Development of an individual display optimization system based on deep convolutional neural network transition learning for somatostatin receptor scintigraphy.

Somatostatin receptor scintigraphy (SRS) is an essential examination for the diagnosis of neuroendocrine tumors (NETs). This study developed a method to individually optimize the display of whole-body SRS images using a deep convolutional neural network (DCNN) reconstructed by transfer learning of a DCNN constructed using Gallium-67 (67Ga) images. The initial DCNN was constructed using U-Net to optimize the display of 67Ga images (493 cases/986 images), and a DCNN with transposed weight coefficients was reconstructed for the optimization of whole-body SRS images (133 cases/266 images). A DCNN was constructed for each observer using reference display conditions estimated in advance. Furthermore, to eliminate information loss in the original image, a grayscale linear process is performed based on the DCNN output image to obtain the final linearly corrected DCNN (LcDCNN) image. To verify the usefulness of the proposed method, an observer study using a paired-comparison method was conducted on the original, reference, and LcDCNN images of 15 cases with 30 images. The paired comparison method showed that in most cases (29/30), the LcDCNN images were significantly superior to the original images in terms of display conditions. When comparing the LcDCNN and reference images, the number of LcDCNN and reference images that were superior to each other in the display condition was 17 and 13, respectively, and in both cases, 6 of these images showed statistically significant differences. The optimized SRS images obtained using the proposed method, while reflecting the observer's preference, were superior to the conventional manually adjusted images.

Automatic ROI construction for analyzing time-signal intensity curve in dynamic contrast-enhanced MR imaging of the breast.

Our purpose in this study was to construct a 3-dimensional (3D) region of interest (ROI) for analyzing the time-signal intensity curve (TIC) semi-automatically in dynamic contrast-enhanced magnetic resonance (DCE-MR) imaging of the breast. DCE-MR breast imaging datasets were acquired by a 3.0-Tesla MR system with the use of a 3D fast gradient echo sequence. The essential idea in the new method was to analyze each pixel and to construct an ROI made up of pixels with similar TICs. First, an analyst selected a starting point in the contrast media-enhanced tumor. Second, we calculated Pearson's correlation coefficients (CCs) between the TIC in the starting coordinate selected by the analyst and the TIC in the other coordinates. Third, ROI pixels were selected if their CC threshold satisfied a level of coefficient variation of the ROI determined by prior research performed in our institution. We made a retrospective review of patients who underwent breast DCE-MR examination for pre-operative diagnosis. To confirm the feasibility of the resulting 3D-ROI from TIC analysis, we compared Fischer's score obtained from 3D-ROI by applying a new method to a score obtained from a manually selected 2-dimensional (2D) ROI which was used during routine clinical examination. The Fischer's scores obtained from both the automatically selected 3D-ROI and the manually selected 2D-ROI showed almost equivalent results. Thus, we considered that the new method was comparable to the conventional method. Furthermore, the new method has the potential to be used for evaluation of the extent of tumors.