Dataset Information

A comparison study of image features between FFDM and film mammogram images.

ABSTRACT: This work is to provide a direct, quantitative comparison of image features measured by film and full-field digital mammography (FFDM). The purpose is to investigate whether there is any systematic difference between film and FFDM in terms of quantitative image features and their influence on the performance of a computer-aided diagnosis (CAD) system.The authors make use of a set of matched film-FFDM image pairs acquired from cadaver breast specimens with simulated microcalcifications consisting of bone and teeth fragments using both a GE digital mammography system and a screen-film system. To quantify the image features, the authors consider a set of 12 textural features of lesion regions and six image features of individual microcalcifications (MCs). The authors first conduct a direct comparison on these quantitative features extracted from film and FFDM images. The authors then study the performance of a CAD classifier for discriminating between MCs and false positives (FPs) when the classifier is trained on images of different types (film, FFDM, or both).For all the features considered, the quantitative results show a high degree of correlation between features extracted from film and FFDM, with the correlation coefficients ranging from 0.7326 to 0.9602 for the different features. Based on a Fisher sign rank test, there was no significant difference observed between the features extracted from film and those from FFDM. For both MC detection and discrimination of FPs from MCs, FFDM had a slight but statistically significant advantage in performance; however, when the classifiers were trained on different types of images (acquired with FFDM or SFM) for discriminating MCs from FPs, there was little difference.The results indicate good agreement between film and FFDM in quantitative image features. While FFDM images provide better detection performance in MCs, FFDM and film images may be interchangeable for the purposes of training CAD algorithms, and a single CAD algorithm may be applied to either type of images.

SUBMITTER: Jing H

PROVIDER: S-EPMC3396708 | biostudies-other | 2012 Jul

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:PurposeDeveloping deep learning algorithms for breast cancer screening is limited due to the lack of labeled full-field digital mammograms (FFDMs). Since FFDM is a new technique that rose in recent decades and replaced digitized screen-film mammograms (DFM) as the main technique for breast cancer screening, most mammogram datasets were still stored in the form of DFM. A solution for developing deep learning algorithms based on FFDM while leveraging existing labeled DFM datasets is a generative algorithm that generates FFDM from DFM. Generating high-resolution FFDM from DFM remains a challenge due to the limitations of network capacity and lacking GPU memory.MethodIn this study, we developed a deep-learning-based generative algorithm, HRGAN, to generate synthesized FFDM (SFFDM) from DFM. More importantly, our algorithm can keep the image resolution and details while using high-resolution DFM as input. Our model used FFDM and DFM for training. First, a sliding window was used to crop DFMs and FFDMs into 256 × 256 pixels patches. Second, the patches were divided into three categories (breast, background, and boundary) by breast masks. Patches from the DFM and FFDM datasets were paired as inputs for training our model where these paired patches should be sampled from the same category of the two different image sets. U-Net liked generators and modified discriminators with two-channels output, one channel for distinguishing real and SFFDMs and the other for representing a probability map for breast mask, were used in our algorithm. Last, a study was designed to evaluate the usefulness of HRGAN. A mass segmentation task and a calcification detection task were included in the study.ResultsTwo public mammography datasets, the CBIS-DDSM dataset and the INbreast dataset, were included in our experiment. The CBIS-DDSM dataset includes 753 calcification cases and 891 mass cases with verified pathology information, resulting in a total of 3568 DFMs. The INbreast dataset contains a total of 410 FFDMs with annotations of masses, calcifications, asymmetries, and distortions. There were 1784 DFMs and 205 FFDM randomly selected as Dataset A. The remaining DFMs from the CBIS-DDSM dataset were selected as Dataset B. The remaining FFDMs from the INbreast dataset were selected as Dataset C. All DFMs and FFDMs were normalized to 100μm × 100μm in our experiments. A study with a mass segmentation task and a calcification detection task was performed to evaluate the usefulness of HRGAN.ConclusionsThe proposed HRGAN can generate high-resolution SFFDMs from DFMs. Extensive experiments showed the SFFDMs were able to help improve the performance of deep-learning-based algorithms for breast cancer screening on DFM when the size of the training dataset is small.

Project description:BackgroundFour patient-reported outcome (PRO) instruments are commonly used to assess body image in idiopathic scoliosis (IS): the Quality of Life Profile for Spinal Deformities (QLPSD), SRS-22 Self-Image scale, Spinal Appearance Questionnaire (SAQ), and Trunk Appearance Perception Scale (TAPS). The aim of this study is to compare the psychometric properties of these instruments in patients with IS and report the translational/cultural adaptation of the SAQ to Spanish.MethodsThe four instruments in a Spanish version were administered to 80 patients with IS aged 10 to 40 years old. The sample was stratified according to scoliosis magnitude (less and more than 45º). Analysis was also conducted for age groups. The psychometric properties studied included convergent and divergent construct validity, as well as internal consistency. Convergent validity was evaluated by correlation analysis between the self-image instruments and Cobb angle. Divergent validity was assessed with correlation analysis between PRO scores and SRS-22 dimensions scores such as Function, Pain and Mental Health.ResultsIn the overall sample, each of the PRO instruments demonstrated high internal consistency (QLPSD Body Image, α = 0.80; SRS-22 Self Image, α = 0.78; SAQ, α = 0.89; TAPS, α = 0.87), also both for younger and adult patients subgroups. Correlation with curve magnitude was significant for each of the four scales. However, the correlation was higher for the pictorial scales (SAQ Appearance r = 0.61, TAPS r = -0.62) than for the textual scales (QLPSD-bi r = 0.36, SRS-22 Self-Image scale r = -0.41). In the younger group, correlation between Cobb angle and textual scales (QLPSD-bi and SRS-22 Self-Image Scale) was not significant. Body Image scales showed significant correlations with SRS-22 Pain, Function and Mental Health dimensions.ConclusionsAll four instruments tested have good psychometric properties. Pictorial scales (SAQ Appearance and TAPS) correlated better with the radiological magnitude of the curve and this correlation is independent of age. Unexpectedly, all four scales demonstrated significant correlations with non-body image dimensions and the divergent hypothesis was not confirmed. Globally, pictorial scales showed slightly better construct validity to test body image perception than textual scales.

Dataset Information

A comparison study of image features between FFDM and film mammogram images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets