Improved detection of cholesterol gallstones using quasi-material decomposition images generated from single-energy computed tomography images via deep learning.

In this study, we developed a method for generating quasi-material decomposition (quasi-MD) images from single-energy computed tomography (SECT) images using a deep convolutional neural network (DCNN). Our aim was to improve the detection of cholesterol gallstones and to determine the clinical utility of quasi-MD images. Four thousand pairs of virtual monochromatic images (70 keV) and MD images (fat/water) of the same section, obtained via dual-energy computed tomography (DECT), were used to train the DCNN. The trained DCNN can automatically generate quasi-MD images from the SECT images. Additional SECT images were obtained from 70 patients (40 with and 30 without cholesterol gallstones) to generate quasi-MD images for testing. The presence of gallstones in this dataset was confirmed by ultrasonography. We conducted a receiver operating characteristic (ROC) observer study with three radiologists to validate the clinical utility of the quasi-MD images for detecting cholesterol gallstones. The mean area under the ROC curve for the detection of cholesterol gallstones improved from 0.867 to 0.921 (p = 0.001) when quasi-MD images were added to SECT images. The clinical utility of quasi-MD imaging for detecting cholesterol gallstones was showed. This study demonstrated that the lesion detection capability of images obtained from SECT can be improved using a DCNN trained with DECT images obtained using high-end computed tomography systems.

[Measurement of residual effect in the amorphous selenium flat panel detector system].

The purpose of this study was to evaluate the residual effect generated by the amorphous selenium flat panel detector system (a-Se FPD). A residual effect occurs as a result of the addition of delayed electrons by previous X-ray irradiation joining the signal and change in detector sensitivity caused by hole-electron recombination or trapped electrons in a-Se. To evaluate the effect of previous radiation exposure, we irradiated a-Se FPD that were half-shielded by a 3 mm thick lead plate. A residual effect was generated in irradiated areas, with the unirradiated areas serving as reference points. Next, we removed the lead plate and took a new image using uniform irradiation. The difference in pixel value between irradiated and nonirradiated areas was measured using a variety of time intervals between each exposure. Through a comparison of pixel values from images taken over various time intervals, we discovered our system needs 20 hours to return to a normal state and become capable of producing a residual-free image.