Automatic detection of lung nodules in CT datasets based on stable 3D mass–spring models

Abstract

a b s t r a c tWe propose a computer-aided detection (CAD) system which can detect small-sized (from 3 mm) pulmonary nodules in spiral CT scans. A pulmonary nodule is a small lesion in the lungs, round-shaped (parenchymal nodule) or worm-shaped (juxtapleural nodule). Both kinds of lesions have a radiodensity greater than lung parenchyma, thus appearing white on the images. Lung nodules might indicate a lung cancer and their early stage detection arguably improves the patient survival rate. CT is considered to be the most accurate imaging modality for nodule detection. However, the large amount of data per examination makes the full analysis difficult, leading to omission of nodules by the radiologist. We developed an advanced computerized method for the automatic detection of internal and juxtapleural nodules on low-dose and thin-slice lung CT scan. This method consists of an initial selection of nodule candidates list, the segmentation of each candidate nodule and the classification of the features computed for each segmented nodule candidate.The presented CAD system is aimed to reduce the number of omissions and to decrease the radiologist scan examination time. Our system locates with the same scheme both internal and juxtapleural nodules. For a correct volume segmentation of the lung parenchyma, the system uses a Region Growing (RG) algorithm and an opening process for including the juxtapleural nodules. The segmentation and the extraction of the suspected nodular lesions from CT images by a lung CAD system constitutes a hard task. In order to solve this key problem, we use a new Stable 3D Mass-Spring Model (MSM) combined with a spline curves reconstruction process. Our model represents concurrently the characteristic gray value range, the directed contour information as well as shape knowledge, which leads to a much more robust and efficient segmentation process. For distinguishing the real nodules among nodule candidates, an additional classification step is applied; furthermore, a neural network is applied to reduce the false positives (FPs) after a doublethreshold cut. The system performance was tested on a set of 84 scans made available by the Lung Image Database Consortium (LIDC) annotated by four expert radiologists. The detection rate of the system is 97% with 6.1 FPs/CT. A reduction to 2.5 FPs/CT is achieved at 88% sensitivity. We presented a new 3D segmentation technique for lung nodules in CT datasets, using deformable MSMs. The result is a efficient segmentation process able to converge, identifying the shape of the generic ROI, after a few iterations. Our suitable results show that the use of the 3D AC model and the feature analysis based FPs reduction process constitutes an accurate approach to the segmentation and the classification of lung nodules.

Automatic 3D pulmonary nodule detection in CT images: A survey

“…After this analysis, only 38 articles [24,4,18,22,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58] were identified as 3D automated algorithms to segment lung nodules in CT images, the target of this work.…”

“…This stage is important since the lungs also contain several structures that can be confused with nodules. Just eight of the selected works for this review indicate the preprocessing techniques used: linear interpolation [26,29,46], median filter [27,28], morphological Hat operation [28], Gaussian filter [32,52] and weighted-sum filter [51].…”

“…The radiologist may also suffer interference factors such as fatigue, Authors Computational technique(s) Choi and Choi [24], Santos et al [4], Chen et al [27] and Li and Doi [80] Hessian matrix based method El-Baz et al [22] and Le et al [81] Genetic algorithm template matching Cascio et al [26] Stable 3D mass-spring models Soltaninejad, Keshani and Tajeripour [28] k-Nearest Neighbors (k-NN) classifier and active contour Suiyuan and Junfeng [29] Thresholding Awai et al [82] Sieve filter Tanino et al [83] Variable n-quoit filter Riccardi et al [30] 3D fast radial transform Namin et al [32] and Murphy et al [84] Shape index Ozekes, Osman and Ucan [38] 3D template matching Ge et al [45] Adaptive weighted k-means clustering Yamada et al [85] and Kanazawa et al [86] Fuzzy clustering Mekada et al [51] Maximum distance inside a connected component Mao et al [87] Fragmentary window filtering Mendonça et al [88] Curvature tensor Paik et al [89] Statistical shape model Agam and Armato [90] Correlation-based enhancement filters Wang et al [25] and Armato III et al [91] Multiple gray-level thresholding Saita et al [92] 3D labeling method subjectivity of the analysis, images acquired with improper configuration of the equipment and noise. A detailed analysis of the LIDC-IDRI database can help us understand the difficulties encountered during this task.…”

“…Computational classifier Santos et al [4], Wang et al [25], Choi and Choi [24], Riccardi et al [30], Liu et al [31], Ozekes and Osman [37], Yang, Periaswamy and Wu [39] and Orozco et al [94] Support vector machines (SVM) El-Baz et al [22] Bayesian supervised Cascio et al [26], Ashwin et al [72], Lin et al [95] and Bellotti et al [96] Artificial neural networks (ANN)…”

“…Cascio et al [26] proposed an aid diagnosis system able to detect small lung nodules (3 mm diameter) on CT scans based on stable 3D mass-spring models. This method consists of an automated initial selection from the list of potential nodules (isolated and juxtapleural), and their respective segmentation and classification.…”