False-positive reduction using Hessian features in computer-aided detection of pulmonary nodules on thoracic CT images

Sahiner, Berkman; Ge, Zhanyu; Chan, Heang Ping; Hadjiiski, Lubomir M.; Bogot, Naama; Cascade, Philip N.; Kazerooni, Ella A.

doi:10.1117/12.595714

Cited by 7 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CAD system in our study uses some of the components of a previously developed CAD system [33], [34], [35], [36], [37]. This system consisted of three main modules: pre-screening, feature extraction, and classification.…”

Section: Methodsmentioning

confidence: 99%

Seamless Lesion Insertion for Data Augmentation in CAD Training

Pezeshk

Petrick

Chen

et al. 2017

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

The performance of a classifier is largely dependent on the size and representativeness of data used for its training. In circumstances where accumulation and/or labeling of training samples is difficult or expensive, such as medical applications, data augmentation can potentially be used to alleviate the limitations of small datasets. We have previously developed an image blending tool that allows users to modify or supplement an existing CT or mammography dataset by seamlessly inserting a lesion extracted from a source image into a target image. This tool also provides the option to apply various types of transformations to different properties of the lesion prior to its insertion into a new location. In this study, we used this tool to create synthetic samples that appear realistic in chest CT. We then augmented different size training sets with these artificial samples, and investigated the effect of the augmentation on training various classifiers for the detection of lung nodules. Our results indicate that the proposed lesion insertion method can improve classifier performance for small training datasets, and thereby help reduce the need to acquire and label actual patient data.

show abstract

Section: Methodsmentioning

confidence: 99%

Seamless Lesion Insertion for Data Augmentation in CAD Training

Pezeshk

Petrick

Chen

et al. 2017

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to gain a good specificity for the enhancement of blood vessels, Sato et al [11] developed a line enhancement filter based on the eigenvalues of Hessian matrix, and generalized their filter for highlighting the blob-like and sheet-like structures in 3D image space [12]. Those enhancement filters were further improved by Li et al [13], and Sahiner et al [15].…”

Section: Related Workmentioning

confidence: 97%

“…Some nodules, especially those with ground-glass opacity (GGO), may have very low CT values and low contrast, which makes the nodule detection difficult using those model based methods. Thus the second-order derivative information was extracted for enhancing and analysing the blob-like and line-like objects by employing the Hessian Matrix, which has been shown to be useful in the literature [10,11,12,13,14,15].…”

Section: Introductionmentioning

confidence: 99%

Enhancement Filter for Computer-Aided Detection of Pulmonary Nodules on Thoracic CT images

Zhao

2006

Sixth International Conference on Intelligent Systems Design and Applications

View full text Add to dashboard Cite

Computer-aided detection (CAD) schemes can assist radiologists in the early detection of lung cancer which is crucial to the chance for curative treatment. Characterizing the pulmonary nodules in the Multislice X-ray computed tomography (CT) images is notoriously difficult. This is due to the fact that the anatomical structures such as blood vessels, bronchi, and alveoli are subject to partial volume effects. Furthermore, the nodules connected with other dense anatomical structures increases the detection difficulties.In this paper, we propose a multiscale enhancement filter to improve the sensitivity for nodule detection, which is based on the undecimated wavelet transform and the eigenvalues of Yu matrix in multiplanar slices. As a preprocessing step of CAD for nodule detection, our enhancement filter can simultaneously enhance blob-like objects and suppress line-like structures. Therefore, it would be useful for reducing the number of false positives. We applied our enhancement filter to synthesized images and real medical images to demonstrate that it works well on enhancing a specific shape and suppressing other shapes. Our approach proposed in this paper is generic and can be applied for the analysis of blob-like structures in various other applications.Index Terms -biomedical image, image enhancement, nodule detection, undecimated wavelet, Yu matrix.

show abstract

“…The Curvedness feature measures the magnitude of the curvedness at a point where zero (0) is flat. This methodology has been applied to reject false positives (Sahiner, et al 2005) and has been correlated with the LIDC ratings for spiculation (Wiemker, et al 2009). …”

Section: Image Featuresmentioning

confidence: 99%

Predicting LIDC diagnostic characteristics by combining spatial and diagnostic opinions

2010

View full text Add to dashboard Cite

Computer-aided diagnostic characterization (CADc) aims to support medical imaging decision making by objectively rating the radiologists' subjective, perceptual opinions of visual diagnostic characteristics of suspicious lesions. This research uses the publicly available Lung Image Database Consortium (LIDC) collection of radiologists' outlines of nodules and ratings of boundary and shape characteristics: spiculation, margin, lobulation, and sphericity. The approach attempts to reduce the observed disagreement between radiologists on the extent of nodules by combining their spatial opinion using probability maps to create regions of interest (ROIs). From these ROIs, images features are extracted and combined using machine learning models to predict a combined opinion, the median rating and a thresholded, binary version of their diagnostic characteristics. The results show slight to fair agreement-linear-weighted Kappa-between the CADc models and median radiologist opinion for the full scale five-level rating and fair to moderate agreement using a binary version of the median radiologist opinion.

show abstract

False-positive reduction using Hessian features in computer-aided detection of pulmonary nodules on thoracic CT images

Cited by 7 publications

References 0 publications

Seamless Lesion Insertion for Data Augmentation in CAD Training

Seamless Lesion Insertion for Data Augmentation in CAD Training

Enhancement Filter for Computer-Aided Detection of Pulmonary Nodules on Thoracic CT images

Predicting LIDC diagnostic characteristics by combining spatial and diagnostic opinions

Contact Info

Product

Resources

About