An Artificial Intelligence Model Based on ACR TI-RADS Characteristics for US Diagnosis of Thyroid Nodules.

Background US-based diagnosis of thyroid nodules is subjective and influenced by radiologists' experience levels. Purpose To develop an artificial intelligence model based on American College of Radiology Thyroid Imaging Reporting and Data System characteristics for diagnosing thyroid nodules and identifying nodule characteristics (hereafter, MTI-RADS) and to compare the performance of MTI-RADS, radiologists, and a model trained on benign and malignant status based on surgical histopathologic analysis (hereafter, MDiag). Materials and Methods In this retrospective study, 1588 surgically proven nodules from 636 consecutive patients (mean age, 49 years ± 14 [SD]; 485 women) were included. MTI-RADS and MDiag were trained on US images of 1345 nodules (January 2018 to December 2019). The performance of MTI-RADS was compared with that of MDiag and radiologists with different experience levels on the test data set (243 nodules, January 2019 to December 2019) with the DeLong method and McNemar test. Results The area under the receiver operating characteristic curve (AUC) and sensitivity of MTI-RADS were 0.91 and 83% (55 of 66 nodules), respectively, which were not significantly different from those of experienced radiologists (0.93 [P = .45] and 92% [61 of 66 nodules; P = .07]) and exceeded those of junior radiologists (0.78 [P < .001] and 70% [46 of 66 nodules; P = .04]). The specificity of MTI-RADS (87% [154 of 177 nodules]) was higher than that of both experienced and junior radiologists (80% [141 of 177 nodules; P = .02] and 75% [133 of 177 nodules; P = .001], respectively). The AUC of MTI-RADS was higher than that of MDiag (0.91 vs 0.84, respectively; P = .001). In the test set of 243 nodules, the consistency rates between MTI-RADS and the experienced group were higher than those between MTI-RADS and the junior group for composition (79% [n = 193] vs 73% [n = 178], respectively; P = .02), echogenicity (75% [n = 183] vs 68% [n = 166]; P = .04), shape (93% [n = 227] vs 88% [n = 215]; P = .04), and smooth or ill-defined margin (72% [n = 174] vs 63% [n = 152]; P = .002). Conclusion The area under the receiver operating characteristic curve (AUC) of an artificial intelligence model based on the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) was higher than that of a model trained on benign and malignant status based on surgical histopathologic analysis. The AUC and sensitivity of the model based on TI-RADS exceeded those of junior radiologists; the specificity of the model was higher than that of both experienced and junior radiologists. © RSNA, 2022.

The value of the Demetics ultrasound-assisted diagnosis system in the differential diagnosis of benign from malignant thyroid nodules and analysis of the influencing factors.

OBJECTIVES: To evaluate the value of Demetics and to explore whether Demetics can help radiologists with varying years of experience in the differential diagnosis of benign from malignant thyroid nodules. METHODS: The clinical application value of Demetics was assessed by comparing the diagnostic accuracy of radiologists before and after applying Demetics. This retrospective analysis included 284 thyroid nodules that underwent pathological examinations. Two different combined methods were applied. Using method 1: the original TI-RADS classification was forcibly upgraded or downgraded by one level when Demetics classified the thyroid nodules as malignant or benign. Using method 2: the TI-RADS and benign or malignant classification of the thyroid nodules were flexibly adjusted after the physician learned the Demetics' results. RESULTS: Demetics exhibited a higher sensitivity than did junior radiologist 1 (pD1 = 0.029) and was similar in sensitivity to the two senior radiologists. Demetics had a higher AUC than both junior radiologists (pD1 = 0.042, pD2 = 0.038) and an AUC similar to that of the senior radiologists. The sensitivity (p = 0.035) and AUC (p = 0.031) of junior radiologist 1 and the specificity (p < 0.001) and AUC (p = 0.026) of junior radiologist 2 improved with combined method 1. The AUC of junior radiologist 2 improved with combined method 2 (p = 0.045). The factors influencing the diagnostic results of Demetics include sonographic signs (echogenicity and echogenic foci), contrast of the image, and nodule size. CONCLUSION: Demetics exhibited high sensitivity and accuracy in the differential diagnosis of benign from malignant thyroid nodules. Demetics could improve the diagnostic accuracy of junior radiologists. KEY POINTS: • Demetics exhibited a high sensitivity and accuracy in the differential diagnosis of benign from malignant thyroid nodules. • Demetics could improve the diagnostic accuracy of junior radiologists in the differential diagnosis of benign from malignant thyroid nodules. • Factors influencing the diagnostic results of Demetics include the sonographic signs (echogenicity and echogenic foci), contrast of the image, and nodule size.

Palliative Radiofrequency Ablation Accelerates the Residual Tumor Progression Through Increasing Tumor-Infiltrating MDSCs and Reducing T-Cell-Mediated Anti-Tumor Immune Responses in Animal Model.

Previous studies showed that radiofrequency ablation (RFA) has a favorable treatment efficacy for hepatocellular carcinoma (HCC) or colorectal liver metastases (CRLMs). Palliative RFA (pRFA) resulting from larger HCC or multiple CRLMs further accelerated the progression of potential residual tumor, yet its mechanism was still unknown. This study investigated the influence of myeloid-derived suppressor cells (MDSCs) on T-cell immune responses and tumor recurrence after pRFA. CT26 tumor models were used. The percentage of MDSCs in peripheral blood was analyzed by flow cytometry after pRFA. The level of Th1 and Th2 cytokines were measured by ELISA through different treatments (n = 4/group). The tumor-infiltrating MDSCs, dendritic cells, and intracellular cytokines level were analyzed by IHC staining after different treatments. The functional CD8+ T cells were confirmed by the co-localization immunofluorescence staining. The long-term outcomes were also evaluated through CT26 and 4T1 tumor models. The results showed that tumor models treated with pRFA displayed significant increases in the percentage of MDSCs of peripheral blood and tumor infiltration. The expression level of TGF-ß and IL-6 after pRFA was higher than that before pRFA by ELISA and IHC staining. After depleting MDSCs by combining with Abs, the pRFA + Abs group achieved a higher level of Th1 cytokines and greatly enhanced the percentage of tumor-infiltrating functional CD8+ T cells when compared with pRFA alone. The depletion of MDSCs through combination with Abs also resulted in tumor regression. In conclusion, pRFA accelerates the residual tumor progression through increasing tumor-infiltrating MDSCs and reducing T-cell-mediated anti-tumor immune responses, which could provide a potential approach for delaying tumor recurrence caused by pRFA.

The Influencing Factors of Venous Intravasation During Transvaginal Four-dimensional Hysterosalpingo-contrast Sonography With SonoVue.

Transvaginal 4-D hysterosalpingo-contrast sonography with SonoVue (TV 4-D HyCoSy) is the preferred imaging method for evaluating tubal patency. However, venous intravasation in 4-D HyCoSy may affect the diagnosis of tubal patency. The objective of this study was to analyze influencing factors of venous intravasation during TV 4-D HyCoSy. This study included 643 infertile patients who underwent TV 4-D HyCoSy. We analyzed the relationship between the incidence of venous intravasation and patients' basic clinical data, endometrial thickness, inspection timing (clean day of menstruation) and tubal patency. A total of 169 (26.28%) patients exhibited intravasation during TV 4-D HyCoSy. The following are risk factors for venous intravation: secondary infertility, type C + C, type B + C and type B + B in bilateral fallopian tubal patency grouping; endometrial thickness ≤5.45 mm; and taking TV 4-D HyCoSy after menstruation ≤6 d. Infertility duration, intrauterine lesions, a history of pelvic inflammatory disease and a history of pelvic surgery were uncorrelated with venous intravasation. To reduce the incidence of venous intravasation, TV 4-D HyCoSy should be performed 7-10 d after menstruation or when endometrial thickness is thicker than 5.45 mm.

Comparison of Assessment Methods for Fallopian Tubal Patency and Peritubal Adhesion Between Transvaginal 4-Dimensional Hysterosalpingo-Contrast Sonography and Laparoscopic Chromopertubation.

OBJECTIVES: The purpose of this study was to compare transvaginal 4-dimensional hysterosalpingo-contrast sonography with laparoscopic chromopertubation and evaluate the former's clinical value in assessing fallopian tubal patency and peritubal adhesion. METHODS: Fifty-six patients visiting infertility clinics were included in the study and underwent surgery by their own choice in 1 month. In total, 112 fallopian tubes were assessed. Twenty-five were primarily infertile, and the rest were secondarily infertile. Laparoscopic chromopertubation was taken as the reference standard. RESULTS: In a comparison of fallopian tubal patency between transvaginal hysterosalpingo-contrast sonography and laparoscopic chromopertubation, the sensitivity, specify, positive predictive value, and negative predictive value of hysterosalpingo-contrast sonography for diagnosing blocked fallopian tubes were 88.4%, 85.2%, 90.5%, and 82.1% respectively. In a comparison of spray at the fimbrial end between the no-peritubal adhesion and peritubal adhesion groups, the spray score at the fimbrial end in the no-peritubal adhesion group was significantly lower than that in the peritubal adhesion group. In a comparison of periovarian diffusion between the no-peritubal adhesion and peritubal adhesion groups, the periovarian diffusion score in the no-peritubal adhesion group was significantly lower than that in the peritubal adhesion group. In a comparison of periovarian diffusion between the patent-tube and blocked groups confirmed by chromopertubation, the periovarian diffusion score in the patent group was significantly lower than that in the blocked group. CONCLUSIONS: Transvaginal hysterosalpingo-contrast sonography is a method with high sensitivity and specificity for screening fallopian tubal patency and peritubal adhesion.

[Detection of binding capability of targeted KDR ultrasound contrast agent in vitro for evaluating endometrial receptivity].

OBJECTIVE: To prepare a new targeted liposome ultrasonic contrast agent with anti-KDR antibody that binds specifically with KDR as the main receptor of VEGF and evaluate its physical characteristics, biological activity and specific binding capability in vitro. METHODS: A sonicator was used to prepare the biotinylated lipid micro-bubbles (MB-B), and biotin-avidin-mediated technique was used for attachment of anti-mouse KDR monoclonal antibody to the micro-bubble shell to generate MB-BAB-KDR. MB-BAB-KDR was incubated with fluorescent second antibody to assess the link condition, and the control groups were the MB-B and micro-bubbles with the antibody alone (MB-B-KDR). A parallel plate flow chamber system was used to characterize micro-bubbles attachment efficiency to KDR Fc. RESULTS: The surface of the micro-bubbles could carry KDR antibody through the biotin-avidin bridge and MB-BAB-KDR were spherical and well-distributed. After incubation with the second antibody, MB-BAB-KDR could be observed to emit bright green fluorescence (Grade II) as compared with little or weak fluorescence in the control MB-B group (Grade 0) and MB-B-KDR group (Grade I). Targeted micro-bubbles bound to KDR Fc increased as the KDR Fc concentration increased (P<0.05). CONCLUSION: The targeted liposome contrast agent linked with KDR antibody by biotin-avidin bridge we prepared shows an increased binding number as the KDR Fc concentration increases, which provides a novel approach to molecular imaging study of endometrial receptivity.

[Value of contrast-enhanced ultrasound imaging in monitoring malignant tumor during argon-helium cryosurgery].

OBJECTIVE: To assess the value of contrast-enhanced ultrasound imaging in monitoring the therapeutic effect of argon-helium cryosurgical treatment of malignant tumors. METHODS: Before and after argon-helium cryosurgical treatment, 42 patients underwent contrast-enhanced ultrasound imaging, conventional ultrasound imaging and enhanced CT or magnetic resonance imaging (MRI) for examining the number of tumor foci and the size of necrotic areas. RESULTS: A total of 80 tumor lesions were detected by contrast-enhanced ultrasound imaging. Compared with conventional ultrasound imaging, contrast-enhanced ultrasound imaging detected a significantly greater number of tumors and the intratumoral necrotic areas (96 vs 19) as well as a significantly increased mean size of necrotic areas (5.7∓3.6 cm vs 2.8∓1.7 cm), showing no significant differences from the results by enhanced CT and MRI (94 and 5.5∓3.3 cm, P=0.872 and 0.978, respectively). The short-term therapeutic effect of argon-helium cryosurgery evaluated by contrast-enhanced ultrasound imaging were also similar to that assessed by enhanced CT or MRI (P=0.906). CONCLUSION: Contrast-enhanced ultrasound imaging has important values in monitoring malignant tumors during argon-helium cryosurgical treatment and in evaluating the short-term therapeutic effect of the treatment.