A new dataset of computed-tomography angiography images for computer-aided detection of pulmonary embolism

Masoudi, Mojtaba; Pourreza, Hamid Reza; Saadatmand-Tarzjan, Mahdi; Eftekhari, Noushin; Zargar, F; Rad, Masoud Pezeshki

doi:10.1038/sdata.2018.180

Cited by 46 publications

(25 citation statements)

References 24 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We refer the reader to these references for a description and thorough evaluation of the other methods. The ASU-Mayo method is best described in [15] and the FUM-Mvlab method in [22]. The x-axis scale changes between the left and the right columns.…”

Section: Resultsmentioning

confidence: 99%

“…Second, the scans on which we trained the dataset and the scans on which we tested them come from the same institution and had been obtained with the same acquisition machines, which might bias the results positively. The evaluation on external datasets, such as the one in [22], was left for future work. Third, there is room to improve the segmentation performance of the network, since the baseline network structure is very simple.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Computer Aided Detection of Pulmonary Embolism Using Multi-Slice Multi-Axial Segmentation

2020

View full text Add to dashboard Cite

Pulmonary Embolism (PE) is a respiratory disease caused by blood clots lodged in the pulmonary arteries, blocking perfusion, limiting blood oxygenation, and inducing a higher load on the right ventricle. Pulmonary embolism is diagnosed using contrast enhanced Computed Tomography Pulmonary Angiography (CTPA), resulting in a 3 D image where the pulmonary arteries appear as bright structures, and emboli appear as filling defects, with these often being difficult to see, especially in the subsegmental case. In comparison to an expert panel, the average radiologist has a sensitivity of between 77% and 94 % . Computer Aided Detection (CAD) is regarded as a promising system to detect emboli, but current algorithms are hindered by a high false positive rate. In this paper, we propose a novel methodology for emboli detection. Instead of finding candidate points and characterizing them, we find emboli directly on the whole image slice. Detections across different slices are merged into a single detection volume that is post-processed to generate emboli detections. The system was evaluated on a public PE database of 80 scans. On 20 test scans, our system obtained a per-embolus sensitivity of 68% at a regime of one false positive per scan, improving on state-of-the-art methods. We therefore conclude that our multi-slice emboli segmentation CAD for PE method is a valuable alternative to the standard methods of candidate point selection and classification.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Computer Aided Detection of Pulmonary Embolism Using Multi-Slice Multi-Axial Segmentation

2020

View full text Add to dashboard Cite

show abstract

“…The complete experimental analysis is carried out using MATLAB tool using DICOM images. In this work, we have obtained publically amiable data and their corresponding ground truth [16]. For each patient, the CTA image slices are stored in DICOM format and ground truth is stored in .MAT format.…”

Section: Resultsmentioning

confidence: 99%

Maximum Likelihood Probabilistic Model for Pulmonary Embolism Nodule Detection (ML-PPED) using Computer Vision

2019

IJRTE

View full text Add to dashboard Cite

Computer–aided detection and diagnosis systems have been adopted widely to improve the diagnosis performance by detecting and analyzing the lung diseases. The pulmonary embolism is considered as a fetal condition related to lung where the blood clot cause blockage to the lung arteries and this condition can cause death to the patient. Early detection of blood clot can help to diagnose the pulmonary embolism. In order to detect the PE, lung segmentation and nodule detection is the main task for any CAD system. Several approaches have been introduced to perform the segmentation but the accuracy and false positives of segmentation remains a challenging task in this field. Thus, we focus on the lung segmentation and nodule detection using computer vision approach for PE detection and developed Maximum Likelihood Probabilistic model for Pulmonary Embolism nodule detection (ML-PPED). According to the proposed approach, first of all we extract the lungs regions i.e. left and right lung regions followed by segmentation and finally a maximum likelihood based probabilistic model is developed to detect the lung nodules. The performance of segmentation is measured in terms of dice similarity coefficient and average segmentation error which are computed based on the segmented outcome of the proposed model and ground truth data. The experimental analysis shows that the proposed approach improved the segmentation performance when compared with the existing techniques.

show abstract

“…section “Methods”), targets lung nodule detection. FUMPE 16 contains CT angiography images of 35 subjects for the detection of pulmonary embolisms. KiTS2019 17 is built around the segmentation of kidney tumours in CT images.…”

Section: Background and Summarymentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

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.

show abstract

A new dataset of computed-tomography angiography images for computer-aided detection of pulmonary embolism

Cited by 46 publications

References 24 publications

Computer Aided Detection of Pulmonary Embolism Using Multi-Slice Multi-Axial Segmentation

Computer Aided Detection of Pulmonary Embolism Using Multi-Slice Multi-Axial Segmentation

Maximum Likelihood Probabilistic Model for Pulmonary Embolism Nodule Detection (ML-PPED) using Computer Vision

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

Contact Info

Product

Resources

About