Utility of the k-means clustering algorithm in differentiating apparent diffusion coefficient values of benign and malignant neck pathologies.
نویسندگان
چکیده
BACKGROUND AND PURPOSE Does the K-means algorithm do a better job of differentiating benign and malignant neck pathologies compared to only mean ADC? The objective of our study was to analyze the differences between ADC partitions to evaluate whether the K-means technique can be of additional benefit to whole-lesion mean ADC alone in distinguishing benign and malignant neck pathologies. MATERIAL AND METHODS MR imaging studies of 10 benign and 10 malignant proved neck pathologies were postprocessed on a PC by using in-house software developed in Matlab. Two neuroradiologists manually contoured the lesions, with the ADC values within each lesion clustered into 2 (low, ADC-ADC(L); high, ADC-ADC(H)) and 3 partitions (ADC(L); intermediate, ADC-ADC(I); ADC(H)) by using the K-means clustering algorithm. An unpaired 2-tailed Student t test was performed for all metrics to determine statistical differences in the means of the benign and malignant pathologies. RESULTS A statistically significant difference between the mean ADC(L) clusters in benign and malignant pathologies was seen in the 3-cluster models of both readers (P = .03 and .022, respectively) and the 2-cluster model of reader 2 (P = .04), with the other metrics (ADC(H), ADC(I); whole-lesion mean ADC) not revealing any significant differences. ROC curves demonstrated the quantitative differences in mean ADC(H) and ADC(L) in both the 2- and 3-cluster models to be predictive of malignancy (2 clusters: P = .008, area under curve = 0.850; 3 clusters: P = .01, area under curve = 0.825). CONCLUSIONS The K-means clustering algorithm that generates partitions of large datasets may provide a better characterization of neck pathologies and may be of additional benefit in distinguishing benign and malignant neck pathologies compared with whole-lesion mean ADC alone.
منابع مشابه
Differentiation of benign and malignant breast lesions by apparent diffusion coefficient value in mass and non-mass lesions
Background: Diffusion-weighted imaging (DWI) is one of methods in evaluation of breast lesions. We aimed to investigate the apparent diffusion coefficient (ADC) values in breast tumors and their accuracy in differentiating benign versus malignant lesions. Methods: In this cross-sectional study, 72 patients with 88 breast lesions were investigated by 1.5-T breast MRI from 2015 to 2017 in Athari...
متن کاملExploring the Possibility of Estimating Degree of Glioma Tumors by Measuring Apparent Diffusion Coefficient
Introduction: Most common glioma tumors are tumors of the central nervous system (CNS) which are the cause of about 40 to 50 percent of brain tumors. This type of cancer includes 2 to 3 percent of cancers in the world. Conventional MRI is powerless in the detection and differentiation of benign and malignant tumors. In this case, diffusion weighted imaging (DWI) can create cont...
متن کاملFeasibility and usefulness of apparent diffusion coefficient at 3T for differentiating benign from malignant tumors of the head and neck
متن کامل
Differentiation of benign and malignant pathology in the head and neck using 3T apparent diffusion coefficient values: early experience.
BACKGROUND AND PURPOSE The purpose of this work was to study differences in apparent diffusion coefficient (ADC) values between benign and malignant head and neck lesions at 3T field strength imaging. MATERIALS AND METHODS Our study population in this retrospective study was derived from the patient population who had undergone routine neck 3T MR imaging (for clinical indications) from Decemb...
متن کاملThe Role of Diffusion-Weighted MR Imaging in Detecting Malignant and Benign Pleural Thickening in Asbestos-Related Pleural Diseases
Objective: The aim of this study was to evaluate the role of diffusion-weighted magnetic resonance imaging (dMRI) in differentiating between diffuse malignant and benign pleural thickening in asbestos-related pleural diseases. Materials and Methods: Sixty-two patients were included in the study. Thirty-two had a benign form and 30 had malignant pleural mesothelioma (MPM). The patient files and ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- AJNR. American journal of neuroradiology
دوره 31 4 شماره
صفحات -
تاریخ انتشار 2010