Logo
Home
Company ProfileMemberships & PartnersBoards & StaffsAcademy of JournalismCareersBlog(EN)Contact Us
Our JournalsInstruction for AuthorsOpen Peer ReviewArticle Processing ChargesPublishing ServicesPublish My ResearchJournal Management System
Publish My Book

IJ Radiology

An Innovative Journal in the Field of Radiology

Home
Current IssueAll IssuesIn PressAccepted ManuscriptsSearch
Instructions
Journal InformationEditors and BoardsIndexing and Listing SourcesJournal MetricsOpen Peer Review (OPR)Publication Ethics and Malpractice StatementContact UsSupportReviewer and AE Registration Form
APC
Authors GuideSubmit Manuscript

Outlines

https://doi.org/10.5812/iranjradiol.99154

A Diagnostic Machine Classifier Using Multi-Parametric MRI to Differentiate Benign from Malignant Myometrial Tumors

Author(s):
Mahrooz MalekMahrooz Malek1, Elnaz TabibianElnaz Tabibian1,*, Milad Rahimi DehgolanMilad Rahimi Dehgolan2, Maryam RahmaniMaryam Rahmani1, Setare AkhavanSetare Akhavan1, Shahrzad Sheikh HasaniShahrzad Sheikh Hasani1, Fatemeh NiliFatemeh NiliFatemeh Nili ORCID1, Hassan HashemiHassan Hashemi1
1Tehran University of Medical Sciences, Tehran, Iran
2Khaje Nasir Toosi University of Technology, Tehran, Iran

IJ Radiology:Vol. 16, issue Special Issue; e99154
Published online:Dec 10, 2019
Article type:Abstract
Received:Oct 26, 2019
Accepted:Dec 10, 2019
How to Cite:Mahrooz MalekElnaz TabibianMilad Rahimi DehgolanMaryam RahmaniSetare AkhavanShahrzad Sheikh HasaniFatemeh NiliHassan Hashemiet al.A Diagnostic Machine Classifier Using Multi-Parametric MRI to Differentiate Benign from Malignant Myometrial Tumors.I J Radiol.16(Special Issue):e99154.https://doi.org/10.5812/iranjradiol.99154.

Abstract

Background:

There are many conditions in medicine that decision making has crucial importance to differentiate between binary diagnoses, such as preoperative discrimination of benign from malignant tumors, e.g. uterine neoplasms. Physicians are not usually able to pool multiple parameters affecting the diagnosis, while “machine learning” techniques, especially “decision trees” with human-readable results, can process such amounts of data. Previous studies have shown that MRI could be helpful in the differentiation of uterine leiomyosarcoma from leiomyoma.

Objectives:

Hereby, for preoperative diagnosis of these tumors and to reduce unnecessary costs and surgeries, we applied a machine classifier using multi-parametric MRI to construct practical diagnostic algorithms.

Methods:

A total of 105 myometrial lesions were included in two groups of benign and malignant, according to postoperative tissue diagnosis. Multi-parametric MRI including T1-, T2-, and diffusion-weighted images (DWI) with apparent diffusion coefficient (ADC) map, contrast-enhanced images, as well as MR spectroscopy, were performed for each lesion. Thirteen singular MRI features were extracted from the mentioned sequences. Various combination sets of selective features were fed into a machine classifier (coarse decision-tree) to predict malignant or benign tumors. The accuracy metrics of either singular or combinational models were assessed (Figures 1 and 2). Eventually, two diagnostic algorithms, including a simple decision-tree and a complex one, were proposed using the most accurate models by MATLAB 2017.

Results:

Among all singular features, the visual assessment of DWI-ADC restriction, followed by the T2 map, achieved the best accuracies as 96.2% and 92.0%, respectively. Our final simple decision-tree comprised three features including T2, central necrosis (CN), and DWI-ADC restriction with accuracy of 96.2%, sensitivity of 100%, and specificity of 95%. However, the complex tree made up of four features including T2 map, CN, DWI-ADC restriction, and Tumor to Myometrium Contrast-Enhanced Ratio yielded accuracy, sensitivity, and specificity values of 100%.

Conclusion:

The complex diagnostic algorithm, compared to the simple model, could differentiate tumors, with equal sensitivity but higher specificity. However, it needs more advanced calculations and a high level of patient cooperation; moreover, it might be a time-consuming method. Therefore, physicians should wisely trade-off in different clinical situations and request imaging modalities in a way to reduce additional costs and most importantly, to prevent unnecessary surgeries, by helping early accurate diagnosis.

Keywords
Diagnostic Algorithms
Machine Learning
Leiomyosarcoma
Decision Trees
Uterine Neoplasms

To see figures, please refer to the PDF file.

comments

Leave a comment here

Import into EndNoteImport into BibTex
Crossmark
Crossmark
Checking
Share on
Comments
Number of Comments:0
Cited by
Metrics
Get Permission (article level)

Purchasing Reprints

  • Copyright Clearance Center (CCC) handles bulk orders for article reprints for Brieflands. To place an order for reprints, please click here (   https://www.copyright.com/landing/reprintsinquiryform/ ). Clicking this link will bring you to a CCC request form where you can provide the details of your order. Once complete, please click the ‘Submit Request’ button and CCC’s Reprints Services team will generate a quote for your review.
Search Relations

Author(s):

Related Articles

Related Article in PubMed

Related Article in Google Scholar

Create Citation Alert via Google Reader