The additional value of the lateral chest radiograph for the detection of small pulmonary nodules—a ROC analysis

Kluthke, Robin Alexander; Kickuth, Ralph; Bansmann, P. M.; Tüshaus, Carolin; Adams, Stefan; Liermann, D.; Kirchner, Johannes

doi:10.1259/bjr.20160394

Cited by 6 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We observed that the material-suppressed iodine image, as a virtual non-enhanced CT, which has a perfect image match, can reduce the measurement error from the position change of SPNs in different phases. We also found that the area under the curve of the enhancement degree [21,22], iodine concentration and 40 keV and 50 keV monochromatic the arterial phase were similar, which may be due to the linear correlation between CT attenuation value and iodine concentration for both monochromatic and polychromatic images [23]; thus, we did not do a series of parallel tests.…”

Section: Discussionmentioning

confidence: 92%

Energy spectrum computed tomography improves the differentiation between benign and malignant solitary pulmonary nodules

Zhao

Chai

Zhang

et al. 2019

CIM

View full text Add to dashboard Cite

Purpose: To evaluate the diagnostic efficiency of computed tomography (CT) values at the 40~140 keV monochromatic level for the differential diagnosis of solitary pulmonary nodules (SPNs). Methods: Energy spectrum CT data of 44 patients with SPNs were analyzed retrospectively; 24 patients with malignant SPNs served as the malignant group and 20 patients with benign SPNs served as the benign group. The basic material concentration and the enhancement degree differences in double-phase enhanced scans were compared between the two groups. The sensitivity and specificity were calculated to determine diagnosis, and were compared with the pathology results. Results: The CT values at the 40~90 keV monochromatic level and the iodine concentrations of malignant group were higher than those of benign group in the arterial phase (all P < 0.05). The enhancement degree of the malignant group was higher than that for the benign group in the arterial phase (36.36 ± 33.18 HU vs 16.93 ± 24.17 HU t = 2.243, P = 0.030); however, the enhancement degrees of the two groups were similar in the venous phase (21.99 ± 15.87 HU vs 17.62 ± 24.15 HU t = 0.694, P = 0.493). The area under the curve of the enhancement degree in the arterial phase was 0.792. Conclusions: Monochromatic imaging and base material concentration of energy spectrum CT can help differentiate between benign and malignant SPNs.

show abstract

Section: Discussionmentioning

confidence: 92%

Energy spectrum computed tomography improves the differentiation between benign and malignant solitary pulmonary nodules

Zhao

Chai

Zhang

et al. 2019

CIM

View full text Add to dashboard Cite

show abstract

“…A lateral chest X-ray taken additional to the postero-anterior view may not improve the sensitivity or specificity of detection of conditions like pneumonia [1] . Lateral view of the thorax on the chest X-ray also does not give any additional benefit in detecting small pulmonary nodules [2] . CT chest is also proven to be superior to chest X-ray in patients with major blunt trauma [3] , [4] .…”

Section: Discussionmentioning

confidence: 99%

The forgotten view: Chest X-ray - Lateral view

Ittyachen

Vijayan

Isac

2017

Respiratory Medicine Case Reports

View full text Add to dashboard Cite

With CT (computed tomography) chest gaining more importance as a diagnostic tool, chest X-ray especially the lateral view is taken less commonly nowadays. Besides CT chest is also proven to be superior to chest X-ray in patients with major blunt trauma. We are presenting a 68-year old male who was partially treated from outside for a left sided pneumonia. He came to our hospital because of persisting chest pain. Chest X-ray, frontal view (postero-anterior) was almost normal except for a mild opacity in the left lower zone. CT scan of the chest revealed a fluid collection posteriorly enclosed within enhancing pleura. Chest X-ray, left lateral view showed a corresponding posterior pleural based opacity. We are presenting this case to highlight the importance of the lateral view of the chest X-ray. In selected cases there is still a role for the lateral view. With the three dimensional visualization provided by the CT, the lateral view of the chest may be easier to understand. Consequent to the initial diagnosis by CT further follow up can be done with the chest X-ray. In a limited way this mitigates unnecessary expenditure and more importantly prevents the patient from exposure to harmful radiation in the form of repeated CT.

show abstract

“…Following earlier work, we simplified image annotations by only using top-level PadChest label categories and restricted experiments to frontal images only. Lateral images have been reported to not provide much benefit and to be difficult to interpret (Gaber et al, 2005 ; Kluthke et al, 2016 ; Bertrand et al, 2019 ). Following the experiments done by Bertrand et al ( 2019 ) we applied class weights to the positive labels to counteract the label imbalance.…”

Section: Methodsmentioning

confidence: 99%

Reducing Annotation Burden Through Multimodal Learning

et al. 2020

View full text Add to dashboard Cite

Choosing an optimal data fusion technique is essential when performing machine learning with multimodal data. In this study, we examined deep learning-based multimodal fusion techniques for the combined classification of radiological images and associated text reports. In our analysis, we (1) compared the classification performance of three prototypical multimodal fusion techniques: Early, Late , and Model fusion, (2) assessed the performance of multimodal compared to unimodal learning; and finally (3) investigated the amount of labeled data needed by multimodal vs. unimodal models to yield comparable classification performance. Our experiments demonstrate the potential of multimodal fusion methods to yield competitive results using less training data (labeled data) than their unimodal counterparts. This was more pronounced using the Early and less so using the Model and Late fusion approaches. With increasing amount of training data, unimodal models achieved comparable results to multimodal models. Overall, our results suggest the potential of multimodal learning to decrease the need for labeled training data resulting in a lower annotation burden for domain experts.

show abstract

The additional value of the lateral chest radiograph for the detection of small pulmonary nodules—a ROC analysis

Cited by 6 publications

References 19 publications

Energy spectrum computed tomography improves the differentiation between benign and malignant solitary pulmonary nodules

Energy spectrum computed tomography improves the differentiation between benign and malignant solitary pulmonary nodules

The forgotten view: Chest X-ray - Lateral view

Reducing Annotation Burden Through Multimodal Learning

Contact Info

Product

Resources

About