Benign Nodules Research Articles

Artificial intelligence-assisted quantitative CT parameters in predicting the degree of risk of solitary pulmonary nodules

Introduction Artificial intelligence (AI) shows promise for evaluating solitary pulmonary nodules (SPNs) on computed tomography (CT). Accurately determining cancer invasiveness can guide treatment. We aimed to investigate quantitative CT parameters for invasiveness prediction. Methods Patients with stage 0–IB NSCLC after surgical resection were retrospectively analysed. Preoperative CTs were evaluated with specialized software for nodule segmentation and CT quantification. Pathology was the reference for invasiveness. Univariate and multivariate logistic regression assessed predictors of high-risk SPN. Results Three hundred and fifty-five SPN were included. On multivariate analysis, CT value mean and nodule type (ground glass opacity vs. solid) were independent predictors of high-risk SPN. The area under the curve (AUC) was 0.811 for identifying high-risk nodules. Conclusions Quantitative CT measures and nodule type correlated with invasiveness. Software-based CT assessment shows potential for noninvasive prediction to guide extent of resection. Further prospective validation is needed, including comparison with benign nodules.

The study of plain CT combined with contrast-enhanced CT-based models in predicting malignancy of solitary solid pulmonary nodules

To compare the diagnostic performance between plain CT-based model and plain plus contrast CT-based modelin the classification of malignancy for solitary solid pulmonary nodules. Between January 2012 and July 2021, 527 patients with pathologically confirmed solitary solid pulmonary nodules were collected at dual centers with similar CT examinations and scanning parameters. Before surgery, all patients underwent both plain and contrast-enhanced chest CT scans. Two clinical characteristics, fifteen plain CT characteristics, and four enhanced characteristics were used to develop two logistic regression models: model 1 (plain CT only) and model 2 (plain + contrast CT). The diagnostic performance of the two models was assessed separately in the development and external validation cohorts using the AUC. 392 patients from Center A were included in the training cohort (median size, 20.0 [IQR, 15.0–24.0] mm; mean age, 55.8 [SD, 9.9] years; male, 53.3%). 135 patients from Center B were included in the external validation cohort (median size, 20.0 [IQR, 16.0–24.0] mm; mean age, 56.4 [SD, 9.6] years; male, 51.9%). Preoperative patients with 201 malignant (adenocarcinoma, 148 [73.6%]; squamous cell carcinoma, 35 [17.4%]; large cell carcinoma,18 [9.0%]) and 326 benign (pulmonary hamartoma, 118 [36.2%]; sclerosing pneumocytoma, 35 [10.7%]; tuberculosis, 104 [31.9%]; inflammatory pseudonodule, 69 [21.2%]) solitary solid pulmonary nodules were gathered from two independent centers. The mean sensitivity, specificity, accuracy, PPV, NPV, and AUC (95%CI) of model 1 (Plain CT only) were 0.79, 0.78, 0.79, 0.67, 0.87, and 0.88 (95%CI, 0.82–0.93), the model 2 (Plain + Contrast CT) were 0.88, 0.91, 0.90, 0.84, 0.93, 0.93 (95%CI, 0.88–0.98) in external validation cohort, respectively. A logistic regression model based on plain and contrast-enhanced CT characteristics showed exceptional performance in the evaluation of malignancy for solitary solid lung nodules. Utilizing this contrast-enhanced CT model would provide recommendations concerning follow-up or surgical intervention for preoperative patients presenting with solid lung nodules.

Mechanism study of serum extracellular nano-vesicles miR-412-3p targeting regulation of TEAD1 in promoting malignant biological behavior of sub-centimeter lung nodules.

To investigate the impact and potential mechanisms of serum extracellular nano-vesicles (sEVs) miR-412-3p released from sub-centimeter lung nodules with a diameter of ⩽ 10mm on the malignant biological function of micro-nodular lung cancer (mnLC). A total of 87participants were included and divided into a mnLC group (n= 30), a benign lung nodule (BLN) group (n= 27), and a healthy people control group (n= 30). Transmission electron microscopy (TEM), nanoparticle tracking analysis (NTA) and Western blot (WB) were used to measure the morphological characteristics and surface markers of sEVs. In vitro analysis, real-time quantitative polymerase chain reaction (RT-qPCR), CCK-8 cell proliferation assay, clone formation assay, Transwell, stem cell sphere-forming assay, and WB assay were conducted to verify the effect of miR-412-3p/TEAD1 signaling axis on the biological function of lung cancer cells through, respectively. Further validation was conducted using the serum sEVs of the participants. The expression level of sEVs-miR-412-3p in the mnLC group was significantly higher than that in the BLN and healthy groups (P< 0.01). In lung cancer cell lines, miR-412-3p can negatively regulate the targeted gene TEAD1. The miR-412-3p/TEAD1 signaling axis is involved in promoting the EMT signaling pathway and regulating the malignant biological functions of lung cancer cell proliferation, migration, and stemness (P< 0.05). In addition, sEVs in the mnLC group significantly promoted lung cancer cell proliferation, migration, and stemness compared to the BLN and healthy groups, inhibited the expression of E-cadherin and TEAD1 in lung cancer cells, and promoted the expression of N-cadherin and Vimentin (P< 0.05). sEVs-miR-412-3p could promote the biological process of EMT, and lead to the occurrence of malignant biological behavior in sub-centimeter lung nodules. This provides evidence for the miR-412-3p/TEAD1 signaling axis as a potential therapeutic target for mnLC.

Multimodal Deep Learning Network for Differentiating Between Benign and Malignant Pulmonary Ground Glass Nodules.

This study aimed to establish a multimodal deep-learning network model to enhance the diagnosis of benign and malignant pulmonary ground glass nodules [GGNs]. Retrospective data on pulmonary GGNs were collected from multiple centers across China, including North, Northeast, Northwest, South, and Southwest China. The data were divided into a training set and a validation set in an 8:2 ratio. In addition, a GGN dataset was also obtained from our hospital database and used as the test set. All patients underwent chest computed tomography [CT], and the final diagnosis of the nodules was based on postoperative pathological reports. The Residual Network [ResNet] was used to extract imaging data, the Word2Vec method for semantic information extraction, and the Self Attention method for combining imaging features and patient data to construct a multimodal classification model. Then, the diagnostic efficiency of the proposed multimodal model was compared with that of existing ResNet and VGG models and radiologists. The multicenter dataset comprised 1020 GGNs, including 265 benign and 755 malignant nodules, and the test dataset comprised 204 GGNs, with 67 benign and 137 malignant nodules. In the validation set, the proposed multimodal model achieved an accuracy of 90.2%, a sensitivity of 96.6%, and a specificity of 75.0%, which surpassed that of the VGG [73.1%, 76.7%, and 66.5%] and ResNet [78.0%, 83.3%, and 65.8%] models in diagnosing benign and malignant nodules. In the test set, the multimodal model accurately diagnosed 125 [91.18%] malignant nodules, outperforming radiologists [80.37% accuracy]. Moreover, the multimodal model correctly identified 54 [accuracy, 80.70%] benign nodules, compared to radiologists' accuracy of 85.47%. The consistency test comparing radiologists' diagnostic results with the multimodal model's results in relation to postoperative pathology showed strong agreement, with the multimodal model demonstrating closer alignment with gold standard pathological findings [Kappa=0.720, P<0.01]. The multimodal deep learning network model exhibited promising diagnostic effectiveness in distinguishing benign and malignant GGNs and, therefore, holds potential as a reference tool to assist radiologists in improving the diagnostic accuracy of GGNs, potentially enhancing their work efficiency in clinical settings.

SPGAN Optimized by Piranha Foraging Optimization for Thyroid Nodule Classification in Ultrasound Images.

In this research work, Semantic-Preserved Generative Adversarial Network optimized by Piranha Foraging Optimization for Thyroid Nodule Classification in Ultrasound Images (SPGAN-PFO-TNC-UI) is proposed. Initially, ultrasound images are gathered from the DDTI dataset. Then the input image is sent to the pre-processing step. During pre-processing stage, the Multi-Window Savitzky-Golay Filter (MWSGF) is employed to reduce the noise and improve the quality of the ultrasound (US) images. The pre-processed output is supplied to the Generalized Intuitionistic Fuzzy C-Means Clustering (GIFCMC). Here, the ultrasound image's Region of Interest (ROI) is segmented. The segmentation output is supplied to the Fully Numerical Laplace Transform (FNLT) to extract the features, such as geometric features like solidity, orientation, roundness, main axis length, minor axis length, bounding box, convex area, and morphological features, like area, perimeter, aspect ratio, and AP ratio. The Semantic-Preserved Generative Adversarial Network (SPGAN) separates the image as benign or malignant nodules. Generally, SPGAN does not express any optimization adaptation methodologies for determining the best parameters to ensure the accurate classification of thyroid nodules. Therefore, the Piranha Foraging Optimization (PFO) algorithm is proposed to improve the SPGAN classifier and accurately identify the thyroid nodules. The metrics, like F-score, accuracy, error rate, precision, sensitivity, specificity, ROC, computing time is examined. The proposed SPGAN-PFO-TNC-UI method attains 30.54%, 21.30%, 27.40%, and 18.92% higher precision and 26.97%, 20.41%, 15.09%, and 18.27% lower error rate compared with existing techniques, like Thyroid detection and classification using DNN with Hybrid Meta-Heuristic and LSTM (TD-DL-HMH-LSTM), Quantum-Inspired convolutional neural networks for optimized thyroid nodule categorization (QCNN-OTNC), Thyroid nodules classification under Follow the Regularized Leader Optimization based Deep Neural Networks (CTN-FRL-DNN), Automatic classification of ultrasound thyroids images using vision transformers and generative adversarial networks (ACUTI-VT-GAN) respectively.

Diagnostic value of microRNA-200 expression in peripheral blood-derived extracellular vesicles in early-stage non-small cell lung cancer

ObjectiveThis study assessed the diagnostic value of microRNA-200 (miR-200) expression in peripheral blood-derived extracellular vesicles (EVs) in early-stage non-small cell lung cancer (NSCLC).MethodsThis study retrospectively analyzed 100 healthy volunteers (the control group) receiving physical examinations, 168 early-stage NSCLC patients (the NSCLC group), and 128 patients with benign lung nodules (the benign group). The basic and clinical data of participants were obtained, including age, sex, smoking history, carbohydrate antigen 242 (CA242), carcinoembryonic antigen (CEA), carbohydrate antigen 199 (CA199), forced expiratory volume in 1 s, maximal voluntary ventilation, forced vital capacity, interleukin-6 (IL-6), tumor necrosis factor-α (TNF-α), and miR-200 expression. The correlation of miR-200 expression in peripheral blood-derived EVs with CA242, CEA, and CA199 was analyzed, and the diagnostic value of peripheral blood-derived EV miR-200 for early-stage NSCLC was assessed. The risk factors of early-stage NSCLC development were also determined.ResultsAge, the percentage of patients with smoking history, CA242, CEA, CA199, IL-6, and TNF-α levels, and miR-200 expression in peripheral blood-derived EVs were significantly higher in the NSCLC group than in the benign and control groups. Lung disease patients with high miR-200 expression in peripheral blood-derived EVs comprised a higher percentage of patients with smoking history and mixed lesions and had higher CA242, CEA, CA199, and TNF-α levels than those with low miR-200 expression in peripheral blood-derived EVs. In lung diseases, miR-200 expression in peripheral blood-derived EVs was significantly and positively correlated with CA242, CEA, and CA199. Peripheral blood-derived EV miR-200 combined with CA242, CEA and CA199 had higher diagnostic value (area under the curve = 0.942) than single detection, along with higher specificity, and high expression of peripheral blood-derived EV miR-200 was an independent risk factor for early-stage NSCLC.ConclusionPeripheral blood-derived EV miR-200 expression in patients with lung diseases is closely correlated with CA242, CEA, and CA199, and high expression of peripheral blood-derived EV miR-200 is an independent risk factor for early-stage NSCLC and is of high clinical diagnostic value for early-stage NSCLC.

Integrating the incident angle of main vessel of breast nodule with BI-RADS can improve the efficacy of breast malignancy evaluation

The aim of this study was to investigate the measurement of the incident angle of the main blood vessel, and the benefits of its integral with ultrasound malignant features of breast nodules for the assessment of breast malignancy based on BI-RADS. The incident angles of main blood vessels of 185 breast nodules in 185 patients who underwent breast nodule surgical excision or biopsy were quantitatively measured using color Doppler ultrasound from October 2022 to October 2023 in a tertiary hospital, and related data were collected and analyzed. Based on histopathology as the gold standard, the breast nodules were classified into benign and malignant groups. The incident angle values of both groups were compared, Receiver Operating Characteristic (ROC) curves were plotted, and the optimal cutoff value for distinguishing between benign and malignant breast nodules was determined. The malignancy risk of the breast nodules was assessed using the incident angle of the breast main vessel, BI-RADS classification, and a combination of ultrasound malignant features with the incident angle. The areas under the ROC curves (AUC) for each method were calculated and compared. The average incident angle of the main vessel of the breast nodule for the benign and malignant breast nodule groups was (41.47 ± 14.27)° and (22.65 ± 11.09)°, respectively, with a statistically significant difference (t = 10.027, P < 0.001). There was a significant negative correlation between the breast nodule vessel incident angle and histopathological malignancy (r = – 0.593, P < 0.001). The ROC curve and Youden index suggested that the optimal cutoff value for distinguishing between benign and malignant breast nodules using the vascular incident angle was 26.9°, with a sensitivity of 76.34%, specificity of 84.78%, positive predictive value of 83.53%, negative predictive value of 78.00%, and AUC of 0.853. The diagnostic performance of BI-RADS classification based on ultrasound malignant features of the breast nodules alone in assessing the malignancy risk of breast nodules showed a sensitivity of 78.50%, specificity of 92.39%, positive predictive value of 91.25%, negative predictive value of 79.95%, and AUC of 0.905. The integral of ultrasound malignant features and vascular incident angle for BI-RADS based assessment for breast nodule malignancy risk demonstrated a sensitivity of 90.32%, specificity of 89.13%, positive predictive value of 89.36%, negative predictive value of 90.11%, and AUC of 0.940. The differences in negative predictive value and AUC between ultrasound malignant features BI-RADS classification alone and the combination of ultrasound malignant features BI-RADS classification with the incident angle of the main vessel of the breast nodule were all statistically significant (x2 = 3.243, P = 0.042; Z = 2.955, P = 0.003). Measuring the incident angle of the main blood vessel of breast nodules and combining this measurement with ultrasound malignant features for BI-RADS classification can enhance the effectiveness of malignancy risk assessment of breast nodules, increase the negative predictive value, and potentially reduce unnecessary biopsies.

Risk of malignancy in thyroid nodules with increased 11C-Choline uptake detected incidentally on PET/CT: A diagnostic accuracy study.

The purpose was to evaluate the pathological nature of focal thyroid uptake seen in 11C-Choline PET/CT performed for prostate cancer. The study was IRB-approved. All 11C-Choline PET/CT exam reports for studies performed between January 01, 2018, and July 30, 2021, in male patients with prostate cancer in our institution were retrospectively reviewed. Exams with "focal thyroid uptake" on their final report were selected. Patients with surgery or ablation in the thyroid prior to the PET/CT, proven parathyroid adenomas or absent thyroid ultrasound were excluded. Repeated PET/CT exams of same patient were excluded. PET images were analyzed visually and semi-quantitatively by measuring the maximum standardized uptake value (SUVmax) of the focal thyroid uptake. Available thyroid ultrasound images, cytology and pathology reports were reviewed. Statistical analyses were performed. Out of 10,047 sequential 11C-Choline PET/CT studies, 318 reports included "focal thyroid uptake." About 128 of these studies were repeat exams and were excluded. Additional 87 patients were excluded, because the uptake was determined to be adjacent, rather than confined to the thyroid gland. Out of the remaining 103 patients, 74 patients had focal thyroid uptake and concurrent thyroid sonographic evaluation. Out of the 74 focal uptakes evaluated with ultrasound, 21 were presumed benign thyroid nodules based on the ultrasound and 53 had further evaluation with biopsy. Sixty three nodules were benign (21 presumed benign on ultrasound and 42 cytology or surgical pathology-proven), 9 nodules were malignant and 2 remained indeterminate. There was no significant difference between the SUVs of the benign and malignant groups (P > .3). In this retrospective study of patients with prostate cancer who underwent 11C-Choline PET/CT, we identified a group of patients who underwent thyroid ultrasound for incidental finding of focal 11C-Choline thyroid uptake. Incidence of malignancy in this group was 12%. Therefore, further investigation with ultrasound and possibly ultrasound-guided biopsy may be warranted when a choline avid thyroid nodule is found incidentally on choline PET.

EIF1AX mutation in thyroid nodules: a histopathologic analysis of 56 cases in the context of institutional practices.

EIF1AX mutation has been identified as a driver mutation for papillary thyroid carcinoma (PTC) by The Cancer Genome Atlas (TCGA) study. Subsequent studies confirmed this mutation in PTC and Anaplastic Thyroid Carcinoma (ATC) but also reported EIF1AX mutation in Follicular nodular disease (FND) and benign thyroid nodules. In this study, we review thyroid nodules with EIF1AX mutation from two institutions: a tertiary care hospital (YNHH, n = 22) and a major cancer referral center (MSKCC, n = 34) and report the varying histomorphology in the context of additional genetic abnormalities and institutional practices. Pathology diagnoses were reviewed according to the WHO 5th edition and correlated with the type of EIF1AX mutation and additional concurrent molecular alterations, if any. Most cases were splice site type mutations. Cases consisted of 9 FND, 7 follicular (FA) or oncocytic adenomas (OA), 2 non-invasive follicular thyroid neoplasms with papillary-like nuclear features (NIFTP) and 38 follicular-cell derived thyroid carcinomas. Of 8 cases with isolated EIF1AX mutation, 7 were FND, FA or OA (88%) and one was an oncocytic carcinoma (12%). Of 12 cases with EIF1AX and one additional molecular alteration, 9 (75%) were FND, FA or OA, 2 (17%) were NIFTPs and one (8%) was a poorly differentiated thyroid carcinoma. All 36 cases with EIF1AX mutation and molecular alterations were malignant (100%) and included TP53 and TERT promoter mutations associated with ATC (n = 8) and high-grade follicular cell-derived non-anaplastic carcinoma (HGC, n = 2). Isolated EIF1AX mutation was noted only in thyroid nodules seen at YNHH and were predominantly encountered in benign thyroid nodules including FND. Accumulation of additional genetic abnormalities appears to be progressively associated with malignant tumors.

Thermal Ablation for Benign Thyroid Nodules and Papillary Thyroid Microcarcinoma.

Ultrasound-guided minimally invasive thermoablative (MIT) therapies are a therapeutic option for selected patients with large, hypoenhancing, benign thyroid nodules that cause compression disorders or aesthetic discomfort. MIT, which does not require general anaesthesia, causes thermal necrosis of the treated nodule, which is reduced in size by 50 % without functional consequences, and is indicated for patients who are not too young or in the presence of anaesthesia-related risk factors or recurrence following thyroidectomy or refusal of surgery. For the above indications, MIT complements surgery but does not replace it; it must always be performed in centres and by surgeons with proven technical skills and clinical experience. Subject to appropriate informed consent, the treatment is short-duration, well-tolerated by the patient, safe, and non-invasive. It does not require anaesthesia and complications are rare and transient. MIT, and in particular laser-based procedures (TAL), can also be effective and safe for the treatment of potentially destructible papillary microcarcinoma, as shown by the limited but sufficient literature, including the most recent guidelines, which consider it to be a therapeutic alternative that requires a better understanding of its efficacy and safety.

Quantitative and qualitative analysis of contrast-enhanced ultrasound for differentiating benign and malignant superficial enlarged lymph nodes.

In many clinical situations, it is critical to exclude or identify abnormally lymph nodes (LNs). The nature of superficial abnormally LNs is closely related to the stage, treatment, and prognosis of the disease. Ultrasound (US) is an important method for examining superficial LNs due to its cheap and safe characteristics. However, it is still difficult to determine the nature of some LNs with overlapping benign and malignant features in images. Contrast-enhanced ultrasound (CEUS) can be used to evaluate the microperfusion status of tissues in real time, and it can improve diagnostic accuracy to a certain extent. Therefore, in this study, we will analyze the correlation between CEUS quantitative parameters and benign and malignant superficial abnormally LNs, to evaluate the efficacy and value of CEUS in distinguishing benign and malignant superficial LNs. This study retrospectively analyzed 120 patients of abnormal LNs who underwent US and CEUS at the China-Japan Union Hospital of Jilin University from December 2020 to August 2023. All 120 cases of abnormal LNs underwent US-guided coarse needle biopsy, and accurate pathological results were obtained, along with complete US and CEUS images. According to the pathological results, LNs were divided into benign and malignant groups, and the qualitative and quantitative parameters of US and CEUS between the two groups were analyzed. The cutoff value is determined by the receiver operating characteristic (ROC) curve of the subjects, and sensitivity, specificity, and accuracy are applied to evaluate the ability of the cutoff value to distinguish between the two groups. There were a total of 120 LNs, including 36 in the benign group and 84 in the malignant group. The results showed that malignant LNs were usually characterized by the disappearance of lymphatic hilum, round ness index (L/T) <2, irregular morphology, and the manifestation of uneven perfusion (P<0.05). The differences in the quantitative parameters peak enhancement (PE), rise time (RT), time to peak (TTP), wash-in rate (WIR), and wash-out rate (WOR) were statistically significant (P<0.05). The result showed that RT and TTP in the malignant LNs were higher than those in the benign LNs, while the PE, WIR, and WOR were lower. A comparison of the ∆ values showed that the differences in ∆PE, ∆WIR, and ∆fall time (FT) were statistically significant (P<0.05), Among them, the ∆PE and ∆WIR of malignant LNs were higher than those of benign LNs, while the ∆FT was lower than that of benign LNs. Quantitative analysis of CEUS features is valuable in the diagnosis of benign and malignant LNs, and US combined with CEUS helps to improve the accuracy of identifying the nature of LNs.

Diffusion Weighted Imaging for the Assessment of Lymph Node Metastases in Women with Cervical Cancer: A Meta-analysis of the Apparent Diffusion Coefficient Values

PurposeTo assess the diagnostic performance of Diffusion Weighted Imaging (DWI) and provide optimal apparent diffusion coefficient (ADC) cut-off values for differentiating between benign and metastatic lymph nodes in women with uterine cervical cancer. MethodMEDLINE and EMBASE databases were searched. Methodological quality was assessed with QUADAS-2. Data-analysis was performed for three subgroups: 1. All studies; 2. Studies with maximum b-values of 800 s/mm², and 3. Studies containing b-values of 1000 s/mm². Receiver-operating characteristics (ROC) curves were constructed and the area under the curve (AUC) was calculated. The maximum Youden index was used to determine optimal ADC cut-off values, following calculations of sensitivity and specificity. ResultsSixteen articles (1156 patients) were included. Overall, their quality was limited. For all studies combined, the optimum ADC cut-off value was 0.985 x 10⁻³ mm²/s at maximum Youden Index of 0.77, resulting in sensitivity and specificity of 84%, and 94%, respectively. Studies with b-values up to 800 s/mm², gave an optimum ADC cut-off value of 0.985 x 10⁻³ mm²/s at maximum Youden Index of 0.62, with a sensitivity and specificity of 62%, and 100%. Studies containing b-values of 1000 s/mm² gave an optimum ADC cut-off value of 0.9435 x 10⁻³ mm²/s at maximum Youden Index of 0.93, with a sensitivity and specificity of 100%, and 93%, respectively. ConclusionsStudies using DWI including b-values of 1000 s/mm² have higher sensitivity and specificity than those with b-values up to 800 s/mm². At the cut-off value of 0.9435 x 10⁻³ mm²/s DWI can sufficiently discriminate between benign and metastatic lymph nodes.

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography.

The objective of the study was to use a deep learning model to differentiate between benign and malignant sentinel lymph nodes (SLNs) in patients with breast cancer compared to radiologists' assessments.Seventy-nine women with breast cancer were enrolled and underwent lymphosonography and contrast-enhanced ultrasound (CEUS) examination after subcutaneous injection of ultrasound contrast agent around their tumor to identify SLNs. Google AutoML was used to develop image classification model. Grayscale and CEUS images acquired during the ultrasound examination were uploaded with a data distribution of 80% for training/20% for testing. The performance metric used was area under precision/recall curve (AuPRC). In addition, 3 radiologists assessed SLNs as normal or abnormal based on a clinical established classification. Two-hundred seventeen SLNs were divided in 2 for model development; model 1 included all SLNs and model 2 had an equal number of benign and malignant SLNs. Validation results model 1 AuPRC 0.84 (grayscale)/0.91 (CEUS) and model 2 AuPRC 0.91 (grayscale)/0.87 (CEUS). The comparison between artificial intelligence (AI) and readers' showed statistical significant differences between all models and ultrasound modes; model 1 grayscale AI versus readers, P = 0.047, and model 1 CEUS AI versus readers, P < 0.001. Model 2 r grayscale AI versus readers, P = 0.032, and model 2 CEUS AI versus readers, P = 0.041.The interreader agreement overall result showed κ values of 0.20 for grayscale and 0.17 for CEUS.In conclusion, AutoML showed improved diagnostic performance in balance volume datasets. Radiologist performance was not influenced by the dataset's distribution.

460. THE ADDITIONAL VALUE OF CERVICAL ULTRASOUND IN THE DETECTION OF CERVICAL LYMPH NODE METASTASES IN PATIENTS WITH ESOPHAGEAL CANCER

Abstract Background Esophageal cancer patients with cervical lymph node metastases, staged according to the 8th edition of the American Joint Committee on Cancer (AJCC), are considered to have stage IV disease and are generally not eligible for treatment with curative intent. External cervical ultrasound (US) used to be standard in the diagnostic workup for detection of cervical lymph node metastases in the Netherlands, but is no longer included in the esophageal cancer guideline. This study aimed to assess the additional value of US over 18FDG PET-CT for the detection of cervical lymph node metastases in esophageal cancer patients, to reassure justified removal of cervical US from the guideline. Methods This retrospective cohort study included all esophageal cancer patients referred to or diagnosed in the Amsterdam UMC between January 2014 and January 2021. Radiology and multidisciplinary team meeting reports were reviewed to identify patients with suspected cervical lymph node(s). Primary outcome was detection rate of cervical lymph node metastases on ultrasound and/or 18FDG PET-CT. Golden standard was etiology based on Fine Needle Aspiration (FNA). Results This study included 768 patients, with a median age of 66 years. Patients were predominantly male (75.0%) and the majority had an adenocarcinoma (71.9%). On 18FDG PET-CT, 77 patients had suspected cervical lymph nodes. Of those, 39 proved malignant. Seven malignant lymph nodes were missed on 18FDG PET-CT. 18FDG PET-CT had a positive predictive value (PPV) of 50.6%, a negative predictive value (NPV) of 99.0%, a sensitivity of 84.8% and a specificity of 94.7%. Based on US alone, 134 patients had suspected cervical lymph nodes. Of those, 45 proved malignant. One malignant lymph node was missed on US. US had a PVV of 33.6%, a NPV of 99.8%, a sensitivity of 97.8% and a specificity of 87.7%. In total, suspected cervical lymph nodes were documented in 151 patients (19.7%). FNA was conducted in 134 out of 151 patients. Of those, 46 proved malignant. No major complications after FNA were reported. For 21 patients, this resulted in stage migration and changed policy from curative intent to palliative. Conclusion Standard US increases the number of FNA conducted for benign cervical lymph nodes, as the positive predictive value is low (33.6%). However, it does have an additional value as it identifies 15% of cervical lymph node metastases that were not seen on 18FDG PET-CT.

Diagnostic yield of combined ACR TI-RADS and Sonoelastography in solid thyroid nodules in tertiary care center: A prospective cross-sectional Study

Background: Thyroid nodules are prevalent, and accurate differentiation between benign and malignant nodules is crucial for management. We aim to evaluate the effectiveness of combining Thyroid Imaging Reporting and Data System (TIRADS) scoring with strain elastography, specifically the Elasticity Contrast Index (ECI), to differentiate between benign and malignant thyroid nodules. Methods: This analytical cross-sectional study involved 77 patients with solid thyroid nodules identified through B-mode ultrasonography. ACR TI-RADS scores, ECI values, and combined scores were compared with Fine needle aspiration Cytology (FNAC) results. Statistical analysis was performed using SPSS, and Pearson correlation tests were conducted to assess the correlation with FNAC findings. Result: The TI-RADS scoring system has a sensitivity of 83.3%, a specificity of 66.1%, and a positive predictive value of 42.9% for distinguishing benign and malignant nodules. Strain elastography with ECI values has a sensitivity of 94.4%, specificity of 98.3%, PPV of 94.4%, and NPV of 98.3%. Combining ACR TI-RADS and strain elastography achieves a sensitivity of 100%, specificity of 66.1%, NPV of 100%, and PPV of 47.4%. Conclusion: The study emphasizes the benefits of integrating noninvasive methods like ultrasound elastography and ACR TI-RADS for improved diagnostic precision, minimizing invasion and patient discomfort. This strategy is particularly advantageous for TI-RADS 3 nodules and reduces unnecessary procedures. However, FNAC should be reasonable and validated for higher classifications.

Metabolic reprogramming-related gene classifier distinguishes malignant from the benign pulmonary nodules

The current existing classifiers for distinguishing malignant from benign pulmonary nodules is limited by effectiveness or clinical practicality. In our study, we aimed to develop and validate a gene classifier for lung cancer diagnosis. To identify the genes involved in this process, we used the weighted gene co-expression network analysis to analyze gene expression datasets from Gene Expression Omnibus (GEO). We identified the three most relevant modules associated with malignant nodules and performed functional enrichment analysis on them. The results indicated significant involvement in metabolic, immune-related, cell cycle, and viral-related processes. All three modules showed enrichment in metabolic reprogramming pathways. Based on these genes, we intersected genes from the three modules with metabolic reprogramming-related genes and further intersected with differentially expressed genes to get 78 genes. After machine learning algorithms and manual selection, we finally got a nine-gene classifier consisting of SEC24D, RPSA, PSME3, PSMD8, PSMB7, NCOA1, MED12, LPCAT1, and AKR1C3. Our developed and validated classifier-based model demonstrated good discrimination, with an area under the curve (AUC) of 0.763 in the development cohort, 0.744 in the internal validation cohort, and 0.718 in the external validation cohort, and outperformed previous clinical models. Moreover, the addition of nodule size improved the predictive capability of the classifier. We further verify the expression of the gene in the classifier using TCGA lung cancer samples and found eight of the genes showed significant differential expression in lung adenocarcinoma while all nine genes showed significant differential expression in lung squamous carcinoma. Our findings underscore the significance of metabolic reprogramming pathways in patients with malignant pulmonary nodules, and our gene classifier can assist clinicians in differentiating benign from malignant pulmonary nodules in clinical settings.

Diagnosing and management of thyroid nodules and goiter - current perspectives.

Due to the frequent diagnosis of benign thyroid nodules, it is necessary to deviate from the traditional paradigm based on frequent surgical treatment. This article highlights the evolution of diagnosis and treatment in recent years, beginning from standardization of ultrasound assessment of nodules and cytology results to minimally invasive techniques to reduce the size of symptomatic thyroid nodules. These achievements reduce the number of surgeries, enable more individualized care for patients with benign thyroid disease, reduce long-term complications, and promote cost-effectiveness within healthcare systems. Furthermore, although the use of minimally invasive techniques significantly decreases thyroid nodule volume, the thyroid nodule usually does not disappear and the challenges in this field are discussed (the efficacy of thermal ablation, a variable part of thyroid nodules that remains viable after thermal ablation, some of the nodules treated with thermal ablation may require a second treatment over time and the efficacy of thermal ablation in nodules with different phenotypes). However, although surgery still represents the "gold standard" for establishing the final histopathologic diagnosis, it is associated with lifelong thyroid hormone substitution need and serious complications in rare cases. Therefore, it should represent the ultima ratio only after a detailed diagnostic procedure. In the future, artificial intelligence-assisted programs for the evaluation and management of nodules are expected.

Risk factors for recurrent laryngeal nerve injury in microwave ablation of thyroid nodules: A multicenter study

Background and purposeThis study aimed to investigate the risk factors for recurrent laryngeal nerve (RLN) injury after microwave ablation (MWA) of thyroid nodules and to identify factors influencing the recovery time of post-procedure hoarseness. Materials and methodsWe retrospectively analyzed data from patients who underwent MWA for thyroid nodules at five hospitals between November 2018 and July 2022. Patients were divided into malignant and benign nodule groups. Variables analyzed included nodule size and location, the shortest distance from nodules to the thyroid capsule and tracheoesophageal groove (TEG-D), and ablation parameters. Univariate and multivariate analyses were performed to identify risk factors. Kaplan-Meier and Cox analyses were used to evaluate the recovery time of hoarseness after MWA. ResultsThe study included 1,216 patients (mean age 44 ± 12 [SD] years; 901 women) with 602 malignant nodules and 614 benign nodules. The posterior capsule distance (PCD) and TEG-D were identified as independent influencing factors for hoarseness in all patients (P = 0.014, OR = 0.068; P < 0.001, OR = 0.005; AUC = 0.869). TEG-D was a significant risk factor for hoarseness, with safe thresholds identified at 4.9 mm for malignant nodules and 2.2 mm for benign nodules. Among patients who developed hoarseness, those in the close-distance group (TEG-D≤2 mm) had a longer recovery time compared to the distant-distance group. TEG-D was an independent factor influencing recovery time (P = 0.008, HR = 11.204). ConclusionClinicians should consider several factors, particularly TEG-D and PCD, when assessing the risk of RLN injury before MWA. TEG-D was a vital independent factor influencing recovery time. SummaryClinicians should pay attention to several influencing factors for RLN injury before MWA and TEG-D was an independent influencing factor for recovery time of hoarseness after MWA.

Evaluating the Diagnostic Role of ACR-TIRADS and Bethesda Classifications in Thyroid Nodules Highlighted by Cyto-Histopathological Studies.

To evaluate the accuracy of thyroid imaging reporting and data system (ACR-TIRADS) and the Bethesda system for reporting cytopathology (TBSRCP) classifications for identifying or ruling out thyroid malignancy in relation to the gold standard (post-surgical pathology). This cross-sectional study included 573 patients with single or multiple thyroid nodules. Patients were evaluated using the TIRADS and the TBSRCP classification. The data from a cohort of patients who underwent surgery (77/573, 13.4%) were correlated with post-operative pathology and the relevant clinical features of the patients. Of 573 patients, 545 (95.1%) were euthyroid, 24 (4.1%) were hypothyroid, and 4 (0.8%) were hyperthyroid; 419 (73.1%) had benign nodules (Bethesda II), 115 (20.1%) had intermediate (Bethesda III, IV), and 39 (6.8%) had Bethesda V and VI nodules. Four-hundred twenty (73.3%) patients were categorized as TIRADS 2,3, and 153 (26.7%) were categorized as TIRADS 4,5. The Bethesda and TIRADS classifications concorded significantly in thyroid nodule diagnosis (K=14.9%, P<0.001).Thyroid malignancy was significantly associated with microcalcification and interrupted halo, while benign nodules were significantly associated with macrocalcification and complete halo type (P=0.041, P=0.005, respectively). The TBSRCP could significantly detect malignant thyroid nodules with a sensitivity, specificity, PPV, and NPV of 64.1%, 98.1%, 85.0%, and 94.1%, respectively (K=88.2%, P<0.001), while the respective values for the TIRADS classification were 63.5%, 76.0%, 84.6%, and 50.0% (K=34.8%, P=0.001). The TIRADS and TBSRCP are essential primary steps for evaluating thyroid nodules and both are complimentary. Hence, each patient with thyroid nodules should be evaluated by both approaches before opting for surgery. Highly suspicious TIRADS categories TR4 and TR5 need further evaluation by fine needle aspiration cytology.

Application of artificial intelligence in lung cancer screening: A real-world study in a Chinese physical examination population.

With the rapid increase of chest computed tomography (CT) images, the workload faced by radiologists has increased dramatically. It is undeniable that the use of artificial intelligence (AI) image-assisted diagnosis system in clinical treatment is a major trend in medical development. Therefore, in order to explore the value and diagnostic accuracy of the current AI system in clinical application, we aim to compare the detection and differentiation of benign and malignant pulmonary nodules between AI system and physicians, so as to provide a theoretical basis for clinical application. Our study encompassed a cohort of 23 336 patients who underwent chest low-dose spiral CT screening for lung cancer at the Health Management Center of West China Hospital. We conducted a comparative analysis between AI-assisted reading and manual interpretation, focusing on the detection and differentiation of benign and malignant pulmonary nodules. The AI-assisted reading exhibited a significantly higher screening positive rate and probability of diagnosing malignant pulmonary nodules compared with manual interpretation (p < 0.001). Moreover, AI scanning demonstrated a markedly superior detection rate of malignant pulmonary nodules compared with manual scanning (97.2% vs. 86.4%, p < 0.001). Additionally, the lung cancer detection rate was substantially higher in the AI reading group compared with the manual reading group (98.9% vs. 90.3%, p < 0.001). Our findings underscore the superior screening positive rate and lung cancer detection rate achieved through AI-assisted reading compared with manual interpretation. Thus, AI exhibits considerable potential as an adjunctive tool in lung cancer screening within clinical practice settings.