Digital chest tomosynthesis: The main steps to a computer assisted lung diagnostic system

Hadházi, Dániel; Varga, Roxána; Horváth, Ákos G.; Czetenyi, B.; Horväth, Gábor

doi:10.1109/memea.2015.7145169

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over a series of 45 DTS they achieved relatively high accuracy for lung segmentation and all of the nodules were correctly found. Hadházi et al [18] proposed a domain-specific filters for the enhancement and classification of bright, rounded structures along with a vessel enhancing algorithm based on strain energy filters. To reduce false positive findings supervised vector machine-based classifiers were applied, where features obtained from the vessel enhancement module were used as inputs.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial

et al. 2020

View full text Add to dashboard Cite

Objectives: within this investigation we investigated several approaches to enhance the positive predictive value (PPV) of chest digital tomosynthesis (DTS) in the lung cancer detection Methods: the investigation was carried out within the SOS clinical trial (NCT03645018) for lung cancer screening with DTS. Lung nodules were identified by visual analysis and then classified using the diameter and the radiological aspect of the nodule following a modified lung-RADS classification.Haralick texture features were extracted from the segmented nodules. Both semantic variables and radiomics features were used to build a predictive model using two approaches: logistic regression model on a sub-set of variables selected with backward feature selection or machine learning using the whole sub-set of variables. We used two machine learning methods: a Random Forest and a neural network. Machine learning methods were applied to a training set and validated on a test set. Methods were compared using diagnostic accuracy metrics.Results: binary visual analysis had a good sensitivity (0.95) but a low PPV (0.14). Lung-RADS classification increased the PPV (0.19) but with an unacceptable low sensitivity (0.65). Analogously, logistic regression showed a mildly increased PPV (0.22) and a low sensitivity (0.67). Random Forest demonstrated a low accuracy with a moderate PPV (0.40) but with a dramatically low sensitivity (0.30). Neural network demonstrated to be the best predictor with a nearly perfect PPV (0.95) and a high sensitivity (0.90).Conclusions: among the various technique to reduce the false positive rates of DTS the neural network demonstrated a very high PPV. The use of visual analysis along with neural network could help radiologists to depict a follow-up strategy after a positive DTS.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial

et al. 2020

View full text Add to dashboard Cite

show abstract

Overview of a Digital Tomosynthesis Development: New Approaches for Low-Dose Chest Imaging

Horváth¹,

Wolf²,

Nagy³

et al. 2015

Radiat Prot Dosimetry

View full text Add to dashboard Cite

Lung cancer has the highest mortality rate among all cancer types, and it has especially high occurrence in Hungary. Low-dose computed tomography (LDCT) has been proved to be a beneficial screening method for lung cancer, decreasing the mortality rate by 20 %. Because of the intensifying fears from X-ray radiation, there is a need to develop other modalities that might work with less radiation and have similar sensitivity in lung nodule finding. Digital tomosynthesis (DTS) may be such a modality that can be a real alternative to LDCT. The goal of this article is to summarise the first results of a Hungarian project for developing a DTS system extended with a computer-aided detection system. It describes the main approaches applied and the main benefits of using DTS based on the first clinical examinations.

show abstract

A Study of Pulmonary Nodules from Multi-slice Computed Tomography Using 3-D Structure

Paing

Choomchuay

2017

2017 International Conference on Advanced Computing and Applications (ACOMP)

View full text Add to dashboard Cite

Digital chest tomosynthesis: The main steps to a computer assisted lung diagnostic system

Cited by 3 publications

References 16 publications

Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial

Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial

Overview of a Digital Tomosynthesis Development: New Approaches for Low-Dose Chest Imaging

A Study of Pulmonary Nodules from Multi-slice Computed Tomography Using 3-D Structure

Contact Info

Product

Resources

About