Dataset Information

Application of machine learning to ultrasound images to differentiate follicular neoplasms of the thyroid gland.

ABSTRACT: PURPOSE:This study was conducted to evaluate the diagnostic performance of machine learning in differentiating follicular adenoma from carcinoma using preoperative ultrasonography (US). METHODS:In this retrospective study, preoperative US images of 348 nodules from 340 patients were collected from two tertiary referral hospitals. Two experienced radiologists independently reviewed each image and categorized the nodules according to the 2015 American Thyroid Association guideline. Categorization of a nodule as highly suspicious was considered a positive diagnosis for malignancy. The nodules were manually segmented, and 96 radiomic features were extracted from each region of interest. Ten significant features were selected and used as final input variables in our in-house developed classifier models based on an artificial neural network (ANN) and support vector machine (SVM). The diagnostic performance of radiologists and both classifier models was calculated and compared. RESULTS:In total, 252 nodules from 245 patients were confirmed as follicular adenoma and 96 nodules from 95 patients were diagnosed as follicular carcinoma. As measures of diagnostic performance, the average sensitivity, specificity, and accuracy of the two experienced radiologists in discriminating follicular adenoma from carcinoma on preoperative US images were 24.0%, 84.0%, and 64.8%, respectively. The sensitivity, specificity, and accuracy of the ANN and SVM-based models were 32.3%, 90.1%, and 74.1% and 41.7%, 79.4%, and 69.0%, respectively. The kappa value of the two radiologists was 0.076, corresponding to slight agreement. CONCLUSION:Machine learning-based classifier models may aid in discriminating follicular adenoma from carcinoma using preoperative US.

SUBMITTER: Shin I

PROVIDER: S-EPMC7315296 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Application of machine learning to ultrasound images to differentiate follicular neoplasms of the thyroid gland.

Shin Ilah I Kim Young Jae YJ Han Kyunghwa K Lee Eunjung E Kim Hye Jung HJ Shin Jung Hee JH Moon Hee Jung HJ Youk Ji Hyun JH Kim Kwang Gi KG Kwak Jin Young JY

Ultrasonography (Seoul, Korea) 20200229 3

<h4>Purpose</h4>This study was conducted to evaluate the diagnostic performance of machine learning in differentiating follicular adenoma from carcinoma using preoperative ultrasonography (US).<h4>Methods</h4>In this retrospective study, preoperative US images of 348 nodules from 340 patients were collected from two tertiary referral hospitals. Two experienced radiologists independently reviewed each image and categorized the nodules according to the 2015 American Thyroid Association guideline. ...[more]

PMID: 32299197

Similar Datasets

Project description:ObjectivesTo investigate the ability of the currently used ultrasound-based malignancy risk stratification systems for thyroid neoplasms (ATA, AACE/ACE/AME, K-TIRADS, EU-TIRADS, ACR-TIRADS and C-TIRADS) in distinguishing follicular thyroid carcinoma (FTC) from follicular thyroid adenoma (FTA). Additionally, we evaluated the ability of these systems in correctly determining the indication for biopsy.MethodsThree hundred twenty-nine follicular neoplasms with definitive postoperative histopathology were included. The nodules were categorized according to each of six stratification systems, based on ultrasound findings. We dichotomized nodules into the positive predictive group of FTC (high and intermediate risk) and negative group of FTC based on the classification results. Missed biopsy was defined as neoplasms that were diagnosed as FTCs but for which biopsy was not indicated based on lesion classification. Unnecessary biopsy was defined as neoplasms that were diagnosed as FTAs but for whom biopsy was considered indicated based on classification. The diagnostic performance and missed and unnecessary biopsy rates were evaluated for each stratification system.ResultsThe area under the curve of each system for distinguishing follicular neoplasms was < 0.700 (range, 0.511-0.611). The missed biopsy rates were 9.0-22.4%. The missed biopsy rates for lesions ≤ 4 cm and lesions sized 2-4 cm were 16.2-35.1% and 0-20.0%, respectively. Unnecessary biopsy rates were 65.3-93.1%. In ≤ 4 cm group, the unnecessary biopsy rates were 62.2-89.7%.ConclusionThe malignancy risk stratification systems can select appropriate nodules for biopsy in follicular neoplasms, while they have limitations in distinguishing follicular neoplasms and reducing unnecessary biopsy. Specific stratification systems and recommendations should be established for follicular neoplasms.Key points• Current ultrasound-based malignancy risk stratification systems of thyroid nodules had low efficiency in the characterization of follicular neoplasms. • The adopted stratification systems showed acceptable performance for selecting FTC for biopsy but unsatisfactory performance for reducing unnecessary biopsy.

Project description:Noninvasive follicular thyroid neoplasms with papillary-like nuclear features (NIFTP) are follicular-patterned thyroid neoplasms defined by nuclear atypia and indolent behavior. They harbor RAS mutations, rather than BRAFV600E mutations as is observed in papillary thyroid carcinomas with extensive follicular growth. Reliably identifying NIFTPs aids in safe therapy de-escalation, but has proven to be challenging due to interobserver variability and morphologic heterogeneity. The genomic scoring system BRS (BRAF-RAS score) was developed to quantify the extent to which a tumor's expression profile resembles a BRAFV600E or RAS-mutant neoplasm. We proposed that deep learning prediction of BRS could differentiate NIFTP from other follicular-patterned neoplasms. A deep learning model was trained on slides from a dataset of 115 thyroid neoplasms to predict tumor subtype (NIFTP, PTC-EFG, or classic PTC), and was used to generate predictions for 497 thyroid neoplasms within The Cancer Genome Atlas (TCGA). Within follicular-patterned neoplasms, tumors with positive BRS (RAS-like) were 8.5 times as likely to carry an NIFTP prediction than tumors with negative BRS (89.7% vs 10.5%, P < 0.0001). To test the hypothesis that BRS may serve as a surrogate for biological processes that determine tumor subtype, a separate model was trained on TCGA slides to predict BRS as a linear outcome. This model performed well in cross-validation on the training set (R2 = 0.67, dichotomized AUC = 0.94). In our internal cohort, NIFTPs were near universally predicted to have RAS-like BRS; as a sole discriminator of NIFTP status, predicted BRS performed with an AUC of 0.99 globally and 0.97 when restricted to follicular-patterned neoplasms. BRAFV600E-mutant PTC-EFG had BRAFV600E-like predicted BRS (mean -0.49), nonmutant PTC-EFG had more intermediate predicted BRS (mean -0.17), and NIFTP had RAS-like BRS (mean 0.35; P < 0.0001). In summary, histologic features associated with the BRAF-RAS gene expression spectrum are detectable by deep learning and can aid in distinguishing indolent NIFTP from PTCs.

Project description:Background and objectiveDynamic muscle fascicle length measurements through B-mode ultrasound have become popular for the non-invasive physiological insights they provide regarding musculoskeletal structure-function. However, current practices typically require time consuming post-processing to track muscle length changes from B-mode images. A real-time measurement tool would not only save processing time but would also help pave the way toward closed-loop applications based on feedback signals driven by in vivo muscle length change patterns. In this paper, we benchmark an approach that combines traditional machine learning (ML) models with B-mode ultrasound recordings to obtain muscle fascicle length changes in real-time. To gauge the utility of this framework for 'in-the-loop' applications, we evaluate accuracy of the extracted muscle length change signals against time-series' derived from a standard, post-hoc automated tracking algorithm.MethodsWe collected B-mode ultrasound data from the soleus muscle of six participants performing five defined ankle motion tasks: (a) seated, constrained ankle plantarflexion, (b) seated, free ankle dorsi/plantarflexion, (c) weight-bearing, calf raises (d) walking, and then a (e) mix. We trained machine learning (ML) models by pairing muscle fascicle lengths obtained from standardized automated tracking software (UltraTrack) with the respective B-mode ultrasound image input to the tracker, frame-by-frame. Then we conducted hyperparameter optimizations for five different ML models using a grid search to find the best performing parameters for a combination of high correlation and low RMSE between ML and UltraTrack processed muscle fascicle length trajectories. Finally, using the global best model/hyperparameter settings, we comprehensively evaluated training-testing outcomes within subject (i.e., train and test on same subject), cross subject (i.e., train on one subject, test on another) and within/direct cross task (i.e., train and test on same subject, but different task).ResultsSupport vector machine (SVM) was the best performing model with an average r = 0.70 ±0.34 and average RMSE = 2.86 ±2.55 mm across all direct training conditions and average r = 0.65 ±0.35 and average RMSE = 3.28 ±2.64 mm when optimized for all cross-participant conditions. Comparisons between ML vs. UltraTrack (i.e., ground truth) tracked muscle fascicle length versus time data indicated that ML tracked images reliably capture the salient qualitative features in ground truth length change data, even when correlation values are on the lower end. Furthermore, in the direct training, calf raises condition, which is most comparable to previous studies validating automated tracking performance during isolated contractions on a dynamometer, our ML approach yielded 0.90 average correlation, in line with other accepted tracking methods in the field.ConclusionsBy combining B-mode ultrasound and classical ML models, we demonstrate it is possible to achieve real-time tracking of human soleus muscle fascicles across a number of functionally relevant contractile conditions. This novel sensing modality paves the way for muscle physiology in-the-loop applications that could be used to modify gait via biofeedback or unlock novel wearable device control techniques that could enable restored or augmented locomotion performance.

Dataset Information

Application of machine learning to ultrasound images to differentiate follicular neoplasms of the thyroid gland.

Publications

Application of machine learning to ultrasound images to differentiate follicular neoplasms of the thyroid gland.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets