Advancing Alzheimer's research: Radiomics visualization of the default mode network in cerebral perfusion imaging.

OBJECTIVE: Alzheimer's disease, an irreversible neurological condition, demands timely diagnosis for effective clinical intervention. This study employs radiomics analysis to assess image features in default mode network cerebral perfusion imaging among individuals with cognitive impairment. METHODS: A radiomics analysis of cerebral perfusion imaging was conducted on 117 patients with cognitive impairment. They were divided into training and validation sets in a 7:3 ratio. Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest were employed to select and model image features, followed by logistic regression analysis of LASSO and Random Forest results. Diagnostic performance was assessed by calculating the area under the curve (AUC). RESULTS: In the training set, LASSO achieved AUC of 0.978, Random Forest had an AUC of 0.933. In the validation set, LASSO had AUC of 0.859, Random Forest had AUC of 0.986. By conducting Logistic Regression analysis in combination with LASSO and Random Forest, we identified a total of five radiomics features, with four related to morphology and one to textural features, originating from the medial prefrontal cortex and middle temporal gyrus. In the training set, Logistic Regression achieved AUC of 0.911, while in the validation set, it attained AUC of 0.925. CONCLUSION: The medial prefrontal cortex and middle temporal gyrus are the two brain regions within the default mode network that hold the highest significance for Alzheimer's disease diagnosis. Radiomics analysis contributes to the clinical assessment of Alzheimer's disease by delving into image data to extract deeper layers of information.

Diagnosis of thyroid disease using deep convolutional neural network models applied to thyroid scintigraphy images: a multicenter study.

Objectives: The aim of this study was to improve the diagnostic performance of nuclear medicine physicians using a deep convolutional neural network (DCNN) model and validate the results with two multicenter datasets for thyroid disease by analyzing clinical single-photon emission computed tomography (SPECT) image data. Methods: In this multicenter retrospective study, 3194 SPECT thyroid images were collected for model training (n=2067), internal validation (n=514) and external validation (n=613). First, four pretrained DCNN models (AlexNet, ShuffleNetV2, MobileNetV3 and ResNet-34) for were tested multiple medical image classification of thyroid disease types (i.e., Graves' disease, subacute thyroiditis, thyroid tumor and normal thyroid). The best performing model was then subjected to fivefold cross-validation to further assess its performance, and the diagnostic performance of this model was compared with that of junior and senior nuclear medicine physicians. Finally, class-specific attentional regions were visualized with attention heatmaps using gradient-weighted class activation mapping. Results: Each of the four pretrained neural networks attained an overall accuracy of more than 0.85 for the classification of SPECT thyroid images. The improved ResNet-34 model performed best, with an accuracy of 0.944. For the internal validation set, the ResNet-34 model showed higher accuracy (p < 0.001) when compared to that of the senior nuclear medicine physician, with an improvement of nearly 10%. Our model achieved an overall accuracy of 0.931 for the external dataset, a significantly higher accuracy than that of the senior physician (0.931 vs. 0.868, p < 0.001). Conclusion: The DCNN-based model performed well in terms of diagnosing thyroid scintillation images. The DCNN model showed higher sensitivity and greater specificity in identifying Graves' disease, subacute thyroiditis, and thyroid tumors compared to those of nuclear medicine physicians, illustrating the feasibility of deep learning models to improve the diagnostic efficiency for assisting clinicians.

SPECT Imaging with Tc-99m-Labeled HYNIC-FAPI-04 to Extend the Differential Time Window in Evaluating Tumor Fibrosis.

The so-far used Ga-68- or F-18-labelled tracers are of a relative short time window in differentiating tumor fibrosis. SPECT applicable imaging probe, 99mTc-HYNIC-FAPI-04, was synthesized and evaluated in tumor cells and animal models of FAP-positive glioma and FAP-negative hepatoma, and then compared with 18F-FDG or 68Ga-FAPI-04 PET/CT. The radio-labeling rate of 99mTc-HYNIC-FAPI-04 was greater than 90%, and the radiochemical purity was >99% after purification with sep-pak C18 column. In vitro cell uptake experiments of 99mTc-HYNIC-FAPI-04 showed good FAP binding specificity, and the cellular uptake significantly decreased when blocked by DOTA-FAPI-04, reflecting the similar targeting mechanism of HYNIC-FAPI-04 and DOTA-FAPI-04. SPECT/CT imaging showed that U87MG tumor was distinguishable and of a high uptake of 99mTc-HYNIC-FAPI-04 (2.67 ± 0.35 %ID/mL at 1.5 h post injection (h P.I.), while tumor signal of FAP-negative HUH-7 was as low as 0.34 ± 0.06 %ID/mL. At 5 h P.I., U87MG tumor was still distinguishable (1.81 ± 0.20 %ID/mL). In comparison, although U87MG tumor was of obvious 68Ga-FAPI-04 uptake and clearly visible at 1 h P.I., the tumorous radioactive signals were fuzzy at 1.5 h P.I. 99mTc-HYNIC-FAPI-04 specifically bound to FAP-positive tumors and qualified with the ability of evaluating tumor fibrosis over longer time windows.

Poly (lactic-co-glycolic acid)-encapsulated iodine-131 nanoparticles fabricated with rhTSH induce apoptosis and immobilization of thyroid cancer cells.

Background: Aggressive thyroid carcinoma (ATC) usually loses radioiodine avidity to iodine-131 (131I) due to the downregulation of sodium/iodide symporter (NIS). The expression of thyroid stimulating hormone receptor (TSHR) is more persistent than NIS and the administration of recombinant human thyroid stimulating hormone (rhTSH) promotes de novo NIS synthesis. Hence, exploring methods integrating 131I with rhTSH might be a feasible therapeutic strategy for selective delivery of 131I into thyroid cancer to fortify the effect of radioiodine ablation. Methods: The 131I, poly (lactic-co-glycolic acid) (PLGA) and rhTSH were used to synthesize of the 131I-PLGA-rhTSH nanoparticles. The characteristics of the 131I-PLGA-rhTSH nanoparticles was determined using a light microscopy, scanning electron microscopy (SEM), autoradiography and immunofluorescence (IF) staining. The diameter of the 131I-PLGA-rhTSH nanoparticles was measured with a Mastersizer 3000, and the encapsulation efficiency (EF) of 131I in 131I-PLGA-rhTSH nanoparticles and the radioactivity of a single nanoparticle were determined. Then, the mouse tumor xenograft model was established, and the biodistribution and effect of 131I-PLGA-rhTSH nanoparticles on apoptosis of thyroid cance cells were investigated in vivo. Thereafter, the role of 131I-PLGA-rhTSH nanoparticles in cell viability using cell counting kit-8 and lactate dehydrogenase (LDH) release assays. Subsequently, the underlying mechanism of 131I-PLGA-rhTSH nanoparticles in reducing cell viability was assessed using immunostaining, boyden invasion assays and phalloidin staining. Results: Our results showed that the method of developing nanoparticles-encapsulated 131I using poly (lactic-co-glycolic acid) (PLGA) and modified with rhTSH (131I-PLGA-rhTSH), was a feasible avenue for the integration of 131I and rhTSH. Meanwhile, the encapsulation efficiency (EF) of 131I-PLGA-rhTSH nanoparticles was approximately 60%, and the radioactivity of a single nanoparticle was about 1.1×10-2 Bq. Meanwhile, the 131I-PLGA-rhTSH nanoparticles were selectively delivered into, gradually enriched and slowly downregulated in xenograft tumor after the administration of 131I-PLGA-rhTSH nanoparticles through tail vein in mouse tumor xenograft model. Thereafter, the tumor weight was significantly reduced after the administration of 131I-PLGA-rhTSH nanoparticles. Subsequently, the application of 131I-PLGA-rhTSH nanoparticles facilitated apoptosis and attenuated immobilization via inhibiting F-actin assembling of FTC-133 cells. Conclusion: The present study develops a suitable approach integrating 131I and rhTSH, and this strategy is a feasible regimen enhancing the effect of radioiodine ablation for the treatment of thyroid cancer.

Analysis of factors influencing the clinical outcome after surgery and 131I therapy in patients with moderate-risk thyroid papillary carcinoma.

Purpose: Generally, the prognosis for papillary thyroid cancer (PTC) is favorable. However, the moderate risk involved warrants further evaluation. Hence, we investigated the clinical outcomes in patients with moderate-risk PTC following surgery and the first 131I therapy, as well as the relevant factors that influence the therapeutic efficacy. Methods: Retrospective analyses of 175 patients with medium-risk PTC who visited the Second Affiliated Hospital of Chongqing Medical University from September 2017 to April 2019 were conducted. In according with the 2015 American Thyroid Association (ATA) guideline treatment response evaluation system, the patients were categorized into the following groups: excellent response (ER), indeterminate response (IDR), biochemical incomplete response (BIR), and structurally incomplete response (SIR), of which IDR, BIR, and SIR were collectively referred to as the NER group. To compare the general clinical features between the 2 groups of patients, 2 independent samples t-tests, χ2 test, and Mann-Whitney U-test were performed, followed by multivariate logistic regression analyses. With reference to the receiver operating characteristic (ROC) curve, the predicted value of ps-Tg to ER was evaluated, and the best cut-off value was determined. The subgroups with BRAFV600E test results were analyzed by χ2 test only. Results: The treatment responses of 123 patients were ER, while those of 52 patients were NER. The differences in the maximum tumor diameter (U = 2495.50), the amount of metastatic lymph nodes (U = 2313.50), the size of metastatic lymph node (U = 2113.50), the metastatic lymph node ratio (U = 2111.50), metastatic lymph node location (χ2 = 9.20), and ps-Tg level (U = 1011.00) were statistically significant. Multivariate regression analysis revealed that ps-Tg (OR = 1.209, 95% CI: 1.120-1.305) was an independent variable affecting ER. The cut-off value of ps-Tg for predicting ER was 6.915 ug/L, while its sensitivity and specificity were 69.2% and 89.4%, respectively. Conclusions: Patients with smaller tumor size, fewer lymph nodes, lower metastatic lymph node ratio, metastatic lymph nodes in the central region, smaller lymph node size, and ps-Tg <6.915 ug/L demonstrated better therapeutic effects after the initial treatment.