Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists.
<h4>Introduction</h4>Benign and malignant myxoid soft tissue tumors have shared clinical, imaging, and histologic features that can make diagnosis challenging. The purpose of this study is comparison of the diagnostic performance of a radiomic based machine learning (ML) model to musculo...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0318072 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540211000639488 |
|---|---|
| author | Joshua M Lawrenz Can Cui Samuel R Johnson Katherine S Hajdu Stephen W Chenard Akhil Rekulapelli Cullen P Moran John J Block Nicholson S Chadwick Joanna L Shechtel Brian Bingham Leo Y Luo Jennifer L Halpern Herbert S Schwartz Ginger E Holt David S Smith Benoit Dawant Hakmook Kang |
| author_facet | Joshua M Lawrenz Can Cui Samuel R Johnson Katherine S Hajdu Stephen W Chenard Akhil Rekulapelli Cullen P Moran John J Block Nicholson S Chadwick Joanna L Shechtel Brian Bingham Leo Y Luo Jennifer L Halpern Herbert S Schwartz Ginger E Holt David S Smith Benoit Dawant Hakmook Kang |
| author_sort | Joshua M Lawrenz |
| collection | DOAJ |
| description | <h4>Introduction</h4>Benign and malignant myxoid soft tissue tumors have shared clinical, imaging, and histologic features that can make diagnosis challenging. The purpose of this study is comparison of the diagnostic performance of a radiomic based machine learning (ML) model to musculoskeletal radiologists.<h4>Methods</h4>Manual segmentation of 90 myxoid soft tissue tumors (45 myxomas and 45 myxofibrosarcomas) was performed on axial T1, and T2FS or STIR magnetic resonance imaging sequences. Eighty-seven radiomic features from each modality were extracted. Five ML models were trained to classify tumors as benign or malignant in 40 tumors and then tested with an additional 50 tumors using cross validation. The accuracy of the best ML model based on area under the receiver operating characteristic curve (AUC) was compared to the consensus diagnosis of three musculoskeletal radiologists. Correlation between radiologist confidence (equivocal, probably, consistent with) and accuracy was tested.<h4>Results</h4>The best ML classifier was a logistic regression model (AUC 0.792). Using T1 + T2/STIR images, the ML model classified 78% (39/50) of tumors correctly at a similar rate compared to 74% (37/50) by radiologists. When radiologists disagreed, the consensus diagnosis classified 50% of tumors (7/14) correctly compared to 86% (12/14) by the ML model, though this did not reach statistical significance. Radiologists had a cumulative accuracy of 91% (30/33) when they rated their confidence 'consistent with' compared to 61% (31/51) when they rated their confidence 'equivocal/probably' (P = 0.006). For cases when radiologists rated their confidence 'equivocal/probably', the ML model had 76% accuracy (39/51).<h4>Conclusions</h4>A radiomic based ML model predicted benign or malignant diagnosis in myxoid soft tissue tumors similarly to the consensus diagnosis by three musculoskeletal radiologists. Radiologist confidence in the diagnosis strongly correlated with their diagnostic accuracy. Though radiomics and radiologists perform similarly overall, radiomics may provide novel diagnostic utility when radiologist confidence is low, or when radiologists disagree. |
| format | Article |
| id | doaj-art-cbccdf96c77c43cb96a22319efe1c47a |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-cbccdf96c77c43cb96a22319efe1c47a2025-02-05T05:32:06ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031807210.1371/journal.pone.0318072Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists.Joshua M LawrenzCan CuiSamuel R JohnsonKatherine S HajduStephen W ChenardAkhil RekulapelliCullen P MoranJohn J BlockNicholson S ChadwickJoanna L ShechtelBrian BinghamLeo Y LuoJennifer L HalpernHerbert S SchwartzGinger E HoltDavid S SmithBenoit DawantHakmook Kang<h4>Introduction</h4>Benign and malignant myxoid soft tissue tumors have shared clinical, imaging, and histologic features that can make diagnosis challenging. The purpose of this study is comparison of the diagnostic performance of a radiomic based machine learning (ML) model to musculoskeletal radiologists.<h4>Methods</h4>Manual segmentation of 90 myxoid soft tissue tumors (45 myxomas and 45 myxofibrosarcomas) was performed on axial T1, and T2FS or STIR magnetic resonance imaging sequences. Eighty-seven radiomic features from each modality were extracted. Five ML models were trained to classify tumors as benign or malignant in 40 tumors and then tested with an additional 50 tumors using cross validation. The accuracy of the best ML model based on area under the receiver operating characteristic curve (AUC) was compared to the consensus diagnosis of three musculoskeletal radiologists. Correlation between radiologist confidence (equivocal, probably, consistent with) and accuracy was tested.<h4>Results</h4>The best ML classifier was a logistic regression model (AUC 0.792). Using T1 + T2/STIR images, the ML model classified 78% (39/50) of tumors correctly at a similar rate compared to 74% (37/50) by radiologists. When radiologists disagreed, the consensus diagnosis classified 50% of tumors (7/14) correctly compared to 86% (12/14) by the ML model, though this did not reach statistical significance. Radiologists had a cumulative accuracy of 91% (30/33) when they rated their confidence 'consistent with' compared to 61% (31/51) when they rated their confidence 'equivocal/probably' (P = 0.006). For cases when radiologists rated their confidence 'equivocal/probably', the ML model had 76% accuracy (39/51).<h4>Conclusions</h4>A radiomic based ML model predicted benign or malignant diagnosis in myxoid soft tissue tumors similarly to the consensus diagnosis by three musculoskeletal radiologists. Radiologist confidence in the diagnosis strongly correlated with their diagnostic accuracy. Though radiomics and radiologists perform similarly overall, radiomics may provide novel diagnostic utility when radiologist confidence is low, or when radiologists disagree.https://doi.org/10.1371/journal.pone.0318072 |
| spellingShingle | Joshua M Lawrenz Can Cui Samuel R Johnson Katherine S Hajdu Stephen W Chenard Akhil Rekulapelli Cullen P Moran John J Block Nicholson S Chadwick Joanna L Shechtel Brian Bingham Leo Y Luo Jennifer L Halpern Herbert S Schwartz Ginger E Holt David S Smith Benoit Dawant Hakmook Kang Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. PLoS ONE |
| title | Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. |
| title_full | Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. |
| title_fullStr | Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. |
| title_full_unstemmed | Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. |
| title_short | Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. |
| title_sort | distinguishing benign and malignant myxoid soft tissue tumors performance of radiomics vs radiologists |
| url | https://doi.org/10.1371/journal.pone.0318072 |
| work_keys_str_mv | AT joshuamlawrenz distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT cancui distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT samuelrjohnson distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT katherineshajdu distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT stephenwchenard distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT akhilrekulapelli distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT cullenpmoran distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT johnjblock distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT nicholsonschadwick distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT joannalshechtel distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT brianbingham distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT leoyluo distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT jenniferlhalpern distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT herbertsschwartz distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT gingereholt distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT davidssmith distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT benoitdawant distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists AT hakmookkang distinguishingbenignandmalignantmyxoidsofttissuetumorsperformanceofradiomicsvsradiologists |