Diagnosis Of Nodules Research Articles

Diagnostic accuracy of radiomics and artificial intelligence models in diagnosing lymph node metastasis in head and neck cancers: a systematic review and meta-analysis

Abstract Introduction Head and neck cancers are the seventh most common globally, with lymph node metastasis (LNM) being a critical prognostic factor, significantly reducing survival rates. Traditional imaging methods have limitations in accurately diagnosing LNM. This meta-analysis aims to estimate the diagnostic accuracy of Artificial Intelligence (AI) models in detecting LNM in head and neck cancers. Methods A systematic search was performed on four databases, looking for studies reporting the diagnostic accuracy of AI models in detecting LNM in head and neck cancers. Methodological quality was assessed using the METRICS tool and meta-analysis was performed using bivariate model in R environment. Results 23 articles met the inclusion criteria. Due to the absence of external validation in most studies, all analyses were confined to internal validation sets. The meta-analysis revealed a pooled AUC of 91% for CT-based radiomics, 84% for MRI-based radiomics, and 92% for PET/CT-based radiomics. Sensitivity and specificity were highest for PET/CT-based models. The pooled AUC was 92% for deep learning models and 91% for hand-crafted radiomics models. Models based on lymph node features had a pooled AUC of 92%, while those based on primary tumor features had an AUC of 89%. No significant differences were found between deep learning and hand-crafted radiomics models or between lymph node and primary tumor feature-based models. Conclusion Radiomics and deep learning models exhibit promising accuracy in diagnosing LNM in head and neck cancers, particularly with PET/CT. Future research should prioritize multicenter studies with external validation to confirm these results and enhance clinical applicability.

PET/CT radiomics and deep learning in the diagnosis of benign and malignant pulmonary nodules: progress and challenges

Lung cancer is currently the leading cause of cancer-related deaths, and early diagnosis and screening can significantly reduce its mortality rate. Since some early-stage lung cancers lack obvious clinical symptoms and only present as pulmonary nodules (PNs) in imaging examinations, accurately determining the benign or malignant nature of PNs is crucial for improving patient survival rates. 18F-FDG PET/CT is important in diagnosing PNs, but its specificity needs improvement. Radiomics can provide information beyond traditional visual assessment, overcoming its limitations by extracting high-throughput quantitative features from medical images. Radiomics features based on 18F-FDG PET/CT and deep learning methods have shown great potential in the noninvasive diagnosis of PNs. This paper reviews the latest advancements in these methods and discusses their contributions to improving diagnostic accuracy and the challenges they face.

Feasibility, efficacy, and safety of core needle biopsy as a first-line method for cervical lymphadenopathy.

This study aimed to determine the feasibility, diagnostic efficacy, and safety of ultrasound-guided core needle biopsy (CNB) as a first-line biopsy method for cervical lymphadenopathy of non-thyroid origin. This retrospective cohort study included consecutive patients with cervical lymphadenopathy in whom US-guided CNB was used as the first-line biopsy method for cervical lymph nodes (LNs) of presumed non-thyroid origin. The coaxial CNB technique was routinely used, while the tilting and hydrodissection CNB techniques were selectively employed for small high-risk LNs. The primary endpoint of this study was the diagnostic efficacy of CNB, evaluated by the rate of inconclusive results (nondiagnostic and indeterminate) and diagnostic accuracy (criterion 1: malignant results; criterion 2: malignant or indeterminate result). The secondary outcomes included the feasibility and safety of CNB, assessed based on the technical success rate and complication rate, respectively. The rates of nondiagnostic, indeterminate, and inconclusive results were 0.7%, 3.4%, and 4.1%, respectively. The sensitivity, specificity, and accuracy of CNB for malignant LNs were 96.2%, 100%, and 97.8%, respectively, with criterion 1, and these values were all 99.8% with criterion 2. The technical success rate of CNB was 99.3%. There were no major complications and 7 cases (0.6%) of minor complications (asymptomatic hematomas). CNB was technically feasible, effective, and safe as a first-line biopsy method for cervical lymphadenopathy of non-thyroid origin with high diagnostic accuracy for malignant nodal disease. Question The role of US-guided CNB as a first-line biopsy method for cervical LNs has not yet been verified and established. Findings US-guided CNB, as a first-line method, demonstrated a high technical success rate and diagnostic accuracy for malignant nodes, with few minor complications. Clinical relevance US-guided CNB can be used as an effective first-line biopsy method for cervical lymphadenopathy and will enable accurate diagnosis of malignant LNs.

Optimizing thyroid AUS nodules malignancy prediction: a comprehensive study of logistic regression and machine learning models

BackgroundThe accurate diagnosis of thyroid nodules with indeterminate cytology, particularly in the atypia of undetermined significance (AUS) category, remains challenging. This study aims to predict the risk of malignancy in AUS nodules by comparing two machine learning (ML) and three conventional logistic regression (LR) models.MethodsA retrospective study on 356 AUS nodules in 342 individuals from 6728 patients who underwent thyroid surgery in 2021. All the clinical, ultrasonographic, and molecular data were collected and randomly separated into training and validation cohorts at a ratio of 7: 3. ML (random forest and XGBoost) and LR (lasso regression, best subset selection, and backward stepwise regression) models were constructed and evaluated using area under the curve (AUC), calibration, and clinical utility metrics.ResultsApproximately 90% (321/356) of the AUS nodules were malignant, predominantly papillary thyroid carcinoma with 68.6% BRAF V600E mutations. The final LR prediction model based on backward stepwise regression exhibited superior discrimination with AUC values of 0.83 (95% CI: 0.73-0.92) and 0.80 (95% CI: 0.67-0.94) in training and validation, respectively. Well calibration, and clinical utility were also confirmed. The ML models showed moderate performance. A nomogram was developed on the final LR model.ConclusionsThe LR model developed using the backward stepwise regression, outperformed ML models in predicting malignancy in AUS thyroid nodules. The corresponding nomogram based on this model provides a valuable and practical tool for personalized risk assessment, potentially reducing unnecessary surgeries and enhancing clinical decision-making.

Do as Sonographers Think: Contrast-Enhanced Ultrasound for Thyroid Nodules Diagnosis via Microvascular Infiltrative Awareness.

Dynamic contrast-enhanced ultrasound (CEUS) imaging can reflect the microvascular distribution and blood flow perfusion, thereby holding clinical significance in distinguishing between malignant and benign thyroid nodules. Notably, CEUS offers a meticulous visualization of the microvascular distribution surrounding the nodule, leading to an apparent increase in tumor size compared to gray-scale ultrasound (US). In the dual-image obtained, the lesion size enlarged from gray-scale US to CEUS, as the microvascular appeared to be continuously infiltrating the surrounding tissue. Although the infiltrative dilatation of microvasculature remains ambiguous, sonographers believe it may promote the diagnosis of thyroid nodules. We propose a deep learning model designed to emulate the diagnostic reasoning process employed by sonographers. This model integrates the observation of microvascular infiltration on dynamic CEUS, leveraging the additional insights provided by gray-scale US for enhanced diagnostic support. Specifically, temporal projection attention is implemented on time dimension of dynamic CEUS to represent the microvascular perfusion. Additionally, we employ a group of confidence maps with flexible Sigmoid Alpha Functions to aware and describe the infiltrative dilatation process. Moreover, a self-adaptive integration mechanism is introduced to dynamically integrate the assisted gray-scale US and the confidence maps of CEUS for individual patients, ensuring a trustworthy diagnosis of thyroid nodules. In this retrospective study, we collected a thyroid nodule dataset of 282 CEUS videos. The method achieves a superior diagnostic accuracy and sensitivity of 89.52% and 94.75%, respectively. These results suggest that imitating the diagnostic thinking of sonographers, encompassing dynamic microvascular perfusion and infiltrative expansion, proves beneficial for CEUS-based thyroid nodule diagnosis.

Enhancing the differential diagnosis of small pulmonary nodules: a comprehensive model integrating plasma methylation, protein biomarkers, and LDCT imaging features

BackgroundAccurate differentiation between malignant and benign pulmonary nodules, especially those measuring 5–10 mm in diameter, continues to pose a significant diagnostic challenge. This study introduces a novel, precise approach by integrating circulating cell-free DNA (cfDNA) methylation patterns, protein profiling, and computed tomography (CT) imaging features to enhance the classification of pulmonary nodules.MethodsBlood samples were collected from 419 participants diagnosed with pulmonary nodules ranging from 5 to 30 mm in size, before any disease-altering procedures such as treatment or surgical intervention. High-throughput bisulfite sequencing was used to conduct DNA methylation profiling, while protein profiling was performed utilizing the Olink proximity extension assay. The dataset was divided into a training set and an independent test set. The training set included 162 matched cases of benign and malignant nodules, balanced for sex and age. In contrast, the test set consisted of 46 benign and 49 malignant nodules. By effectively integrating both molecular (DNA methylation and protein profiling) and CT imaging parameters, a sophisticated deep learning-based classifier was developed to accurately distinguish between benign and malignant pulmonary nodules.ResultsOur results demonstrate that the integrated model is both accurate and robust in distinguishing between benign and malignant pulmonary nodules. It achieved an AUC score 0.925 (sensitivity = 83.7%, specificity = 82.6%) in classifying test set. The performance of the integrated model was significantly higher than that of individual methylation (AUC = 0.799, P = 0.004), protein (AUC = 0.846, P = 0.009), and imaging models (AUC = 0.866, P = 0.01). Importantly, the integrated model achieved a higher AUC of 0.951 (sensitivity = 83.9%, specificity = 89.7%) in 5–10 mm small nodules. These results collectively confirm the accuracy and robustness of our model in detecting malignant nodules from benign ones.ConclusionsOur study presents a promising noninvasive approach to distinguish the malignancy of pulmonary nodules using multiple molecular and imaging features, which has the potential to assist in clinical decision-making.Trial registration: This study was registered on ClinicalTrials.gov on 01/01/2020 (NCT05432128). https://classic.clinicaltrials.gov/ct2/show/NCT05432128.

Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study

ObjectiveTo develop a ultrasound images based dual-channel deep learning model to achieve accurate early diagnosis of thyroid nodules less than 1 cm. MethodsA dual-channel deep learning model called thyroid nodule transformer network (TNT-Net) was proposed. The model has two input channels for transverse and longitudinal ultrasound images of thyroid nodules, respectively. A total of 9649 nodules from 8455 patients across five hospitals were retrospectively collected. The data were divided into a training set (8453 nodules, 7369 patients), an internal test set (565 nodules, 512 patients), and an external test set (631 nodules, 574 patients). ResultsTNT-Net achieved an area under the curve (AUC) of 0.953 (95 % confidence interval (CI): 0.934, 0.969) on the internal test set and 0.941 (95 % CI: 0.921, 0.957) on the external test set, significantly outperforming traditional deep convolutional neural network models and single-channel swin transformer model, whose AUCs ranged from 0.800 (95 % CI: 0.759, 0.837) to 0.856 (95 % CI: 0.819, 0.881). Furthermore, feature heatmap visualization showed that TNT-Net could extract richer and more energetic malignant nodule patterns. ConclusionThe proposed TNT-Net model significantly improved the recognition capability for thyroid nodules with size less than 1 cm. This model has the potential to reduce overdiagnosis and overtreatment of such nodules, providing essential support for precise management of thyroid nodules while complementing fine-needle aspiration biopsy.

The accuracy of fine needle aspiration cytology and ultrasonography in assessing thyroid nodules in correlation with histopathology: a retrospective study

Background: Accurately diagnosing thyroid nodules is vital for preventing unnecessary surgeries and providing prompt therapy. Although fine needle aspiration cytology (FNAC) and ultrasonography (US) are widely used diagnostic methods, their reliability is questioned. This study investigates the effectiveness of US and FNAC in thyroid nodule diagnosis and differentiates benign from malignant nodules in relation to final histopathological diagnosis. Method: A retrospective study including 307 adult patients with thyroid diseases who underwent neck US and FNAC before surgery was conducted between April 2019 and May 2023. The diagnostic efficacy of US, FNAC, and their combination usage was compared to histopathological results. Result: Histopathological findings revealed that 187(61%) cases were benign, while 120 (39%) were malignant. The US features of “taller-than-wider” forms and hypoechoic appearance had the highest diagnostic accuracy in characterizing malignant thyroid nodules, with 83% and 73% accuracy, respectively. The combination of US parameters demonstrated high sensitivity, specificity, positive predictive value, and negative predictive value (NPV) of 88.33%, 63.10%, 60.6%, and 89.4%, with a statistically significant area under the ROC curve (AUC: 0.828, P<0.001) than individual parameters. FNAC’s sensitivity, specificity, PPV NPV, and accuracy in detecting malignant lesions were 50%, 95%, 86%, 75%, and 77%, respectively, with acceptable discrimination and statistical significance (AUC: 0.723, P<0.0001). The combination of US parameters and FNAC significantly improved the AUC value (AUC: 0.878, P<0.0001), sensitivity (83.33%), and specificity (79.14%). Univariate analysis showed that hypoechoic appearance, heterogenicity, large mass size (>4 cm), “taller-than-wider,” infiltrative margins, and microcalcifications were risk factors for malignancy in thyroid nodules and were statistically significant (all P values <0.05). Conclusion: Combining US characteristics with FNAC results can afford the maximum analytical accuracy in distinguishing benign from malignant thyroid nodules. This strategy is practical due to its simplicity, minimal invasiveness, and cost-effectiveness, enabling robust management regimens and avoiding additional surgical procedures.

Ring-Enhancement on CEUS: Is it Useful in the Differential Diagnosis of Solid Thyroid Nodules?

To investigate the efficiency of contrast-enhanced ultrasound (CEUS) features, particularly ring-enhancement patterns, in the differential diagnosis of thyroid nodules. 302 nodules with CEUS ring-enhancement were retrospectively enrolled, including 135 benign and 167 malignant ones. The ring-enhancement patterns were classified into regular and irregular hyper- or hypo-ring enhancement. Comparative analyses of ultrasound (US) and CEUS features between benign and malignant nodules were performed. The diagnostic performances of the ring-enhancement patterns and Chinese Thyroid Imaging Reporting and Data System (C-TIRADS) were compared in nodules with different sizes. Irregular hypo-ring enhancement was much more common in malignancies than that in benign ones, and it was an independent predictor for thyroid malignant nodules. With irregular hypo-ring enhancement as the diagnostic criteria for malignant nodules, the specificity was higher than that of C-TIRADS (85.2% vs. 75.6%, p = .037) while the AUC was comparable (0.845 vs. 0.803, p = .136) in all nodules. When the nodule size was taken into account, the specificity and AUC were both significantly higher than those of C-TIRADS (92.8% vs. 81.1%, p = .021; 0.907 vs. 0.823, p = .026) in nodules ≥10 mm, which can decrease the unnecessary FNA rate. Irregular hypo-ring enhancement was a valuable CEUS feature for the differential diagnosis of thyroid nodules, especially in nodules ≥10 mm.

Application of 18 F-fluorodeoxyglucose PET/computed tomography in the diagnosis of infiltrative subsolid nodules in lung adenocarcinoma.

To investigate the diagnostic value of 18 F-fluorodeoxyglucose(FDG) PET/computed tomography (CT) for infiltrative subsolid nodules at different stages of lung adenocarcinoma and to explore predictive factors for invasive adenocarcinoma, providing compelling evidence for timely intervention. A retrospective analysis was conducted on PET/CT imaging data of 170 subsolid nodules lesions confirmed postoperatively as lung adenocarcinoma or precursor glandular lesions. Lesions were categorized into preinvasive lesions including atypical adenomatous hyperplasia and adenocarcinoma in situ, microinvasive adenocarcinoma, and invasive adenocarcinoma. Compared the differences in imaging features and metabolic parameters among different groups and used a multifactor logistic regression model and receiver operating characteristic curve analysis to identify predictive factors for invasive adenocarcinoma. From preinvasive lesions through microinvasive adenocarcinoma to invasive adenocarcinoma, there was a gradual increase in nodule diameter, nodule area, and proportion of part-solid nodule. Statistical significance ( P < 0.05) was observed in the rates of spiculation and pleural indentation between preinvasive lesions versus microinvasive adenocarcinoma and invasive adenocarcinoma groups. The maximum standardized uptake value and maximum standardized uptake ratio show statistically significant differences ( P < 0.05) between the invasive adenocarcinoma group and the other groups. Logistic regression analysis indicated that nodule composition, nodule diameter, and maximum standardized uptake ratio were predictive factors for invasive adenocarcinoma ( P < 0.05). For part-solid nodules, the longest diameter of the solid component has a high diagnostic value. The imaging features of 18 F-FDG PET/CT contribute to the diagnosis of infiltrative subsolid nodules at different stages of lung adenocarcinoma, providing robust evidence for timely intervention.

MA08.07 Transthoracic Versus Transbronchial Approaches for Diagnosis of Pulmonary Nodules Located in the Middle Lung Zone

MA08.07 Transthoracic Versus Transbronchial Approaches for Diagnosis of Pulmonary Nodules Located in the Middle Lung Zone

Thoracoscopic minimally invasive surgical treatment with the same incisions in a patient with uremia complicated with large thymoma and right upper lobe lung cancer: a case report

A 41 year old female with stage 5 chronic kidney disease undergoing hemodialysis was admitted to the hospital. Chest CT scan revealed a large mass lesion of approximately 6.0 × 3.5x4.9 cm in size in the anterior superior mediastinum and a ground glass nodule in the upper lobe of the right lung, which increased in size from 9 × 7 mm 1 year and 9 months ago to 11mmx9mm before surgery. We designed a localization method to accurately locate the pulmonary nodule and successfully performed thoracoscopic minimally invasive resection of both thymoma and lung cancer through a subxiphoid approach with the same incision for this patient. With the support of perioperative hemodialysis, the patient's outcome is good. The pathological diagnosis of the anterior mediastinal mass is thymoma (b1 type), and the pathological diagnosis of the right upper lobe nodule is invasive lung adenocarcinoma (acinar type). This report describes the diagnosis and treatment process of the case.

68Ga]Ga-LNC1007 versus 2-[18F]FDG in the evaluation of patients with metastatic differentiated thyroid cancer: a head-to-head comparative study.

This head-to-head comparison study aimed to compare the performance of [68Ga]Ga-FAPI-RGD (LNC1007) and 2-[18F]FDG PET/CT in the evaluation of patients with metastatic differentiated thyroid cancer (mDTC). Ten unexplained hyperthyroglobulinemia (UHTg) patients and 20 patients with definite metastatic lesions of thyroid cancer (DmDTC) were enrolled in the study. All patients underwent both [68Ga]Ga-LNC1007 and 2-[18F]FDG PET/CT within 1week. The final diagnosis was based on histopathological results and a comprehensive evaluation of laboratory tests and multimodal imaging characteristics. In patients with UHTg, [68Ga]Ga-LNC1007 PET/CT detected more metastatic lymph nodes (LNs) (17 vs. 15, P = 0.317) and lung lesions (2 vs. 0) than 2-[18F]FDG. In patients with DmDTC, [68Ga]Ga-LNC1007 PET/CT also detected more true positive lesions than 2-[18F]FDG (Total: 133 vs. 103, LN: 20 vs. 15, lung: 18 vs. 10, bone: 87 vs.73). [68Ga]Ga-LNC1007 PET/CT demonstrated significantly higher SUVmax (Total: 6.30 vs. 3.84, LN: 8.28 vs. 4.82, Lung: 3.31 vs. 1.49, Bone: 5.73 vs. 3.87, all P < 0.05) and TBR (Total: 6.92 vs. 4.93, LN: 6.48 vs. 4.16, Lung: 5.16 vs. 2.57, Bone: 7.22 vs. 5.41, all P < 0.05) in true positive lesions compared to 2-[18F]FDG. Specifically, the sensitivity of [68Ga]Ga-LNC1007 PET/CT was higher than that of 2-[18F]FDG in detecting lung and bone metastases (94.7% vs. 52.6% and 100% vs. 83.9%, all P < 0.05). [68Ga]Ga-LNC1007 PET/CT exhibited better specificity and accuracy in diagnosing LNs (96.9% vs. 66.7% and 96.3% vs. 68.5%, all P < 0.05). However, the specificity of [68Ga]Ga-LNC1007 for bone metastasis was inferior to 2-[18F]FDG (15.4% vs. 88.5%, P < 0.05). Compared with 2-[18F]FDG, [68Ga]Ga-LNC1007 PET/CT could detect more metastatic lesions, with higher SUVmax and TBR, in patients with mDTC. [68Ga]Ga-LNC1007 had better accuracy in the diagnosis of LN and lung metastasis. Trial registration ClinicalTrials.gov NCT05515783. Registered 01 May 2022. URL of registry https://classic. gov/ct2/show/NCT05515783.

The Current Progress of Artificial Intelligence in Approach to Thyroid Nodules: A Narrative Review

Background: Artificial intelligence (AI) can play a significant role in the future of thyroidology. Thyroid nodules are common conditions that may benefit from AI through more accurate and efficient diagnosis, risk stratification, and medical or surgical management. Objective: This paper aims to review the latest developments in AI applications for diagnosing and managing thyroid nodules and cancers. Methods: English full-text articles published in the PubMed and Google Scholar databases from January 2014 to March 2024 were collected and reviewed to provide a comprehensive understanding of the topic. A total of 45 studies were selected based on relevance, robust methodology, statistical significance, and broader topic coverage. Results: Artificial intelligence has emerged as a powerful tool for managing thyroid nodules. First, several studies have demonstrated how AI-powered ultrasound interpretation enhances the diagnosis and classification of nodules while reducing the need for invasive fine-needle aspiration (FNA) biopsies. Second, AI significantly improves the cytopathological differentiation between benign and malignant thyroid nodules by minimizing reliance on pathologists' expertise and implementing standardized diagnostic criteria. When cytopathology is inconclusive, AI also aids in identifying molecular markers from omics data, distinguishing between normal and cancerous cells. Moreover, AI tools have been developed for prognosis assessment, predicting distant metastasis, recurrence, and surveillance by integrating medical imaging features with molecular and clinical factors. Additionally, some AI tools are designed for intraoperative evaluation, improving surgical techniques and reducing complications during thyroidectomy. In non-surgical treatments, several models have been developed to optimize therapeutic doses of radioactive iodine (RAI) and predict the outcomes of new drug formulations. Conclusions: Artificial intelligence has the potential to assist physicians in accurate thyroid nodule diagnosis, classification, decision-making, optimizing treatment strategies, and improving patient outcomes. However, there are still limitations to this technology. Artificial intelligence-driven tools require further advancements before they can be fully integrated into clinical practice and replace specialists.

Huge and Multiple Xanthomas Misdiagnosed as Rheumatoid Nodules and Mistreated with Multiple Surgical Excisions over 4 Years, A Case Report

Background: Xanthoma is the iceberg of familial hypercholesterolemia; it’s resemblance to other cutaneous lesions such as rheumatoid nodules might lead to misdiagnosis. We emphasize in this case report the importance of comprehensive clinical and investigatory approach to cutaneous lesions as they could be the only manifestation of systemic diseases, and this helps to avoid delayed management and unnecessary interventions. Aim: Xanthomas as a possible diagnosis for multiple skin nodules, as it can be easily supported by performing simple noninvasive blood tests; the lipid panel. Case report: Female patient, presented with multiple skin lesions and a strong family history of premature coronary artery disease. She was firstly managed with multiple surgical resections as having benign masses, and later was misdiagnosed as having rheumatoid nodules and referred to rheumatology clinic for evaluation, wherein a clinical suspicion of xanthomas originated, and was supported by the severely elevated serum LDL level and a tissue diagnosis of xanthoma. She has been started on statins with regular clinic. Conclusion: The purpose of this case study is to explain the importance of including xanthomas within the differential diagnosis of recurrent skin lesions. Whereas the tissue diagnosis is the gold-slandered investigation, simple noninvasive blood test, serum lipid measurement can be the clue for diagnosis of the hidden fatal but easily controllable disease; familial hypercholesterolemia.

Lymph node metastasis determined miRNAs in esophageal squamous cell carcinoma.

There is no golden noninvasive and effective technique to diagnose lymph node metastasis (LNM) for esophageal squamous cell carcinoma (ESCC) patients. Here, a classifier was proposed consisting of miRNAs to screen ESCC patients with LNM from the ones without LNM. miRNA expression and clinical data files of 93 ESCC samples were downloaded from TCGA as the discovery set and 119 ESCC samples with similar dataset GSE43732 as the validation set. Differentially expressed miRNAs (DE-miRNAs) were analyzed between patients with LNM and without LNM. LASSO regression was performed for selecting the DE-miRNA pair to consist the classifier. To validate the accuracy and reliability of the classifier, the SVM and AdaBoost algorithms were applied. The CCK-8 and wound healing assay were used to evaluate the role of the miRNA in ESCC cells. There were 43 DE miRNAs between the LNM+ group and LNM- group. Among them, miR-224-5p, miR-99a-5p, miR-100-5p, miR-34c-5p, miR-503-5p, and miR-452-5p were identified by LASSO to establish the classifier. SVM and AdaBoost showed that the model could classify the ESCC patients with LNM from the ones without LNM precisely and reliably in 2 data sets. miR-224-5p in the classifier as the top contributor to discriminate the two groups of patients based on AdaBoost, promoted ESCC cell proliferation and migration in vitro. The classifier based on these 6 miRNAs could classify the ESCC patients with LNM from the ones without LNM successfully.

12572 Incidental Adrenal Enlargement On Ct Scan In South Brooklyn Health, How Often Is It Functional?

Abstract Disclosure: R. Ruggiero: None. N. Simon: None. Background: Incidental findings of adrenal hyperplasia are increased due to the widespread rise in cross sectional imaging, as well as improvement of imaging modalities. There is a lack of literature reporting on the prevalence of incidental adrenal hyperplasia. One study reported a prevalence of 11.3%. Adrenocortical hyperplasia can result from endocrine disorders such as ACTH dependent and independent Cushing syndrome, primary aldosteronism, Multiple Endocrine Neoplasia type 1, and congenital adrenal hyperplasia. Other reported causes are radiographic adrenal enlargement of unknown cause and without clinical or biochemical manifestations, inflammation, neoplasms, and depression. Most cases are a radiographic finding with no clinical significance. One study reported that 69.23% of cases were nonfunctional. There are currently no guidelines in place for biochemical evaluation of incidental adrenocortical hyperplasia. Patients are typically referred to endocrinology services. Objective: The purposes of this study was to: 1. Evaluate the number of patients referred to endocrinology clinic for incidental abnormal adrenal imaging. 2. Examine the percentage of abnormal adrenal imaging findings on CT scan, in particular adrenal hyperplasia, that are hormonally active. Methods: This was a retrospective study of patients who were referred to endocrinology clinic or electronic endocrine consult for incidental abnormal adrenal imaging, excluding those with clear diagnosis of masses, nodules, adenomas, or cysts. Data collected included demographics, type of study imaging and radiologist reader, hormonal studies, comorbid conditions such as diabetes mellitus, hypertension, obesity, osteoporosis, as well as visit type to endocrinology service (e-consult vs in person). Results: The total number of consults referred to endocrinology during this period was 138. Due to repeat referral or having an adrenal pathology other than hyperplasia, 83 patients were excluded from analysis. There were 55 patients with isolated adrenal hyperplasia, 86% of whom were Caucasian, 11% Hispanic, and 78% of patients were female. Median age 63 years old. Hypertension was noted in 69% of patients, 36% had diabetes mellitus or dysglycemia, 36% were obese, and 1.8% had osteoporosis. Imaging reading was performed by 3 radiologists, 75% of cases reported by one reader. Only 5% of referrals were answered as an e-consult. About 27% of patients did not show up to establish care. Hormonal workup was completed by 60% of the patients, with 16 % having abnormal findings. One patient required confirmatory workup. No patients required treatment. Conclusion: Adrenal Hyperplasia is often an incidental radiologic finding, that can be reader dependent. Most cases are nonfunctioning without abnormal findings on hormonal workup. E-Consultation can be an efficient tool to help PCP and reduce endocrine clinic visits. Presentation: 6/1/2024

6999 Utilizing Machine Learning for One-Step Diagnosis Of Adrenal Diseases: Integrating Clinical, Serum Steroid, And Body Composition Data

Abstract Disclosure: S. Park: None. J. Noh: None. J. Kim: None. T. Kim: None. H. Seo: None. J. Choo: None. M. Choi: None. J. Kim: None. Background: With the increasing incidence of adrenal incidentalomas, the precise diagnosis of subtypes, such as mild autonomous cortisol secretion (MACS), adrenal Cushing’s syndrome (ACS), primary aldosteronism (PA), pheochromocytoma and paraganglioma (PPGL), or nonfunctioning adrenal adenomas (NFA) is becoming more critical. However, the process of making accurate diagnoses remains intricate and challenging. This study aims to explore a streamlined, one-step method for diagnosing adrenal nodules, employing a machine learning (ML) model that integrates clinical data (CL), serum steroid profiles (SSP), and computed tomography-based body composition data (BC). Methods: We utilized ML models for subtyping adrenal diseases within a cohort of 641 patients (comprising MACS=141, ACS=64, PA=265, PPGL=78, and NFA=93), incorporating 37 CL, 64 SSP, and 15 BC features. Patients were randomly split into training and test cohorts at a 4:1 ratio, with each disease proportionally represented. The ML-based pipeline involved ML model selection, outlier detection, feature selection, and re-sampling algorithm. An ML model was developed to classify each of the five distinct adrenal diseases individually. In addition, separate ML models were also developed and optimized for individual comparisons between NFA and each of the other four diseases. The performance was evaluated using balanced accuracy, sensitivity, specificity, area under the curve (AUC), and F1 score. Results: The OneVsRest Classifier exhibited the best performance in the multi-class classification of the five adrenal diseases, achieving a balanced accuracy (0.78), sensitivity (0.77), specificity (0.93), and an AUC of 0.89. In this process, 10 CL features and 39 SSP features were utilized, whereas BC did not yield significant features. Using only SSP, the ML model achieved a balanced accuracy of 0.71 and an AUC of 0.89, whereas the ML model using only CL demonstrated a relatively lower accuracy of 0.58 and an AUC of 0.82. In models comparing MACS, ACS, PA, and PPGL with NFAs, the accuracies were 0.85, 0.94, 0.78, and 0.86, respectively, with AUCs of 0.96, 0.99, 0.90, and 0.94, respectively. The ML model differentiating between NFA and the other functioning adrenal diseases exhibited an accuracy of 0.75 and an AUC of 0.79 Conclusion: We have developed a highly sensitive and specific one-step ML model for differentiating adrenal diseases using CL, SSP, and BC. This approach is anticipated to facilitate precise diagnoses of adrenal nodules, thereby enhancing patient care and improving clinical outcomes. Presentation: 6/2/2024

NAS FD Lung: A novel lung assist diagnostic system based on neural architecture search

In the detection and recognition of lung nodules, pulmonary nodules vary in size and shape and contain many similar tissues and organs around them, leading to the problems of both missed detection and false detection in existing detection algorithms. Designing proprietary detection and recognition networks manually requires substantial professional expertise. This process is time-consuming and labour-intensive and leads to issues like parameter redundancy and improper feature selection. Therefore, this paper proposes a new pulmonary CAD (computer-aided diagnosis) system for pulmonary nodules, NAS FD Lung (Using the NAS approach to search deep FPN and DPN networks), that can automatically learn and generate a deep learning network tailored to pulmonary nodule detection and recognition task requirements. NAS FD Lung aims to use automatic search to generate deep learning networks in the auxiliary diagnosis of pulmonary nodules to replace the manual design of deep learning networks. NAS FD Lung comprises two automatic search networks: BM NAS-FPN (Using NAS methods to search for deep FPN structures with Binary operation and Matrix multiplication fusion methods) network for nodule detection and NAS-A-DPN (Using the NAS approach to search deep DPN networks with attention mechanism) for nodule identification. The proposed technique is tested on the LUNA16 dataset, and the experimental results show that the model is superior to many existing state-of-the-art approaches. The detection accuracy of lung nodules is 98.23%. Regarding the lung nodules classification, the accuracy, specificity, sensitivity, and AUC values achieved 96.32%,97.14%,95.82%, and 98.33%, respectively.

Value of spectral parameters in the differential diagnosis of benign and malignant breast nodules in non-enhanced chest CT.

Dual-layer spectral computed tomography (DSCT) is capable of acquiring both conventional and spectral images during one routine scan, and is widely used for the quantitative and qualitative analyses of substances, differential diagnosis, and disease staging. However, limited research has been conducted on its performance in the differential diagnosis of benign and malignant breast nodules using non-enhanced scans. This study aimed to assess the diagnostic performance of multiple quantitative parameters derived from non-enhanced DSCT in differentiating benign from malignant breast nodules. This retrospective cross-sectional study examined a total of 121 breast nodules from 114 patients (malignant group: n=68; benign group: n=53) identified during chest physical examination or routine admission for the treatment of breast diseases at The First Affiliated Hospital of Soochow University from March 2023 to December 2023. All the patients underwent DSCT scanning and pathological diagnosis. The DSCT quantitative parameters, including the effective atomic number (Zeff), computed tomography (CT) attenuation values at 40-70 keV, and the slope of the spectral Hounsfield unit curve (λHU), in non-enhanced images were measured. The λHU was calculated as follows: λHU = CT70 keV - CT40 keV/30 HU. Additionally, typical radiological features were analyzed. A DSCT parameter diagnostic model and a conventional CT diagnostic model were assessed using receiver operating characteristic (ROC) curves. The Delong test was used to assess and compare the diagnostic performance of each model. The DSCT parameters, including the Zeff (P<0.001), λHU (P<0.001), and CT attenuation values at 40 keV (P<0.001) and 50 keV (P=0.001), as well as the presence of the lobular sign (P<0.001) and spicule sign (P<0.001), exhibited statistically significant differences between the benign and malignant groups. The logistic regression analysis revealed that the Zeff [odds ratio (OR): 9.22; 95% confidence interval (CI): 2.11-40.35; P=0.003], λHU (OR: 0.64; 95% CI: 0.52-0.79; P<0.001), 40 keV CT attenuation value (OR: 8.69; 95% CI: 3.28-23.06; P<0.001), 50 keV CT attenuation value (OR: 0.01; 95% CI: 0.001-0.07; P<0.001), and lobular sign (OR: 3.95; 95% CI: 1.52-10.31; P=0.005) were independent predictors of malignancy. Compared to the benign group, the malignant group had a higher likelihood of presenting with the lobular sign and higher Zeff values but lower λHU values. The ROC curve indicated that the Zeff had the highest diagnostic efficacy [area under the curve (AUC) of the ROC =0.792, 95% CI: 0.71-0.87]. Further, the DSCT parameter diagnostic model had improved diagnostic efficacy with an AUC of 0.899 (95% CI: 0.84-0.96), which was higher than the AUC of the conventional CT diagnostic model (AUC =0.796, 95% CI: 0.72-0.87). The Delong test revealed a statistically significant difference between these two models (P=0.04). DSCT parameters derived from non-enhanced DSCT images, such as the Zeff value and λHU, can be used to differentiate benign and malignant breast nodules, and the differential diagnosis efficacy of the DSCT parameters is higher than that of conventional CT parameters.