Benign features of infection‐related tumor‐like lesions of the lung: A retrospective imaging review study

Huang, Chun-Chao; Hung, Sho-Ting; Chang, Wei‐Jen; Sheu, Chin-Yin

doi:10.1111/1754-9485.12588

Cited by 3 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can intuitively reflect similar or different manifestations of lesions caused by a different pathological process. Due to the exudation and fibroplasias, ill-defined boundaries and peripheral changes were more common in ILs than in MLs in our study (27)(28)(29). In contrast, more MLs in our study had lobulation and spiculation due to the variations in differentiation and growth rate of cancer cells and the contraction of internal fibers.…”

Section: Discussioncontrasting

confidence: 58%

Sensitivity and specificity of computed tomography hypodense sign when differentiating pulmonary inflammatory and malignant mass-like lesions

Fu¹,

Lv²,

Lv³

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Hypodense sign (HyS) reportedly is associated with pulmonary fungal infection, while it also common in many non-fungal lesions. This study aims to determine the significance of a HyS presented on contrast-enhanced computed tomography (CECT) when distinguishing pulmonary inflammatory from malignant mass-like lesions.Methods: From January 2013 to January 2021, we retrospectively evaluated the clinical and computed tomography (CT) data of patients with pathologically confirmed pulmonary inflammatory lesions (ILs) and malignant lesions (MLs). We analyzed and compared the CT features of the HyS in MLs and ILs, and then evaluated whether the HyS helped to differentiate MLs and ILs.Results: There were significant differences in age and tumor markers between patients with ILs and MLs (both P<0.05). Compared with that in MLs, the occurrence of the HyS in ILs was higher (62.81% vs.28.81%; P<0.0001). In ILs, more HyS were single, round or oval, well-defined, and had lower enhancement (ΔCT). Logistic regression analysis revealed that an ill-defined boundary, peripheral fibrosis, presence of a well-defined HyS, and a ΔCT value of the HyS <9.5 Hounsfield units (HU) were independent indicators for predicting ILs. After including the HyS CT features, the area under the curve (AUC) of the model predicting ILs increased from 0.953 to 0.986 with a sensitivity of 96.03% and a specificity of 94.03% (P=0.0027). Conclusions:The HyS is more common in ILs than in MLs. A single, regular, and well-defined HyS with a ΔCT value of <9.5 HU on CECT is highly suggestive of ILs. Combining the HyS with other morphological features could improve the diagnosis accuracy of pulmonary mass-like lesions.

show abstract

Section: Discussioncontrasting

confidence: 58%

Sensitivity and specificity of computed tomography hypodense sign when differentiating pulmonary inflammatory and malignant mass-like lesions

Fu¹,

Lv²,

Lv³

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…In addition, the incidence of pneumonia is high in working-age patients and is also the leading infectious disease in that population [3]. Features of pulmonary lesions, such as their shape, margin, and orientation, are fundamental for predicting treatment outcomes as well as in distinguishing benign and malignant lesions [5][6][7]. Thus, precise and reliable segmentation is required for quantification in clinical practice.…”

Section: Introductionmentioning

confidence: 99%

Boundary Restored Network for Subpleural Pulmonary Lesion Segmentation on Ultrasound Images at Local and Global Scales

Zhang

et al. 2020

J Digit Imaging

View full text Add to dashboard Cite

To evaluate the application of machine learning for the detection of subpleural pulmonary lesions (SPLs) in ultrasound (US) scans, we propose a novel boundary-restored network (BRN) for automated SPL segmentation to avoid issues associated with manual SPL segmentation (subjectivity, manual segmentation errors, and high time consumption). In total, 1612 ultrasound slices from 255 patients in which SPLs were visually present were exported. The segmentation performance of the neural network based on the Dice similarity coefficient (DSC), Matthews correlation coefficient (MCC), Jaccard similarity metric (Jaccard), Average Symmetric Surface Distance (ASSD), and Maximum symmetric surface distance (MSSD) was assessed. Our dual-stage boundary-restored network (BRN) outperformed existing segmentation methods (U-Net and a fully convolutional network (FCN)) for the segmentation accuracy parameters including DSC (83.45 ± 16.60%), MCC (0.8330 ± 0.1626), Jaccard (0.7391 ± 0.1770), ASSD (5.68 ± 2.70 mm), and MSSD (15.61 ± 6.07 mm). It also outperformed the original BRN in terms of the DSC by almost 5%. Our results suggest that deep learning algorithms aid fully automated SPL segmentation in patients with SPLs. Further improvement of this technology might improve the specificity of lung cancer screening efforts and could lead to new applications of lung US imaging.

show abstract

Long-term cancer risk associated with lung nodules observed on low-dose screening CT scans

Pinsky

Gierada

2020

Lung Cancer

View full text Add to dashboard Cite

Benign features of infection‐related tumor‐like lesions of the lung: A retrospective imaging review study

Cited by 3 publications

References 49 publications

Sensitivity and specificity of computed tomography hypodense sign when differentiating pulmonary inflammatory and malignant mass-like lesions

Sensitivity and specificity of computed tomography hypodense sign when differentiating pulmonary inflammatory and malignant mass-like lesions

Boundary Restored Network for Subpleural Pulmonary Lesion Segmentation on Ultrasound Images at Local and Global Scales

Long-term cancer risk associated with lung nodules observed on low-dose screening CT scans

Contact Info

Product

Resources

About