Multiple Kernel Synthesis of Head CT Using a Task-Based Loss Function

In CT imaging of the head, multiple image series are routinely reconstructed with different kernels and slice thicknesses. Reviewing the redundant information is an inefficient process for radiologists. We address this issue with a convolutional neural network (CNN)-based technique, synthesiZed Improved Resolution and Concurrent nOise reductioN (ZIRCON), that creates a single, thin, low-noise series that combines the favorable features from smooth and sharp head kernels. ZIRCON uses a CNN model with an autoencoder U-Net architecture that accepts two input channels (smooth- and sharp-kernel CT images) and combines their salient features to produce a single CT image. Image quality requirements are built into a task-based loss function with a smooth and sharp loss terms specific to anatomical regions. The model is trained using supervised learning with paired routine-dose clinical non-contrast head CT images as training targets and simulated low-dose (25%) images as training inputs. One hundred unique de-identified clinical exams were used for training, ten for validation, and ten for testing. Visual comparisons and contrast measurements of ZIRCON revealed that thinner slices and the smooth-kernel loss function improved gray-white matter contrast. Combined with lower noise, this increased visibility of small soft-tissue features that would be otherwise impaired by partial volume averaging or noise. Line profile analysis showed that ZIRCON images largely retained sharpness compared to the sharp-kernel input images. ZIRCON combined desirable image quality properties of both smooth and sharp input kernels into a single, thin, low-noise series suitable for both brain and skull imaging.

Threshold-dependent iodine imaging and spectral separation in a whole-body photon-counting CT system

OBJECTIVE

To evaluate the dual-energy (DE) performance and spectral separation with respect to iodine imaging in a photon-counting CT (PCCT) and compare it to dual-source CT (DSCT) DE imaging.

METHODS

A semi-anthropomorphic phantom extendable with fat rings equipped with iodine vials is measured in an experimental PCCT. The system comprises a PC detector with two energy bins (20 keV, T) and (T, eU) with threshold T and tube voltage U. Measurements using the PCCT are performed at all available tube voltages (80 to 140 kV) and threshold settings (50-90 keV). Further measurements are performed using a conventional energy-integrating DSCT. Spectral separation is quantified as the relative contrast media ratio R between the energy bins and low/high images. Image noise and dose-normalized contrast-to-noise ratio (CNRD) are evaluated in resulting iodine images. All results are validated in a post-mortem angiography study.

RESULTS

R of the PC detector varies between 1.2 and 2.6 and increases with higher thresholds and higher tube voltage. Reference R of the EI DSCT is found as 2.20 on average overall phantoms. Maximum CNRD in iodine images is found for T = 60/65/70/70 keV for 80/100/120/140 kV. The highest CNRD of the PCCT is obtained using 140 kV and is decreasing with decreasing tube voltage. All results could be confirmed in the post-mortem angiography study.

CONCLUSION

Intrinsically acquired DE data are able to provide iodine images similar to conventional DSCT. However, PCCT thresholds should be chosen with respect to tube voltage to maximize image quality in retrospectively derived image sets.

KEY POINTS

• Photon-counting CT allows for the computation of iodine images with similar quality compared to conventional dual-source dual-energy CT. • Thresholds should be chosen as a function of the tube voltage to maximize iodine contrast-to-noise ratio in derived image sets. • Image quality of retrospectively computed image sets can be maximized using optimized threshold settings.

Automatic multi-organ segmentation in dual-energy CT (DECT) with dedicated 3D fully convolutional DECT networks

PURPOSE

Dual-energy computed tomography (DECT) has shown great potential in many clinical applications. By incorporating the information from two different energy spectra, DECT provides higher contrast and reveals more material differences of tissues compared to conventional single-energy CT (SECT). Recent research shows that automatic multi-organ segmentation of DECT data can improve DECT clinical applications. However, most segmentation methods are designed for SECT, while DECT has been significantly less pronounced in research. Therefore, a novel approach is required that is able to take full advantage of the extra information provided by DECT.

METHODS

In the scope of this work, we proposed four three-dimensional (3D) fully convolutional neural network algorithms for the automatic segmentation of DECT data. We incorporated the extra energy information differently and embedded the fusion of information in each of the network architectures.

RESULTS

Quantitative evaluation using 45 thorax/abdomen DECT datasets acquired with a clinical dual-source CT system was investigated. The segmentation of six thoracic and abdominal organs (left and right lungs, liver, spleen, and left and right kidneys) were evaluated using a fivefold cross-validation strategy. In all of the tests, we achieved the best average Dice coefficients of 98% for the right lung, 98% for the left lung, 96% for the liver, 92% for the spleen, 95% for the right kidney, 93% for the left kidney, respectively. The network architectures exploit dual-energy spectra and outperform deep learning for SECT.

CONCLUSIONS

The results of the cross-validation show that our methods are feasible and promising. Successful tests on special clinical cases reveal that our methods have high adaptability in the practical application.