Nodule Margin Research Articles

Factors related to the absorption rate of benign thyroid nodules after image-guided microwave ablation: a 3-year follow-up

Purpose To assess the absorption rate and factors related to the development of benign thyroid nodules (BTNs) following image-guided microwave ablation (MWA). Materials and methods This retrospective study reviewed nodule efficacy in patients who underwent MWA of BTNs between January 2016 and January 2018. The endpoint was a third-year follow-up. Nodules were categorized into those showing complete absorption (volumes with less than 100% volume reduction ratio (VRR) and those showing partial absorption (100% VRR)). Univariable and multivariable regression analyses were carried out to identify variables that were associated with nodule absorption rates. Results A total of 173 BTNs (median volume= 4.23 ml; 25–75 percentiles= 2.27–9.00 ml) from 173 patients were evaluated. 49.7% (86/173) of patients had nodules that became completely absorbed. The mean VRRs of all BTNs were 18.0%, 78.7%, 89.0%, 94.5%, and 97.1% at the 1-, 6-,12-, 24- and 36- month follow-ups. At the 3-year follow-up time point, nodule characteristics related to nodule VRR included nodule volume (adjusted odds ratio [AOR], 1.1 [95% CI: 1.0, 1.2]; p = 0.03) and nodule margin (AOR, 5.3 [95% CI: 1.8, 16.0]; p < 0.01). Treatment-related characteristics included energy per ml in nodular volume (AOR, 1.0 [95% CI: 1.0, 1.0]; p < 0.01) and blockage of peripheral flow (AOR, 3.3 [95% CI: 1.3 8.3]; p = 0.01). Conclusions US-guided image-guided MWA results in satisfactory long-term outcomes for the patients with BTNs. Factors related to nodule absorption rate were the volume and margin of the nodule, energy per ml in nodular volume and blockage of peripheral flow.

Lung nodule malignancy classification with weakly supervised explanation generation.

Purpose: Explainable AI aims to build systems that not only give high performance but also are able to provide insights that drive the decision making. However, deriving this explanation is often dependent on fully annotated (class label and local annotation) data, which are not readily available in the medical domain. Approach: This paper addresses the above-mentioned aspects and presents an innovative approach to classifying a lung nodule in a CT volume as malignant or benign, and generating a morphologically meaningful explanation for the decision in the form of attributes such as nodule margin, sphericity, and spiculation. A deep learning architecture that is trained using a multi-phase training regime is proposed. The nodule class label (benign/malignant) is learned with full supervision and is guided by semantic attributes that are learned in a weakly supervised manner. Results: Results of an extensive evaluation of the proposed system on the LIDC-IDRI dataset show good performance compared with state-of-the-art, fully supervised methods. The proposed model is able to label nodules (after full supervision) with an accuracy of 89.1% and an area under curve of 0.91 and to provide eight attributes scores as an explanation, which is learned from a much smaller training set. The proposed system's potential to be integrated with a sub-optimal nodule detection system was also tested, and our system handled 95% of false positive or random regions in the input well by labeling them as benign, which underscores its robustness. Conclusions: The proposed approach offers a way to address computer-aided diagnosis system design under the constraint of sparse availability of fully annotated images.

Assessment of Nerve Fiber Density and Expression of Hormonal Receptors Within Rectosigmoid Endometriosis Nodules

To assess nerve fiber density and expression of hormone receptors in bowel endometriosis. Cross-sectional study. Private hospital. Women with endometriosis undergoing laparoscopic segmental bowel resection (n=54). Tissue samples were obtained from patients with surgically treated rectosigmoid endometriosis. The rectosigmoid specimen containing the endometriosis nodule was manually sectioned and divided into 3 areas: core of the nodule, margin of the nodule, and healthy bowel tissue. The intensity of expression of estrogen and progesterone receptors was evaluated by immunohistochemistry and measured according to the Allred score. Nerve fibers were stained by immunohistochemistry using Protein Gene Product 9.5, and the density of nerve fillets was counted and expressed in number/mm². All glandular and stromal cells stained for estrogen; however, glandular cells stained more strongly than stromal cells (61.1% vs 35.2%; p=.01). Most of glandular and stromal cells stained strongly for progesterone receptors (90.7% vs 98.1%; p=.2). The density of nerve fibers was very high in the margin of the nodule (172.22±45.66/mm²), moderate in healthy bowel tissue (111.48±48.57/mm²), and very low in the core of the nodule (7.31±4.9/mm²); p=.01. Both glandular and stromal cells within the rectosigmoid endometriosis nodule express estrogen and progesterone receptors. Higher intensity of expression of estrogen receptors occurs in glandular cells. The density of nerve fibers is extremely high at the nodule margin and very low in the center of the nodule.

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

BackgroundReidentification of prior nodules for temporal comparison is an important but time-consuming step in lung cancer screening. We develop and evaluate an automated nodule detector that utilizes the axial-slice number of nodules found in radiology reports to generate high precision nodule predictions.Methods888 CTs from Lung Nodule Analysis were used to train a 2-dimensional (2D) object detection neural network. A pipeline of 2D object detection, 3D unsupervised clustering, false positive reduction, and axial-slice numbers were used to generate nodule candidates. 47 CTs from the National Lung Cancer Screening Trial (NLST) were used for model evaluation.ResultsOur nodule detector achieved a precision of 0.962 at a recall of 0.573 on the NLST test set for any nodule. When adjusting for unintended nodule predictions, we achieved a precision of 0.931 at a recall 0.561, which corresponds to 0.06 false positives per CT. Error analysis revealed better detection of nodules with soft tissue attenuation compared to ground glass and undeterminable attenuation. Nodule margins, size, location, and patient demographics did not differ between correct and incorrect predictions.ConclusionsUtilization of axial-slice numbers from radiology reports allowed for development of a lung nodule detector with a low false positive rate compared to prior feature-engineering and machine learning approaches. This high precision nodule detector can reduce time spent on reidentification of prior nodules during lung cancer screening and can rapidly develop new institutional datasets to explore novel applications of computer vision in lung cancer imaging.

TO EVALUATE ROLE OF MORPHOLOGICAL CRITERIA ON USG AND ELASTOGRAPHY IN DIFFERENTIATING BENIGN AND MALIGNANT THYROID LESION

Introduction: Thyroid nodules are common and are commonly benign. The reported prevalence of nodular thyroid disease depends on the population studied and the methods used to detect nodules. Numerous studies suggest a prevalence of 2-6% with palpation, 19-35% with ultrasound, and 8-65% in autopsy data. Aims and objectives: To evaluate diagnostic reliability of ultrasound morphological criteria (ACR-TIRADS system) and elastographyin differentiating benign from malignant thyroid nodules in patients using cytopathology or histopathology as gold standard. Materials and methods: Prospective observational study, Patients visiting LLR (Hallet) Hospital with clinically suspicious thyroid nodule, LLR (Hallet) Hospital, GSVM Medical College, Jan 2019 to Oct 2020. Result: Showing distribution of composition of nodules in our study subjects Maximum nodules have mixed solid cystic composition . Showing distribution of echogenicity of nodules in our study subjects. Maximum nodules in our study have to hyperechoic echogenicity. Showing distribution of margin of nodules in our study subjects. Maximum nodules in our study have ill dened margin. Conclusion: In conclusion, no single investigation was found to be 100% sensitive or specic in diagnosing malignancy in nodular goiter but a good clinical, FNAC and USG examinations are complimentary to each other in predicting malignancy and avoid unnecessary or inadequate surgery.

Inter-Reader Variability of Volumetric Subsolid Pulmonary Nodule Radiomic Features

To evaluate the inter-observer consistency for subsolid pulmonary nodule radiomic features. Subsolid nodules were selected by reviewing radiology reports of CT examinations performed December 1, 2015 to April 1, 2016. Patients with CTs at two time points were included in this study. There were 55 patients with subsolid nodules, of whom 14 had two nodules. Of 69 subsolid nodules, 66 were persistent at the second time point, yielding 135 lesions for segmentation. Two thoracic radiologists and an imaging fellow segmented the lesions using a semi-automated volumetry algorithm (Syngo.via Vb20, Siemens). Coefficient of variation (CV) was used to assess consistency of 91 quantitative measures extracted from the subsolid nodule segmentations, including first and higher order texture features. The accuracy of segmentation was visually graded by an experienced thoracic radiologist. Influencing factors on radiomic feature consistency and segmentation accuracy were assessed using generalized estimating equation analyses and the Exact Mann-Whitney test. Mean patient age was 71 (38-93 years), with 39 women and 16 men. Mean nodule volume was 1.39mL, range .03-48.2mL, for 135 nodules. Several radiomic features showed high inter-reader consistency (CV<5%), including entropy, uniformity, sphericity, and spherical disproportion. Descriptors such as surface area and energy had low consistency across inter-reader segmentations (CV>10%). Nodule percent solid component and attenuation influenced inter-reader variability of some radiomic features. The presence of contrast did not significantly affect the consistency of subsolid nodule radiomic features. Near perfect segmentation, within 5% of actual nodule size, was achieved in 68% of segmentations, and very good segmentation, within 25% of actual nodule size, in 94%. Morphologic features including nodule margin and shape (each p <0.01), and presence of air bronchograms (p = 0.004), bubble lucencies (p = 0.02) and broad pleural contact (p < 0.01) significantly affected the probability of near perfect segmentation. Stroke angle (p = 0.001) and length (p < 0.001) also significantly influenced probability of near perfect segmentation. The inter-observer consistency of radiomic features for subsolid pulmonary nodules varies, with high consistency for several features, including sphericity, spherical disproportion, and first and higher order entropy, and normalized non-uniformity. Nodule morphology influences the consistency of subsolid nodule radiomic features, and the accuracy of subsolid nodule segmentation.

3-D Ultrasound and Thyroid Cancer Diagnosis: A Prospective Study

This study tests the hypothesis that evaluation of thyroid nodule (TN) margin irregularities by three-dimensional ultrasound (3-D-US) distinguishes benign from malignant TNs with greater sensitivity and specificity than two-dimensional ultrasound (2-D-US). We prospectively evaluated 344 TNs using both 2-D-US and 3-D-US followed by fine needle aspiration biopsy. TNs were divided into four groups based on the 3-D-US appearance of the margins. Bi-variate and multi-variate analyses were used. Surgical pathology confirmed 44 thyroid cancers in 40 patients. For 2-D-US, irregular margins and micro-calcifications (p < 0.001) were found more frequently in malignant TNs. Irregular margins on 2-D-US had a sensitivity and specificity of 61.4% and 79.3%, respectively. Irregular margins on 3-D-US had a sensitivity and specificity of 86.4% and 83.3%, respectively. Sensitivity, specificity, positive and negative predictive values were higher for irregular margins on 3-D-US than micro-calcifications and irregular margins on 2-D-US. Evaluation of TN margins by 3-D-US distinguished benign from malignant TNs with greater sensitivity and specificity than 2-D-US.

Multi-Crop Convolutional Neural Networks for Fast Lung Nodule Segmentation

Computed tomography (CT) images are formally taken as an assistance of early diagnosis in lung nodule analysis. Thus the accurate lung nodule segmentation is in great need for image-driven tasks. However, as heterogeneity exists between different types of lung nodules, the similar visual appearance between the pixels of nodules and pixels of non-nodule area make it difficult for automatic lung nodule segmentation. In this article, we propose a fast end-to-end framework, called Fast Multi-crop Guided Attention (FMGA) network, to accurately segment lung nodules in CT images. Our method utilizes multi-crop nodule slices as input to aggregate contextual information (2D context from current image slice and 3D context from adjacent axial slices), and exploits a global convolutional layer for nodule pixel embedding matching. To further make use of the information from border pixels near the nodule margin for better segmentation, we develop a weighted loss function to facilitate the model training by considering a balanced class samples of pixels around the nodule margin. Moreover, we utilize a central pooling layer to facilitate the contexts feature propagation in pixel neighbors. We evaluate our method on the largest public lung CT dataset LIDC and the collected lung CT data from Wuhan local hospital, respectively. Experimental results show that FMGA achieves superior performance among the state-of-the-arts. In addition, we give an ablation study and visualization results to illustrate how each component works for accurate lung nodule segmentation.

Thermal Treatment Options for Benign Thyroid Nodules—The Role of Radio-Frequency Ablation and Laser Therapy

Thermal Treatment Options for Benign Thyroid Nodules—The Role of Radio-Frequency Ablation and Laser Therapy

Visual Interpretability in Computer-Assisted Diagnosis of Thyroid Nodules Using Ultrasound Images.

BackgroundThe number of studies on deep learning in artificial intelligence (AI)-assisted diagnosis of thyroid nodules is increasing. However, it is difficult to explain what the models actually learn in artificial intelligence-assisted medical research. Our aim is to investigate the visual interpretability of the computer-assisted diagnosis of malignant and benign thyroid nodules using ultrasound images.Material/MethodsWe designed and implemented 2 experiments to test whether our proposed model learned to interpret the ultrasound features used by ultrasound experts to diagnose thyroid nodules. First, in an anteroposterior/transverse (A/T) ratio experiment, multiple models were trained by changing the A/T ratio of the original nodules, and their classification, accuracy, sensitivity, and specificity were tested. Second, in a visualization experiment, class activation mapping used global average pooling and a fully connected layer to visualize the neural network to show the most important features. We also examined the importance of data preprocessing.ResultsThe A/T ratio experiment showed that after changing the A/T ratio of the nodules, the accuracy of the neural network model was reduced by 9.24–30.45%, indicating that our neural network model learned the A/T ratio information of the nodules. The visual experiment results showed that the nodule margins had a strong influence on the prediction of the neural network.ConclusionsThis study was an active exploration of interpretability in the deep learning classification of thyroid nodules. It demonstrated the neural network-visualized model focused on irregular nodule margins and the A/T ratio to classify thyroid nodules.

Roles of contrast-enhanced ultrasonography in identifying volume change of benign thyroid nodule and optical time of secondary radiofrequency ablation

BackgroundUltrasonography-guided radiofrequency ablation (RFA) was was proved to be an effective and safe treatment with few complications for benign thyroid nodule. In cases of incompletely treated nodule margin, secondary RFAs are necessary. The present study was designed to analyze the dynamic change of nodular volume of benign thyroid tumors accessed using contrast-enhanced ultrasonography (CEUS) after RFA, and hopefully to offer evidence for time decision of secondary RFA.MethodsA total of 105 patients who received ultrasonography-guided RFA in the Department of Ultrasound, Chinese PLA General Hospital between April 2014 and August 2018 for benign thyroid nodule were enrolled in this retrospective study. Vt increase (regrowth) and vital volume (Vv) of thyroid nodule were followed up at 0, 1, 3, 6, 12, 24 and 36 months after RFA.ResultsA total of 105 nodules of 105 patients were enrolled in the present study, with a mean age of 46.70 ± 13.05 years, and 87 of them (82.9%) were female. The median follow up time was 25.1 months (12 months to 36 months). During the follow up, regrowth occurred in 43 cases, 95.35% of nodular regrowth occurred in 12 months after RFA, and the rate showed substantial consistency with that on the 36th month postoperatively (Kappa = 0.656).ConclusionsCEUS was an effective and safe tool to monitor volume change of benign thyroid nodules after RFA. The majority cases of regrowth occurred in 12 months after RFA, thus, the 12th month after RFA might be the optimal time for volume assessment to make the decision of secondary RFAs.

MON-460 An Extremely Rare Case of Urothelial Carcinoma Metastasizing to the Thyroid Gland

BACKGROUND Metastasis of primary malignancies to the thyroid gland is uncommon, with an overall incidence of 2%. The most common malignancy to metastasize to the thyroid is lung neoplasm (22%) as reported in an autopsy series and renal cell carcinoma (25%) in a clinical series. CLINICAL CASE A 78 year-old-white male was found to have a thyroid nodule on CT neck performed for surveillance of urothelial carcinoma diagnosed 3 years prior. On retrospective review of CT chest from the previous year, the thyroid nodule had increased in size but didn’t meet criteria for FNAC. Neck/Thyroid US demonstrated a right lobe solid hypoechoic nodule measuring 1.1 x 0.7 x 1.1 cm (longitudinal x anterior-posterior, lateral respectively). Nodule margin was well defined, with no internal vascularity, microcalcifications or abnormal cervical lymph nodes. Seven months later, US reported the nodule to have increased in size to 2.1 x 2.1 x 4.7 cm at which point FNAC was performed. Cytology revealed malignant cells compatible with metastasis from the urothelial carcinoma. Three years prior, his high-grade papillary urothelial carcinoma with extensive infiltration into the muscularis propria had been treated with a partial cystectomy and radiation therapy. Surgical margins and all tested lymph nodes had been negative for neoplasm. The patient underwent right thyroid lobectomy and pathology confirmed high-grade malignant neoplasm consistent with metastatic tumor from the patient’s known urothelial carcinoma. CONCLUSION We present a rare case of urothelial carcinoma with metastasis to the thyroid gland. While evaluating thyroid nodules in patients with other known malignancies, clinicians should have a lower threshold for FNAC. This will assist with earlier diagnosis of potential metastatic disease and improve clinical outcomes.

Predictive model for the diagnosis of benign/malignant small pulmonary nodules.

There is some doubt that all nodules <8 mm are really mainly benign and that simple follow-up is adequate in all cases. The purpose of this study is to create a predictive model for the diagnosis of benign and malignant small pulmonary nodules.This was a retrospective case–control study of patients who had undergone pulmonary nodule resection at the Zhejiang University Jinhua Hospital. Patients with pulmonary nodules of ≤10 mm in size on chest high-resolution computed tomography were included. Patients’ demographic characteristics, clinical features, and high-resolution computed tomography findings were collected. Logistic regression and receiver-operating characteristic analysis were used to create a predictive model for malignancy.A total of 216 patients were included: 160 with malignant and 56 with benign nodules. Nodule density (odds ratio [OR] = 0.996, 95% confidence interval [CI]: 0.993–0.998, P = .001), vascular penetration sign (OR = 3.49, 95% CI: 1.39–8.76, P = .008), nodule type (OR = 4.27, 95% CI: 1.48–12.29, P = .007), and incisure surrounding nodules (OR = 0.18, 95% CI: 0.04–0.84, P = .03) were independently associated with malignant nodules. These factors were used to create a mathematical model that had an area under the receiver-operating characteristic curve of 0.744. Using a cut-off of 0.762 resulted in 63.1% sensitivity and 75.0% specificity.This study proposes a pulmonary nodule prediction model that can estimate benign/malignant lung nodules with good sensitivity and specificity. Mixed ground-glass nodules, vascular penetration sign, density of lung nodules, and the absence of incisure signs are independently associated with malignant lung nodules.

MR findings for differentiating decidualized endometriomas from seromucinous borderline tumors of the ovary.

Decidualized endometriomas (DEs) and seromucinous borderline tumors (SMBTs) exhibit similar MR findings including markedly hyperintense mural nodules within endometriotic cysts on T2-weighted images. The present study aimed to assess the efficacy of MR imaging for differentiating between DEs and SMBTs of the ovary. MR images of 8 DEs and 14 SMBTs were retrospectively assessed and compared according to pathologies. With regard to quantitative assessments of mural nodules, the number and signal intensity ratios (SIRs) on T1-weighted images were significantly greater in DEs than in SMBTs (11.0 ± 8.4 vs. 4.3 ± 4.1, p < 0.05 and 2.36 ± 0.56 vs. 1.49 ± 0.27, p < 0.01, respectively), whereas the height was significantly lower in DEs than in SMBTs (4.5 ± 1.4mm vs. 21.9 ± 11.4mm, p < 0.01). However, there were no significant differences between DEs and SMBTs in the SIRs on T2-weighted images, SIRs on diffusion-weighted images, and apparent diffusion coefficient values. With regard to qualitative assessments of mural nodules, the lobulated margin, pedunculated configuration, and T2 hypointense core were significantly more frequent in SMBTs than in DEs (71% vs. 0%, p < 0.01; 86% vs. 0%, p < 0.01; and 43% vs. 0%, p < 0.05, respectively). The number, height, SIRs on T1-weighted images, lobulated margin, pedunculated configuration, and T2 hypointense core of mural nodules within endometriotic cysts were useful MR findings for differentiating DEs from SMBTs.

Diagnostic accuracy of ultrasonography in classifying thyroid nodules compared with fine-needle aspiration

Background:Classifying thyroid lesions is challenging; nonetheless, using ultrasonography may allow for accurate diagnosis, differentiation and management of thyroid lesions and help avoid unnecessary biopsy.Objectives:The main objective of the study is to determine the diagnostic accuracy of ultrasonography in classifying thyroid nodules compared with fine-needle aspiration.Materials and Methods:This retrospective study included all 68 patients diagnosed with thyroid nodules at King Fahd Hospital of the University, Al Khobar, Saudi Arabia, between June 1, 2014, and November 30, 2016. Parameters were selected based on the Society of Radiologists in Ultrasound criteria. Ultrasonographic features, namely, nodule margins, echotexture, vascularity and calcifications, and fine-needle aspiration cytology (FNAC) results were reviewed by two radiologists blinded to each other's findings and validated by another experienced interventional radiologist. Ultrasonography results were compared against that of FNAC to calculate sensitivity and positive- and negative-likelihood ratios, and the nodule types were compared using Fisher's exact test.Results:Of the 68 nodules analyzed, 59 were reported as benign using FNAC (specificity = 95%; P < 0.001). Of these 59, 56 were also reported as benign using ultrasonography. The specificity of ultrasonography in determining benign nodules was 94.9%, and the positive- and negative-likelihood ratios were 13.0 and 0.35, respectively. Six of the nine suspicious nodules were confirmed as malignant using FNAC, and the ultrasonography and FNAC findings were strongly associated (P = 0.001). According to the Society of Radiologists in Ultrasound criteria, FNAC and ultrasonography findings were significantly associated for nodule calcification (P = 0.001) and echogenicity (P = 0.001).Conclusion:The diagnostic specificity of ultrasonography and FNAC in this study are consistent with those reported previously, indicating that ultrasonography reliably classifies thyroid nodules, and thus can assist in the decision-making regarding need for biopsy.

Shape and margin-aware lung nodule classification in low-dose CT images via soft activation mapping.

A number of studies on lung nodule classification lack clinical/biological interpretations of the features extracted by convolutional neural network (CNN). The methods like class activation mapping (CAM) and gradient-based CAM (Grad-CAM) are tailored for interpreting localization and classification tasks while they ignored fine-grained features. Therefore, CAM and Grad-CAM cannot provide optimal interpretation for lung nodule categorization task in low-dose CT images, in that fine-grained pathological clues like discrete and irregular shape and margins of nodules are capable of enhancing sensitivity and specificity of nodule classification with regards to CNN. In this paper, we first develop a soft activation mapping (SAM) to enable fine-grained lung nodule shape & margin (LNSM) feature analysis with a CNN so that it can access rich discrete features. Secondly, by combining high-level convolutional features with SAM, we further propose a high-level feature enhancement scheme (HESAM) to localize LNSM features. Experiments on the LIDC-IDRI dataset indicate that 1) SAM captures more fine-grained and discrete attention regions than existing methods, 2) HESAM localizes more accurately on LNSM features and obtains the state-of-the-art predictive performance, reducing the false positive rate, and 3) we design and conduct a visually matching experiment which incorporates radiologists study to increase the confidence level of applying our method to clinical diagnosis.

Unboxing AI - Radiological Insights Into a Deep Neural Network for Lung Nodule Characterization

To explain predictions of a deep residual convolutional network for characterization of lung nodule by analyzing heat maps. A 20-layer deep residual CNN was trained on 1245 Chest CTs from National Lung Screening Trial (NLST) trial to predict the malignancy risk of a nodule. We used occlusion to systematically block regions of a nodule and map drops in malignancy risk score to generate clinical attribution heatmaps on 103 nodules from Lung Image Database Consortium image collection and Image Database Resource Initiative (LIDC-IDRI) dataset, which were analyzed by a thoracic radiologist. The features were described as heat inside nodule -bright areas inside nodule, peripheral heat continuous/interrupted bright areas along nodule contours, heat in adjacent plane -brightness in scan planes juxtaposed with the nodule, satellite heat - a smaller bright spot in proximity to nodule in the same scan plane, heat map larger than nodule bright areas corresponding to the shape of the nodule seen outside the nodule margins and heat in calcification. These six features were assigned binary values. This feature vector was fedinto a standard J48 decision tree with 10-fold cross-validation, which gave an 85 % weighted classification accuracy with a 77.8% True Positive (TP) rate, 8% False Positive (FP) rate for benign cases and 91.8% TP and 22.2% FP rates for malignant cases. Heat Inside nodule was more frequently observed in nodules classified as malignant whereas peripheral heat, heat in adjacent plane, and satellite heat were more commonly seen in nodules classified as benign. We discuss the potential ability of a radiologist to visually parse the deep learning algorithm generated "heat map" to identify features aiding classification.

Differentiating minimally invasive and invasive adenocarcinomas in patients with solitary sub-solid pulmonary nodules with a radiomics nomogram

To evaluate the preoperative differentiation between the minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) in patients with sub-solid pulmonary nodules using a radiomics nomogram. A total of 100 patients with sub-solid pulmonary nodules who had pathologically confirmed MIA (43 patients, 13 male and 30 female) or IAC (57 patients, 26 male and 31 female) were recruited retrospectively. Radiomics features were extracted from computed tomography (CT) images. A radiomics signature was constructed by the least absolute shrinkage and selection operator (LASSO) algorithm. Solid presence, lesion size, shape regularity, and margins of pulmonary nodules were assessed to construct a subjective finding model. An integrated model of radiomics signatures and CT-based subjective findings, which was presented as a radiomics nomogram, was developed based on a multivariate logistic regression. The nomogram performance was assessed by its calibration, discrimination, and clinical usefulness. The radiomics signature, which consisted of 11 radiomics features, showed good discrimination accuracy. The radiomics nomogram showed good calibration and discrimination in the training set (AUC [area under the curve] 0.943; 95% confidence interval [CI]: 0.895-0.991) and validation set (AUC 0.912; 95% CI: 0.780-1.000). The radiomics nomogram was determined to be clinically useful in the decision curve analysis (DCA). The proposed radiomics nomogram has the potential to preoperatively differentiate MIA and IAC in patients with sub-solid pulmonary nodules.

Integration of Sonoelastography Into the TIRADS Lexicon Could Influence the Classification.

Aim: Numerous TIRADS (Thyroid Image Reporting and Data System) classifications have been developed, and various ultrasound (US) parameters are employed in different countries. The aim of our study was to introduce risk classification and management in a native population based on the Guidelines of Polish National Societies Diagnostics and Treatment of Thyroid Carcinoma but with the addition of sonoelastography.Materials and Methods: We examined prospectively 208 patients with 305 thyroid lesions employing B-mode ultrasound and sonoelastography (SE). Nodule composition, echogenicity, margins, shape, presence or absence of calcifications, thyroid capsule, nodule size were assessed using B-mode ultrasound. Moreover, sonoelastography results were presented using the Asteria scale.Results: In univariate analysis, the following US features were significantly associated with malignancy: >50% solid /solid component, marked hypoechogenicity, ill-defined margins, micro and macrocalcification, taller-than wide shape, no/partial halo pattern, infiltration of the capsule and an Asteria score of 4. Multivariate logistic regression analysis of B-mode features revealed that ill-defined margins (OR 10.77), markedly hypoechogenicity (OR 5.12), microcalcifications (OR 4.85), thyroid capsule infiltrations (OR 3.2), macrocalcifications (OR 3.01), and hard lesion in SE (OR 6.85) were associated with a higher Odds Ratio (OR) for malignancy. Multivariate logistic regression analysis revealed that combining two features increases the OR and the best combination was irregular margins and Asteria scale 4 (OR 20.21). Adding a third feature did not increase the OR.Conclusions: Sonoelastography increases the value risk of predicted malignancy, with consequent different approach to further clinical investigation and management. A solitary feature (Asteria 4) in a solid tumor can result in its categorization as TIRADS 4, but coexistence with high risk features allows it to be upgraded to TIRADS 5. The irregular margin was the strongest single feature which allowed for the assignment of a solid tumor into TIRADS 5 category. The highest accuracy was found by combining the features of age, margin, echogenicity (markedly hypoechoic), capsule infiltration, microcalcifications and sonoelastography (Asteria 3,4) of the tumors.

Radiofrequency ablation of thyroid nodules

The treatment goals of Image-guided intervention for thyroid nodule are the relief of symptoms by reducing the nodule volume and the maintaining of symptom free status without regrowth of treated lesion. Thus, it is basically not indicated for the nodules which are not related to the patient's discomfort even they are large. And up to now, except for few limited cases impossible to get surgery, the applications for the malignant disease and follicular neoplasm have not been established firmly. For this reason, preoperative cytopathologic and ultrasonographic evaluations are important to confirm that the target lesion is benign. Thermal ablation is one category of it and consists of radiofrequency ablation (RFA), laser ablation, microwave ablation and high-intensity-focus-ultrasound. RFA for benign thyroid nodules have been reported to have a high efficacy with a low complication rate. Its efficacy is generally evaluated by volume reduction rate. Reported short-term results are 50-80% volume reduction at 6 months, 79-90% at 2 years, and 93% at 4 years. Recurrence rates after the procedure have been reported 5.6%. All recurrent cases showed regrowth of the incompletely treated nodule margin. For this reason, it is recommended to ablate the nodule completely to minimize recurrence. The multiple sessions are needed to get the well-ablated nodule without damaging the adjacent tissues. In this presentation, we can discuss how to make a plan before and after thyroid RFA to reach more successful treatment goal, minimizing the recurrence and the complications.