<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.4 20241031//EN"
        "https://jats.nlm.nih.gov/publishing/1.4/JATS-journalpublishing1-4.dtd">
<article  article-type="research-article"        dtd-version="1.4">
            <front>

                <journal-meta>
                                                                <journal-id>genel tıp derg</journal-id>
            <journal-title-group>
                                                                                    <journal-title>Genel Tıp Dergisi</journal-title>
            </journal-title-group>
                                        <issn pub-type="epub">2602-3741</issn>
                                                                                            <publisher>
                    <publisher-name>Selçuk Üniversitesi</publisher-name>
                </publisher>
                    </journal-meta>
                <article-meta>
                                        <article-id pub-id-type="doi">10.54005/geneltip.1746638</article-id>
                                                                <article-categories>
                                            <subj-group  xml:lang="en">
                                                            <subject>Radiology and Organ Imaging</subject>
                                                    </subj-group>
                                            <subj-group  xml:lang="tr">
                                                            <subject>Radyoloji ve Organ Görüntüleme</subject>
                                                    </subj-group>
                                    </article-categories>
                                                                                                                                                        <title-group>
                                                                                                                        <article-title>Distinguishing Osteosarcoma and Chondrosarcoma Using Radiomic Features Derived from T2-Weighted MR Images: A Pilot Study</article-title>
                                                                                                                                                                                                <trans-title-group xml:lang="tr">
                                    <trans-title>T2 Ağırlıklı Manyetik Rezonans Görüntülerden Elde Edilen Radyomik Özelliklerle Osteosarkom ve Kondrosarkomun Ayırt Edilmesi: Pilot Çalışma</trans-title>
                                </trans-title-group>
                                                                                                    </title-group>
            
                                                    <contrib-group content-type="authors">
                                                                        <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0003-1437-8998</contrib-id>
                                                                <name>
                                    <surname>Yazol</surname>
                                    <given-names>Merve</given-names>
                                </name>
                                                                    <aff>GAZİ ÜNİVERSİTESİ, TIP FAKÜLTESİ, DAHİLİ TIP BİLİMLERİ BÖLÜMÜ, RADYOLOJİ ANABİLİM DALI, PEDİYATRİK RADYOLOJİ BİLİM DALI</aff>
                                                            </contrib>
                                                    <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0002-9423-3598</contrib-id>
                                                                <name>
                                    <surname>Keser</surname>
                                    <given-names>Aydin Cem</given-names>
                                </name>
                                                                    <aff>İHSAN DOĞRAMACI BİLKENT ÜNİVERSİTESİ, FEN FAKÜLTESİ, FİZİK BÖLÜMÜ</aff>
                                                            </contrib>
                                                    <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0001-6529-9232</contrib-id>
                                                                <name>
                                    <surname>Kesen Özbek</surname>
                                    <given-names>Sevcihan</given-names>
                                </name>
                                                                    <aff>GAZİ ÜNİVERSİTESİ, TIP FAKÜLTESİ, DAHİLİ TIP BİLİMLERİ BÖLÜMÜ, RADYOLOJİ ANABİLİM DALI</aff>
                                                            </contrib>
                                                    <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0001-6109-5240</contrib-id>
                                                                <name>
                                    <surname>Akdulum</surname>
                                    <given-names>İsmail</given-names>
                                </name>
                                                                    <aff>GAZİ ÜNİVERSİTESİ, TIP FAKÜLTESİ, DAHİLİ TIP BİLİMLERİ BÖLÜMÜ, RADYOLOJİ ANABİLİM DALI, PEDİYATRİK RADYOLOJİ BİLİM DALI</aff>
                                                            </contrib>
                                                    <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0002-5200-1588</contrib-id>
                                                                <name>
                                    <surname>Boyunaga</surname>
                                    <given-names>Öznur Leman</given-names>
                                </name>
                                                                    <aff>GAZİ ÜNİVERSİTESİ, TIP FAKÜLTESİ, DAHİLİ TIP BİLİMLERİ BÖLÜMÜ, RADYOLOJİ ANABİLİM DALI, PEDİYATRİK RADYOLOJİ BİLİM DALI</aff>
                                                            </contrib>
                                                                                </contrib-group>
                        
                                        <pub-date pub-type="pub" iso-8601-date="20260428">
                    <day>04</day>
                    <month>28</month>
                    <year>2026</year>
                </pub-date>
                                        <volume>36</volume>
                                        <issue>2026</issue>
                                        <fpage>1</fpage>
                                        <lpage>7</lpage>
                        
                        <history>
                                    <date date-type="received" iso-8601-date="20250915">
                        <day>09</day>
                        <month>15</month>
                        <year>2025</year>
                    </date>
                                                    <date date-type="accepted" iso-8601-date="20251103">
                        <day>11</day>
                        <month>03</month>
                        <year>2025</year>
                    </date>
                            </history>
                                        <permissions>
                    <copyright-statement>Copyright © 1990, Genel Tıp Dergisi</copyright-statement>
                    <copyright-year>1990</copyright-year>
                    <copyright-holder>Genel Tıp Dergisi</copyright-holder>
                </permissions>
            
                                                                                                <abstract><p>Aim: Osteosarcoma (OS) and chondrosarcoma (CS) are common malignant bone tumors with overlapping clinical and radiological features, making accurate differentiation challenging. Biopsy, the gold standard, is invasive and prone to sampling errors. This pilot study aimed to evaluate whether radiomic features from T2-Weighted magnetic resonance imaging (MRI) can non-invasively distinguish OS from CS.Materials and Methods: This retrospective study included 29 histopathologically confirmed patients (OS=15, CS=14). Pre-treatment T2WI scans were acquired on 1.5T/3T MRI scanners. An experienced radiologist manually segmented tumors, excluding hemorrhage, necrosis, or edema. 107 radiomic features extracted. Features were ranked by combining statistical testing with Principal Component Analysis (PCA) loadings, and the top five were retained. A baseline linear discriminant analysis (LDA) was evaluated with five-fold stratified cross-validation, and an advanced pipeline (standardization, SMOTE, kernel PCA, LDA, and RBF-SVM) was optimized by grid search and cross-validation on the training set, and subsequently tested on an independent split. Model performance was evaluated with accuracy, F1 score, balanced accuracy, ROC–AUC, and confusion matrices, expressed as misclassification between tumor subtypes.Results: Of 107 extracted radiomic features, shape and texture metrics were most highly prioritized. A baseline LDA achieved modest cross-validated accuracy (0.53) with respect to OS but showed significant class separation. The optimized pipeline improved test performance, reaching a balanced accuracy of 0.83, F1 score of 0.86, ROC–AUC of 0.78, and 100% sensitivity with respect to OS at the optimal threshold.Conclusions: Radiomic analysis of pre-treatment T2WIs shows promise for differentiating osteosarcoma from chondrosarcoma, achieving high sensitivity and balanced accuracy, and may serve as a complementary tool to conventional diagnosis in musculoskeletal oncology.</p></abstract>
                                                                                                                                    <trans-abstract xml:lang="tr">
                            <p>Amaç: Osteosarkom (OS) ve kondrosarkom (KS), örtüşen klinik ve radyolojik özelliklere sahip en yaygın malign kemik tümörlerinden olup bu da iki tümörün doğru ayrımını zorlaştırır. Tanıda altın standart biyopsi olsa da invazivdir ve örnekleme hatalarına eğilimlidir. Bu pilot çalışma, T2 ağırlıklı manyetik rezonans görüntüleme (MRG)’ den elde edilen radyomik özelliklerin OS’yi KS’den invaziv olmayan bir şekilde ayırt edip edemeyeceğini değerlendirmeyi amaçlamıştır.Gereç ve Yöntem: Bu retrospektif çalışma, histopatolojik olarak doğrulanmış 29 hastayı (OS=15, CS=14) kapsamaktadır. Tüm olguların tedavi öncesi T2 ağırlıklı MR görüntülemeleri 1,5T/3T cihazlarda elde edilmişti. Deneyimli bir radyolog, tümörleri kanama, nekroz veya ödemi hariç tutarak manuel segmente etti. Toplam 107 radyomik özellik çıkarıldı. Özellikler, istatistiksel testler ile Temel Bileşen Analizi (PCA) analizinin birleştirilmesiyle sıralandı ve ilk beş özellik seçildi. Beş katlı tabakalı çapraz doğrulama ile bir temel doğrusal ayrımcılık analizi (LDA) değerlendirildi. Daha gelişmiş bir iş akışı (standardizasyon, Sentetik Azınlık Aşırı Örnekleme Tekniği (SMOTE), kernel PCA, LDA ve RBF-SVM) eğitim verileri üzerinde grid arama ve çapraz doğrulama yöntemiyle optimize edildi ve bağımsız bir veri grubunda test edildi. Model performansı doğruluk, F1 skoru, dengeli doğruluk, ROC–AUC ve tümör alt tipleri arasındaki yanlış sınıflamayı gösteren karışıklık matrisleri ile değerlendirildi.Bulgular: Elde edilen 107 radyomik özellikten şekil ve doku metrikleri en yüksek önceliğe sahipti. Temel LDA modeli çapraz doğrulamada OS’e açısından sınırlı bir doğruluk (0.53) sağladı ancak belirgin sınıf ayrımı gösterdi. Optimize edilmiş veri hattı, test performansını iyileştirerek, optimum eşikte OS açısından 0,83’lük dengeli bir doğruluğa, 0,86’lık F1 skoruna, 0,78’lik ROC-AUC’ye ve 100% hassasiyete ulaşmıştır.Sonuçlar: Tedavi öncesi T2 ağırlıklı MRG’den elde edilen radyomik analiz, osteosarkomu kondrosarkomdan ayırmada yüksek duyarlılık ve dengeli doğruluk sağlamada umut verici olup, kas-iskelet onkolojisinde konvansiyonel tanıya tamamlayıcı bir araç olarak kullanılabilir.</p></trans-abstract>
                                                            
            
                                                            <kwd-group>
                                                    <kwd>osteosarcoma</kwd>
                                                    <kwd>  chondrosarcoma</kwd>
                                                    <kwd>  MRI</kwd>
                                                    <kwd>  radiomics</kwd>
                                                    <kwd>  T2WI</kwd>
                                            </kwd-group>
                                                        
                                                                            <kwd-group xml:lang="tr">
                                                    <kwd>osteosarkom</kwd>
                                                    <kwd>  kondrosarkom</kwd>
                                                    <kwd>  MRG</kwd>
                                                    <kwd>  radyomik</kwd>
                                                    <kwd>  T2AG</kwd>
                                            </kwd-group>
                                                                                                            </article-meta>
    </front>
    <back>
                            <ref-list>
                                    <ref id="ref1">
                        <label>1</label>
                        <mixed-citation publication-type="journal">1.	Rozeman L, Cleton-Jansen A, Hogendoorn P. Pathology of primary malignant bone and cartilage tumours. Int Orthop. 2006; 30:437–44.</mixed-citation>
                    </ref>
                                    <ref id="ref2">
                        <label>2</label>
                        <mixed-citation publication-type="journal">2.	Parvizi J. High Yield Orthopaedics. Elsevier Health Sciences; 2010.</mixed-citation>
                    </ref>
                                    <ref id="ref3">
                        <label>3</label>
                        <mixed-citation publication-type="journal">3.	Redondo A, Bagué S, Bernabeu D, et al. Malignant bone tumors (other than Ewing’s): clinical practice guidelines for diagnosis, treatment and follow-up by Spanish Group for Research on Sarcomas (GEIS). Cancer Chemother Pharmacol. 2017; 80:1113–31.</mixed-citation>
                    </ref>
                                    <ref id="ref4">
                        <label>4</label>
                        <mixed-citation publication-type="journal">4.	Zając AE, Kopeć S, Szostakowski B, et al. Chondrosarcoma—from molecular pathology to novel therapies. Cancers (Basel). 2021; 13:2390.</mixed-citation>
                    </ref>
                                    <ref id="ref5">
                        <label>5</label>
                        <mixed-citation publication-type="journal">5.	Erdem F, Tamsel İ, Demirpolat G. The use of radiomics and machine learning for the differentiation of chondrosarcoma from enchondroma. J Clin Ultrasound. 2023; 51:1027–35.</mixed-citation>
                    </ref>
                                    <ref id="ref6">
                        <label>6</label>
                        <mixed-citation publication-type="journal">6.	Craft A. Osteosarcoma and chondrosarcoma. In: Cancer in Children: Clinical Management. Springer; 1992. p. 282–94.</mixed-citation>
                    </ref>
                                    <ref id="ref7">
                        <label>7</label>
                        <mixed-citation publication-type="journal">7.	Ghasemi A, Ahlawat S, Fayad LM, editors. Magnetic resonance imaging biomarkers of bone and soft tissue tumors. Semin Musculoskelet Radiol. 2024.</mixed-citation>
                    </ref>
                                    <ref id="ref8">
                        <label>8</label>
                        <mixed-citation publication-type="journal">8.	Caloro E, Gnocchi G, Quarrella C, et al. Artificial intelligence in bone metastasis imaging: recent progresses from diagnosis to treatment—a narrative review. Crit Rev Oncog. 2024;29.</mixed-citation>
                    </ref>
                                    <ref id="ref9">
                        <label>9</label>
                        <mixed-citation publication-type="journal">9.	Cè M, Cellina M, Ueanukul T, et al. Multimodal imaging of osteosarcoma: From first diagnosis to radiomics. Cancers (Basel). 2025; 17:599.</mixed-citation>
                    </ref>
                                    <ref id="ref10">
                        <label>10</label>
                        <mixed-citation publication-type="journal">10.	Zhong J, Hu Y, Ge X, et al. A systematic review of radiomics in chondrosarcoma: assessment of study quality and clinical value needs handy tools. Eur Radiol. 2023; 33:1433–44.</mixed-citation>
                    </ref>
                                    <ref id="ref11">
                        <label>11</label>
                        <mixed-citation publication-type="journal">11.	Li L, Wang K, Ma X, et al. Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma. Eur J Radiol. 2019; 118:81–7.</mixed-citation>
                    </ref>
                                    <ref id="ref12">
                        <label>12</label>
                        <mixed-citation publication-type="journal">12.	Gao Z, Dai Z, Ouyang Z, et al. Radiomics analysis in differentiating osteosarcoma and chondrosarcoma based on T2-weighted imaging and contrast-enhanced T1-weighted imaging. Sci Rep. 2024; 14:26594.</mixed-citation>
                    </ref>
                                    <ref id="ref13">
                        <label>13</label>
                        <mixed-citation publication-type="journal">13.	Yen C-H, Chang C-Y, Teng MM-H, et al. Different and identical features of chondroblastic osteosarcoma and chondrosarcoma: highlights on radiography and magnetic resonance imaging. J Chin Med Assoc. 2009; 72:76–82.</mixed-citation>
                    </ref>
                                    <ref id="ref14">
                        <label>14</label>
                        <mixed-citation publication-type="journal">14.	Resnick DL, Jacobson JA, Chung CB, Kransdorf MJ, Pathria MN. Bone and Joint Imaging. Elsevier Health Sciences; 2024.</mixed-citation>
                    </ref>
                                    <ref id="ref15">
                        <label>15</label>
                        <mixed-citation publication-type="journal">15.	Zhang X, Peng J, Ji G, et al. Research status and progress of radiomics in bone and soft tissue tumors: A review. Medicine (Baltimore). 2023;102: e36196.</mixed-citation>
                    </ref>
                                    <ref id="ref16">
                        <label>16</label>
                        <mixed-citation publication-type="journal">16.	Saifuddin A, Tyler P, Hargunani R. Musculoskeletal MRI. CRC Press; 2016.</mixed-citation>
                    </ref>
                                    <ref id="ref17">
                        <label>17</label>
                        <mixed-citation publication-type="journal">17.	Meng Y, Yang Y, Hu M, Zhang Z, Zhou X, editors. Artificial intelligence-based radiomics in bone tumors: Technical advances and clinical application. Semin Cancer Biol. 2023.</mixed-citation>
                    </ref>
                                    <ref id="ref18">
                        <label>18</label>
                        <mixed-citation publication-type="journal">18.	Dai Y, Yin P, Mao N, et al. Differentiation of pelvic osteosarcoma and Ewing sarcoma using radiomic analysis based on T2-weighted images and contrast-enhanced T1-weighted images. Biomed Res Int. 2020; 2020:9078603.</mixed-citation>
                    </ref>
                                    <ref id="ref19">
                        <label>19</label>
                        <mixed-citation publication-type="journal">19.	Lisson CS, Lisson CG, Flosdorf K, et al. Diagnostic value of MRI-based 3D texture analysis for tissue characterisation and discrimination of low-grade chondrosarcoma from enchondroma: a pilot study. Eur Radiol. 2018; 28:468–77.</mixed-citation>
                    </ref>
                                    <ref id="ref20">
                        <label>20</label>
                        <mixed-citation publication-type="journal">20.	Gitto S, Cuocolo R, van Langevelde K, et al. MRI radiomics-based machine learning classification of atypical cartilaginous tumour and grade II chondrosarcoma of long bones. EBioMedicine. 2022;75.</mixed-citation>
                    </ref>
                                    <ref id="ref21">
                        <label>21</label>
                        <mixed-citation publication-type="journal">21.	Yin P, Mao N, Zhao C, et al. A triple-classification radiomics model for the differentiation of primary chordoma, giant cell tumor, and metastatic tumor of sacrum based on T2-weighted and contrast-enhanced T1-weighted MRI. J Magn Reson Imaging. 2019; 49:752–9.</mixed-citation>
                    </ref>
                                    <ref id="ref22">
                        <label>22</label>
                        <mixed-citation publication-type="journal">22.	Elawad A, Shah A, Davies M, Botchu R. The use of gadolinium in musculoskeletal MRI—time to rethink? Indian J Radiol Imaging. 2021; 31:635–43.</mixed-citation>
                    </ref>
                                    <ref id="ref23">
                        <label>23</label>
                        <mixed-citation publication-type="journal">23.	Long Q-Y, Wang F-Y, Hu Y, et al. Development of the interpretable typing prediction model for osteosarcoma and chondrosarcoma based on machine learning and radiomics: a multi-center retrospective study. Front Med (Lausanne). 2024; 11:1497309.</mixed-citation>
                    </ref>
                            </ref-list>
                    </back>
    </article>
