A Novel Run-length based wavelet features for Screening Thyroid Nodule Malignancy

Abstract: Thyroid nodules are cell growths in the thyroid which might be for in one of two categories benign or malignant. Nodular thyroid disease is common and because of the associated risk of malignancy and hyper-function; these nodules have to be examined thoroughly. Hence diagnosing thyroid nodule malignancy in the early stage can mitigate the possibility of death. This paper presents an intelligent thyroid nodules malignancy diagnosis using texture information in run-length matrix derived from 2- level 2D wavelet transform bands (approximation and details). In this work, ANOVA test has been used to for feature selection to reduce for feature selection about 45 run-length features with and without wavelet generated, before feeding those features which clinical importance to the Support Vector Machine(SVM) and Decision Tree (DT) classifier to perform the automated diagnosis. The validation of this work is activated using 100-thyroid nodule images spliced equally between the two categories (50 Benign and 50 Malignant). The proposed system can detect thyroid nodules malignancy with an average accuracy of about 97% using SVM classifier for the run- length matrix, features derived from spatial domain while the average accuracy is increased to 98% in case of hybrid feature derived from spatial domain and 2-level wavelet decomposition. For the other proposed classifier (DT), the average accuracy in case of spatial domain based features is 93% whereas the average accuracy of the hybrid features system is 97%. Hence the proposed system can be used for the screening of thyroid nodules.

Differentiation of adult pilocytic astrocytomas and hemangioblastomas using texture analysis / 实用放射学杂志

Objective To investigate the diagnostic value of the texture analysis in differentiating adult pilocytic astrocytomas (PA)from hemangioblastomas(HB).Methods 22 adult patients with PA and 20 patients with HB which were confirmed by postoperative pathological were retrospectively reviewed.The conventional MRI features and texture parameters were analyzed.Eight texture parameters were extracted using run-length matrix(RLM),and the differences of texture parameters of the two groups were analyzed by independent-samples t test.Results The short run emphasis(SRE),grey-level non-uniformity(GLNU),run-length non-uniformity(RLNU),high grey-level run emphasis(HGRE)and short run high grey-level emphasis(SRHGE)were higher in adult PA than in HB.The long run emphasis(LRE),low grey-level run emphasis(LGRE)and short run low grey-level emphasis(SRLGE)were lower in adult PA than in HB.The eight texture parameters had significant differences between the two groups(P<0.05).Conclusion Texture analysis can provide reliably objective basis for differentiating adult PA from HB.

The Study on MR Image Texture Features of Cerebral Infarction Patients / 中国医学物理学杂志

Objective:Based on Co-occurrence Matrix and Run-length Matrix,we studied cerebral infarction patients' MR image texture characters.The aim is to investigate the differences of lesion textures characters between patients' groups and normal control groups,so that we can use this tiny change to realize early diagnosis of cerebral infarction.Methods:Texture features were extracted from MR images of patients and normal control groups respectively.Fisher test was applied to choose valid textures characters and made features classifier.Results:Linear discriminant analysis can achieve 88.31% classification accuracy.This demonstrated that cerebral infarction patients and normal control groups have the differences of textures Characters in MR image.Conclusion:We can discover cerebral infarction patients' MR image texture characters change by texture analysis,so that early diagnosis of cerebral infarction would be realized.