detection of nodules inside the lung fields, segmentation of the detected nodules, and diagnosis of the nodules as benign or malignant. This paper overviews the current state-of-the-art techniques that have been developed to implement each of these CAD processing steps. For each technique, various aspects of technical issues, implemented methodologies, training and testing databases, and validation methods, as well as achieved performances, are described. In addition, the paper addresses several challenges that researchers face in each implementation step and outlines the strengths and drawbacks of the existing approaches for lung cancer CAD systems.

Automated segmentation refinement of small lung nodules in CT scans by local shape analysis

One of the most important problems in the segmentation of lung nodules in CT imaging arises from possible attachments occurring between nodules and other lung structures, such as vessels or pleura. In this report, we address the problem of vessels attachments by proposing an automated correction method applied to an initial rough segmentation of the lung nodule. The method is based on a local shape analysis of the initial segmentation making use of 3-D geodesic distance map representations. The correction method has the advantage that it locally refines the nodule segmentation along recognized vessel attachments only, without modifying the nodule boundary elsewhere. The method was tested using a simple initial rough segmentation, obtained by a fixed image thresholding. The validation of the complete segmentation algorithm was carried out on small lung nodules, identified in the ITALUNG screening trial and on small nodules of the lung image database consortium (LIDC) dataset. In fully automated mode, 217/256 (84.8%) lung nodules of ITALUNG and 139/157 (88.5%) individual marks of lung nodules of LIDC were correctly outlined and an excellent reproducibility was also observed. By using an additional interactive mode, based on a controlled manual interaction, 233/256 (91.0%) lung nodules of ITALUNG and 144/157 (91.7%) individual marks of lung nodules of LIDC were overall correctly segmented. The proposed correction method could also be usefully applied to any existent nodule segmentation algorithm for improving the segmentation quality of juxta-vascular nodules.

Texture-based identification and characterization of interstitial pneumonia patterns in lung multidetector CT

Identification and characterization of diffuse parenchyma lung disease (DPLD) patterns challenges computer-aided schemes in computed tomography (CT) lung analysis. In this study, an automated scheme for volumetric quantification of interstitial pneumonia (IP) patterns, a subset of DPLD, is presented, utilizing a multidetector CT (MDCT) dataset. Initially, lung-field segmentation is achieved by 3-D automated gray-level thresholding combined with an edge-highlighting wavelet preprocessing step, followed by a texture-based border refinement step. The vessel tree volume is identified and removed from lung field, resulting in lung parenchyma (LP) volume. Following, identification and characterization of IP patterns is formulated as a three-class pattern classification of LP into normal, ground glass, and reticular patterns, by means of k-nearest neighbor voxel classification, exploiting 3-D cooccurrence features. Performance of the proposed scheme in indentifying and characterizing ground glass and reticular patterns was evaluated by means of volume overlap (ground glass: 0.734 +/- 0.057, reticular: 0.815 +/- 0.037), true-positive fraction (ground glass: 0.638 +/- 0.055, reticular: 0.942 +/- 0.023) and false-positive fraction (ground glass: 0.361 +/- 0.027, reticular: 0.147 +/- 0.032) on five MDCT scans.

Texture classification-based segmentation of lung affected by interstitial pneumonia in high-resolution CT

Accurate and automated lung field (LF) segmentation in high-resolution computed tomography (HRCT) is highly challenged by the presence of pathologies affecting lung borders, also affecting the performance of computer-aided diagnosis (CAD) schemes. In this work, a two-dimensional LF segmentation algorithm adapted to interstitial pneumonia (IP) patterns is presented. The algorithm employs k-means clustering followed by a filling operation to obtain an initial LF order estimate. The final LF border is obtained by an iterative support vector machine neighborhood labeling of border pixels based on gray level and wavelet coefficient statistics features. A second feature set based on gray level averaging and gradient features was also investigated to evaluate its effect on segmentation performance of the proposed method. The proposed method is evaluated on a dataset of 22 HRCT cases spanning a range of IP patterns such as ground glass, reticular, and honeycombing. The accuracy of the method is assessed using area overlap and shape differentiation metrics (d(mean), d(rms), and d(max)), by comparing automatically derived lung borders to manually traced ones, and further compared to a gray level thresholding-based (GLT-based) method. Accuracy of the methods evaluated is also compared to interobserver variability. The proposed method incorporating gray level and wavelet coefficient statistics demonstrated the highest segmentation accuracy, averaged over left and right LFs (overlap=0.954, d(mean)=1.080 mm, d(rms)=1.407 mm, and d(max)=4.944 mm), which is statistically significant (two-tailed student's t test for paired data, p<0.0083) with respect to all metrics considered as compared to the proposed method incorporating gray level averaging and gradient features (overlap=0.918, d(mean)=2.354 mm, d(rms)=3.711 mm, and d(max)=14.412 mm) and the GLT-based method (overlap=0.897, d(mean)=3.618 mm, d(rms)=5.007 mm, and d(max)=16.893 mm). The performance of the three segmentation methods, although decreased as IP pattern severity level (mild, moderate, and severe) was increased, did not demonstrate statistically significant difference (two-tailed student's t test for unpaired data, p>0.0167 for all metrics considered). Finally, the accuracy of the proposed method, based on gray level and wavelet coefficient statistics ranges within interobserver variability. The proposed segmentation method could be used as an initial stage of a CAD scheme for IP patterns.