Realistic simulated lung nodule dataset for testing CAD detection and sizing

Ambrosini, Robert; O’Dell, Walter G.

doi:10.1117/12.843996

Cited by 7 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the new lesions are simulated using a mathematical model and inserted into the existing medical images such as the study in [10] for lung nodules in CT, the one in [11] for breast lesions in mammography, and the one in [12] for digital breast tomosynthesis (DBT). In [13]- [16], an actual lesion is firstly extracted from real CT-scan images and then inserted into a new location on other images using image-processing techniques. Our previous works [17], [18] proposed augmentation techniques for creating synthetic images to improve the segmentation network's performance by increasing the number and diversity of training data.…”

Section: Related Workmentioning

confidence: 99%

Urinary Stones Segmentation in Abdominal X-Ray Images Using Cascaded U-Net Pipeline With Stone-Embedding Augmentation and Lesion-Size Reweighting Approach

et al. 2023

View full text Add to dashboard Cite

In this research, we proposed a two-stage pipeline for segmenting urinary stones. The first stage U-Net generated the map localizing the urinary organs in full abdominal x-ray images. Then, this map was used for creating partitioned images input to the second stage U-Net to reduce class imbalance and was also used in stone-embedding augmentation to increase a number of training data. The U-Net model was trained with the combination of real stone-contained images and synthesized stone-embedded images to segment urinary stones on the partitioned input images. In addition, we proposed to use an inverse weighting method in the focal Tversky loss function in order to rebalance lesion size. The U-Net model using our proposed pipeline produced a 71.28% pixel-wise F 2 score and a 69.82% region-wise F 2 score, which were higher than 2.88% and 7.63%, respectively, by a baseline method. Experimental results showed that the proposed method improved urinary stone segmentation results, especially for small stones and stones in uncommon locations.INDEX TERMS Computer-aided detection and diagnosis; urinary stone; deep learning; image segmentation; abdominal X-ray imaging.

show abstract

Section: Related Workmentioning

confidence: 99%

Urinary Stones Segmentation in Abdominal X-Ray Images Using Cascaded U-Net Pipeline With Stone-Embedding Augmentation and Lesion-Size Reweighting Approach

et al. 2023

View full text Add to dashboard Cite

show abstract

“…For example, new lesions are simulated using a mathematical model and then superimposed on existing medical images, as demonstrated in the study in [5] for lung nodules, the one in [6] for mammography, and the one in [7] for digital breast tomosynthesis (DBT). In [8]- [11], actual lesions are extracted from real CT scan images and then inserted at new locations in other images using various blending techniques. In our previous work [12], we proposed a method for superimposing a random urinary stone into normal x-ray images during the training stage, by blending the properties of the inserting stone and background.…”

Section: Related Workmentioning

confidence: 99%

Improvement of Urinary Stone Segmentation Using GAN-Based Urinary Stones Inpainting Augmentation

et al. 2022

View full text Add to dashboard Cite

A urinary stone is a type of abnormality that occurs frequently in the urinary system. An automated segmentation of urinary stones is important for assisting medical doctors in early diagnosis and further treatment. While deep learning techniques are effective for image segmentation, they require a large number of datasets to achieve high accuracy. We proposed a GAN-based augmentation technique for creating synthetic images based on stone and non-stone mask inputs in order to improve the segmentation network's performance by increasing the number and diversity of training data. The synthetic training images were generated from stone-contained images and stone-free images using existing stone ground truth and corresponding stone location maps, respectively. To segment urinary stones from full abdominal x-ray images, we trained the MultiResUnet model using both original stone-contained and our proposed synthetic samples. The proposed method obtained a 69.59% pixel-wise F 1 score and a 68.14% region-wise F 1 score, which achieved an improvement of 2.12% and 2.13%, respectively, over a model trained with only the original stone-contained dataset.

show abstract

“…1,2 Other researchers investigated a different approach that consists of extracting a lesion from one image and blending it into another using image processing techniques. 3,4 Our group has been working on a sophisticated implementation of this last approach for insertion of nodules on CT images [5][6][7] and insertion of masses on mammograms. 8 A potential application of computational lesion insertion is the assessment of a computer-aided detection (CADe) device for image acquisition technology.…”

Section: Introductionmentioning

confidence: 99%

Computational insertion of microcalcification clusters on mammograms: reader differentiation from native clusters and computer-aided detection comparison

2018

View full text Add to dashboard Cite

Mammographic computer-aided detection (CADe) devices are typically first developed and assessed for a specific "original" acquisition system. When developers are ready to apply their CADe device to a mammographic acquisition system, they typically assess the device with images acquired using the system. Collecting large repositories of clinical images containing verified lesion locations acquired by a system is costly and time consuming. We previously developed an image blending technique that allows users to seamlessly insert regions of interest (ROIs) from one medical image into another image. Our goal is to assess the performance of this technique for inserting microcalcification clusters from one mammogram into another, with the idea that when fully developed, our technique may be useful for reducing the clinical data burden in the assessment of a CADe device for use with an image acquisition system. We first perform a reader study to assess whether experienced observers can distinguish between computationally inserted and native clusters. For this purpose, we apply our insertion technique to 55 clinical cases. ROIs containing microcalcification clusters from one breast of a patient are inserted into the contralateral breast of the same patient. The analysis of the reader ratings using receiver operating characteristic (ROC) methodology indicates that inserted clusters cannot be reliably distinguished from native clusters (area under the ROC curve ¼ 0.58 AE 0.04). Furthermore, CADe sensitivity is evaluated on mammograms of 68 clinical cases with native and inserted microcalcification clusters using a commercial CADe system. The average by-case sensitivities for native and inserted clusters are equal, 85.3% (58/68). The average by-image sensitivities for native and inserted clusters are 72.3% and 67.6%, respectively, with a difference of 4.7% and a 95% confidence interval of [−2.1 11.6]. These results demonstrate the potential for using the inserted microcalcification clusters for assessing mammographic CADe devices.

show abstract

Realistic simulated lung nodule dataset for testing CAD detection and sizing

Cited by 7 publications

References 22 publications

Urinary Stones Segmentation in Abdominal X-Ray Images Using Cascaded U-Net Pipeline With Stone-Embedding Augmentation and Lesion-Size Reweighting Approach

Urinary Stones Segmentation in Abdominal X-Ray Images Using Cascaded U-Net Pipeline With Stone-Embedding Augmentation and Lesion-Size Reweighting Approach

Improvement of Urinary Stone Segmentation Using GAN-Based Urinary Stones Inpainting Augmentation

Computational insertion of microcalcification clusters on mammograms: reader differentiation from native clusters and computer-aided detection comparison

Contact Info

Product

Resources

About