Automatic Lung Segmentation of Volumetric Low-Dose CT Scans Using Graph Cuts

Automatic anatomy recognition in whole-body PET/CT images

PURPOSE

Whole-body positron emission tomography/computed tomography (PET/CT) has become a standard method of imaging patients with various disease conditions, especially cancer. Body-wide accurate quantification of disease burden in PET/CT images is important for characterizing lesions, staging disease, prognosticating patient outcome, planning treatment, and evaluating disease response to therapeutic interventions. However, body-wide anatomy recognition in PET/CT is a critical first step for accurately and automatically quantifying disease body-wide, body-region-wise, and organwise. This latter process, however, has remained a challenge due to the lower quality of the anatomic information portrayed in the CT component of this imaging modality and the paucity of anatomic details in the PET component. In this paper, the authors demonstrate the adaptation of a recently developed automatic anatomy recognition (AAR) methodology [Udupa et al., "Body-wide hierarchical fuzzy modeling, recognition, and delineation of anatomy in medical images," Med. Image Anal. 18, 752-771 (2014)] to PET/CT images. Their goal was to test what level of object localization accuracy can be achieved on PET/CT compared to that achieved on diagnostic CT images.

METHODS

The authors advance the AAR approach in this work in three fronts: (i) from body-region-wise treatment in the work of Udupa et al. to whole body; (ii) from the use of image intensity in optimal object recognition in the work of Udupa et al. to intensity plus object-specific texture properties, and (iii) from the intramodality model-building-recognition strategy to the intermodality approach. The whole-body approach allows consideration of relationships among objects in different body regions, which was previously not possible. Consideration of object texture allows generalizing the previous optimal threshold-based fuzzy model recognition method from intensity images to any derived fuzzy membership image, and in the process, to bring performance to the level achieved on diagnostic CT and MR images in body-region-wise approaches. The intermodality approach fosters the use of already existing fuzzy models, previously created from diagnostic CT images, on PET/CT and other derived images, thus truly separating the modality-independent object assembly anatomy from modality-specific tissue property portrayal in the image.

RESULTS

Key ways of combining the above three basic ideas lead them to 15 different strategies for recognizing objects in PET/CT images. Utilizing 50 diagnostic CT image data sets from the thoracic and abdominal body regions and 16 whole-body PET/CT image data sets, the authors compare the recognition performance among these 15 strategies on 18 objects from the thorax, abdomen, and pelvis in object localization error and size estimation error. Particularly on texture membership images, object localization is within three voxels on whole-body low-dose CT images and 2 voxels on body-region-wise low-dose images of known true locations. Surprisingly, even on direct body-region-wise PET images, localization error within 3 voxels seems possible.

CONCLUSIONS

The previous body-region-wise approach can be extended to whole-body torso with similar object localization performance. Combined use of image texture and intensity property yields the best object localization accuracy. In both body-region-wise and whole-body approaches, recognition performance on low-dose CT images reaches levels previously achieved on diagnostic CT images. The best object recognition strategy varies among objects; the proposed framework however allows employing a strategy that is optimal for each object.

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.

Lung tumor segmentation in PET images using graph cuts

The aim of segmentation of tumor regions in positron emission tomography (PET) is to provide more accurate measurements of tumor size and extension into adjacent structures, than is possible with visual assessment alone and hence improve patient management decisions. We propose a segmentation energy function for the graph cuts technique to improve lung tumor segmentation with PET. Our segmentation energy is based on an analysis of the tumor voxels in PET images combined with a standardized uptake value (SUV) cost function and a monotonic downhill SUV feature. The monotonic downhill feature avoids segmentation leakage into surrounding tissues with similar or higher PET tracer uptake than the tumor and the SUV cost function improves the boundary definition and also addresses situations where the lung tumor is heterogeneous. We evaluated the method in 42 clinical PET volumes from patients with non-small cell lung cancer (NSCLC). Our method improves segmentation and performs better than region growing approaches, the watershed technique, fuzzy-c-means, region-based active contour and tumor customized downhill.

Machine learning and radiology

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers.

Shape "break-and-repair" strategy and its application to automated medical image segmentation

In three-dimensional medical imaging, segmentation of specific anatomy structure is often a preprocessing step for computer-aided detection/diagnosis (CAD) purposes, and its performance has a significant impact on diagnosis of diseases as well as objective quantitative assessment of therapeutic efficacy. However, the existence of various diseases, image noise or artifacts, and individual anatomical variety generally impose a challenge for accurate segmentation of specific structures. To address these problems, a shape analysis strategy termed "break-and-repair" is presented in this study to facilitate automated medical image segmentation. Similar to surface approximation using a limited number of control points, the basic idea is to remove problematic regions and then estimate a smooth and complete surface shape by representing the remaining regions with high fidelity as an implicit function. The innovation of this shape analysis strategy is the capability of solving challenging medical image segmentation problems in a unified framework, regardless of the variability of anatomical structures in question. In our implementation, principal curvature analysis is used to identify and remove the problematic regions and radial basis function (RBF) based implicit surface fitting is used to achieve a closed (or complete) surface boundary. The feasibility and performance of this strategy are demonstrated by applying it to automated segmentation of two completely different anatomical structures depicted on CT examinations, namely human lungs and pulmonary nodules. Our quantitative experiments on a large number of clinical CT examinations collected from different sources demonstrate the accuracy, robustness, and generality of the shape "break-and-repair" strategy in medical image segmentation.