Classification of breast masses in ultrasound images using self-adaptive differential evolution extreme learning machine and rough set feature selection

Prabusankarlal, K.M.; Thirumoorthy, P.; Manavalan, R.

doi:10.1117/1.jmi.4.2.024507

Cited by 11 publications

(4 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ten features of the BI‐RADS were extracted from ultrasound images to differentiate between benign and malignant breast nodules, and the best AUC was 0.84 31 . During another study, 32 29 texture features and 500 morphological features acquired from 140 breast ultrasound images were applied to classify breast lesions, producing an AUC of 0.96, specificity of 97.5%, sensitivity of 96.7%, and accuracy of 97.1%. By extracting the edge echo and edge angle features from the breast ultrasound image and the age of the patient, a radiomics model was constructed (AUC, 0.870) 33 .…”

Section: Discussionmentioning

confidence: 99%

An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions

Wang

Yang

et al. 2021

J of Ultrasound Medicine

View full text Add to dashboard Cite

Objectives To develop and test an optimized radiomics model based on multi‐planar automated breast volume scan (ABVS) images to identify malignant and benign breast lesions. Methods Patients (n = 200) with breast lesions who underwent ABVS examinations were included. For each patient, 208 radiomics features were extracted from the ABVS images, including axial plane and coronal plane. Recursive feature elimination, random forest, and chi‐square test were used to select features. A support vector machine, logistic regression, and extreme gradient boosting were utilized as classifiers to differentiate malignant and benign breast lesions. The area under the curve, sensitivity, specificity, accuracy, and precision was used to evaluate the performance of the radiomics models. Generalization of the radiomics models was verified through 5‐fold cross‐validation. Results For a single plane or a combination of planes, a combination of recursive feature elimination, and support vector machine yielded the best performance when identifying breast lesions. The machine learning models based on a combination of planes performed better than those based on a single plane. Regarding the axial plane and coronal plane, the machine learning model using a combination of recursive feature elimination and support vector machine yielded the optimal identification performance: average area under the curve (0.857 ± 0.058, 95% confidence interval, 0.763–0.957); the average values of sensitivity, specificity, accuracy, and precision were 87.9, 68.2, 80.7, and 82.9%, respectively. Conclusions The optimized radiomics model based on ABVS images can provide valuable information for identifying benign and malignant breast lesions preoperatively and guide the accurate clinical treatment. Further external validation is required.

show abstract

Section: Discussionmentioning

confidence: 99%

An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions

Wang

Yang

et al. 2021

J of Ultrasound Medicine

View full text Add to dashboard Cite

show abstract

“…For each gender, seven ML-based approaches (single and hybrid) were applied to model the PVBSP. These ML classification methodologies included the single algorithm support vector machine (SVM) [ 36 ], K-nearest neighbor (KNN) [ 52 ], random forest (RF) [ 53 ], decision tree (DT) [ 54 ], and extreme learning machine (ELM) [ 55 ], as well as the hybrid self-adaptive ELM (SA-ELM) [ 56 ], and a combination of decision tree and self-adaptive ELM (DT-SAELM). For details on their implementation, refer to Additional file 5 .…”

Section: Methodsmentioning

confidence: 99%

Single nucleotide polymorphism genes and mitochondrial DNA haplogroups as biomarkers for early prediction of knee osteoarthritis structural progressors: use of supervised machine learning classifiers

Bonakdari

Pelletier

Blanco

et al. 2022

BMC Med

View full text Add to dashboard Cite

Background Knee osteoarthritis is the most prevalent chronic musculoskeletal debilitating disease. Current treatments are only symptomatic, and to improve this, we need a robust prediction model to stratify patients at an early stage according to the risk of joint structure disease progression. Some genetic factors, including single nucleotide polymorphism (SNP) genes and mitochondrial (mt)DNA haplogroups/clusters, have been linked to this disease. For the first time, we aim to determine, by using machine learning, whether some SNP genes and mtDNA haplogroups/clusters alone or combined could predict early knee osteoarthritis structural progressors. Methods Participants (901) were first classified for the probability of being structural progressors. Genotyping included SNP genes TP63, FTO, GNL3, DUS4L, GDF5, SUPT3H, MCF2L, and TGFA; mtDNA haplogroups H, J, T, Uk, and others; and clusters HV, TJ, KU, and C-others. They were considered for prediction with major risk factors of osteoarthritis, namely, age and body mass index (BMI). Seven supervised machine learning methodologies were evaluated. The support vector machine was used to generate gender-based models. The best input combination was assessed using sensitivity and synergy analyses. Validation was performed using tenfold cross-validation and an external cohort (TASOAC). Results From 277 models, two were defined. Both used age and BMI in addition for the first one of the SNP genes TP63, DUS4L, GDF5, and FTO with an accuracy of 85.0%; the second profits from the association of mtDNA haplogroups and SNP genes FTO and SUPT3H with 82.5% accuracy. The highest impact was associated with the haplogroup H, the presence of CT alleles for rs8044769 at FTO, and the absence of AA for rs10948172 at SUPT3H. Validation accuracy with the cross-validation (about 95%) and the external cohort (90.5%, 85.7%, respectively) was excellent for both models. Conclusions This study introduces a novel source of decision support in precision medicine in which, for the first time, two models were developed consisting of (i) age, BMI, TP63, DUS4L, GDF5, and FTO and (ii) the optimum one as it has one less variable: age, BMI, mtDNA haplogroup, FTO, and SUPT3H. Such a framework is translational and would benefit patients at risk of structural progressive knee osteoarthritis.

show abstract

“…The boundaries of the lesion play an important role in ultrasound based diagnosis of early breast cancer. Preserving the tiny structure of lesions is significant when they are despeckled [31]. The corresponding numerical comparisons in Table.7 show that the proposed NLM method can retain image boundaries and preserve small lesion structures more effectively than other methods.…”

Section: Experiments On Real Us Imagesmentioning

confidence: 96%

Modified NLM Model for Despeckling Ultrasound Images Using FCM Clustering Based Pre Classification and Ribm

Prabusankarlal¹,

Thirumoorthy²,

Manavalan³

et al. 2018

IJIVP

View full text Add to dashboard Cite

Speckle noise is an inherent characteristic of ultrasound which reduces the classification accuracy of computer aided diagnosis (CAD) systems. A modified non local means (NLM) filter for despeckling ultrasound images is proposed in this article. The proposed NLM model utilizes a preclassification method in which the feature vectors of the input image are constructed using moment invariants and then they are clustered using fuzzy c means (FCM) algorithm. The rotationally invariant block matching (RIBM) algorithm is applied among the blocks within each cluster instead of the entire image. This intra cluster block matching reduces computational complexity of NLM process without the elimination of any pixel candidate. Further, the rotationally invariant moment distance measure improves the noise reduction performance of the algorithm by increasing the chance of getting more similar candidates for NLM process. Extensive experiments are conducted using synthetic images, phantom images and ultrasound images. The method is comparatively evaluated with other denoising methods using statistical parameters such as MSE, PSNR, SSIM, EPI and ENL. The quantitative results suggested that the proposed method outperforms other four state of the art methods in despeckling and preservation of image details.

show abstract

Classification of breast masses in ultrasound images using self-adaptive differential evolution extreme learning machine and rough set feature selection

Cited by 11 publications

References 70 publications

An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions

An Optimized Radiomics Model Based on Automated Breast Volume Scan Images to Identify Breast Lesions

Single nucleotide polymorphism genes and mitochondrial DNA haplogroups as biomarkers for early prediction of knee osteoarthritis structural progressors: use of supervised machine learning classifiers

Modified NLM Model for Despeckling Ultrasound Images Using FCM Clustering Based Pre Classification and Ribm

Contact Info

Product

Resources

About