1
|
Valenzuela RF, Duran-Sierra E, Canjirathinkal M, Amini B, Torres KE, Benjamin RS, Ma J, Wang WL, Hwang KP, Stafford RJ, Wu C, Zarzour AM, Bishop AJ, Lo S, Madewell JE, Kumar R, Murphy WA, Costelloe CM. Perfusion-weighted imaging with dynamic contrast enhancement (PWI/DCE) morphologic, qualitative, semiquantitative, and radiomics features predicting undifferentiated pleomorphic sarcoma (UPS) treatment response. Sci Rep 2024; 14:21681. [PMID: 39289469 PMCID: PMC11408515 DOI: 10.1038/s41598-024-72780-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2024] [Accepted: 09/10/2024] [Indexed: 09/19/2024] Open
Abstract
Undifferentiated pleomorphic sarcoma (UPS) is the largest subgroup of soft tissue sarcomas. This study determined the value of perfusion-weighted imaging with dynamic-contrast-enhancement (PWI/DCE) morphologic, qualitative, and semiquantitative features for predicting UPS pathology-assessed treatment effect (PATE). This retrospective study included 33 surgically excised extremity UPS patients with pre-surgical MRI. Volumetric tumor segmentation from PWI/DCE was obtained at Baseline (BL), Post-Chemotherapy (PC), and Post-Radiation Therapy (PRT). The surgical specimens' PATE separated cases into Responders (R) (≥ 90%, 16 patients), Partial-Responders (PR) (89 - 31%, 10 patients), and Non-Responders (NR) (≤ 30%, seven patients). Seven semiquantitative kinetic parameters and maps were extracted from time-intensity curves (TICs), and 107 radiomic features were derived. Statistical analyses compared R vs. PR/NR. At PRT, 79% of R displayed a "Capsular" morphology (P = 1.49 × 10-7), and 100% demonstrated a TIC-type II (P = 8.32 × 10-7). 80% of PR showed "Unipolar" morphology (P = 1.03 × 10-5), and 60% expressed a TIC-type V (P = 0.06). Semiquantitative wash-in rate (WiR) was able to separate R vs. PR/NR (P = 0.0078). The WiR radiomics displayed significant differences in the first_order_10 percentile (P = 0.0178) comparing R vs. PR/NR at PRT. The PWI/DCE TIC-type II curve, low WiR, and "Capsular" enhancement represent PRT patterns typically observed in successfully treated UPS and demonstrate potential for UPS treatment response assessment.
Collapse
Affiliation(s)
- R F Valenzuela
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - E Duran-Sierra
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - M Canjirathinkal
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - B Amini
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - K E Torres
- Department of Surgical Oncology, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - R S Benjamin
- Department of Sarcoma Medical Oncology, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - J Ma
- Department of Imaging Physics, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - W L Wang
- Department of Anatomical Pathology, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - K P Hwang
- Department of Imaging Physics, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - R J Stafford
- Department of Imaging Physics, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - C Wu
- Department of Imaging Physics, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - A M Zarzour
- Department of Sarcoma Medical Oncology, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - A J Bishop
- Department of Radiation Oncology, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - S Lo
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - J E Madewell
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - R Kumar
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - W A Murphy
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| | - C M Costelloe
- Department of Musculoskeletal Imaging, The University of Texas, MD Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1475, Houston, TX, 77030-4009, USA
| |
Collapse
|
2
|
Schmitz F, Sedaghat S. Diagnostic Value of Magnetic Resonance Imaging Radiomics and Machine-learning in Grading Soft Tissue Sarcoma: A Mini-review on the Current State. Acad Radiol 2024:S1076-6332(24)00598-1. [PMID: 39261231 DOI: 10.1016/j.acra.2024.08.035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2024] [Revised: 07/15/2024] [Accepted: 08/17/2024] [Indexed: 09/13/2024]
Abstract
Soft tissue sarcomas (STS) are a heterogeneous group of rare malignant tumors. Tumor grade might be underestimated in biopsy due to intratumoral heterogeneity. This mini-review aims to present the current state of predicting malignancy grades of STS through radiomics, machine learning, and deep learning on magnetic resonance imaging (MRI). Several studies investigated various machine-learning and deep-learning approaches in T2-weighted (w) images, contrast-enhanced (CE) T1w images, and DWI/ADC maps with promising results. Combining semantic imaging features, radiomics features, and deep-learning signatures in machine-learning models has demonstrated superior predictive performances compared to individual feature sources. Furthermore, incorporating features from both tumor volume and peritumor region is beneficial. Especially random forest and support vector machine classifiers, often combined with the least absolute shrinkage and selection operator (LASSO) and/or synthetic minority oversampling technique (SMOTE), did show high area under the curve (AUC) values and accuracies in existing studies.
Collapse
Affiliation(s)
- Fabian Schmitz
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany (F.S., S.S.)
| | - Sam Sedaghat
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany (F.S., S.S.).
| |
Collapse
|
3
|
Schmitz F, Sedaghat S. Inferring malignancy grade of soft tissue sarcomas from magnetic resonance imaging features: A systematic review. Eur J Radiol 2024; 177:111548. [PMID: 38852328 DOI: 10.1016/j.ejrad.2024.111548] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2024] [Revised: 04/22/2024] [Accepted: 06/02/2024] [Indexed: 06/11/2024]
Abstract
PURPOSE Systematic reviews on the grading of STS using MRI are lacking. This review analyses the role of different MRI features in inferring the histological grade of STS. MATERIALS AND METHODS A systematic review was conducted and is reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) checklist. The electronic databases of PubMed/MEDLINE were systematically searched for literature addressing the correlation of MRI findings in soft tissue sarcoma with tumor grade. As keywords "MRI", "magnetic resonance imaging", "sarcoma", "grade", "grading", and "FNCLCC" have been selected. RESULTS 14 studies have been included in this systematic review. Tumor size (p = 0.015 (51 patients) to p = 0.81 (36 patients)), tumor margin (p < 0.001 (95 patients) to 0.93 (36 patients)), necrosis (p = 0.004 (50 patients) to p = 0.65 (95 patients)), peritumoral edema (p = 0.002 (130 patients) to p = 0.337 (40 patients)), contrast enhancement (p < 0.01 (50 patients) to 0.019 (51 patients)) and polycyclic/multilobulated tumor configuration (p = 0.008 (71 patients)) were significantly associated with STS malignancy grade in most of the included studies. Heterogeneity in T2w images (p = 0.003 (130 patients) to 0.202 (40 patients)), signal intensity in T1w images/ hemorrhage (p = 0.02 (130 patients) to 0.5 (31 patients)), peritumoral contrast enhancement (p < 0.001 (95 patients) to 0.253 (51 patients)) and tumoral diffusion restriction (p = 0.01 (51 patients) to 0.53 (52 patients)) were regarded as significantly associated with FNCLCC grade in some of the studies which investigated these features. Most other MRI features were not significant. CONCLUSION Several MRI features, such as tumor size, necrosis, peritumoral edema, peritumoral contrast enhancement, intratumoral contrast enhancement, and polycyclic/multilobulated tumor configuration may indicate the malignancy grade of STS. However, further studies are needed to gain consensus.
Collapse
Affiliation(s)
- Fabian Schmitz
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany
| | - Sam Sedaghat
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany.
| |
Collapse
|
4
|
Lee CH, Shen HY(D, Shiue YL(S, Chan HY, Chan HP. Myxofibrosarcoma of the Chest Wall Detected on 99mTc-MDP Whole-Body Bone Scan. Diagnostics (Basel) 2024; 14:857. [PMID: 38667502 PMCID: PMC11049239 DOI: 10.3390/diagnostics14080857] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 04/15/2024] [Accepted: 04/18/2024] [Indexed: 04/28/2024] Open
Abstract
Myxofibrosarcoma is a type of soft tissue sarcoma, predominantly characterized by a high propensity for local recurrence, albeit demonstrating a relatively diminished risk for distant metastasis. Its prevalence is notably higher in elderly patients. Here, we present a case of a 73-year-old woman diagnosed with Myxofibrosarcoma. She was subjected to a whole-body bone scan using 99mTc-methylene diphosphonate (MDP) to survey potential bony metastasis. It revealed marked MDP accumulation with peripheral soft tissue uptake in the right lateral chest region of this patient. This imaging phenotype could potentially be attributed to the augmented vascularity within the tumor, a finding that was prominently displayed in this particular case.
Collapse
Affiliation(s)
- Chia-Hsuan Lee
- Department of Nuclear Medicine, Kaohsiung Veterans General Hospital, Kaohsiung City 813, Taiwan; (C.-H.L.); (H.-Y.S.); (H.-Y.C.)
- Department of Psychiatry, Kaohsiung Medical University Hospital, Kaohsiung City 807, Taiwan
| | - Hueng-Yuan (Daniel) Shen
- Department of Nuclear Medicine, Kaohsiung Veterans General Hospital, Kaohsiung City 813, Taiwan; (C.-H.L.); (H.-Y.S.); (H.-Y.C.)
| | - Yow-Ling (Shirley) Shiue
- Institute of Biomedical Sciences, College of Medicine, National Sun Yat-sen University, Kaohsiung City 804, Taiwan;
- Institute of Precision Medicine, College of Medicine, National Sun Yat-sen University, Kaohsiung City 804, Taiwan
| | - Hung-Yen Chan
- Department of Nuclear Medicine, Kaohsiung Veterans General Hospital, Kaohsiung City 813, Taiwan; (C.-H.L.); (H.-Y.S.); (H.-Y.C.)
| | - Hung-Pin Chan
- Department of Nuclear Medicine, Kaohsiung Veterans General Hospital, Kaohsiung City 813, Taiwan; (C.-H.L.); (H.-Y.S.); (H.-Y.C.)
- Institute of Biomedical Sciences, College of Medicine, National Sun Yat-sen University, Kaohsiung City 804, Taiwan;
| |
Collapse
|
5
|
De Angelis R, Casale R, Coquelet N, Ikhlef S, Mokhtari A, Simoni P, Bali MA. The impact of radiomics in the management of soft tissue sarcoma. Discov Oncol 2024; 15:62. [PMID: 38441726 PMCID: PMC10914656 DOI: 10.1007/s12672-024-00908-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/02/2023] [Accepted: 02/23/2024] [Indexed: 03/08/2024] Open
Abstract
INTRODUCTION Soft tissue sarcomas (STSs) are rare malignancies. Pre-therapeutic tumour grading and assessment are crucial in making treatment decisions. Radiomics is a high-throughput method for analysing imaging data, providing quantitative information beyond expert assessment. This review highlights the role of radiomic texture analysis in STSs evaluation. MATERIALS AND METHODS We conducted a systematic review according to the Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive search was conducted in PubMed/MEDLINE and Scopus using the search terms: 'radiomics [All Fields] AND ("soft tissue sarcoma" [All Fields] OR "soft tissue sarcomas" [All Fields])'. Only original articles, referring to humans, were included. RESULTS A preliminary search conducted on PubMed/MEDLINE and Scopus provided 74 and 93 studies respectively. Based on the previously described criteria, 49 papers were selected, with a publication range from July 2015 to June 2023. The main domains of interest were risk stratification, histological grading prediction, technical feasibility/reproductive aspects, treatment response. CONCLUSIONS With an increasing interest over the last years, the use of radiomics appears to have potential for assessing STSs from initial diagnosis to predicting treatment response. However, additional and extensive research is necessary to validate the effectiveness of radiomics parameters and to integrate them into a comprehensive decision support system.
Collapse
Affiliation(s)
- Riccardo De Angelis
- Institut Jules Bordet, Anderlecht, Belgium
- Université Libre de Bruxelles, Brussels, Belgium
| | - Roberto Casale
- Institut Jules Bordet, Anderlecht, Belgium.
- Université Libre de Bruxelles, Brussels, Belgium.
| | | | - Samia Ikhlef
- Institut Jules Bordet, Anderlecht, Belgium
- Université Libre de Bruxelles, Brussels, Belgium
| | - Ayoub Mokhtari
- Institut Jules Bordet, Anderlecht, Belgium.
- Université Libre de Bruxelles, Brussels, Belgium.
| | - Paolo Simoni
- Université Libre de Bruxelles, Brussels, Belgium
| | - Maria Antonietta Bali
- Institut Jules Bordet, Anderlecht, Belgium
- Université Libre de Bruxelles, Brussels, Belgium
| |
Collapse
|
6
|
Generaal JD, Glas HH, Ubbels JF, Stevenson MG, Huijing MA, van Leeuwen BL, Been LB. Calculating Tumor Volume Using Three-Dimensional Models in Preoperative Soft-Tissue Sarcoma Surgical Planning: Does Size Matter? J Clin Med 2023; 12:7242. [PMID: 38068294 PMCID: PMC10871107 DOI: 10.3390/jcm12237242] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Revised: 11/12/2023] [Accepted: 11/21/2023] [Indexed: 02/18/2024] Open
Abstract
This feasibility study aims to explore the use of three-dimensional virtual surgical planning to preoperatively determine the need for reconstructive surgery following resection of an extremity soft-tissue sarcoma. As flap reconstruction is performed more often in advanced disease, we hypothesized that tumor volume would be larger in the group of patients that had undergone flap reconstruction. All patients that were treated by surgical resection for an extremity soft-tissue sarcoma between 1 January 2016 and 1 October 2019 in the University Medical Center Groningen were included retrospectively. Three-dimensional models were created using the diagnostic magnetic resonance scan. Tumor volume was calculated for all patients. Three-dimensional tumor volume was 107.8 (349.1) mL in the group of patients that had undergone primary closure and 29.4 (47.4) mL in the group of patients in which a flap reconstruction was performed, p = 0.004. Three-dimensional tumor volume was 76.1 (295.3) mL in the group of patients with a complication following ESTS treatment, versus 57.0 (132.4) mL in patients with an uncomplicated course following ESTS treatment, p = 0.311. Patients who had undergone flap reconstruction had smaller tumor volumes compared to those in the group of patients treated by primary closure. Furthermore, a larger tumor volume did not result in complications for patients undergoing ESTS treatment. Therefore, tumor volume does not seem to influence the need for reconstruction. Despite the capability of three-dimensional virtual surgical planning to measure tumor volume, we do not recommend its utilization in the multidisciplinary extremity soft-tissue sarcoma treatment, considering the findings of the study.
Collapse
Affiliation(s)
- Jasmijn D. Generaal
- Department of Surgery, Division of Surgical Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ Groningen, The Netherlands; (B.L.v.L.); (L.B.B.)
| | - Haye H. Glas
- Department of Maxillofacial Surgery, 3D Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ Groningen, The Netherlands;
| | - Jan F. Ubbels
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ Groningen, The Netherlands;
| | - Marc G. Stevenson
- Department of Surgery, Isala Hospital, Dr. van Heesweg 2, 8025 AB Zwolle, The Netherlands;
| | - Marijn A. Huijing
- Department of Plastic Surgery, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ Groningen, The Netherlands;
| | - Barbara L. van Leeuwen
- Department of Surgery, Division of Surgical Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ Groningen, The Netherlands; (B.L.v.L.); (L.B.B.)
| | - Lukas B. Been
- Department of Surgery, Division of Surgical Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ Groningen, The Netherlands; (B.L.v.L.); (L.B.B.)
| |
Collapse
|
7
|
Sedaghat M, Sedaghat S. Primary synovial sarcoma on MRI - a case series and review of the literature. Pol J Radiol 2023; 88:e325-e330. [PMID: 37576379 PMCID: PMC10415809 DOI: 10.5114/pjr.2023.130048] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2023] [Accepted: 06/07/2023] [Indexed: 08/15/2023] Open
Abstract
Purpose Simple MRI features are mandatory to facilitate the diagnostics of synovial sarcomas, especially for radiolo-gists outside multidisciplinary sarcoma centres. In this case-series and review, we investigate the main appearance of synovial sarcoma on MRI. Material and methods Fifteen histologically proven primary synovial sarcomas who underwent MRI at 2 different sarcoma centres were included in this case series. Patients and their primary synovial sarcomas were examined for age, localization, mean tumour size (in mm), histological grade (G - according to the Fédération Nationale des Centres de Lutte Contre Le Cancer [FNCLCC]), configuration, T2 signal intensity, presence/absence of "triple sign", heterogeneity/homogeneity, borders (well-defined or infiltrative), and intensity of contrast enhancement on MRI. Additionally, a comprehensive literature review to identify observational studies, reviews, and case-reports assessing MRI features of primary synovial sarcoma was performed. Results The mean age of the patients was 47.6 years (SD: 17.2). The mean size of primary synovial sarcoma was 59.3 mm (SD: 42). Primary synovial sarcomas were significantly most often multilobulated (n = 12, p < 0.01), heterogeneous (n = 10), and infiltrative (n = 9). Additionally, 3 other primary synovial sarcomas showed the following configurations: ovoid/nodular (n = 2) and fascicular (n = 1). Ovoid/nodular synovial sarcomas were solely depicted as homogeneous with well-defined borders. All tumours showed T2 hyperintense signal and presented with marked contrast enhancement. Conclusions Primary synovial sarcomas are mainly multilobulated, heterogeneous, and infiltrative tumours. In minor cases, ovoid/nodular or fascicular configurations occur. Knowing the main appearance of synovial sarcoma can help facilitate the diagnostics of primary synovial sarcomas.
Collapse
Affiliation(s)
- Maya Sedaghat
- Department for Radiology and Neuroradiology, University Hospital Schleswig-Holstein, Campus Kiel, Germany
| | - Sam Sedaghat
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, Germany
| |
Collapse
|
8
|
Pluetrattanabha N, Direksunthorn T. Recent Advances in Ultrasound of Soft Tissue Lesions. Int J Gen Med 2023; 16:1163-1170. [PMID: 37020931 PMCID: PMC10069506 DOI: 10.2147/ijgm.s404682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2023] [Accepted: 03/24/2023] [Indexed: 03/31/2023] Open
Abstract
The superficial soft tissue lesions are commonly discovered during routine clinical practice. However, their diagnosis can be challenging. Non-invasive imaging can differentiate the features of various superficial soft tissue lesions. Moreover, imaging-based evaluations can help guide treatment and surgical planning, evaluate tumor extension, and perform staging and follow-up. Novel imaging modalities and techniques have been developed to improve diagnostic performance and differentiate between benign and malignant lesions in vivo. The authors reviewed the literature to determine how ultrasound has been utilized to diagnose and treat superficial soft tissue lesions.
Collapse
|
9
|
Sudjai N, Siriwanarangsun P, Lektrakul N, Saiviroonporn P, Maungsomboon S, Phimolsarnti R, Asavamongkolkul A, Chandhanayingyong C. Tumor-to-bone distance and radiomic features on MRI distinguish intramuscular lipomas from well-differentiated liposarcomas. J Orthop Surg Res 2023; 18:255. [PMID: 36978182 PMCID: PMC10044811 DOI: 10.1186/s13018-023-03718-4] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/24/2022] [Accepted: 03/15/2023] [Indexed: 03/30/2023] Open
Abstract
Background To develop a machine learning model based on tumor-to-bone distance and radiomic features derived from preoperative MRI images to distinguish intramuscular (IM) lipomas and atypical lipomatous tumors/well-differentiated liposarcomas (ALTs/WDLSs) and compared with radiologists. Methods The study included patients with IM lipomas and ALTs/WDLSs diagnosed between 2010 and 2022, and with MRI scans (sequence/field strength: T1-weighted (T1W) imaging at 1.5 or 3.0 Tesla MRI). Manual segmentation of tumors based on the three-dimensional T1W images was performed by two observers to appraise the intra- and interobserver variability. After radiomic features and tumor-to-bone distance were extracted, it was used to train a machine learning model to distinguish IM lipomas and ALTs/WDLSs. Both feature selection and classification steps were performed using Least Absolute Shrinkage and Selection Operator logistic regression. The performance of the classification model was assessed using a tenfold cross-validation strategy and subsequently evaluated using the receiver operating characteristic curve (ROC) analysis. The classification agreement of two experienced musculoskeletal (MSK) radiologists was assessed using the kappa statistics. The diagnosis accuracy of each radiologist was evaluated using the final pathological results as the gold standard. Additionally, we compared the performance of the model and two radiologists in terms of the area under the receiver operator characteristic curves (AUCs) using the Delong’s test. Results There were 68 tumors (38 IM lipomas and 30 ALTs/WDLSs). The AUC of the machine learning model was 0.88 [95% CI 0.72–1] (sensitivity, 91.6%; specificity, 85.7%; and accuracy, 89.0%). For Radiologist 1, the AUC was 0.94 [95% CI 0.87–1] (sensitivity, 97.4%; specificity, 90.9%; and accuracy, 95.0%), and as to Radiologist 2, the AUC was 0.91 [95% CI 0.83–0.99] (sensitivity, 100%; specificity, 81.8%; and accuracy, 93.3%). The classification agreement of the radiologists was 0.89 of kappa value (95% CI 0.76–1). Although the AUC of the model was lower than of two experienced MSK radiologists, there was no statistically significant difference between the model and two radiologists (all P > 0.05). Conclusions The novel machine learning model based on tumor-to-bone distance and radiomic features is a noninvasive procedure that has the potential for distinguishing IM lipomas from ALTs/WDLSs. The predictive features that suggested malignancy were size, shape, depth, texture, histogram, and tumor-to-bone distance. Supplementary Information The online version contains supplementary material available at 10.1186/s13018-023-03718-4.
Collapse
Affiliation(s)
- Narumol Sudjai
- grid.10223.320000 0004 1937 0490Department of Orthopaedic Surgery, Faculty of Medicine Siriraj Hospital, Mahidol University, 2 Wanglang Road, Bangkoknoi, Bangkok, 10700 Thailand
| | - Palanan Siriwanarangsun
- grid.10223.320000 0004 1937 0490Department of Radiology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, 10700 Thailand
| | - Nittaya Lektrakul
- grid.10223.320000 0004 1937 0490Department of Radiology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, 10700 Thailand
| | - Pairash Saiviroonporn
- grid.10223.320000 0004 1937 0490Department of Radiology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, 10700 Thailand
| | - Sorranart Maungsomboon
- grid.10223.320000 0004 1937 0490Department of Pathology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, 10700 Thailand
| | - Rapin Phimolsarnti
- grid.10223.320000 0004 1937 0490Department of Orthopaedic Surgery, Faculty of Medicine Siriraj Hospital, Mahidol University, 2 Wanglang Road, Bangkoknoi, Bangkok, 10700 Thailand
| | - Apichat Asavamongkolkul
- grid.10223.320000 0004 1937 0490Department of Orthopaedic Surgery, Faculty of Medicine Siriraj Hospital, Mahidol University, 2 Wanglang Road, Bangkoknoi, Bangkok, 10700 Thailand
| | - Chandhanarat Chandhanayingyong
- grid.10223.320000 0004 1937 0490Department of Orthopaedic Surgery, Faculty of Medicine Siriraj Hospital, Mahidol University, 2 Wanglang Road, Bangkoknoi, Bangkok, 10700 Thailand
| |
Collapse
|
10
|
Weiss S, Korthaus A, Baumann N, Yamamura J, Spiro AS, Lübke AM, Frosch KH, Schlickewei C, Priemel M. Musculoskeletal Soft-Tissue Sarcoma: Quality Assessment of Initial MRI Reports Shows Frequent Deviation from ESSR Guidelines. Diagnostics (Basel) 2021; 11:695. [PMID: 33919690 PMCID: PMC8069769 DOI: 10.3390/diagnostics11040695] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2021] [Revised: 04/07/2021] [Accepted: 04/12/2021] [Indexed: 01/27/2023] Open
Abstract
Soft-tissue sarcomas (STS) are a rare subtype of soft-tissue mass and are frequently misinterpreted as benign lesions. Magnetic resonance imaging (MRI) is the primary recommended type of diagnostics. To assess the quality of primary radiology reports, we investigated whether recommended MRI report elements were included in compliance with European Society of Musculoskeletal Radiology (ESSR) guidelines. A total of 1107 patients were evaluated retrospectively, and 126 radiological reports on patients with malignant STS were assessed for ESSR quality criteria. One or more required sequences or planes were missing in 67% of the reports. In all 126 cases, the report recognized the mass as anomalous (100%). Sixty-eight percent of the reports mentioned signs of malignancy. The majority of reports (n = 109, 87%) articulated a suspected diagnosis, 32 of which showed a mismatch with the final diagnosis (25%). Thirty-two percent of the reports had a misinterpretation of the masses as benign. Benign misinterpretations were more common in masses smaller than 5 cm (65% vs. 27%). Thirty percent of the reports suggested tissue biopsy and 6% recommended referral to a sarcoma center. MRI reports showed frequent deviations from ESSR guidelines, and protocol guidelines were not routinely met. Deviations from standard protocol and reporting guidelines could put patients at risk for inadequate therapy.
Collapse
Affiliation(s)
- Sebastian Weiss
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
| | - Alexander Korthaus
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
| | - Nora Baumann
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
| | - Jin Yamamura
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany;
| | - Alexander S. Spiro
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
- Department of Pediatric Orthopedics, Children’s Hospital Hamburg Altona, 22763 Hamburg, Germany
| | - Andreas M. Lübke
- Institute of Pathology, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany;
| | - Karl-Heinz Frosch
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
- Department of Trauma Surgery, Orthopaedics and Sports Traumatology, BG Klinikum Hamburg, 21033 Hamburg, Germany
| | - Carsten Schlickewei
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
| | - Matthias Priemel
- Department of Trauma and Orthopaedic Surgery, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany; (A.K.); (N.B.); (A.S.S.); (K.-H.F.); (C.S.); (M.P.)
| |
Collapse
|