No abstract

No abstract

The CmRI reflects the response of peritoneal metastases to induction intraperitoneal chemotherapy. It may be a useful biomarker for indicating gastrectomy in gastric cancer patients with peritoneal metastasis.

Simultaneous dual-isotope SPECT imaging with 201Tl and (123)I-β-methyl-p-iodophenylpentadecanoic acid (BMIPP) is used to study the perfusion-metabolism mismatch. It predicts post-ischemic functional recovery by detecting stunned myocardium. On the other hand, (99m)Tc-MIBI is another radioisotope widely used in myocardial perfusion imaging because of its better image quality and lower radiation exposure than 201Tl. However, since the photopeak energies of (99m)Tc and (123)I are very similar, crosstalk hampers the simultaneous use of these two radioisotopes. To overcome this problem, we conducted simultaneous dual-isotope imaging study using the D-SPECT scanner (Spectrum-Dynamics, Israel) which has a novel detector design and excellent energy resolution. We first conducted a basic experiment using cardiac phantom to simulate the condition of normal perfusion and impaired fatty acid metabolism. Subsequently, we prospectively recruited 30 consecutive patients who underwent successful percutaneous coronary intervention for acute myocardial infarction, and performed (99m)Tc-MIBI/(123)I-BMIPP dual-isotope imaging within 5 days after reperfusion. Images were interpreted by two experienced cardiovascular radiologists to identify the infarcted and stunned areas based on the coronary artery territories. As a result, cardiac phantom experiment revealed no significant crosstalk between (99m)Tc and (123)I. In the subsequent clinical study, (99m)Tc-MIBI/(123)I-BMIPP dual-isotope imaging in all participant yielded excellent image quality and detected infarcted and stunned areas correctly when compared with coronary angiographic findings. Furthermore, we were able to reduce radiation exposure to significantly approximately one-eighth. In conclusion, we successfully demonstrated the practical application of simultaneous assessment of myocardial perfusion and fatty acid metabolism by (99m)Tc-MIBI and (123)I-BMIPP using a D-SPECT cardiac scanner. Compared with conventional (201)TlCl/(123)I-BMIPP dual-isotope imaging, the use of (99m)Tc-MIBI instead of (201)TlCl improves image quality as well as lowers radiation exposure.

Background and Aim: Recently, multimodal representation learning for images and other information such as numbers or language has gained much attention. The aim of the current study was to analyze the diagnostic performance of deep multimodal representation model-based integration of tumor image, patient background, and blood biomarkers for the differentiation of liver tumors observed using B-mode ultrasonography (US). Method: First, we applied supervised learning with a convolutional neural network (CNN) to 972 liver nodules in the training and development sets to develop a predictive model using segmented B-mode tumor images. Additionally, we also applied a deep multimodal representation model to integrate information about patient background or blood biomarkers to B-mode images. We then investigated the performance of the models in an independent test set of 108 liver nodules. Results: Using only the segmented B-mode images, the diagnostic accuracy and area under the curve (AUC) values were 68.52% and 0.721, respectively. As the information about patient background and blood biomarkers was integrated, the diagnostic performance increased in a stepwise manner. The diagnostic accuracy and AUC value of the multimodal DL model (which integrated B-mode tumor image, patient age, sex, aspartate aminotransferase, alanine aminotransferase, platelet count, and albumin data) reached 96.30% and 0.994, respectively. Conclusion: Integration of patient background and blood biomarkers in addition to US image using multimodal representation learning outperformed the CNN model using US images. We expect that the deep multimodal representation model could be a feasible and acceptable tool for the definitive diagnosis of liver tumors using B-mode US.