Detection Of Nodules Research Articles

Pulmonary nodules and the psychological harm they can cause: A scoping review

More than 1.6 million pulmonary nodules are diagnosed in the United States each year. Although the majority of nodules are found to be benign, nodule detection and the process of ruling out malignancy can cause patients psychological harm to varying degrees. The present study undertakes a scoping review of the literature investigating pulmonary nodule-related psychological harm as a primary or secondary outcome. Online databases were systematically searched to identify papers published through June 30, 2023, from which 19 publications were reviewed. We examined prevalence by type, measurement, associated factors, and behavioral or clinical consequences. Of the 19 studies reviewed, 11 studies investigated distress, anxiety (n = 6), and anxiety and depression (n = 4). Prevalence of distress was 24.0 %-56.7 %; anxiety 9.9 %-42.1 %, and 14.6 %-27.0 % for depression. A wide range of demographic and social characteristics and clinical factors were associated with nodule-related psychological harm. Outcomes of nodule-related harms included experiencing conflict when deciding about treatment or surveillance, decreased adherence to surveillance, adoption of more aggressive treatment, and lower health-related quality of life. Our scoping review demonstrates that nodule-related psychological harm is common. Findings provide evidence that nodule-related psychological harm can influence clinical decisions and adherence to treatment recommendations. Future research should focus on discerning between nodule-related distress and anxiety; identifying patients at risk; ascertaining the extent of psychological harm on patient behavior and clinical decisions; and developing interventions to assist patients in managing psychological harm for better health-related quality of life and treatment outcomes.

Automated estimation of offshore polymetallic nodule abundance based on seafloor imagery using deep learning.

The burgeoning demand for critical metals used in high-tech and green technology industries has turned attention toward the vast resources of polymetallic nodules on the ocean floor. Traditional methods for estimating the abundance of these nodules, such as direct sampling or acoustic imagery are time and labour-intensive or often insufficient for large-scale or accurate assessment. This paper advocates for the automatization of polymetallic nodules detection and abundance estimation using deep learning algorithms applied to seabed photographs. We propose UNET convolutional neural network framework specifically trained to process the unique features of seabed imagery, which can reliably detect and estimate the abundance of polymetallic nodules based on thousands of seabed photographs in significantly reduced time (below 10 h for 30 thousand photographs). Our approach addresses the challenges of data preparation, variable image quality, coverage-abundance transition model and sediments presence. We indicated the utilization of this approach can substantially increase the efficiency and accuracy of resource estimation, dramatically reducing the time and cost currently required for manual assessment. Furthermore, we discuss the potential of this method to be integrated into large-scale systems for sustainable exploitation of these undersea resources.

Automatic detection of lung nodules in computed tomography images using U-Net

Automatic detection of lung nodules in computed tomography images using U-Net

Expressive feature representation pyramid network for pulmonary nodule detection

Expressive feature representation pyramid network for pulmonary nodule detection

An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images

BackgroundThis study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs.MethodsNon-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong’s test was used to compare the CPIs group with the VMIs group.ResultsWhen distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P < 0.05). And Delong’s test indicated that the differences between the area-under-the-curve (AUC) values of the CPIs group and the VMIs group were not statistically significant (P > 0.05).ConclusionThe AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.

Feature Extraction and Identification of Rheumatoid Nodules Using Advanced Image Processing Techniques

Background/Objectives: Accurate detection and classification of nodules in medical images, particularly rheumatoid nodules, are critical due to the varying nature of these nodules, where their specific type is often unknown before analysis. This study addresses the challenges of multi-class prediction in nodule detection, with a specific focus on rheumatoid nodules, by employing a comprehensive approach to feature extraction and classification. We utilized a diverse dataset of nodules, including rheumatoid nodules sourced from the DermNet dataset and local rheumatologists. Method: This study integrates 62 features, combining traditional image characteristics with advanced graph-based features derived from a superpixel graph constructed through Delaunay triangulation. The key steps include image preprocessing with anisotropic diffusion and Retinex enhancement, superpixel segmentation using SLIC, and graph-based feature extraction. Texture analysis was performed using Gray-Level Co-occurrence Matrix (GLCM) metrics, while shape analysis was conducted with Fourier descriptors. Vascular pattern recognition, crucial for identifying rheumatoid nodules, was enhanced using the Frangi filter. A Hybrid CNN–Transformer model was employed for feature fusion, and feature selection and hyperparameter tuning were optimized using Gray Wolf Optimization (GWO) and Particle Swarm Optimization (PSO). Feature importance was assessed using SHAP values. Results: The proposed methodology achieved an accuracy of 85%, with a precision of 0.85, a recall of 0.89, and an F1 measure of 0.87, demonstrating the effectiveness of the approach in detecting and classifying rheumatoid nodules in both binary and multi-class classification scenarios. Conclusions: This study presents a robust tool for the detection and classification of nodules, particularly rheumatoid nodules, in medical imaging, offering significant potential for improving diagnostic accuracy and aiding in the early identification of rheumatoid conditions.

Tube voltage in chest and abdomen DR imaging: Which settings return maximal non-prewhitening model observer with eye filter (NPWE) detectability?

The non-prewhitening computational model observer with eye filter (NPWE) has been shown to reasonably predict human observer performance in general radiography and is an appropriate substitute when real clinical trials are not feasible. In this study, the NPWE model observer is used to detect specific tasks (circular designer nodules) ranging between 1 and 30mm in diameter using chest and abdomen phantom images acquired across the diagnostic energy range (60-125 kVp) with and without an anti-scatter grid. The aim of this study was to derive tube voltage (kVp) settings that return maximal NPWE detectability (d') of designer nodules, for digital radiography (DR) chest and abdomen imaging. Images of a chest phantom (LucAl phantom) and a surrogate for an abdomen (18.5cm PMMA) were acquired across the diagnostic energy range (60-125 kVp) with matched effective dose (for the respective anatomies), with and without an anti-scatter grid, on a general x-ray system. Images were captured using an Agfa DX-D 40C wireless indirect caesium iodide (CsI) imaging panel. Modulation transfer function (MTF), normalized noise power spectrum (NNPS), and contrast (C) were measured in each image and the detectability index d' was calculated for circular designer nodules with diameters ranging from 1 to 30mm (in steps of 1mm). The calculated d' peaked at a nodule diameter of 3mm irrespective of tube voltage, for both chest and abdomen images. A tube voltage of 80kVp returned maximal d' for chest imaging across all nodule diameters both with and without an anti-scatter grid. A tube voltage of 70 kVp returned maximal d' for abdomen imaging. The NPWE observer model has been used to derive tube voltages (kVp) that return maximal detectability (d') of designer nodules for chest and abdomen radiography using a modern DR imaging system. This will provide the medical physicist with a starting point in the task of optimising tube voltage range for chest and abdomen imaging.

Virtual thoracoscopic imaging for accurate pulmonary nodule localization: clinical experience.

The increasing detection of small pulmonary nodules on computed tomography (CT) warrants simple and effective nodule localization methods. We describe our clinical experience using an experimental computer that displays virtual thoracoscopic images. This device constructs three-dimensional images from preoperative CT scans and simulates the deflated lung parenchyma in the lateral decubitus position. Five patients underwent lung resection using this technology. The device provided images that closely resembled actual thoracoscopic images in all cases. This method addresses the limitations of other localization techniques such as allergic reactions and mechanical marker-related complications. The method only requires preoperative CT images, and the process is semi-automatically performed by specifying the nodule location, thoracoscopic camera insertion site, and camera angle. This study is still in the preliminary phase and has several limitations. However, this method has the potential to accurately predict nodule locations and eliminate the many risks associated with other techniques.

Editorial Comment: Computer-Aided Detection of Lung Nodules on Low-Dose Pediatric Chest CT-A Cautionary Tale.

Editorial Comment: Computer-Aided Detection of Lung Nodules on Low-Dose Pediatric Chest CT-A Cautionary Tale.

P4.04C.05 AI-Assisted CXR Analysis in the Detection of Lung Nodules and Incidental Lung Cancers

P4.04C.05 AI-Assisted CXR Analysis in the Detection of Lung Nodules and Incidental Lung Cancers

Software using artificial intelligence for nodule and cancer detection in CT lung cancer screening: systematic review of test accuracy studies

ObjectivesTo examine the accuracy and impact of artificial intelligence (AI) software assistance in lung cancer screening using CT.MethodsA systematic review of CE-marked, AI-based software for automated detection and analysis of...

Multi-View Soft Attention-Based Model for the Classification of Lung Cancer-Associated Disabilities.

Background: The detection of lung nodules at their early stages may significantly enhance the survival rate and prevent progression to severe disability caused by advanced lung cancer, but it often requires manual and laborious efforts for radiologists, with limited success. To alleviate it, we propose a Multi-View Soft Attention-Based Convolutional Neural Network (MVSA-CNN) model for multi-class lung nodular classifications in three stages (benign, primary, and metastatic). Methods: Initially, patches from each nodule are extracted into three different views, each fed to our model to classify the malignancy. A dataset, namely the Lung Image Database Consortium Image Database Resource Initiative (LIDC-IDRI), is used for training and testing. The 10-fold cross-validation approach was used on the database to assess the model's performance. Results: The experimental results suggest that MVSA-CNN outperforms other competing methods with 97.10% accuracy, 96.31% sensitivity, and 97.45% specificity. Conclusions: We hope the highly predictive performance of MVSA-CNN in lung nodule classification from lung Computed Tomography (CT) scans may facilitate more reliable diagnosis, thereby improving outcomes for individuals with disabilities who may experience disparities in healthcare access and quality.

Evaluation of the relationship between thyroid cancer and the concurrent detection of thyroid nodules on the background of primary hyperparathyroidism

Introduction: Primary Hyperparathyroidism (PHPT) is commonly caused by a benign parathyroid adenoma that results in overactivity of the gland and subsequent hypercalcemia due to elevated parathyroid hormone (PTH). This endocrine pathology is associated with thyroid cancer, specifically Papillary Thyroid Cancer (PTC). However, the explanation for their synchronous presentation is unknown. Moreover, it causes diagnostic and treatment challenges that impact patient outcomes. Aims and Objectives: To critically analyze published research to address the relationship between PHPT and thyroid cancer, the role of ultrasound imaging in detecting sinister thyroid nodules in PHPT patients and the features of PHPT that predispose the risk of thyroid malignancy. Study Design: Literature Review Methodology: Electronic database searches of PubMed and CINAHL Plus through EBSCOhost were conducted using the keywords "primary hyperparathyroidism", "thyroid nodules" and "thyroid cancer". Following application of filters and removal of duplicates, 627 relevant results remained. Articles were screened for eligibility based on predetermined selection criteria. Following a review of titles and abstracts, 10 peer-reviewed articles were chosen for further analysis. The studies included were critically appraised using the EBL Critical Appraisal Checklist. Results: 10 articles were examined, 2 were prospective cohort studies and 8 were retrospective cohort studies. All studies involved exhaustive medical chart reviews of patients with PHPT, to investigate the concomitance of thyroid malignancy. Six studies established cervical ultrasound as the optimal method of recognition and preoperative localization of thyroid and parathyroid lesions. Overall, the incidence of thyroid cancer among PHPT patients ranged between 2.9% to 32.9%. Four studies established age, gender and PTH levels as risk factors. Conclusion: The existing literature is consistent with previous studies and purports that individuals with a background fo PHPT are at an increased risk of thyroid cancer. Furthermore the highest likelihood of identifying thyroid cancer is through preoperative localization of parathyroid adenomas by cervical ultrasound, in female patients over the age of 50. Key Findings: Further research is needed to understand the underlying pathogenesis and genetic mechanisms that encompass the relationship between PHPT and thyroid cancer.

Performance of Lung-Nodule Computer-Aided Detection Systems on Standard-Dose and Low-Dose Pediatric CT Scans: An Intraindividual Comparison.

Background: When applying lung-nodule computer-aided detection (CAD) systems for pediatric CT, performance may be degraded on low-dose scans due to increased image noise. Objective: To conduct an intraindividual comparison of the performance for lung nodule detection of two CAD systems trained using adult data between low-dose and standard-dose pediatric chest CT scans. Methods: This retrospective study included 73 patients (32 female, 41 male; mean age, 14.7 years; age range, 4-20 years) who underwent both clinical standard-dose and investigational low-dose chest CT examinations within the same encounter from November 30, 2018 to August 31, 2020 as part of an earlier prospective study. Fellowship-trained pediatric radiologists annotated lung nodules to serve as the reference standard. Both CT scans were processed using two publicly available lung-nodule CAD systems previously trained using adult data: FlyerScan and Medical Open Network for Artificial Intelligence (MONAI). The systems' sensitivities for nodules measuring 3-30 mm (n=247) were calculated when operating at a fixed frequency of two false-positives per scan. Results: FlyerScan exhibited detection sensitivities of 76.9% (190/247; 95% CI: 73.3-80.8%) on standard-dose scans and 66.8% (165/247; 95% CI: 62.6-71.5) on low-dose scans. MONAI exhibited detection sensitivities of 67.6% (167/247, 95% CI: 61.5-72.1) on standard-dose scans and 62.3% (154/247, 95% CI: 56.1-66.5%) on low-dose scans. The number of detected nodules for standard-dose versus low-dose scans for 3-mm nodules was 33 versus 24 (FlyerScan) and 16 versus 13 (MONAI), 4-mm nodules was 46 versus 42 (FlyerScan) and 39 versus 30 (MONAI), 5-mm nodules was 38 versus 33 (FlyerScan) and 32 versus 31 (MONAI), and 6-mm nodules was 27 versus 20 (FlyerScan) and 24 versus 24 (MONAI). For nodules measuring ≥7 mm, detection did not show a consistent pattern between standard-dose and low-dose scans for either system. Conclusions: Two lung-nodule CAD systems demonstrated decreased sensitivity on low-dose versus standard-dose pediatric CT scans performed in the same patients. The reduced detection at low dose was overall more pronounced for nodules measuring less than 5 mm. Clinical Impact: Caution is needed when using low-dose CT protocols in combination with CAD systems to help detect small lung nodules in pediatric patients.

7235 Papillary Thyroid Carcinoma in a Hyperfunctioning Thyroid Nodule

Abstract Disclosure: J. Yang: None. P.V. Nadkarni: None. Background: The prevalence of malignancy in a hyperfunctioning or hot thyroid nodule is considered to be low. According to the 2015 American Thyroid Association Guidelines, no cytologic evaluation is routinely recommended for hyperfunctioning nodules since they are rarely associated with malignancy (1). We present a case of a 71-year-old female with a hot nodule containing papillary thyroid cancer. Clinical Case: A 71-year-old female with Type 1 diabetes mellitus and coronary artery disease on dual antiplatelet therapy was found to have a 1.5 cm firm, non-tender right-sided thyroid nodule on a routine physical exam. Laboratory tests demonstrated low TSH &amp;lt;0.01 (normal 0.36 - 3.74 m[IU]/L) and FT4 level elevated at 1.62 (normal 0.76 -1.46 ng/dL). She noticed palpitations and started on low dose Methimazole. Thyroid ultrasound results showed a 2.1 x 2.0 x 2.0 cm right inferior lobe thyroid nodule. This thyroid nodule appeared mixed cystic and solid, hypoechoic, not taller than wide, with ill-defined margins and peripheral calcifications (ACR TI-RADS risk category: TR4). Nuclear medicine thyroid uptake scan demonstrated focally increased activity in the right lower pole corresponding with her right inferior thyroid nodule seen on ultrasound. Remainder of the gland appeared suppressed. She was recommended for ultrasound-guided fine needle aspiration biopsy of her right inferior thyroid nodule, given concerning characteristics on ultrasound findings despite results consistent with a hot nodule. Timing of her antiplatelet therapy was coordinated with her cardiologist, and her biopsy procedure scheduled after she stopped dual antiplatelet therapy. Her FNA results showed clusters of follicular cells with nuclear and architectural atypia, suspicious for papillary thyroid carcinoma. She underwent right thyroid lobectomy. Surgical pathology revealed 2 foci of papillary thyroid carcinoma, follicular variant (2.0 cm, 0.1 cm) and confined to the thyroid. All regional lymph nodes were negative for tumor. Methimazole was discontinued post-operatively, and she started Levothyroxine suppression therapy. Discussion: We present a rare association of papillary thyroid carcinoma presenting as a hot thyroid nodule. Though uncommon, detection of a hyperfunctioning thyroid nodule does not exclude the possibility of thyroid carcinoma and warrants careful evaluation. Clinicians should retain a high index of suspicion particularly when ultrasonography demonstrates findings suspicious for malignancy and consider additional evaluation with fine needle aspiration. Reference: (1) Haugen BR, Alexander EK, Bible KC et al. 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. Thyroid. 2016 Jan;26(1):1-133. Presentation: 6/2/2024

8414 Utilization of Cell Free DNA Integrity Index to Differentiate Benign from Malignant Thyroid Nodules

Abstract Disclosure: S. Tarafdar: None. S. Dutta: None. P. Mukhopadhyay: None. N.P. Bhattacharya: None. S. Ghosh: None. Introduction: Recent advances in molecular genetics have evaluated a potential role for plasma cell-free DNA (cfDNA) integrity index as a non-invasive cancer marker. Data on cfDNA integrity in differentiated thyroid cancer is sparse and needs to be investigated further. Aim of the study: The purpose of this study is to investigate the hypothesis that longer DNA strands in plasma may serve as a marker for thyroid cancer. Methods: Patients presenting with thyroid nodules underwent ultrasonography with Thyroid Image Reporting and Data Systems (TIRADS) scoring and FNAC (Bethesda classification).Patients with Bethesda 3, 4, 5, and 6 had surgery and confirmation by histopathology. Patients with Bethesda 2 presenting with compressive symptoms and cosmetic concerns underwent surgery; the remaining patients were considered benign based on clinical follow-up, USG, and FNAC characteristics. Blood sample collected prior to FNAC was used to extract and quantify cfDNA. To assess the integrity index 180/67, 306/67, and 476/67 for the APP gene, we used a quantitative real-time PCR (qPCR) method based on the quantification of four amplicons of varying lengths (67, 180, 306, and 476 bp, respectively). Because culture cells had extremely intact genomic DNA, the genomic DNA obtained from the MDA-T32 papillary thyroid cancer cell line was utilised as a reference to estimate the relative DNA strand integrity in plasma DNA. To determine the (ΔCt) value for 67,180, 306, and 476 bp, the Ct value of the sample was subtracted from that of the MDA-T32 control. Results: A total of 161 subjects were recruited, of these 92 were benign and 69 had differentiated thyroid cancer(confirmed by histopathology). Using the 180/67 bp integrity index benign thyroid nodule patients had significant lower value (median 0.39, 95% CI: 0.33-0.46) compared to patients with differentiated thyroid cancer (median 0.62, 95% CI: 0.56-0.68). A cfDNA integrity index of 180/67 bp could significantly differentiate between benign and malignant thyroid nodules (P&amp;lt;0.001). However, there was no significant difference between malignant and benign thyroid nodules based on the cell free DNA integrity indexes of 306/67 and 476/67. Conclusions: The cfDNA integrity score of 180/67 exhibits potential as a circulating marker for the detection of thyroid nodules and as a means of monitoring cfDNA fragmentation in patients with thyroid cancer. However, further confirmation through prospective trials is necessary. Presentation: 6/3/2024

8385 Coexistence of Parathyroid Adenoma &amp; Papillary Thyroid Cancer: A Rare Case Report

Abstract Disclosure: K. Dash: None. S. Verma: None. U. Ayyagari: None. M. Roy: None. S. Rathore: None. Prevalence of primary hyperparathyroidism (pHPT) ranges from 0.1- 0.4% in general population. Nodular thyroid disease is an increasingly common incidental diagnosis due to widespread use of ultrasound. Papillary thyroid cancer (PTC) is the most common cancer of thyroid gland. Here we report a 53 year old post-menopausal woman presented with weight loss, generalised body aches, arthralgia, myalgia, and proximal muscle weakness. She was hypertensive and clinically euthyroid. Physical examination revealed generalized tenderness all over the body but no thyroid or parathyroid nodules on palpation. Biochemical evaluation showed hypercalcemia 12.1mg/dl (8.4-10.2mg/dl), PTH&amp;gt;2000pg/ml (14-72pg/ml), ALP-1855 U/L (40–125 U/L), decreased phosphorous of 2.4mg/dl (25-4.6 mg/dl), and vitamin-D of 46 nmol/L ( 75-250 nmol/L). USG neck revealed a heterogeneous lesion at the lower pole of right lobe of thyroid gland &amp; two small hypoechoic nodules seen in the right lobe of thyroid gland. FNAC from nodules was inconclusive. USG abdomen revealed nephrocalcinosis. DEXA scan showed severe osteoporosis. Tc99mSestamibi SPECT-CT showed uptake at lower pole of right lobe of thyroid. On exploration, two nodules were palpated in the right lobe of the thyroid and simultaneous right hemi-thyroidectomy was performed. Histopathologic report confirmed parathyroid adenoma (figure 1) as well as presence of carcinoma in the two nodules: one was a papillary thyroid cancer (Classic variant) and the other a follicular variant of papillary thyroid carcinoma (figure 2). Margins were negative for malignancy. She was treated with levothyroxine to maintain TSH &amp;lt;0.1U/L and followed up with annual ultrasound screening. At 2 year follow up, patient was symptom free with improved T score on DEXA scan and no nodule over residual thyroid gland. Discussion: Co-existence of pHPT and PTC ranges from 2.3-4.3%. The use of ultrasound neck as a routine imaging modality for localisation of parathyroid adenoma allows detection of thyroid nodules. Benign and/or malignant thyroid nodules are commonly seen in patients with pHPT and this can range from 2-15%. Women have higher risk for co-existence. The relationship between the two diseases is thought to be incidental. Some authors have suggested possible role of shared genes, embryological factors, transcription factors, vitamin-D deficiency and hyperparathyroidism that could lead to activation of angiogenic factors and carcinogenesis. Fig. 1. Parathyroid adenoma. (a)Tc99m sestamibi scan showing right inferior parathyroid adenoma (b) Parathyroid adenoma (400x high power) comprising predominantly of Chief cells with mild pleomorphism. Fig. 2. Histopathology of PTC. (a)Papillary Carcinoma thyroid. 10xPhotomicrograph showing areas of calcification. (b) Papillary Carcinoma thyroid. Photomicrograph showing thyroid with papillary pattern with areas of infiltration. Presentation: 6/1/2024

7812 Community Practice Setting Experience in Evaluation of Incidental Thyroid Nodules

Abstract Disclosure: N. Abate: None. H. Rhodes: None. M. Horlavadi: None. B. Adams-Huet: None. M. Chandalia: Advisory Board Member; Self; Boehringer Ingelheim. Speaker; Self; Boehringer Ingelheim, Eli Lilly &amp; Company, Novo Nordisk. Background: There is a significant increase in detection of incidental thyroid nodules due to increase in routine screening ultrasounds at church, workplace, and health fairs, increase in routine ultrasound in primary care clinics and incidental finding of thyroid nodule during carotid artery ultrasound. These patients are then referred for thyroid nodule fine needle aspiration biopsy. Aim of this study was to evaluate real world data in frequency of thyroid cancer in patients referred for incidental thyroid nodule to a nonacademic Endocrinology clinic utilizing centralized collection of cytology and molecular analysis. Method: Medical records were reviewed for consecutive FNA of incidental thyroid nodule in an Endocrinology clinic in greater Houston from 2021 to 2023. FNA was performed in patients selected based on ACR TI-RADS classification. Patients with Bethesda score of 3 or more had molecular testing with Thyroseq performed. Patients with intermediate or high probability of cancer on Thyroseq as well as Patients with Bethesda 4 and 5 on cytopathology were referred for surgery. Surgical pathology was obtained in patients who underwent surgery. Data was tabulated and analyzed using SAS. Results: A total of 304 subjects, 267 Female and 37 males, age 57 ± 13, nodule size 2.69 ± 1.4 (mean ± SD), had thyroid nodule FNA between 2021 and 2023. Of these FNA, 23 (7.5%) sample collections were insufficient, 233 (77.3%) were benign (Bethesda 2), 46 (15%) were Atypia of undetermined significance or Suspicious for malignancy. Of those subjects with Bethesda 3 or higher, 36 patients had molecular testing by Thyroseq Method. Fifteen patients had intermediate and high risk finding on Thyroseq. Thirty-four subjects had surgery and 8 patients had malignancy on surgical pathology. One patient was identified as Medullary Thyroid cancer on Thyroseq, confirmed by surgery. Frequency of malignancy in incidentally detected thyroid nodule in the whole group was 2.6%, those with Bethesda 3 and more was 17.4% and those with Thyroseq intermediate or high risk was 27%. Conclusion: Availability of centralized cytopathology and reflex molecular testing to Community practice settings helps reducing unnecessary thyroid surgeries in patients with incidental thyroid nodules. Presentation: 6/1/2024

8414 Utilization Of Cell Free DNA Integrity Index To Differentiate Benign From Malignant Thyroid Nodules

Abstract Disclosure: S. Tarafdar: None. S. Dutta: None. P. Mukhopadhyay: None. N.P. Bhattacharya: None. S. Ghosh: None. Introduction: Recent advances in molecular genetics have evaluated a potential role for plasma cell-free DNA (cfDNA) integrity index as a non-invasive cancer marker. Data on cfDNA integrity in differentiated thyroid cancer is sparse and needs to be investigated further. Aim of the study: The purpose of this study is to investigate the hypothesis that longer DNA strands in plasma may serve as a marker for thyroid cancer. Methods: Patients presenting with thyroid nodules underwent ultrasonography with Thyroid Image Reporting and Data Systems (TIRADS) scoring and FNAC (Bethesda classification).Patients with Bethesda 3, 4, 5, and 6 had surgery and confirmation by histopathology. Patients with Bethesda 2 presenting with compressive symptoms and cosmetic concerns underwent surgery; the remaining patients were considered benign based on clinical follow-up, USG, and FNAC characteristics. Blood sample collected prior to FNAC was used to extract and quantify cfDNA. To assess the integrity index 180/67, 306/67, and 476/67 for the APP gene, we used a quantitative real-time PCR (qPCR) method based on the quantification of four amplicons of varying lengths (67, 180, 306, and 476 bp, respectively). Because culture cells had extremely intact genomic DNA, the genomic DNA obtained from the MDA-T32 papillary thyroid cancer cell line was utilised as a reference to estimate the relative DNA strand integrity in plasma DNA. To determine the (ΔCt) value for 67,180, 306, and 476 bp, the Ct value of the sample was subtracted from that of the MDA-T32 control. Results: A total of 161 subjects were recruited, of these 92 were benign and 69 had differentiated thyroid cancer(confirmed by histopathology). Using the 180/67 bp integrity index benign thyroid nodule patients had significant lower value (median 0.39, 95% CI: 0.33-0.46) compared to patients with differentiated thyroid cancer (median 0.62, 95% CI: 0.56-0.68). A cfDNA integrity index of 180/67 bp could significantly differentiate between benign and malignant thyroid nodules (P&amp;lt;0.001). However, there was no significant difference between malignant and benign thyroid nodules based on the cell free DNA integrity indexes of 306/67 and 476/67. Conclusions: The cfDNA integrity score of 180/67 exhibits potential as a circulating marker for the detection of thyroid nodules and as a means of monitoring cfDNA fragmentation in patients with thyroid cancer. However, further confirmation through prospective trials is necessary. Presentation: 6/3/2024

Deep Learning Enhanced CNN with Bio-Inspired Techniques and BCE For Effective Lung Nodules Detection &amp; Classification For Accurate Diagnosis

Objectives: To propose a new hybrid deep learning model to boost lung nodule detection and classification in combination with a bioinspired method for efficient hyper-parameter optimization to maximize true positive and nodule discrimination rates. Methods: In order to extract the intrinsic and complex features from different lung nodules, deep learning-based enhanced CNN (ECNN) is used. Segmentation masks are generated using Mask-RCNN to isolate and capture the ROIs, which serve as input to CNN. Prior to segmentation and extraction, data cleaning, transformation, and augmentation is done. Hyper-parameter optimization is done using a bio-inspired differential evolution method, which helps to identify the learning rate and number of layers to achieve optimal performance. We utilize BCE to quantify the performance of classification tasks. A large-scale CT-DICOM image dataset with 25,1135 images is used for this research work, collected from the cancer imaging archive, which has a clinically proven record of 355 instances with detailed image analysis, tumor location, and bounding boxes with a resolution of 512x512 pixels. 175794 images are used for training, and 75341 images are used for testing and validation. The performance of the new system is assessed using MATLAB, where results are compared with existing models such as SVM-WSS, GCPSO-PNN, and 3D-DLCNN models. Findings: The newly suggested ECNN with DE Bio-inspired model boosts the performance of lung nodule detection and classification with 94.7% accuracy, 93.8% sensitivity, 94.5% specificity, 93.4% F1 score, 92.4% dice coefficient, 0.1 Log Loss and AUC-ROC with 0.93 TPR and 0.07 FPR. Novelty: The novel method presents an advanced computational model using deep learning and bio-inspired algorithms for robust classification of lung nodules, which significantly improves the early diagnosis. This CAD model overcomes the limitations of the existing approaches SVM-WSS, GCPSO-PNN, and 3D-DLCNN in terms of segmentation, classification, error detection, and hyper-parameter tuning. Keywords: Lung Nodules, Deep Learning, Disease Classification, Image Processing, ECNN- DE Classifier, CT-DICOM Dataset