Dataset Information

LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction.

ABSTRACT: Deep learning approaches for tomographic image reconstruction have become very effective and have been demonstrated to be competitive in the field. Comparing these approaches is a challenging task as they rely to a great extent on the data and setup used for training. With the Low-Dose Parallel Beam (LoDoPaB)-CT dataset, we provide a comprehensive, open-access database of computed tomography images and simulated low photon count measurements. It is suitable for training and comparing deep learning methods as well as classical reconstruction approaches. The dataset contains over 40000 scan slices from around 800 patients selected from the LIDC/IDRI database. The data selection and simulation setup are described in detail, and the generating script is publicly accessible. In addition, we provide a Python library for simplified access to the dataset and an online reconstruction challenge. Furthermore, the dataset can also be used for transfer learning as well as sparse and limited-angle reconstruction scenarios.

SUBMITTER: Leuschner J

PROVIDER: S-EPMC8052416 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction.

Leuschner Johannes J Schmidt Maximilian M Baguer Daniel Otero DO Maass Peter P

Scientific data 20210416 1

Deep learning approaches for tomographic image reconstruction have become very effective and have been demonstrated to be competitive in the field. Comparing these approaches is a challenging task as they rely to a great extent on the data and setup used for training. With the Low-Dose Parallel Beam (LoDoPaB)-CT dataset, we provide a comprehensive, open-access database of computed tomography images and simulated low photon count measurements. It is suitable for training and comparing deep learni ...[more]

PMID: 33863917

Similar Datasets

Project description:Dynamic cerebral perfusion computed tomography (DCPCT) has the ability to evaluate the hemodynamic information throughout the brain. However, due to multiple 3-D image volume acquisitions protocol, DCPCT scanning imposes high radiation dose on the patients with growing concerns. To address this issue, in this paper, based on the robust principal component analysis (RPCA, or equivalently the low-rank and sparsity decomposition) model and the DCPCT imaging procedure, we propose a new DCPCT image reconstruction algorithm to improve low-dose DCPCT and perfusion maps quality via using a powerful measure, called Kronecker-basis-representation tensor sparsity regularization, for measuring low-rankness extent of a tensor. For simplicity, the first proposed model is termed tensor-based RPCA (T-RPCA). Specifically, the T-RPCA model views the DCPCT sequential images as a mixture of low-rank, sparse, and noise components to describe the maximum temporal coherence of spatial structure among phases in a tensor framework intrinsically. Moreover, the low-rank component corresponds to the "background" part with spatial-temporal correlations, e.g., static anatomical contribution, which is stationary over time about structure, and the sparse component represents the time-varying component with spatial-temporal continuity, e.g., dynamic perfusion enhanced information, which is approximately sparse over time. Furthermore, an improved nonlocal patch-based T-RPCA (NL-T-RPCA) model which describes the 3-D block groups of the "background" in a tensor is also proposed. The NL-T-RPCA model utilizes the intrinsic characteristics underlying the DCPCT images, i.e., nonlocal self-similarity and global correlation. Two efficient algorithms using alternating direction method of multipliers are developed to solve the proposed T-RPCA and NL-T-RPCA models, respectively. Extensive experiments with a digital brain perfusion phantom, preclinical monkey data, and clinical patient data clearly demonstrate that the two proposed models can achieve more gains than the existing popular algorithms in terms of both quantitative and visual quality evaluations from low-dose acquisitions, especially as low as 20 mAs.

Project description:PurposeTo describe a large, publicly available dataset comprising computed tomography (CT) projection data from patient exams, both at routine clinical doses and simulated lower doses.Acquisition and validation methodsThe library was developed under local ethics committee approval. Projection and image data from 299 clinically performed patient CT exams were archived for three types of clinical exams: noncontrast head CT scans acquired for acute cognitive or motor deficit, low-dose noncontrast chest scans acquired to screen high-risk patients for pulmonary nodules, and contrast-enhanced CT scans of the abdomen acquired to look for metastatic liver lesions. Scans were performed on CT systems from two different CT manufacturers using routine clinical protocols. Projection data were validated by reconstructing the data using several different reconstruction algorithms and through use of the data in the 2016 Low Dose CT Grand Challenge. Reduced dose projection data were simulated for each scan using a validated noise-insertion method. Radiologists marked location and diagnosis for detected pathologies. Reference truth was obtained from the patient medical record, either from histology or subsequent imaging.Data format and usage notesProjection datasets were converted into the previously developed DICOM-CT-PD format, which is an extended DICOM format created to store CT projections and acquisition geometry in a nonproprietary format. Image data are stored in the standard DICOM image format and clinical data in a spreadsheet. Materials are provided to help investigators use the DICOM-CT-PD files, including a dictionary file, data reader, and user manual. The library is publicly available from The Cancer Imaging Archive (https://doi.org/10.7937/9npb-2637).Potential applicationsThis CT data library will facilitate the development and validation of new CT reconstruction and/or denoising algorithms, including those associated with machine learning or artificial intelligence. The provided clinical information allows evaluation of task-based diagnostic performance.

Project description:ObjectiveTo evaluate the impact of iterative reconstruction (IR) on the assessment of diffuse interstitial lung disease (DILD) using CT.Materials and methodsAn American College of Radiology (ACR) phantom (module 4 to assess spatial resolution) was scanned with 10-100 effective mAs at 120 kVp. The images were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction (ASIR), with blending ratios of 0%, 30%, 70% and 100%, and model-based iterative reconstruction (MBIR), and their spatial resolution was objectively assessed by the line pair structure method. The patient study was based on retrospective interpretation of prospectively acquired data, and it was approved by the institutional review board. Chest CT scans of 23 patients (mean age 64 years) were performed at 120 kVp using 1) standard dose protocol applying 142-275 mA with dose modulation (high-resolution computed tomography [HRCT]) and 2) low-dose protocol applying 20 mA (low dose CT, LDCT). HRCT images were reconstructed with FBP, and LDCT images were reconstructed using FBP, ASIR, and MBIR. Matching images were randomized and independently reviewed by chest radiologists. Subjective assessment of disease presence and radiological diagnosis was made on a 10-point scale. In addition, semi-quantitative results were compared for the extent of abnormalities estimated to the nearest 5% of parenchymal involvement.ResultsIn the phantom study, ASIR was comparable to FBP in terms of spatial resolution. However, for MBIR, the spatial resolution was greatly decreased under 10 mA. In the patient study, the detection of the presence of disease was not significantly different. The values for area under the curve for detection of DILD by HRCT, FBP, ASIR, and MBIR were as follows: 0.978, 0.979, 0.972, and 0.963. LDCT images reconstructed with FBP, ASIR, and MBIR tended to underestimate reticular or honeycombing opacities (-2.8%, -4.1%, and -5.3%, respectively) and overestimate ground glass opacities (+4.6%, +8.9%, and +8.5%, respectively) compared to the HRCT images. However, the reconstruction methods did not differ with respect to radiologic diagnosis.ConclusionThe diagnostic performance of LDCT with MBIR was similar to that of HRCT in typical DILD cases. However, caution should be exercised when comparing disease extent, especially in follow-up studies with IR.

Dataset Information

LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction.

Publications

LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets