An Automated Decision Support System to Analyze Malignancy Patterns of Breast Masses Employing Medically Relevant Features of Ultrasound Images.
An automated computer-aided approach might aid radiologists in diagnosing breast cancer at a primary stage. This study proposes a novel decision support system to classify breast tumors into benign and malignant based on clinically important features, using ultrasound images. Nine handcrafted featur...
| Published in: | Journal of Digital Imaging Vol. 37; no. 1; pp. 45 - 60 |
|---|---|
| Main Authors: | , , , , , |
| Format: | computer program diagnostic images research tables/charts Journal Article |
| Published: |
Springer Nature
Feb2024
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=175966516&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 175966516 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Feb2024 vid: 37 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 175966516 175966516 175966516 10.1007/s10278-023-00925-7 175966516 ppf: 45 ppct: 15 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: An Automated Decision Support System to Analyze Malignancy Patterns of Breast Masses Employing Medically Relevant Features of Ultrasound Images. aug: au: Azam, Sami Montaha, Sidratul Raiaan, Mohaimenul Azam Khan Rafid, A. K. M. Rakibul Haque Mukta, Saddam Hossain Jonkman, Mirjam affil: https://ror.org/048zcaj52 Faculty of Science and Technology, Charles Darwin University, 0909, Casuarina, NT, Australia sug: subj: Breast Neoplasms Ultrasonography Breast Neoplasms Diagnosis Decision Support Systems, Clinical Decision Making, Computer Assisted Methods Automation Tumor Markers, Biological Human Machine Learning Descriptive Statistics Decision Support Techniques Algorithms Radiologists Diagnosis, Computer Assisted ab: An automated computer-aided approach might aid radiologists in diagnosing breast cancer at a primary stage. This study proposes a novel decision support system to classify breast tumors into benign and malignant based on clinically important features, using ultrasound images. Nine handcrafted features, which align with the clinical markers used by radiologists, are extracted from the region of interest (ROI) of ultrasound images. To validate that these elected clinical markers have a significant impact on predicting the benign and malignant classes, ten machine learning (ML) models are experimented with resulting in test accuracies in the range of 96 to 99%. In addition, four feature selection techniques are explored where two features are eliminated according to the feature ranking score of each feature selection method. The Random Forest classifier is trained with the resultant four feature sets. Results indicate that even when eliminating only two features, the performance of the model is reduced for each feature selection technique. These experiments validate the efficiency and effectiveness of the clinically important features. To develop the decision support system, a probability density function (PDF) graph is generated for each feature in order to find a threshold range to distinguish benign and malignant tumors. Based on the threshold range of particular features, a decision support system is developed in such a way that if at least eight out of nine features are within the threshold range, the image will be denoted as true predicted. With this algorithm, a test accuracy of 99.38% and an F1 Score of 99.05% is achieved, which means that our decision support system outperforms all the previously trained ML models. Moreover, after calculating individual class-based test accuracies, for the benign class, a test accuracy of 99.31% has been attained where only three benign instances are misclassified out of 437 instances, and for the malignant class, a test accuracy of 99.52% has been attained where only one malignant instance is misclassified out of 210 instances. This system is robust, time-effective, and reliable as the radiologists' criteria are followed and may aid specialists in making a diagnosis. pubtype: Academic Journal doctype: computer program diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|