US-based Sequential Algorithm Integrating an AI Model for Advanced Liver Fibrosis Screening.

Background Noninvasive tests can be used to screen patients with chronic liver disease for advanced liver fibrosis; however, the use of single tests may not be adequate. Purpose To construct sequential clinical algorithms that include a US deep learning (DL) model and compare their ability to predict advanced liver fibrosis with that of other noninvasive tests. Materials and Methods This retrospective study included adult patients with a history of chronic liver disease or unexplained abnormal liver function test results who underwent B-mode US of the liver between January 2014 and September 2022 at three health care facilities. A US-based DL network (FIB-Net) was trained on US images to predict whether the shear-wave elastography (SWE) value was 8.7 kPa or higher, indicative of advanced fibrosis. In the internal and external test sets, a two-step algorithm (Two-step#1) using the Fibrosis-4 Index (FIB-4) followed by FIB-Net and a three-step algorithm (Three-step#1) using FIB-4 followed by FIB-Net and SWE were used to simulate screening scenarios where liver stiffness measurements were not or were available, respectively. Measures of diagnostic accuracy were calculated using liver biopsy as the reference standard and compared between FIB-4, SWE, FIB-Net, and European Association for the Study of the Liver guidelines (ie, FIB-4 followed by SWE), along with sequential algorithms. Results The training, validation, and test data sets included 3067 (median age, 42 years [IQR, 33-53 years]; 2083 male), 1599 (median age, 41 years [IQR, 33-51 years]; 1124 male), and 1228 (median age, 44 years [IQR, 33-55 years]; 741 male) patients, respectively. FIB-Net obtained a noninferior specificity with a margin of 5% (P < .001) compared with SWE (80% vs 82%). The Two-step#1 algorithm showed higher specificity and positive predictive value (PPV) than FIB-4 (specificity, 79% vs 57%; PPV, 44% vs 32%) while reducing unnecessary referrals by 42%. The Three-step#1 algorithm had higher specificity and PPV compared with European Association for the Study of the Liver guidelines (specificity, 94% vs 88%; PPV, 73% vs 64%) while reducing unnecessary referrals by 35%. Conclusion A sequential algorithm combining FIB-4 and a US DL model showed higher diagnostic accuracy and improved referral management for all-cause advanced liver fibrosis compared with FIB-4 or the DL model alone. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Ghosh in this issue.

Collaborative Enhancement of Consistency and Accuracy in US Diagnosis of Thyroid Nodules Using Large Language Models.

Background Large language models (LLMs) hold substantial promise for medical imaging interpretation. However, there is a lack of studies on their feasibility in handling reasoning questions associated with medical diagnosis. Purpose To investigate the viability of leveraging three publicly available LLMs to enhance consistency and diagnostic accuracy in medical imaging based on standardized reporting, with pathology as the reference standard. Materials and Methods US images of thyroid nodules with pathologic results were retrospectively collected from a tertiary referral hospital between July 2022 and December 2022 and used to evaluate malignancy diagnoses generated by three LLMs-OpenAI's ChatGPT 3.5, ChatGPT 4.0, and Google's Bard. Inter- and intra-LLM agreement of diagnosis were evaluated. Then, diagnostic performance, including accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), was evaluated and compared for the LLMs and three interactive approaches: human reader combined with LLMs, image-to-text model combined with LLMs, and an end-to-end convolutional neural network model. Results A total of 1161 US images of thyroid nodules (498 benign, 663 malignant) from 725 patients (mean age, 42.2 years ± 14.1 [SD]; 516 women) were evaluated. ChatGPT 4.0 and Bard displayed substantial to almost perfect intra-LLM agreement (κ range, 0.65-0.86 [95% CI: 0.64, 0.86]), while ChatGPT 3.5 showed fair to substantial agreement (κ range, 0.36-0.68 [95% CI: 0.36, 0.68]). ChatGPT 4.0 had an accuracy of 78%-86% (95% CI: 76%, 88%) and sensitivity of 86%-95% (95% CI: 83%, 96%), compared with 74%-86% (95% CI: 71%, 88%) and 74%-91% (95% CI: 71%, 93%), respectively, for Bard. Moreover, with ChatGPT 4.0, the image-to-text-LLM strategy exhibited an AUC (0.83 [95% CI: 0.80, 0.85]) and accuracy (84% [95% CI: 82%, 86%]) comparable to those of the human-LLM interaction strategy with two senior readers and one junior reader and exceeding those of the human-LLM interaction strategy with one junior reader. Conclusion LLMs, particularly integrated with image-to-text approaches, show potential in enhancing diagnostic medical imaging. ChatGPT 4.0 was optimal for consistency and diagnostic accuracy when compared with Bard and ChatGPT 3.5. © RSNA, 2024 Supplemental material is available for this article.

Value of Multimodal Data From Clinical and Sonographic Parameters in Predicting Recurrence of Hepatocellular Carcinoma After Curative Treatment.

OBJECTIVE: The objective of the work described here was to assess the value of the combination of pre-operative multimodal data-including clinical data, contrast-enhanced ultrasound (CEUS) information and liver stiffness measurement (LSM) based on 2-D shear wave elastography (SWE)-in predicting early (within 1 y) and late (after 1 y) recurrence of hepatocellular carcinoma (HCC) after curative treatment. METHODS: We retrospectively included 101 patients with HCC who met the Milan criteria and received curative treatment. The multimodel data from clinical parameters, LSM by 2-D SWE and CEUS enhancement patterns were collected. The association between different variables in HCC recurrence was accessed using a Cox proportional hazard model. On the basis of the independent factors of early recurrence, models with different source variables were established (Clinical Model, CEUS-Clinical Model, SWE-Clinical Model, CEUS-SWE-Clinical Model). The goodness-of-fit of models was evaluated and the performance trends of different models were calculated by time-dependent area under the curve (AUC). RESULTS: Two-dimensional SWE, CEUS enhancement patterns and clinical parameters (spleen length, multiple tumors, α-fetoprotein, albumin and prothrombin time) were independently associated with early recurrence (all p values <0.05). Multiple tumors and a decrease in albumin independently contributed to the late recurrence. The model fit of CEUS-SWE-Clinical Model was superior to other models in predicting early recurrence (all p values <0.05). The AUCs of the CEUS-Clinical Model were higher from 2 mo to 7 mo, while the SWE-Clinical Model had higher AUCs from 9 mo to 12 mo. CONCLUSION: CEUS enhancement patterns and 2-D SWE were independent predictors of HCC early recurrence as the two factors contributed to the predictive performance at different times. The multimodal model, which included diverse data in predicting early HCC recurrence, had the best goodness-of-fit.

Discrepancy of Clinical Parameters between the First and Second Molars Can Help to Differentiate Subjects with Aggressive Periodontitis from Chronic Periodontitis: a Cross-sectional Study Based on a Large Chinese Population.

OBJECTIVE: To explore associations between mean discrepancy values for the first and second molars (MDVFSs) and generalised aggressive periodontitis (GAgP) using hospital-based periodontal examination records from a large Chinese population. METHODS: Data from consecutive patients diagnosed as having chronic periodontitis (CP, n = 51,849) and GAgP (n = 2,706) were included. Patient ages, gender, smoking status, mean full-mouth probing depth (PD), and mean full-mouth attachment loss (AL), as well as MDVFSs for PD and AL, were extracted. Multivariate linear regression was used to test associations between MDVFSs and GAgP. RESULTS: After multivariate risk adjustment for potential confounding factors (age, smoking status, and mean PD and AL), the MDVFSs for PD (OR = 2.20, 95%CI: 2.04 to 2.38, P < 0.001) and AL (OR = 1.51, 95CI%: 1.44 to 1.59, P < 0.001) were significantly associated with GAgP. The probability of GAgP was associated with MDVFS for PD falling between 0 mm and 2.5 mm (OR = 4.55, 95%CI: 4.01 to 5.17) and MDVFS for AL falling between 0 mm and 3.5 mm (OR = 2.01, 95%CI: 1.86 to 2.16, P < 0.001). CONCLUSION: This study revealed associations between MDVFSs and GAgP, demonstrating that MDVFSs can serve as promising auxiliary references for the differential diagnosis between CP and GAgP.

Effectiveness of non-surgical periodontal therapy in a large Chinese population with chronic periodontitis.

AIM: The aim of this study was to evaluate the effectiveness of non-surgical periodontal treatment (NSPT) and its influential factors in a large Chinese population with chronic periodontitis. METHODS: Periodontal examination data of 10,789 patients with at least one periodontal re-evaluation record were extracted from a hospital-based electronic periodontal charting record system. Probing depth (PD) and bleeding index (BI) reductions after NSPT and their influential factors were analysed by multilevel analysis. RESULTS: Mean PD reductions at patient level and site level were 0.62 and 0.65 mm respectively. Mean reductions of percentage of tooth with BI > 1 and BI > 2 were 14.9% and 25.21%. Multilevel analysis demonstrated that PD and BI reductions were mainly influenced by baseline PD, baseline attachment loss (AL), baseline mobility, tooth type and frequency of periodontal maintenance (FPM). Besides, PD reduction was associated with baseline BI for all sites and was associated with gender and smoking status for sites with baseline PD ≥ 5 mm. CONCLUSION: The effectiveness of NSPT on patients with chronic periodontitis was proved in a large Chinese population. Outcomes of NSPT were mainly influenced by baseline PD, baseline AL, baseline mobility, tooth type and FPM.

Eukaryotic translation initiation factor 3, subunit a, regulates the extracellular signal-regulated kinase pathway.

The extracellular signal-regulated kinase (ERK) pathway participates in the control of numerous cellular processes, including cell proliferation. Since its activation kinetics are critical for to its biological effects, they are tightly regulated. We report that the protein translation factor, eukaryotic translation initiation factor 3, subunit a (eIF3a), binds to SHC and Raf-1, two components of the ERK pathway. The interaction of eIF3a with Raf-1 is increased by ß-arrestin2 expression and transiently decreased by epidermal growth factor (EGF) stimulation in a concentration-dependent manner. The EGF-induced decrease in Raf-1-eIF3a association kinetically correlates with the time course of ERK activation. eIF3a interferes with Raf-1 activation and eIF3a downregulation by small interfering RNA enhances ERK activation, early gene expression, DNA synthesis, expression of neuronal differentiation markers in PC12 cells, and Ras-induced focus formation in NIH 3T3 cells. Thus, eIF3a is a negative modulator of ERK pathway activation and its biological effects.

[A short-term clinical evaluation of periodontal treatment with an Er:YAG laser for patients with chronic periodontitis: a split-mouth controlled study].

OBJECTIVE: To compare the short-term clinical effects following non-surgical periodontal treatment with Er:YAG laser or with combination of ultrasonic subgingival scaling and root planing with hand instrument (SRP) for patients with chronic periodontitis. METHODS: In the study, 17 patients with chronic periodontitis were randomly treated in a split-mouth design with Er:YAG laser (test group) or a combination of ultrasonic subgingival scaling and root planing with hand instrument (control group). The degree of discomfort experienced during the treatment was graded by the patient using visual analogue scale (VAS) immediately after the completion of test and control treatment procedures. The following clinical parameters were recorded by a calibrated and blinded examiner: plaque index (PLI), bleeding index (BI), probing depth (PD) and attachment loss (AL). RESULTS: The mean VAS score of Er:YAG laser treatment [3 (2, 4.5)] was significantly lower than that of control treatment [5 (4, 6), P=0.013]. Both the groups showed significant reduction of PLI, PD, AL and BI values 2 months and 4 months after treatment. For sites with PD≥4 mm at baseline, the sites treated with Er:YAG laser demonstrated mean PD change from (5.6±1.1) mm to (3.6±1.1) mm and to (3.4±1.0) mm at the end of 2 months and 4 months respectively and demonstrated mean AL change from (5.1±1.5) mm to (3.9±1.6) mm and to (3.8±1.7) mm at the end of 2 months and 4 months respectively, meanwhile the BI value showed significant decrease, P=0.000; the sites treated with conventional SRP demonstrated mean PD change from (5.6±1.1) mm to (3.8±1.1) mm and (3.5± 1.0) mm at the end of 2 months and 4 months respectively and demonstrated mean AL change from (4.8±1.6) mm to (3.8±1.6) mm and (3.6±1.8) mm at the end of 2 months and 4 months respectively, and the BI value also showed significant improvement. No statistical difference for all clinical parameters were found between the two treatment groups. CONCLUSION: The present results indicate that non-surgical periodontal therapy with Er:YAG laser is safe and effective, and Er:YAG laser therapy could be used for patients who was sensitive to pain.

[Relationship between herpesviruses and periodontal pathogenic bacteria in subgingival plaque].

OBJECTIVE: To evaluate the prevalence rates of human cytomegalovirus(HCMV) and Epstein-Barr virus-1(EBV-1) in subgingival plaque and analyze the relationship between herpesviruses, periodontal pathogenic bacteria and periodontal clinical parameters in Chinese patients with aggressive periodontitis(AgP). METHODS: A total of one hundred and twenty subgingival plaque samples were collected from 89 AgP patients and 31 healthy subjects. HCMV and EBV-1 were detected using nested polymerase chain reaction(PCR).Contemporaneously, 8 periodontal pathogenic bacteria including Actinobacillus actinomycetemcomitans(Aa), Porphyromonas gingivalis(Pg), Tannerella forsythensis(Tf), Prevotella intermedia(Pi), Campylobacter rectus(Cr),Fusobacterium nucleatum(Fn), Treponema denticola(Td), Prevotella nigrescens(Pn) were detected by 16S rRNA based PCR. RESULTS: HCMV was more frequently detected in AgP patients (43.8%) than in healthy controls (12.9%, P<0.01). The prevalence rates of HCMV and EBV-1 in AgP patients with 6-8 kinds of bacteria detected were 54.4% and 17.4%, respectively, significantly higher than those with 3-5 kinds of bacteria detected (P<0.05). CONCLUSION: The prevalence rates of HCMV and EBV was higher in AgP patients than in healthy controls. Herpesviruses and periodontal pathogenic bacteria may cooperate synergistically in the development of AgP, which could be considered as a pathogenetic consortium in future investigation of periodontaltitis.