Automated nodule location and size estimation using a multi-scale laplacian of Gaussian filtering approach

Abstract

Abstract-Estimation of nodule location and size is an important pre-processing step in some nodule segmentation algorithms to determine the size and location of the region of interest. Ideally, such estimation methods will consistently find the same nodule location irregardless of where the the seed point (provided either manually or by a nodule detection algorithm) is placed relative to the "true" center of the nodule, and the size should be a reasonable estimate of the true nodule size. We developed a method that estimates nodule location and size using multi-scale Laplacian of Gaussian (LoG) filtering. Nodule candidates near a given seed point are found by searching for blob-like regions with high filter response. The candidates are then pruned according to filter response and location, and the remaining candidates are sorted by size and the largest candidate selected. This method was compared to a previously published template-based method. The methods were evaluated on the basis of stability of the estimated nodule location to changes in the initial seed point and how well the size estimates agreed with volumes determined by a semi-automated nodule segmentation method. The LoG method exhibited better stability to changes in the seed point, with 93% of nodules having the same estimated location even when the seed point was altered, compared to only 52% of nodules for the templatebased method. Both methods also showed good agreement with sizes determined by a nodule segmentation method, with an average relative size difference of 5% and -5% for the LoG and template-based methods respectively.

A joint ROI extraction filter for computer aided lung nodule detection

“…For example, in [21] Gaussian has been used for locate pulmonary nodules, and other studies have shown that the characteristic scale of a Laplacian of Gaussian (LoG) agreed well with radiologistsąŕ estimates of nodule size [22,23]. Kong et al [24] propose a generalized Laplacian of Gaussian (LoG) (gLoG) filter for detecting general elliptical blob structures in images,Miao et al [25] used rank order LoG filter for interest point detection, and Shi et al [2] proposed a dot enhancement filter by combining Hessian matrix and LoG filter.…”

Shaping the Cell and the Future: Recent Advancements in Biophysical Aspects Relevant to Regenerative Medicine

“…The intensity threshold is the oldest method that is based on measuring the absolute intensity difference between cells and black background, either by global or local adaptive thresholding. Another approach is feature detection, which uses image intensity-derived features that are found using linear image filtering or others such as Gaussian or Laplacian-of-Gaussian filters [45][46][47]. In contrast, the morphological filtering method uses e.g., nonlinear filters to examine geometrical and topological properties of objects within images.…”

Tracking Virus Particles in Fluorescence Microscopy Images Using Multi-Scale Detection and Multi-Frame Association

“…However, all approaches described above use only the information from a single scale. Multi-scale approaches have been widely used for object detection in computer vision (e.g., [18], [19], [20]) and medical image analysis (e.g., [21], [22], [23], [24]). For detection of biological particles in microscopy images, a wavelet-based approach was introduced which uses information from multiple scales to increase the robustness to noise [25], [26].…”