Incorporation of a computer-aided vessel-suppression system to detect lung nodules in CT images: effect on sensitivity and reading time in routine clinical settings

Takaishi, Tetsuo; Ozawa, Yuichi; Bando, Yuya; Yamamoto, Akiko; Okochi, Sachiko; Suzuki, Hirochika; Shibamoto, Yuta

doi:10.1007/s11604-020-01043-y

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, if the boundaries are clear with thick spicules, the probability to be benign is relatively high ( 30 ). (IV) The surrounding structure: in the surrounding manifestations, such as inflammatory manifestations, emphysema, obstructive pneumonia, obstructive local atelectasis, or local infiltration and vascular penetration, the probability of malignancy is relatively high ( 31 ). Contrastingly, for example, for PNs with nothing around them, such as satellite lesions, these manifestations may suggest small calcification, and if the boundaries are clear, the probability is relatively high to be benign ( 32 ).…”

Section: Discussionmentioning

confidence: 99%

The predictive value of chest computed tomography images, tumor markers, and metabolomics in the identification of benign and malignant pulmonary nodules

Xu¹,

Ge²,

Liu³

et al. 2023

J Thorac Dis

View full text Add to dashboard Cite

Background Invasive puncture biopsy is currently the main method of identifying benign and malignant pulmonary nodules (PNs). This study aimed to investigate the application effect of chest computed tomography (CT) images, tumor markers (TMs), and metabolomics in the identification of benign and malignant PNs (MPNs). Methods A total of 110 patients with PNs who were hospitalized in Dongtai Hospital of Traditional Chinese Medicine from March 2021 to March 2022 were selected as the study cohort. A retrospective analysis study of chest CT imaging, serum TMs testing, and plasma fatty acid (FA) metabolomics was performed on all participants. Results According to the pathological results, participants were divided into a MPN group (n=72) and a benign PN (BPN) group (n=38). The morphological signs of CT images, the levels and positive rate of serum TMs, and the plasma FA indicator were compared between groups. There were significant differences between the MPN group and the BPN group in the CT morphological signs, including location of PN and the number of patients with or without lobulation sign, spicule sign, and vessel convergence sign (P<0.05). Serum carcinoembryonic antigen (CEA), cytokeratin-19 fragment (CYFRA 21-1), neuron-specific enolase (NSE), and squamous cell carcinoma antigen (SCC-Ag) were not significantly different between the 2 groups. The serum contents of CEA and CYFRA 21-1 in the MPN group were remarkably higher than those in the BPN group (P<0.05). The plasma levels of palmitic acid, total omega-3 polyunsaturated FA (W3), nervonic acid, stearic acid, docosatetraenoic acid, linolenic acid, eicosapentaenoic acid, total saturated FA, and total FA were much higher in the MPN group than the BPN group (P<0.05). Conclusions In conclusion, chest CT images and TMs, combined with metabolomics, has a good application effect in the diagnosis of BPNs and MPNs, and is worthy of further promotion.

show abstract

Section: Discussionmentioning

confidence: 99%

The predictive value of chest computed tomography images, tumor markers, and metabolomics in the identification of benign and malignant pulmonary nodules

Xu¹,

Ge²,

Liu³

et al. 2023

J Thorac Dis

View full text Add to dashboard Cite

show abstract

“…2 ) [ 42 ]. On the other hand, in the detection studies reviewed for CT using the AI-based CAD system [ 37 , 38 , 43 ], the sensitivity ranges from 61.6 to 98.1%, and the value of the FP per scan ranges from 0.125 to 32. Pulmonary nodules have been already detected with high area under the curve (AUC) values close to 1.…”

Section: Methodsmentioning

confidence: 99%

New trend in artificial intelligence-based assistive technology for thoracic imaging

Yanagawa,

Ito,

Nozaki

et al. 2023

Radiol med

View full text Add to dashboard Cite

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

show abstract

Incorporation of a computer-aided vessel-suppression system to detect lung nodules in CT images: effect on sensitivity and reading time in routine clinical settings

Cited by 2 publications

References 15 publications

The predictive value of chest computed tomography images, tumor markers, and metabolomics in the identification of benign and malignant pulmonary nodules

The predictive value of chest computed tomography images, tumor markers, and metabolomics in the identification of benign and malignant pulmonary nodules

New trend in artificial intelligence-based assistive technology for thoracic imaging

Contact Info

Product

Resources

About