Improving image quality of sparse-view lung tumor CT images with U-Net

BACKGROUND

We aimed to improve the image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determine the best tradeoff between number of views, IQ, and diagnostic confidence.

METHODS

CT images from 41 subjects aged 62.8 ± 10.6 years (mean ± standard deviation, 23 men), 34 with lung metastasis, 7 healthy, were retrospectively selected (2016-2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used.

RESULTS

The 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images.

CONCLUSIONS

Projection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level.

RELEVANCE STATEMENT

Our reader study demonstrates the benefit of U-Net postprocessing for regular CT screenings of patients with lung metastasis to increase the IQ and diagnostic confidence while reducing the dose.

KEY POINTS

• Sparse-projection-view streak artifacts reduce the quality and usability of sparse-view CT images. • U-Net-based postprocessing removes sparse-view artifacts while maintaining diagnostically accurate IQ. • Postprocessed sparse-view CTs drastically increase radiologists' confidence in diagnosing lung metastasis.

Evaluation of Spectral X-Ray Imaging for Panoramic Dental Images Based on a Simulation Framework

Modern photon counting detectors allow the calculation of virtual monoenergetic or material decomposed X-ray images but are not yet used for dental panoramic radiography systems. To assess the diagnostic potential and image quality of photon counting detectors in dental panoramic radiography, ethics approval from the local ethics committee was obtained for this retrospective study. Conventional CT scans of the head and neck region were segmented into bone and soft tissue. The resulting datasets were used to calculate panoramic equivalent thickness bone and soft tissue images by forward projection, using a geometry like that of conventional panoramic radiographic systems. The panoramic equivalent thickness images were utilized to generate synthetic conventional panoramic radiographs and panoramic virtual monoenergetic radiographs at various energies. The conventional, two virtual monoenergetic images at 40 keV and 60 keV, and material-separated bone and soft tissue panoramic equivalent thickness X-ray images simulated from 17 head CTs were evaluated in a reader study involving three experienced radiologists regarding their diagnostic value and image quality. Compared to conventional panoramic radiographs, the material-separated bone panoramic equivalent thickness image exhibits a higher image quality and diagnostic value in assessing the bone structure p < . 001 and details such as teeth or root canals p < . 001 . Panoramic virtual monoenergetic radiographs do not show a significant advantage over conventional panoramic radiographs. The conducted reader study shows the potential of spectral X-ray imaging for dental panoramic imaging to improve the diagnostic value and image quality.

Evaluation of Conventional MR Imaging of the Shoulder in the Diagnosis of Lesions of the Biceps Pulley

RATIONALE AND OBJECTIVES

To determine the diagnostic accuracy and reproducibility of conventional MR imaging (MRI) of the shoulder in evaluating biceps pulley lesions using arthroscopy as the standard of reference.

METHODS

In a retrospective study, MR examinations of 68 patients with arthroscopically proven torn or intact biceps pulley were assessed for the presence of pulley lesions by three radiologists. The following criteria were evaluated: displacement of the long head of the biceps tendon (LHBT) relative to the subscapularis tendon (displacement sign), subluxation/dislocation of the LHBT, the integrity of the superior glenohumeral ligament (SGHL) and the coracohumeral ligament (CHL), lesions of the supraspinatus (SSP) and subscapularis (SSC) tendons adjacent to the rotator interval, presence of biceps tendinopathy and subacromial bursitis.

RESULTS

There were 42 patients with pulley lesions in the study group. Conventional MR imaging showed an overall sensitivity of 95.2%, 88.1% and 92.9%, a specificity of 61.5%, 73.1%, and 80.8% and an accuracy of 82.4%, 82.4% and 88.2% in the diagnosis of pulley lesions. Interobserver agreement was substantial (multirater k = 0.75). Biceps tendinopathy (97.6%, 95.2%, 97.6%), defects of the SGHL (86.3%, 81.0%, 88.1%) and the displacement sign (88.1%, 81.0%, 85.7%) were the most sensitive diagnostic criteria. Subluxation/dislocation of the LHBT was insensitive (78.6%, 42.9%, 33.3%), but specific (69.2%, 100,0%, 96.2%).

CONCLUSION

In the diagnosis of pulley lesions, conventional MR imaging is reproducible and shows high sensitivity and accuracy but moderate specificity.

Deep learning enables the differentiation between early and late stages of hip avascular necrosis

OBJECTIVES

To develop a deep learning methodology that distinguishes early from late stages of avascular necrosis of the hip (AVN) to determine treatment decisions.

METHODS

Three convolutional neural networks (CNNs) VGG-16, Inception ResnetV2, InceptionV3 were trained with transfer learning (ImageNet) and finetuned with a retrospectively collected cohort of (n = 104) MRI examinations of AVN patients, to differentiate between early (ARCO 1-2) and late (ARCO 3-4) stages. A consensus CNN ensemble decision was recorded as the agreement of at least two CNNs. CNN and ensemble performance was benchmarked on an independent cohort of 49 patients from another country and was compared to the performance of two MSK radiologists. CNN performance was expressed with areas under the curve (AUC), the respective 95% confidence intervals (CIs) and precision, and recall and f1-scores. AUCs were compared with DeLong's test.

RESULTS

On internal testing, Inception-ResnetV2 achieved the highest individual performance with an AUC of 99.7% (95%CI 99-100%), followed by InceptionV3 and VGG-16 with AUCs of 99.3% (95%CI 98.4-100%) and 97.3% (95%CI 95.5-99.2%) respectively. The CNN ensemble the same AUCs Inception ResnetV2. On external validation, model performance dropped with VGG-16 achieving the highest individual AUC of 78.9% (95%CI 51.6-79.6%) The best external performance was achieved by the model ensemble with an AUC of 85.5% (95%CI 72.2-93.9%). No significant difference was found between the CNN ensemble and expert MSK radiologists (p = 0.22 and 0.092 respectively).

CONCLUSION

An externally validated CNN ensemble accurately distinguishes between the early and late stages of AVN and has comparable performance to expert MSK radiologists.

CLINICAL RELEVANCE STATEMENT

This paper introduces the use of deep learning for the differentiation between early and late avascular necrosis of the hip, assisting in a complex clinical decision that can determine the choice between conservative and surgical treatment.

KEY POINTS

• A convolutional neural network ensemble achieved excellent performance in distinguishing between early and late avascular necrosis. • The performance of the deep learning method was similar to the performance of expert readers.

Evaluating Treatment Response in GEJ Adenocarcinoma: The Role of Pretherapeutic and Posttherapeutic Iodine Mapping

BACKGROUND

Neoadjuvant therapy regimens have significantly improved the prognosis of GEJ (gastroesophageal junction) cancer; however, there are a significant percentage of patients who benefit from earlier resection or adapted therapy regimens, and the true response rate can only be determined histopathologically. Methods that allow preoperative assessment of response are lacking.

PURPOSE

The purpose of this retrospective study is to assess the potential of pretherapeutic and posttherapeutic spectral CT iodine density (IoD) in predicting histopathological response to neoadjuvant chemotherapy in patients diagnosed with adenocarcinoma of the GEJ.

METHODS

In this retrospective cohort study, a total of 62 patients with GEJ carcinoma were studied. Patients received a multiphasic CT scan at diagnosis and preoperatively. Iodine-density maps were generated based on spectral CT data. All tumors were histopathologically analyzed, and the tumor regression grade (TRG) according to Becker et al ( Cancer . 2003;98:1521-1530) was determined. Two experienced radiologists blindly placed 5 defined ROIs in the tumor region of highest density, and the maximum value was used for further analysis. Iodine density was normalized to the aortic iodine uptake. In addition, tumor response was assessed according to standard RECIST measurement. After assessing interrater reliability, the correlation of IoD values with treatment response and with histopathologic TRG was evaluated.

RESULTS

The normalized ΔIoD (IoD at diagnosis - IoD after neoadjuvant treatment) and the normalized IoD after neoadjuvant treatment correlated significantly with the TRG. For the detection of responders and nonresponders, the receiver operating characteristic (ROC) curve for normalized ΔIoD yielded the highest area under the curve of 0.95 and achieved a sensitivity and specificity of 92.3% and 92.1%, respectively. Iodine density after neoadjuvant treatment achieved an area under the curve of 0.88 and a sensitivity and specificity of 86.8% and 84.6%, respectively (cutoff, 0.266). Iodine density at diagnosis and RECIST did not provide information to distinguish responders from nonresponders. Using the cutoff value for IoD after neoadjuvant treatment, a reliable classification of responders and nonresponders was achieved for both readers in a test set of 11 patients. Intraclass correlation coefficient revealed excellent interrater reliability (intraclass correlation coefficient, >0.9). Lastly, using the cutoff value for normalized ΔIoD as a definition for treatment response, a significantly longer survival of responders was shown.

CONCLUSIONS

Changes in IoD after neoadjuvant treatment of GEJ cancer may be a potential surrogate for therapy response.

[Intraoperative imaging with the mobile C-arm : Technique, image creation and radiation protection]

Imaging techniques in the discipline of orthopedics and trauma surgery are essential not only for making a diagnosis but also play a central role in the performance, documentation and monitoring of the corresponding treatment. Procedures such as open reduction and internal fixation (ORIF) and closed reduction and internal fixation (CRIF) of fractures, kyphoplasty and vertebroplasty as well as posterior stabilization of spinal fractures are carried out under X‑ray control. In the relevant operating rooms of emergency departments and operating theaters, mobile fluoroscopy devices are available, which due to their appearance are called C‑arms. These devices can be moved horizontally, vertically, and along the pivotal axis, enabling real-time imaging of joints and bones from various angles. This imaging enables minimally invasive surgical techniques as this often eliminates the need for extensive preparation and resulting in smaller wound defects compared to open surgical preparation. Additionally, surgeons can immediately assess and, if necessary, adjust the reduction outcome to achieve the best possible care and reduce the need for corrective interventions. With current C‑arms it is also possible to generate 3‑dimensional datasets, to enhance the assessment of implant positioning, particularly in complex intra-articular fractures. This availability helps avoid subsequent corrective interventions that would otherwise only be identified through postoperative computed tomography [1].

In-vivo X-ray dark-field computed tomography for the detection of radiation-induced lung damage in mice

•

Radiation-induced lung damage was observed using X-ray dark-field tomography.

•

In this pre-clinical study, mouse lungs were irradiated and subsequently imaged.

•

We report increased sensitivity of X-ray dark-field tomography over absorption-based tomography.

Background and Purpose

Radiotherapy of thoracic tumours can lead to side effects in the lung, which may benefit from early diagnosis. We investigated the potential of X-ray dark-field computed tomography by a proof-of-principle murine study in a clinically relevant radiotherapeutic setting aiming at the detection of radiation-induced lung damage.

Material and Methods

Six mice were irradiated with 20 Gy to the entire right lung. Together with five unirradiated control mice, they were imaged using computed tomography with absorption and dark-field contrast before and 16 weeks post irradiation. Mean pixel values for the right and left lung were calculated for both contrasts, and the right-to-left-ratio R of these means was compared. Radiologists also assessed the tomograms acquired 16 weeks post irradiation. Sensitivity, specificity, inter- and intra-reader accuracy were evaluated.

Results

In absorption contrast the group-average of R showed no increase in the control group and increased by 7% (p = 0.005) in the irradiated group. In dark-field contrast, it increased by 2% in the control group and by 14% (p = 0.005) in the irradiated group. Specificity was 100% for both contrasts but sensitivity was almost four times higher using dark-field tomography. Two cases were missed by absorption tomography but were detected by dark-field tomography.

Conclusions

The applicability of X-ray dark-field computed tomography for the detection of radiation-induced lung damage was demonstrated in a pre-clinical mouse model. The presented results illustrate the differences between dark-field and absorption contrast and show that dark-field tomography could be advantageous in future clinical settings.

Sparse-sampling computed tomography for detection of endoleak after endovascular aortic repair (EVAR)

OBJECTIVES

To evaluate sparse sampling computed tomography (SpSCT) for detection of endoleak after endovascular aortic repair (EVAR) at different dose levels in terms of subjective image criteria and diagnostic accuracy.

METHODS

Twenty clinically indicated computed tomography aortic angiography (CTA) scans were used to obtain simulated low-dose scans with 100%, 50%, 25%, 12.5% and 6.25% of the applicated clinical dose, resulting in five dose levels (DL). From full sampling (FS) data sets, every second (2-SpSCT) or fourth (4-SpSCT) projection was used to generate simulated sparse sampling scans. All examinations were evaluated by four blinded radiologists regarding subjective image criteria and diagnostic performance.

RESULTS

Sensitivity was higher than 93% in 4-SpSCT at the 25% DL which is the same as with FS at full dose (100% DL). High accuracies and relative high AUC-values were obtained for 2- and 4-SpSCT down to the 12.5% DL, while for FS similar values were shown down to 25% DL only. Subjective image quality was significantly higher for 4-SpSCT compared to FS at each dose level. More than 90% of all cases were rated with a high or medium confidence for FS and 2-SpSCT at the 50% DL and for 4-SpSCT at the 25% DL. At DL 25% and 12.5%, more cases showed a high confidence using 2- and 4-SpSCT compared with FS.

CONCLUSIONS

Via SpSCT, a dose reduction down to a 25% dose level (mean effective dose of 1.49 mSv in the current study) for CTA is possible while maintaining high image quality and full diagnostic confidence.

Correlation of image quality parameters with tube voltage in X-ray dark-field chest radiography: a phantom study

Grating-based X-ray dark-field imaging is a novel imaging modality with enormous technical progress during the last years. It enables the detection of microstructure impairment as in the healthy lung a strong dark-field signal is present due to the high number of air-tissue interfaces. Using the experience from setups for animal imaging, first studies with a human cadaver could be performed recently. Subsequently, the first dark-field scanner for in-vivo chest imaging of humans was developed. In the current study, the optimal tube voltage for dark-field radiography of the thorax in this setup was examined using an anthropomorphic chest phantom. Tube voltages of 50–125 kVp were used while maintaining a constant dose-area-product. The resulting dark-field and attenuation radiographs were evaluated in a reader study as well as objectively in terms of contrast-to-noise ratio and signal strength. We found that the optimum tube voltage for dark-field imaging is 70 kVp as here the most favorable combination of image quality, signal strength, and sharpness is present. At this voltage, a high image quality was perceived in the reader study also for attenuation radiographs, which should be sufficient for routine imaging. The results of this study are fundamental for upcoming patient studies with living humans.

Early detection of radiation-induced lung damage with X-ray dark-field radiography in mice

OBJECTIVE

Assessing the advantage of x-ray dark-field contrast over x-ray transmission contrast in radiography for the detection of developing radiation-induced lung damage in mice.

METHODS

Two groups of female C57BL/6 mice (irradiated and control) were imaged obtaining both contrasts monthly for 28 weeks post irradiation. Six mice received 20 Gy of irradiation to the entire right lung sparing the left lung. The control group of six mice was not irradiated. A total of 88 radiographs of both contrasts were evaluated for both groups based on average values for two regions of interest, covering (irradiated) right lung and healthy left lung. The ratio of these average values, R, was distinguished between healthy and damaged lungs for both contrasts. The time-point when deviations of R from healthy lung exceeded 3σ was determined and compared among contrasts. The Wilcoxon-Mann-Whitney test was used to test against the null hypothesis that there is no difference between both groups. A selection of 32 radiographs was assessed by radiologists. Sensitivity and specificity were determined in order to compare the diagnostic potential of both contrasts. Inter-reader and intra-reader accuracy were rated with Cohen's kappa.

RESULTS

Radiation-induced morphological changes of lung tissue caused deviations from the control group that were measured on average 10 weeks earlier with x-ray dark-field contrast than with x-ray transmission contrast. Sensitivity, specificity, and accuracy doubled using dark-field radiography.

CONCLUSION

X-ray dark-field radiography detects morphological changes of lung tissue associated with radiation-induced damage earlier than transmission radiography in a pre-clinical mouse model.

KEY POINTS

• Significant deviations from healthy lung due to irradiation were measured after 16 weeks with x-ray dark-field radiography (p = 0.004). • Significant deviations occur on average 10 weeks earlier for x-ray dark-field radiography in comparison to x-ray transmission radiography. • Sensitivity and specificity doubled when using x-ray dark-field radiography instead of x-ray transmission radiography.

Photon-counting spectral basis component material decomposition for musculoskeletal radiographs

As a very fast and non-invasive examination, conventional X-ray radiography is well established as the first line diagnostic imaging method of the human bone system. While major bone injuries such as fractures and dislocations are usually easily detectable on conventional X-ray images, more subtle injuries such as microfractures are often missed, leading to mistreatment and potential long-term consequences. The technology of Photon-Counting Dual-Energy Radiography (PCDER) yields the possibility to decompose conventional X-ray images into basis material images such as bone- and soft-tissue-equivalence images. The obtained basis material images offer significant advantages in terms of image contrast and image details over the raw attenuation image which shows an overlap of bone and soft tissue. Whereas the advantages of bone- and soft-tissue-equivalence images have been broadly discussed referring to bone subtraction images in the detection of pulmonary diseases, this method has not been considered for the analysis of musculoskeletal images until present. In this study we show that basis component equivalence images have high potential to improve the diagnostic accuracy of the detection of minor bone lesions during clinical trauma imaging. A reader study performed by three experienced radiologists compares the image quality of basis material images to a standard radiograph image of a non-fractured cadaveric hand.

Optimization of tube voltage in X-ray dark-field chest radiography

Grating-based X-ray dark-field imaging is a novel imaging modality which has been refined during the last decade. It exploits the wave-like behaviour of X-radiation and can nowadays be implemented with existing X-ray tubes used in clinical applications. The method is based on the detection of small-angle X-ray scattering, which occurs e.g. at air-tissue-interfaces in the lung or bone-fat interfaces in spongy bone. In contrast to attenuation-based chest X-ray imaging, the optimal tube voltage for dark-field imaging of the thorax has not yet been examined. In this work, dark-field scans with tube voltages ranging from 60 to 120 kVp were performed on a deceased human body. We analyzed the resulting images with respect to subjective and objective image quality, and found that the optimum tube voltage for dark-field thorax imaging at the used setup is at rather low energies of around 60 to 70 kVp. Furthermore, we found that at these tube voltages, the transmission radiographs still exhibit sufficient image quality to correlate dark-field information. Therefore, this study may serve as an important guideline for the development of clinical dark-field chest X-ray imaging devices for future routine use.

Accuracy of Calcium Scoring calculated from contrast-enhanced Coronary Computed Tomography Angiography using a dual-layer spectral CT: A comparison of Calcium Scoring from real and virtual non-contrast data

Purpose

Modern non-invasive evaluation of Coronary Artery Disease (CAD) requires non-contrast low dose Computed Tomography (CT) imaging for determination of Calcium Scoring (CACS) and contrast-enhanced imaging for evaluation of vascular stenosis. Several methods for calculation of CACS from contrast-enhanced images have been proposed before. The main principle for that is generation of virtual non-contrast images by iodine subtraction from a contrast-enhanced spectral CT dataset. However, those techniques have some limitations: Dual-Source CT imaging can lead to increased radiation exposure, and switching of the tube voltage (rapid kVp switching) can be associated with slower rotation speed of the gantry and is thus prone to motion artefacts that are especially critical in cardiac imaging. Both techniques cannot simultaneously acquire spectral data. A novel technique to overcome these difficulties is spectral imaging with a dual-layer detector. After absorption of the lower energetic photons in the first layer, the second layer detects a hardened spectrum of the emitted radiation resulting in registration of two different energy spectra at the same time. The objective of the present investigation was to evaluate the accuracy of virtual non-contrast CACS computed from spectral data in comparison to standard non-contrast imaging.

Methods

We consecutively investigated 20 patients referred to Coronary Computed Tomography Angiography (CCTA) with suspicion of CAD using a Dual-Layer spectral CT system (IQon; Philips Healthcare, The Netherlands). CACS was calculated from both, real- and virtual non-contrast images by certified software for medical use. Correlation analyses for real- and virtual non-contrast images and agreement evaluation with Bland-Altman-Plots were performed.

Results

Mean patient age was 57.7 ± 14 years (n = 20). 13 patients (65%) were male. Inter-quartile-range of clinical CACS was 0–448, the mean was 334. Correlation of CACS from real- and virtual non-contrast images was very high (0.94); p < 0.0001. The slope was 2.3 indicating that values from virtual non-contrast images are approximately half of the results obtained from real non-contrast data. Visual analysis of Bland-Altman-Plot shows good accordance of both methods when results from virtual non-contrast data are multiplied by the slope of the logistic regression model (2.3). The acquired power of this results is 0.99.

Conclusion

Determination of Calcium Score from contrast enhanced CCTA using spectral imaging with a dual-layer detector is feasible and shows good agreement with the conventional technique when a proportionality factor is applied. The observed difference between both methods is due to an underestimation of plaque volume, and—to an even greater extend -an underestimation of plaque density with the virtual non-contrast approach. Our data suggest that radiation exposure can be reduced through omitting additional native scans for patients referred to CCTA when using a dual-layer spectral system without the usual limitations of dual energy analysis.