1
|
Crombé A, Lucchesi C, Bertolo F, Kind M, Spalato-Ceruso M, Toulmonde M, Chaire V, Michot A, Coindre JM, Perret R, Le Loarer F, Bourdon A, Italiano A. Integration of pre-treatment computational radiomics, deep radiomics, and transcriptomics enhances soft-tissue sarcoma patient prognosis. NPJ Precis Oncol 2024; 8:129. [PMID: 38849448 PMCID: PMC11161510 DOI: 10.1038/s41698-024-00616-8] [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: 12/04/2023] [Accepted: 05/17/2024] [Indexed: 06/09/2024] Open
Abstract
Our objective was to capture subgroups of soft-tissue sarcoma (STS) using handcraft and deep radiomics approaches to understand their relationship with histopathology, gene-expression profiles, and metastatic relapse-free survival (MFS). We included all consecutive adults with newly diagnosed locally advanced STS (N = 225, 120 men, median age: 62 years) managed at our sarcoma reference center between 2008 and 2020, with contrast-enhanced baseline MRI. After MRI postprocessing, segmentation, and reproducibility assessment, 175 handcrafted radiomics features (h-RFs) were calculated. Convolutional autoencoder neural network (CAE) and half-supervised CAE (HSCAE) were trained in repeated cross-validation on representative contrast-enhanced slices to extract 1024 deep radiomics features (d-RFs). Gene-expression levels were calculated following RNA sequencing (RNAseq) of 110 untreated samples from the same cohort. Unsupervised classifications based on h-RFs, CAE, HSCAE, and RNAseq were built. The h-RFs, CAE, and HSCAE grouping were not associated with the transcriptomics groups but with prognostic radiological features known to correlate with lower survivals and higher grade and SARCULATOR groups (a validated prognostic clinical-histological nomogram). HSCAE and h-RF groups were also associated with MFS in multivariable Cox regressions. Combining HSCAE and transcriptomics groups significantly improved the prognostic performances compared to each group alone, according to the concordance index. The combined radiomic-transcriptomic group with worse MFS was characterized by the up-regulation of 707 genes and 292 genesets related to inflammation, hypoxia, apoptosis, and cell differentiation. Overall, subgroups of STS identified on pre-treatment MRI using handcrafted and deep radiomics were associated with meaningful clinical, histological, and radiological characteristics, and could strengthen the prognostic value of transcriptomics signatures.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Oncologic Imaging, Bergonié Institute, F-33076, Bordeaux, France.
- Department of Radiology, Pellegrin University Hospital, F-33076, Bordeaux, France.
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France.
| | - Carlo Lucchesi
- Department of Bioinformatics, Bergonié Institute, F-33076, Bordeaux, France
| | - Frédéric Bertolo
- Department of Bioinformatics, Bergonié Institute, F-33076, Bordeaux, France
| | - Michèle Kind
- Department of Oncologic Imaging, Bergonié Institute, F-33076, Bordeaux, France
| | - Mariella Spalato-Ceruso
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Medical Oncology, Bergonié Institute, F-33076, Bordeaux, France
| | - Maud Toulmonde
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Medical Oncology, Bergonié Institute, F-33076, Bordeaux, France
| | - Vanessa Chaire
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Pathology, Bergonié Institute, F-33076, Bordeaux, France
| | - Audrey Michot
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Oncologic Surgery, Bergonié Institute, F-33076, Bordeaux, France
| | - Jean-Michel Coindre
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Pathology, Bergonié Institute, F-33076, Bordeaux, France
| | - Raul Perret
- Department of Pathology, Bergonié Institute, F-33076, Bordeaux, France
| | - François Le Loarer
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Pathology, Bergonié Institute, F-33076, Bordeaux, France
| | - Aurélien Bourdon
- Department of Bioinformatics, Bergonié Institute, F-33076, Bordeaux, France
| | - Antoine Italiano
- Bordeaux Institute of Oncology, BRIC U1312, Sarcotarget team, INSERM, University of Bordeaux, Institut Bergonié, F-33000, Bordeaux, France
- Department of Medical Oncology, Bergonié Institute, F-33076, Bordeaux, France
| |
Collapse
|
2
|
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
|
3
|
Crombé A, Spinnato P, Italiano A, Brisse HJ, Feydy A, Fadli D, Kind M. Radiomics and artificial intelligence for soft-tissue sarcomas: Current status and perspectives. Diagn Interv Imaging 2023; 104:567-583. [PMID: 37802753 DOI: 10.1016/j.diii.2023.09.005] [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: 07/10/2023] [Revised: 09/18/2023] [Accepted: 09/19/2023] [Indexed: 10/08/2023]
Abstract
This article proposes a summary of the current status of the research regarding the use of radiomics and artificial intelligence to improve the radiological assessment of patients with soft tissue sarcomas (STS), a heterogeneous group of rare and ubiquitous mesenchymal malignancies. After a first part explaining the principle of radiomics approaches, from raw image post-processing to extraction of radiomics features mined with unsupervised and supervised machine-learning algorithms, and the current research involving deep learning algorithms in STS, especially convolutional neural networks, this review details their main research developments since the formalisation of 'radiomics' in oncologic imaging in 2010. This review focuses on CT and MRI and does not involve ultrasonography. Radiomics and deep radiomics have been successfully applied to develop predictive models to discriminate between benign soft-tissue tumors and STS, to predict the histologic grade (i.e., the most important prognostic marker of STS), the response to neoadjuvant chemotherapy and/or radiotherapy, and the patients' survivals and probability for presenting distant metastases. The main findings, limitations and expectations are discussed for each of these outcomes. Overall, after a first decade of publications emphasizing the potential of radiomics through retrospective proof-of-concept studies, almost all positive but with heterogeneous and often non-replicable methods, radiomics is now at a turning point in order to provide robust demonstrations of its clinical impact through open-science, independent databases, and application of good and standardized practices in radiomics such as those provided by the Image Biomarker Standardization Initiative, without forgetting innovative research paths involving other '-omics' data to better understand the relationships between imaging of STS, gene-expression profiles and tumor microenvironment.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Radiology, Pellegrin University Hospital, 33000 Bordeaux, France; Department of Oncologic Imaging, Bergonié Institute, 33076 Bordeaux, France; 'Sarcotarget' team, BRIC INSERM U1312 and Bordeaux University, 33000 Bordeaux France.
| | - Paolo Spinnato
- Diagnostic and Interventional Radiology, IRCCS Istituto Ortopedico Rizzoli, Bologna 40136, Italy
| | | | | | - Antoine Feydy
- Department of Radiology, Hopital Cochin-AP-HP, 75014 Paris, France; Université Paris Cité, Faculté de Médecine, 75006 Paris, France
| | - David Fadli
- Department of Radiology, Pellegrin University Hospital, 33000 Bordeaux, France
| | - Michèle Kind
- Department of Oncologic Imaging, Bergonié Institute, 33076 Bordeaux, France
| |
Collapse
|
4
|
Crombé A, Matcuk GR, Fadli D, Sambri A, Patel DB, Paioli A, Kind M, Spinnato P. Role of Imaging in Initial Prognostication of Locally Advanced Soft Tissue Sarcomas. Acad Radiol 2023; 30:322-340. [PMID: 35534392 DOI: 10.1016/j.acra.2022.04.003] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Revised: 03/21/2022] [Accepted: 04/06/2022] [Indexed: 02/07/2023]
Abstract
BACKGROUND Although imaging is central in the initial staging of patients with soft tissue sarcomas (STS), it remains underused and few radiological features are currently used in practice for prognostication and to help guide the best therapeutic strategy. Yet, several prognostic qualitative and quantitative characteristics from magnetic resonance imaging (MRI) and positron emission tomography (PET) have been identified over these last decades. OBJECTIVE After an overview of the current validated prognostic features based on baseline imaging and their integration into prognostic tools, such as nomograms used by clinicians, the aim of this review is to summarize more complex and innovative MRI, PET, and radiomics features, and to highlight their role to predict indirectly (through histologic grade) or directly the patients' outcomes.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Diagnostic and Interventional Oncological Imaging, Institut Bergonié, Regional Comprehensive Cancer of Nouvelle-Aquitaine, 229, cours de l'Argonne, F-33076, Bordeaux, France; Department of musculoskeletal imaging, Pellegrin University Hospital, 2, place Amélie Raba-Léon, F-33000, Bordeaux, France; Models in Oncology (MONC) Team, INRIA Bordeaux Sud-Ouest, CNRS UMR 5251, Institut de Mathématiques de Bordeaux & Bordeaux University, 351 cours de la libération, F-33400 Talence, France.
| | - George R Matcuk
- Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, California
| | - David Fadli
- Department of musculoskeletal imaging, Pellegrin University Hospital, 2, place Amélie Raba-Léon, F-33000, Bordeaux, France
| | - Andrea Sambri
- Alma Mater Studiorum, University of Bologna, Bologna, Italy; IRCCS Policlinico di Sant'Orsola, Bologna, Italy
| | - Dakshesh B Patel
- Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, California
| | - Anna Paioli
- Osteoncology Unit, IRCCS Istituto Ortopedico Rizzoli, Bologna, Italy
| | - Michele Kind
- Department of Diagnostic and Interventional Oncological Imaging, Institut Bergonié, Regional Comprehensive Cancer of Nouvelle-Aquitaine, 229, cours de l'Argonne, F-33076, Bordeaux, France
| | - Paolo Spinnato
- Diagnostic and Interventional Radiology, IRCCS Istituto Ortopedico Rizzoli, Bologna, Italy
| |
Collapse
|
5
|
Crombé A, Bertolo F, Fadli D, Kind M, Le Loarer F, Perret R, Chaire V, Spinnato P, Lucchesi C, Italiano A. Distinct patterns of the natural evolution of soft tissue sarcomas on pre-treatment MRIs captured with delta-radiomics correlate with gene expression profiles. Eur Radiol 2023; 33:1205-1218. [PMID: 36029343 DOI: 10.1007/s00330-022-09104-8] [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: 03/01/2022] [Revised: 07/26/2022] [Accepted: 08/08/2022] [Indexed: 02/03/2023]
Abstract
OBJECTIVES Radiomics of soft tissue sarcomas (STS) is assumed to correlate with histologic and molecular tumor features, but radiogenomics analyses are lacking. Our aim was to identify if distinct patterns of natural evolution of STS obtained from consecutive pre-treatment MRIs are associated with differential gene expression (DGE) profiling in a pathway analysis. METHODS All patients with newly diagnosed STS treated in a curative intent in our sarcoma reference center between 2008 and 2019 and with two available pre-treatment contrast-enhanced MRIs were included in this retrospective study. Radiomics features (RFs) were extracted from fat-sat contrast-enhanced T1-weighted imaging. Log ratio and relative change in RFs were calculated and used to determine grouping of samples based on a consensus hierarchical clustering. DGE and oncogenesis pathway analysis were performed in the delta-radiomics groups identified in order to detect associations between delta-radiomics patterns and transcriptomics features of STS. Secondarily, the prognostic value of the delta-radiomics groups was investigated. RESULTS Sixty-three patients were included (median age: 63 years, interquartile range: 52.5-70). The consensus clustering identified 3 reliable delta-radiomics patient groups (A, B, and C). On imaging, group B patients were characterized by increase in tumor heterogeneity, necrotic signal, infiltrative margins, peritumoral edema, and peritumoral enhancement before the treatment start (p value range: 0.0019-0.0244), and, molecularly, by downregulation of natural killer cell-mediated cytotoxicity genes and upregulation of Hedgehog and Hippo signaling pathways. Group A patients were characterized by morphological stability of pre-treatment MRI traits and no local relapse (log-rank p = 0.0277). CONCLUSIONS This study highlights radiomics and transcriptomics convergence in STS. Proliferation and immune response inhibition were hyper-activated in the STS that were the most evolving on consecutive imaging. KEY POINTS • Three consensual and stable delta-radiomics clusters were identified and captured the natural patterns of morphological evolution of STS on pre-treatment MRIs. • These 3 patterns were explainable and correlated with different well-known semantic radiological features with an ascending gradient of pejorative characteristics from the A group to C group to B group. • Gene expression profiling stressed distinct patterns of up/downregulated oncogenetic pathways in STS from B group in keeping with its most aggressive radiological evolution.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Oncologic Imaging, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France. .,Models in Oncology (MONC) Team, INRIA Bordeaux Sud-Ouest, CNRS UMR 5251 & Bordeaux University, F-33400, Talence, France. .,Department of Musculoskeletal Imaging, Pellegrin University Hospital, 2, place Amélie Raba Léon, F-33000, Bordeaux, France.
| | - Frédéric Bertolo
- Bioinformatics Department, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| | - David Fadli
- Department of Musculoskeletal Imaging, Pellegrin University Hospital, 2, place Amélie Raba Léon, F-33000, Bordeaux, France
| | - Michèle Kind
- Department of Oncologic Imaging, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| | - François Le Loarer
- Department of Pathology, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| | - Raul Perret
- Department of Pathology, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| | - Vanessa Chaire
- Department of Pathology, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| | - Paolo Spinnato
- Diagnostic and Interventional Radiology, IRCCS Istituto Ortopedico Rizzoli, 40136, Bologna, Italy
| | - Carlo Lucchesi
- Bioinformatics Department, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| | - Antoine Italiano
- Department of Medical Oncology, Institut Bergonié, Comprehensive Cancer Center, F-33076, Bordeaux, France
| |
Collapse
|
6
|
Erber BM, Reidler P, Goller SS, Ricke J, Dürr HR, Klein A, Lindner L, Di Gioia D, Geith T, Baur-Melnyk A, Armbruster M. Impact of Dynamic Contrast Enhanced and Diffusion-Weighted MR Imaging on Detection of Early Local Recurrence of Soft Tissue Sarcoma. J Magn Reson Imaging 2023; 57:622-630. [PMID: 35582900 DOI: 10.1002/jmri.28236] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2022] [Revised: 05/03/2022] [Accepted: 05/05/2022] [Indexed: 01/20/2023] Open
Abstract
BACKGROUND Diagnosis of residual or recurrent tumor in soft-tissue sarcomas (STS) is a differential diagnostic challenge since post-therapeutic changes impede diagnosis. PURPOSE To evaluate the diagnostic accuracy of quantitative dynamic contrast enhanced (DCE)-MRI and diffusion-weighted imaging (DWI) to detect local recurrence of STS of the limb. STUDY TYPE Prospective. POPULATION A totalof 64 consecutive patients with primary STS of the limbs were prospectively included 3-6 months after surgery between January 2016 and July 2021. FIELD STRENGTH/SEQUENCE A 1.5 T; axial DWI echo-planar imaging sequences and DCE-MRI using a 3D T1-weighted spoiled gradient-echo sequence. ASSESSMENT The quantitative DCE-MRI parameters relative plasma flow (rPF) and relative mean transit time (rMTT) were calculated and ADC mapping was used to quantify diffusion restriction. Regions of interest of tumor growth and postoperative changes were drawn in consensus by two experts for diffusion and perfusion analysis. An additional morphological assessment was done by three independent and blinded radiologists. STATISTICAL TEST Unpaired t-test, ROC-analysis, and a logistic regression model were applied. Interobserver reliability was calculated using Fleiss kappa statistics. A P value of 0.05 was considered statistically significant. RESULTS A total of 11 patients turned out to have local recurrence. rPF was significantly higher in cases of local recurrence when compared to cases without local recurrence (61.1-4.5) while rMTT was slightly and significantly lower in local recurrence. ROC-analysis showed an area under the curve (AUC) of 0.95 (SEM ± 0.05) for rPF while a three-factor multivariate logistic regression model showed a high diagnostic accuracy of rPF (R2 = 0.71). Compared with morphological assessment, rPF had a distinct higher specificity and true positive value in detection of LR. DATA CONCLUSION DCE-MRI is a promising additional method to differentiate local recurrence from benign postoperative changes in STS of the limb. Especially specificity in detection of LR is increased compared to morphological assessment. EVIDENCE LEVEL 1 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Bernd M Erber
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - Paul Reidler
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - Sophia S Goller
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - Jens Ricke
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - Hans R Dürr
- Department of Orthopaedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), University Hospital, LMU Munich, Munich, Germany
| | - Alexander Klein
- Department of Orthopaedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), University Hospital, LMU Munich, Munich, Germany
| | - Lars Lindner
- Department of Medicine III, University Hospital, LMU Munich, Munich, Germany
| | - Dorit Di Gioia
- Department of Medicine III, University Hospital, LMU Munich, Munich, Germany
| | - Tobias Geith
- Department of Interventional Radiology, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Andrea Baur-Melnyk
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - Marco Armbruster
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| |
Collapse
|
7
|
Crombé A, Roulleau‐Dugage M, Italiano A. The diagnosis, classification, and treatment of sarcoma in this era of artificial intelligence and immunotherapy. CANCER COMMUNICATIONS (LONDON, ENGLAND) 2022; 42:1288-1313. [PMID: 36260064 PMCID: PMC9759765 DOI: 10.1002/cac2.12373] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/23/2022] [Revised: 09/20/2022] [Accepted: 10/08/2022] [Indexed: 01/25/2023]
Abstract
Soft-tissue sarcomas (STS) represent a group of rare and heterogeneous tumors associated with several challenges, including incorrect or late diagnosis, the lack of clinical expertise, and limited therapeutic options. Digital pathology and radiomics represent transformative technologies that appear promising for improving the accuracy of cancer diagnosis, characterization and monitoring. Herein, we review the potential role of the application of digital pathology and radiomics in managing patients with STS. We have particularly described the main results and the limits of the studies using radiomics to refine diagnosis or predict the outcome of patients with soft-tissue sarcomas. We also discussed the current limitation of implementing radiomics in routine settings. Standard management approaches for STS have not improved since the early 1970s. Immunotherapy has revolutionized cancer treatment; nonetheless, immuno-oncology agents have not yet been approved for patients with STS. However, several lines of evidence indicate that immunotherapy may represent an efficient therapeutic strategy for this group of diseases. Thus, we emphasized the remarkable potential of immunotherapy in sarcoma treatment by focusing on recent data regarding the immune landscape of these tumors. We have particularly emphasized the fact that the development of immunotherapy for sarcomas is not an aspect of histology (except for alveolar soft-part sarcoma) but rather that of the tumor microenvironment. Future studies investigating immunotherapy strategies in sarcomas should incorporate at least the presence of tertiary lymphoid structures as a stratification factor in their design, besides including a strong translational program that will allow for a better understanding of the determinants involved in sensitivity and treatment resistance to immune-oncology agents.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of ImagingInstitut BergoniéBordeauxNouvelle‐AquitaineF‐33076France,Faculty of MedicineUniversity of BordeauxBordeauxNouvelle‐AquitaineF‐33000France
| | | | - Antoine Italiano
- Faculty of MedicineUniversity of BordeauxBordeauxNouvelle‐AquitaineF‐33000France,Early Phase Trials and Sarcoma UnitInstitut BergoniéBordeauxNouvelle‐AquitaineF‐33076France
| |
Collapse
|
8
|
Giraudo C, Fichera G, Del Fiore P, Mocellin S, Brunello A, Rastrelli M, Stramare R. Tumor cellularity beyond the visible in soft tissue sarcomas: Results of an ADC-based, single center, and preliminary radiomics study. Front Oncol 2022; 12:879553. [DOI: 10.3389/fonc.2022.879553] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2022] [Accepted: 09/20/2022] [Indexed: 11/13/2022] Open
Abstract
PurposeSoft tissue sarcomas represent approximately 1% of all malignancies, and diagnostic radiology plays a significant role in the overall management of this rare group of tumors. Recently, quantitative imaging and, in particular, radiomics demonstrated to provide significant novel information, for instance, in terms of prognosis and grading. The aim of this study was to evaluate the prognostic role of radiomic variables extracted from apparent diffusion coefficient (ADC) maps collected at diagnosis in patients with soft tissue sarcomas in terms of overall survival and metastatic spread as well as to assess the relationship between radiomics and the tumor grade.MethodsPatients with histologically proven soft tissue sarcomas treated in our tertiary center from 2016 to 2019 who underwent an Magnetic Resonance (MR) scan at diagnosis including diffusion-weighted imaging were included in this retrospective institution review board–approved study. Each primary lesion was segmented using the b50 images; the volumetric region of interest was then applied on the ADC map. A total of 33 radiomic features were extracted, and highly correlating features were selected by factor analysis. In the case of feature/s showing statistically significant results, the diagnostic accuracy was computed. The Spearman correlation coefficient was used to evaluate the relationship between the tumor grade and radiomic features selected by factor analysis. All analyses were performed applying p<0.05 as a significant level.ResultsA total of 36 patients matched the inclusion criteria (15 women; mean age 58.9 ± 15 years old). The most frequent histotype was myxofibrosarcoma (16.6%), and most of the patients were affected by high-grade lesions (77.7%). Seven patients had pulmonary metastases, and, altogether, eight were deceased. Only the feature Imc1 turned out to be a predictor of metastatic spread (p=0.045 after Bonferroni correction) with 76.7% accuracy. The value -0.16 showed 73.3% sensitivity and 71.4% specificity, and patients with metastases showed lower values (mean Imc1 of metastatic patients -0.31). None of the examined variables was a predictor of the overall outcome (p>0.05, each). A moderate statistically significant correlation emerged only between Imc1 and the tumor grade (r=0.457, p=0.005).ConclusionsIn conclusion, the radiomic feature Imc1 acts as a predictor of metastatic spread in patients with soft tissue sarcomas and correlates with the tumor grade.
Collapse
|
9
|
Soft Tissue Sarcomas: The Role of Quantitative MRI in Treatment Response Evaluation. Acad Radiol 2022; 29:1065-1084. [PMID: 34548230 DOI: 10.1016/j.acra.2021.08.007] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2021] [Revised: 07/29/2021] [Accepted: 08/12/2021] [Indexed: 12/12/2022]
Abstract
BACKGROUND Although curative surgery remains the cornerstone of the therapeutic strategy in patients with soft tissue sarcomas (STS), neoadjuvant radiotherapy and chemotherapy (NART and NACT, respectively) are increasingly used to improve operability, surgical margins and patient outcome. The best imaging modality for locoregional assessment of STS is MRI but these tumors are mostly evaluated in a qualitative manner. OBJECTIVE After an overview of the current standard of care regarding treatment for patients with locally advanced STS, this review aims to summarize the principles and limitations of (i) the current methods used to evaluate response to neoadjuvant treatment in clinical practice and clinical trials in STS (RECIST 1.1 and modified Choi criteria), (ii) quantitative MRI sequences (i.e., diffusion weighted imaging and dynamic contrast enhanced MRI), and (iii) texture analyses and (delta-) radiomics.
Collapse
|
10
|
Yue Z, Wang X, Yu T, Shang S, Liu G, Jing W, Yang H, Luo Y, Jiang X. Multi-parametric MRI-based radiomics for the diagnosis of malignant soft-tissue tumor. Magn Reson Imaging 2022; 91:91-99. [PMID: 35525523 DOI: 10.1016/j.mri.2022.05.003] [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: 06/03/2021] [Revised: 03/31/2022] [Accepted: 05/01/2022] [Indexed: 10/18/2022]
Abstract
PURPOSE To develop and validate a multiparametric magnetic resonance imaging-based radiomics nomogram for differentiating malignant and benign soft-tissue tumors. METHODS A total of 91 patients with pathologically confirmed soft-tissue tumors were enrolled between January 2017 and October 2020. Forty-eight patients were consecutively enrolled between November 2020 and March 2022, as a time-independent cohort. All patients underwent contrast-enhanced T1-weighted and T2-weighted fat-suppression magnetic resonance scans at 3.0 T. Radiomics features were extracted and selected from the two modalities to develop the radiomics signature. Significant clinical/morphological characteristics were identified using a multivariate logistic regression analysis. The least absolute shrinkage and selection operator regression were applied to identify discriminative features. A clinical-radiomics nomogram was constructed based on clinical/morphological characteristics and radiomics features. Finally, the performance of the nomogram was validated using the receiver operating characteristic and decision curve analysis (DCA). RESULTS Six features were selected to establish the combined RS. Size, margin, and peritumoral edema were identified as the most important clinical and morphological factors, respectively. The radiomics signature outperformed the clinical model in terms of AUC and sensitivity. The nomogram integrating the combined RS, size, margin, and peritumoral edema achieved favorable predictive efficacy, generating AUCs of 0.954 (95% confidence interval [CI]: 0.907-1.000, Sen = 0.861, Spe = 0.917), 0.962 (95% CI: 0.901-1.000, Sen = 0.944, Spe = 0.923), and 0.935 (95% CI: 0.871-0.998, Sen = 0.815, Spe = 0.952) in the training (n = 60), validation (n = 31) and time-independent (n = 48) cohorts, respectively. The DCA curve indicated good clinical usefulness of the nomogram. CONCLUSIONS Our study demonstrated the clinical potential of multiparametric MRI-based radiomics in distinguishing malignant from benign soft-tissue tumors, which can be considered as a noninvasive tool for individual treatment management.
Collapse
Affiliation(s)
- Zhibin Yue
- Department of Biomedical Engineering, School of Fundamental Sciences, China Medical University, Shenyang 110122, PR China
| | - Xiaoyu Wang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang 110042, PR China
| | - Tao Yu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang 110042, PR China
| | - Shengjie Shang
- Department of Biomedical Engineering, School of Fundamental Sciences, China Medical University, Shenyang 110122, PR China
| | - Guanyu Liu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang 110042, PR China
| | - Wenwen Jing
- Department of Medical Microbiology and Parasitology, Shanghai Medical College of Fudan University, Shanghai 200032, PR China
| | - Huazhe Yang
- Department of Biophysics, School of Fundamental Sciences, China Medical University, Shenyang 110122, PR China
| | - Yahong Luo
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang 110042, PR China
| | - Xiran Jiang
- Department of Biomedical Engineering, School of Fundamental Sciences, China Medical University, Shenyang 110122, PR China.
| |
Collapse
|
11
|
Radiomic features as biomarkers of soft tissue paediatric sarcomas: preliminary results of a PET/MR study. Radiol Oncol 2022; 56:138-141. [PMID: 35344641 PMCID: PMC9122292 DOI: 10.2478/raon-2022-0013] [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: 11/19/2021] [Accepted: 03/04/2022] [Indexed: 11/20/2022] Open
Abstract
BACKGROUND Pediatric soft tissue sarcomas are rare tumors with rhabdomyosarcoma being the most frequent histotype. Diagnostic imaging plays a significant role in the evaluation of this type of tumors. Thus, aim of this study was to assess the prognostic and diagnostic value of radiomic features extracted from axial T2w images of the primary lesion in children with soft tissue sarcomas examined by PET/MR for staging. METHODS Using an open source software, each lesion was segmented and 33 radiomic features then extracted. Factor and logistic regression analyses were applied to select highly correlating features and evaluate their prognostic role, respectively. Differences in radiomic, demographics, metabolic, and laboratory variables according to tumor grade and histotype were investigated by the Students' and Chi-square tests. In case of differences the diagnostic value of the variable/s was assessed by receiver operating curves. RESULTS Eighteen children (11 female; mean age 7.8 ± 4.6-year-old) matched the inclusion criteria. The factor analysis allowed the selection of five highly correlating features which, according to regression analysis, did not influence the outcome (p > 0.05, each). The feature lmc1 was significantly higher in low grade lesions (p = 0.045) and showed 70.4% accuracy in classifying high grade tumors while the feature variance was significantly lower in rhabdomyosarcomas (p = 0.008) and showed 83.3% accuracy for this histotype. CONCLUSIONS In conclusion, our preliminary results suggest that specific radiomic features may act as biomarkers of pediatric soft tissue sarcoma grade and histotype.
Collapse
|
12
|
Peeken JC, Asadpour R, Specht K, Chen EY, Klymenko O, Akinkuoroye V, Hippe DS, Spraker MB, Schaub SK, Dapper H, Knebel C, Mayr NA, Gersing AS, Woodruff HC, Lambin P, Nyflot MJ, Combs SE. MRI-based delta-radiomics predicts pathologic complete response in high-grade soft-tissue sarcoma patients treated with neoadjuvant therapy. Radiother Oncol 2021; 164:73-82. [PMID: 34506832 DOI: 10.1016/j.radonc.2021.08.023] [Citation(s) in RCA: 33] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2021] [Revised: 08/15/2021] [Accepted: 08/27/2021] [Indexed: 02/09/2023]
Abstract
PURPOSE In high-grade soft-tissue sarcomas (STS) the standard of care encompasses multimodal therapy regimens. While there is a growing body of evidence for prognostic pretreatment radiomic models, we hypothesized that temporal changes in radiomic features following neoadjuvant treatment ("delta-radiomics") may be able to predict the pathological complete response (pCR). METHODS MRI scans (T1-weighted with fat-saturation and contrast-enhancement (T1FSGd) and T2-weighted with fat-saturation (T2FS)) of patients with STS of the extremities and trunk treated with neoadjuvant therapy were gathered from two independent institutions (training: 103, external testing: 53 patients). pCR was defined as <5% viable cells. After segmentation and preprocessing, 105 radiomic features were extracted. Delta-radiomic features were calculated by subtraction of features derived from MRI scans obtained before and after neoadjuvant therapy. After feature reduction, machine learning modeling was performed in 100 iterations of 3-fold nested cross-validation. Delta-radiomic models were compared with single timepoint models in the testing cohort. RESULTS The combined delta-radiomic models achieved the best area under the receiver operating characteristic curve (AUC) of 0.75. Pre-therapeutic tumor volume was the best conventional predictor (AUC 0.70). The T2FS-based delta-radiomic model had the most balanced classification performance with a balanced accuracy of 0.69. Delta-radiomic models achieved better reproducibility than single timepoint radiomic models, RECIST or the peri-therapeutic volume change. Delta-radiomic models were significantly associated with survival in multivariate Cox regression. CONCLUSION This exploratory analysis demonstrated that MRI-based delta-radiomics improves prediction of pCR over tumor volume and RECIST. Delta-radiomics may one day function as a biomarker for personalized treatment adaptations.
Collapse
Affiliation(s)
- Jan C Peeken
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany; Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Zentrum, München, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany; Department of Radiation Oncology, University of Washington, Seattle, United States; Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, The Netherlands.
| | - Rebecca Asadpour
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany
| | - Katja Specht
- Institute of Pathology, Technical University of Munich, Germany
| | - Eleanor Y Chen
- Department of Laboratory Medicine and Pathology, University of Washington, Seattle, United States
| | - Olena Klymenko
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany
| | - Victor Akinkuoroye
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany
| | - Daniel S Hippe
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, United States
| | - Matthew B Spraker
- Department of Radiation Oncology, Washington University in St. Louis, United States
| | - Stephanie K Schaub
- Department of Radiation Oncology, University of Washington, Seattle, United States
| | - Hendrik Dapper
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany
| | - Carolin Knebel
- Department of Orthopedics and Sports Orthopedics, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany
| | - Nina A Mayr
- Department of Radiation Oncology, University of Washington, Seattle, United States
| | - Alexandra S Gersing
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany
| | - Henry C Woodruff
- Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, The Netherlands; Department of Radiology and Nuclear Imaging, GROW- School for Oncology and Developmental Biology, Maastricht University Medical Centre, The Netherlands
| | - Philippe Lambin
- Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, The Netherlands; Department of Radiology and Nuclear Imaging, GROW- School for Oncology and Developmental Biology, Maastricht University Medical Centre, The Netherlands
| | - Matthew J Nyflot
- Department of Radiation Oncology, University of Washington, Seattle, United States; Department of Radiology, University of Washington, Seattle, United States
| | - Stephanie E Combs
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Germany; Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Zentrum, München, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
| |
Collapse
|
13
|
Crombé A, Cousin S, Spalato-Ceruso M, Le Loarer F, Toulmonde M, Michot A, Kind M, Stoeckle E, Italiano A. Implementing a Machine Learning Strategy to Predict Pathologic Response in Patients With Soft Tissue Sarcomas Treated With Neoadjuvant Chemotherapy. JCO Clin Cancer Inform 2021; 5:958-972. [PMID: 34524884 DOI: 10.1200/cci.21.00062] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
PURPOSE Neoadjuvant chemotherapy (NAC) has been increasingly used in patients with locally advanced high-risk soft tissue sarcomas in the past decade, but definition and prognostic impact of a good histologic response (GHR) are lacking. Our aim was to investigate which histologic feature from the post-NAC surgical specimen independently correlated with metastatic relapse-free survival (MFS) in combination with clinical, radiologic, and pathologic features using a machine learning approach. METHODS This retrospective study included 175 consecutive patients (median age: 59 years, 75 women) with resectable disease, treated with anthracycline-based NAC between 1989 and 2015 in our sarcoma reference center, and with quantitative histopathologic analysis of the surgical specimen. The outcome of interest was the MFS. A multimodel, multivariate survival analysis was used to define GHR. The added prognostic value of GHR was investigated through the comparisons with the standard model (including histologic grade, size, and depth) and SARCULATOR nomogram using concordance indices (c-index) and Monte-Carlo cross-validation. RESULTS Seventy-two patients (72 of 175, 41.1%) had a metastatic relapse. Stepwise Cox regression, random survival forests, and least absolute shrinkage and selection operator-penalized Cox regression all converged toward the same definition for GHR, ie, < 5% stainable tumor cells. The five-year MFS probability was 1 (95% CI, 1 to 1) in patients with GHR versus 0.73 (95% CI, 0.65 to 0.81) in patients without GHR (log-rank P = .0122). The final prognostic model incorporating the GHR was significantly better than the standard model and SARCULATOR (average c-index in testing sets = 0.72 [95% CI, 0.61 to 0.82] v 0.57 [95% CI, 0.44 to 0.70] and 0.54 [95% CI, 0.45 to 0.64], respectively; P = .0414 and .0091). CONCLUSION Histologic response to NAC improves the prediction of MFS in patients with soft tissue sarcoma and represents a possible end point in future studies exploring innovative regimens in the neoadjuvant setting.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Oncological Imaging, Institut Bergonié, Bordeaux, France.,Mathematical Modeling for Oncology Team, Inria Bordeaux Sud-Ouest, Talence, France.,Bordeaux University, Bordeaux, France
| | - Sophie Cousin
- Early Phase Trials and Sarcoma Units, Department of Medical Oncology, Institut Bergonié, Bordeaux, France
| | - Mariella Spalato-Ceruso
- Early Phase Trials and Sarcoma Units, Department of Medical Oncology, Institut Bergonié, Bordeaux, France
| | - François Le Loarer
- Bordeaux University, Bordeaux, France.,Department of Pathology, Institut Bergonié, Bordeaux, France
| | - Maud Toulmonde
- Early Phase Trials and Sarcoma Units, Department of Medical Oncology, Institut Bergonié, Bordeaux, France
| | - Audrey Michot
- Bordeaux University, Bordeaux, France.,Department of Oncologic Surgery, Institut Bergonié, Bordeaux, France
| | - Michèle Kind
- Department of Oncological Imaging, Institut Bergonié, Bordeaux, France
| | - Eberhard Stoeckle
- Department of Oncologic Surgery, Institut Bergonié, Bordeaux, France
| | - Antoine Italiano
- Bordeaux University, Bordeaux, France.,Early Phase Trials and Sarcoma Units, Department of Medical Oncology, Institut Bergonié, Bordeaux, France
| |
Collapse
|
14
|
Dionisio FCF, Oliveira LS, Hernandes MDA, Engel EE, de Azevedo-Marques PM, Nogueira-Barbosa MH. Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times. Radiol Bras 2021; 54:155-164. [PMID: 34108762 PMCID: PMC8177681 DOI: 10.1590/0100-3984.2020.0028] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
Objective To evaluate the degree of similarity between manual and semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging (MRI). Materials and Methods This was a retrospective study of 15 MRI examinations of patients with histopathologically confirmed soft-tissue sarcomas acquired before therapeutic intervention. Manual and semiautomatic segmentations were performed by three radiologists, working independently, using the software 3D Slicer. The Dice similarity coefficient (DSC) and the Hausdorff distance were calculated in order to evaluate the similarity between manual and semiautomatic segmentation. To compare the two modalities in terms of the tumor volumes obtained, we also calculated descriptive statistics and intraclass correlation coefficients (ICCs). Results In the comparison between manual and semiautomatic segmentation, the DSC values ranged from 0.871 to 0.973. The comparison of the volumes segmented by the two modalities resulted in ICCs between 0.9927 and 0.9990. The DSC values ranged from 0.849 to 0.979 for intraobserver variability and from 0.741 to 0.972 for interobserver variability. There was no significant difference between the semiautomatic and manual modalities in terms of the segmentation times (p > 0.05). Conclusion There appears to be a high degree of similarity between manual and semiautomatic segmentation, with no significant difference between the two modalities in terms of the time required for segmentation.
Collapse
Affiliation(s)
| | - Larissa Santos Oliveira
- Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo (HCFMRP-USP), Ribeirão Preto, SP, Brazil
| | - Mateus de Andrade Hernandes
- Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo (HCFMRP-USP), Ribeirão Preto, SP, Brazil
| | - Edgard Eduard Engel
- Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo (HCFMRP-USP), Ribeirão Preto, SP, Brazil
| | | | | |
Collapse
|
15
|
Navarro F, Dapper H, Asadpour R, Knebel C, Spraker MB, Schwarze V, Schaub SK, Mayr NA, Specht K, Woodruff HC, Lambin P, Gersing AS, Nyflot MJ, Menze BH, Combs SE, Peeken JC. Development and External Validation of Deep-Learning-Based Tumor Grading Models in Soft-Tissue Sarcoma Patients Using MR Imaging. Cancers (Basel) 2021; 13:2866. [PMID: 34201251 PMCID: PMC8227009 DOI: 10.3390/cancers13122866] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2021] [Revised: 05/27/2021] [Accepted: 06/02/2021] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND In patients with soft-tissue sarcomas, tumor grading constitutes a decisive factor to determine the best treatment decision. Tumor grading is obtained by pathological work-up after focal biopsies. Deep learning (DL)-based imaging analysis may pose an alternative way to characterize STS tissue. In this work, we sought to non-invasively differentiate tumor grading into low-grade (G1) and high-grade (G2/G3) STS using DL techniques based on MR-imaging. METHODS Contrast-enhanced T1-weighted fat-saturated (T1FSGd) MRI sequences and fat-saturated T2-weighted (T2FS) sequences were collected from two independent retrospective cohorts (training: 148 patients, testing: 158 patients). Tumor grading was determined following the French Federation of Cancer Centers Sarcoma Group in pre-therapeutic biopsies. DL models were developed using transfer learning based on the DenseNet 161 architecture. RESULTS The T1FSGd and T2FS-based DL models achieved area under the receiver operator characteristic curve (AUC) values of 0.75 and 0.76 on the test cohort, respectively. T1FSGd achieved the best F1-score of all models (0.90). The T2FS-based DL model was able to significantly risk-stratify for overall survival. Attention maps revealed relevant features within the tumor volume and in border regions. CONCLUSIONS MRI-based DL models are capable of predicting tumor grading with good reproducibility in external validation.
Collapse
Affiliation(s)
- Fernando Navarro
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (F.N.); (H.D.); (R.A.); (S.E.C.)
- Department of Informatics, Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching, Germany;
- TranslaTUM—Central Institute for Translational Cancer Research, Einsteinstraße 25, 81675 Munich, Germany
| | - Hendrik Dapper
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (F.N.); (H.D.); (R.A.); (S.E.C.)
| | - Rebecca Asadpour
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (F.N.); (H.D.); (R.A.); (S.E.C.)
| | - Carolin Knebel
- Department of Orthopedics and Sports Orthopedics, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany;
| | - Matthew B. Spraker
- Department of Radiation Oncology, Washington University in St. Louis, 4511 Forest Park Ave, St. Louis, MO 63108, USA;
| | - Vincent Schwarze
- Department of Radiology, Grosshadern Campus, Ludwig-Maximilians-University Munich, Marchioninistraße 15, 81377 Munich, Germany; (V.S.); (A.S.G.)
| | - Stephanie K. Schaub
- Department of Radiation Oncology, University of Washington, 1959 NE Pacific St, 356043, Seattle, WA 98195, USA; (S.K.S.); (N.A.M.); (M.J.N.)
| | - Nina A. Mayr
- Department of Radiation Oncology, University of Washington, 1959 NE Pacific St, 356043, Seattle, WA 98195, USA; (S.K.S.); (N.A.M.); (M.J.N.)
| | - Katja Specht
- Department of Pathology, Technical University of Munich (TUM), Trogerstr. 18, 81675 Munich, Germany;
| | - Henry C. Woodruff
- Department of Precision Medicine, GROW—School for Oncology and Developmental Biology, Maastricht University, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (H.C.W.); (P.L.)
- Department of Radiology and Nuclear Imaging, GROW—School for Oncology and Developmental Biology, P. Debyelaan 25, 6229 HX Maastricht, The Netherlands
| | - Philippe Lambin
- Department of Precision Medicine, GROW—School for Oncology and Developmental Biology, Maastricht University, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands; (H.C.W.); (P.L.)
- Department of Radiology and Nuclear Imaging, GROW—School for Oncology and Developmental Biology, P. Debyelaan 25, 6229 HX Maastricht, The Netherlands
| | - Alexandra S. Gersing
- Department of Radiology, Grosshadern Campus, Ludwig-Maximilians-University Munich, Marchioninistraße 15, 81377 Munich, Germany; (V.S.); (A.S.G.)
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Matthew J. Nyflot
- Department of Radiation Oncology, University of Washington, 1959 NE Pacific St, 356043, Seattle, WA 98195, USA; (S.K.S.); (N.A.M.); (M.J.N.)
- Department of Radiology, University of Washington, 4245 Roosevelt Way NE, Seattle, WA 98105, USA
| | - Bjoern H. Menze
- Department of Informatics, Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching, Germany;
- Department for Quantitative Biomedicine, University of Zurich, Winterthurerstrasse 190, CH-8057 Zurich, Switzerland
| | - Stephanie E. Combs
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (F.N.); (H.D.); (R.A.); (S.E.C.)
- Department for Quantitative Biomedicine, University of Zurich, Winterthurerstrasse 190, CH-8057 Zurich, Switzerland
- Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Ingolstaedter Landstr. 1, 85764 Munich, Germany
| | - Jan C. Peeken
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (F.N.); (H.D.); (R.A.); (S.E.C.)
- Department of Radiology and Nuclear Imaging, GROW—School for Oncology and Developmental Biology, P. Debyelaan 25, 6229 HX Maastricht, The Netherlands
- Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Ingolstaedter Landstr. 1, 85764 Munich, Germany
- Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site, 85764 Munich, Germany
| |
Collapse
|
16
|
Gitto S, Cuocolo R, Albano D, Morelli F, Pescatori LC, Messina C, Imbriaco M, Sconfienza LM. CT and MRI radiomics of bone and soft-tissue sarcomas: a systematic review of reproducibility and validation strategies. Insights Imaging 2021; 12:68. [PMID: 34076740 PMCID: PMC8172744 DOI: 10.1186/s13244-021-01008-3] [Citation(s) in RCA: 35] [Impact Index Per Article: 11.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2021] [Accepted: 05/05/2021] [Indexed: 02/07/2023] Open
Abstract
Background Feature reproducibility and model validation are two main challenges of radiomics. This study aims to systematically review radiomic feature reproducibility and predictive model validation strategies in studies dealing with CT and MRI radiomics of bone and soft-tissue sarcomas. The ultimate goal is to promote achieving a consensus on these aspects in radiomic workflows and facilitate clinical transferability. Results Out of 278 identified papers, forty-nine papers published between 2008 and 2020 were included. They dealt with radiomics of bone (n = 12) or soft-tissue (n = 37) tumors. Eighteen (37%) studies included a feature reproducibility analysis. Inter-/intra-reader segmentation variability was the theme of reproducibility analysis in 16 (33%) investigations, outnumbering the analyses focused on image acquisition or post-processing (n = 2, 4%). The intraclass correlation coefficient was the most commonly used statistical method to assess reproducibility, which ranged from 0.6 and 0.9. At least one machine learning validation technique was used for model development in 25 (51%) papers, and K-fold cross-validation was the most commonly employed. A clinical validation of the model was reported in 19 (39%) papers. It was performed using a separate dataset from the primary institution (i.e., internal validation) in 14 (29%) studies and an independent dataset related to different scanners or from another institution (i.e., independent validation) in 5 (10%) studies. Conclusions The issues of radiomic feature reproducibility and model validation varied largely among the studies dealing with musculoskeletal sarcomas and should be addressed in future investigations to bring the field of radiomics from a preclinical research area to the clinical stage.
Collapse
Affiliation(s)
- Salvatore Gitto
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Riccardo Galeazzi 4, 20161, Milan, Italy.
| | - Renato Cuocolo
- Dipartimento di Medicina Clinica e Chirurgia, Università degli Studi di Napoli "Federico II", Naples, Italy.,Laboratory of Augmented Reality for Health Monitoring (ARHeMLab), Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione, Università degli Studi di Napoli "Federico II", Naples, Italy
| | - Domenico Albano
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy.,Sezione di Scienze Radiologiche, Dipartimento di Biomedicina, Neuroscienze e Diagnostica Avanzata, Università degli Studi di Palermo, Palermo, Italy
| | | | - Lorenzo Carlo Pescatori
- Assistance Publique - Hôpitaux de Paris (AP-HP), Service d'Imagerie Médicale, CHU Henri Mondor, Créteil, France
| | - Carmelo Messina
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Riccardo Galeazzi 4, 20161, Milan, Italy.,IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
| | - Massimo Imbriaco
- Dipartimento di Scienze Biomediche Avanzate, Università degli Studi di Napoli "Federico II", Naples, Italy
| | - Luca Maria Sconfienza
- Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Via Riccardo Galeazzi 4, 20161, Milan, Italy.,IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
| |
Collapse
|
17
|
Crombé A, Kind M, Fadli D, Le Loarer F, Italiano A, Buy X, Saut O. Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients. Sci Rep 2020; 10:15496. [PMID: 32968131 PMCID: PMC7511974 DOI: 10.1038/s41598-020-72535-0] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2020] [Accepted: 08/24/2020] [Indexed: 12/12/2022] Open
Abstract
Intensity harmonization techniques (IHT) are mandatory to homogenize multicentric MRIs before any quantitative analysis because signal intensities (SI) do not have standardized units. Radiomics combine quantification of tumors' radiological phenotype with machine-learning to improve predictive models, such as metastastic-relapse-free survival (MFS) for sarcoma patients. We post-processed the initial T2-weighted-imaging of 70 sarcoma patients by using 5 IHTs and extracting 45 radiomics features (RFs), namely: classical standardization (IHTstd), standardization per adipose tissue SIs (IHTfat), histogram-matching with a patient histogram (IHTHM.1), with the average histogram of the population (IHTHM.All) and plus ComBat method (IHTHM.All.C), which provided 5 radiomics datasets in addition to the original radiomics dataset without IHT (No-IHT). We found that using IHTs significantly influenced all RFs values (p-values: < 0.0001-0.02). Unsupervised clustering performed on each radiomics dataset showed that only clusters from the No-IHT, IHTstd, IHTHM.All, and IHTHM.All.C datasets significantly correlated with MFS in multivariate Cox models (p = 0.02, 0.007, 0.004 and 0.02, respectively). We built radiomics-based supervised models to predict metastatic relapse at 2-years with a training set of 50 patients. The models performances varied markedly depending on the IHT in the validation set (range of AUROC from 0.688 with IHTstd to 0.823 with IHTHM.1). Hence, the use of intensity harmonization and the related technique should be carefully detailed in radiomics post-processing pipelines as it can profoundly affect the reproducibility of analyses.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Radiology, Institut Bergonie, 33000, Bordeaux, France. .,Modelisation in Oncology (MOnc) Team, INRIA Bordeaux-Sud-Ouest, CNRS UMR 5251, Université de Bordeaux, 33405, Talence, France. .,University of Bordeaux, 33000, Bordeaux, France. .,Department of Diagnostic and Interventional Radiology, Institut Bergonié, Comprehensive Cancer Center of Nouvelle-Aquitaine, 229 cours de l'Argonne, 33000, Bordeaux, France.
| | - Michèle Kind
- Department of Radiology, Institut Bergonie, 33000, Bordeaux, France
| | - David Fadli
- Department of Radiology, Institut Bergonie, 33000, Bordeaux, France
| | - François Le Loarer
- University of Bordeaux, 33000, Bordeaux, France.,Department of Pathology, Institut Bergonie, 33000, Bordeaux, France
| | - Antoine Italiano
- University of Bordeaux, 33000, Bordeaux, France.,Department of Medical Oncology, Institut Bergonie, 33000, Bordeaux, France
| | - Xavier Buy
- Department of Radiology, Institut Bergonie, 33000, Bordeaux, France
| | - Olivier Saut
- Modelisation in Oncology (MOnc) Team, INRIA Bordeaux-Sud-Ouest, CNRS UMR 5251, Université de Bordeaux, 33405, Talence, France.,University of Bordeaux, 33000, Bordeaux, France
| |
Collapse
|
18
|
Crombé A, Fadli D, Italiano A, Saut O, Buy X, Kind M. Systematic review of sarcomas radiomics studies: Bridging the gap between concepts and clinical applications? Eur J Radiol 2020; 132:109283. [PMID: 32980727 DOI: 10.1016/j.ejrad.2020.109283] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2020] [Revised: 08/29/2020] [Accepted: 09/08/2020] [Indexed: 12/12/2022]
Abstract
OBJECTIVES Sarcomas are a model for intra- and inter-tumoral heterogeneities making them particularly suitable for radiomics analyses. Our purposes were to review the aims, methods and results of radiomics studies involving sarcomas METHODS: Pubmed and Web of Sciences databases were searched for radiomics or textural studies involving bone, soft-tissues and visceral sarcomas until June 2020. Two radiologists evaluated their objectives, results and quality of their methods, imaging pre-processing and machine-learning workflow helped by the items of the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2), Image Biomarker Standardization Initiative (IBSI) and 'Radiomics Quality Score' (RQS). Statistical analyses included inter-reader agreements, correlations between methodological assessments, scientometrics indices, and their changes over years, and between RQS, number of patients and models performance. RESULTS Fifty-two studies were included involving: soft-tissue sarcomas (29/52, 55.8 %), bone sarcomas (15/52, 28.8 %), gynecological sarcomas (6/52, 11.5 %) and mixed sarcomas (2/52, 3.8 %), mostly imaged with MRI (36/52, 69.2 %), for a total of distinct patients. Median RQS was 4.5 (28.4 % of the maximum, range: -7 - 17). Performances of predictive models and number of patients negatively correlated (p = 0.027). None of the studies detailed all the items from the IBSI guidelines. There was a significant increase in studies' impact factors since the establishing of the RQS in 2017 (p = 0.038). CONCLUSION Although showing promising results, further efforts are needed to make sarcoma radiomics studies reproducible with an acceptable level of evidence. A better knowledge of the RQS and IBSI reporting guidelines could improve the quality of sarcoma radiomics studies and accelerate clinical applications.
Collapse
Affiliation(s)
- Amandine Crombé
- Department of Radiology, Institut Bergonie, F-33000, Bordeaux, France; Modelisation in Oncology (MOnc) Team, INRIA Bordeaux-Sud-Ouest, CNRS UMR 5251, Université De Bordeaux, F-33405, Talence, France; University of Bordeaux, F-33000, Bordeaux, France.
| | - David Fadli
- Department of Radiology, Institut Bergonie, F-33000, Bordeaux, France
| | - Antoine Italiano
- University of Bordeaux, F-33000, Bordeaux, France; Department of Medical Oncology, Institut Bergonie, F-33000, Bordeaux, France
| | - Olivier Saut
- Modelisation in Oncology (MOnc) Team, INRIA Bordeaux-Sud-Ouest, CNRS UMR 5251, Université De Bordeaux, F-33405, Talence, France
| | - Xavier Buy
- Department of Radiology, Institut Bergonie, F-33000, Bordeaux, France
| | - Michèle Kind
- Department of Radiology, Institut Bergonie, F-33000, Bordeaux, France
| |
Collapse
|
19
|
Razek AAKA. Editorial for “Preoperative
MRI
‐Based Radiomic Machine‐Learning Nomogram May Accurately Distinguish Between Benign and Malignant Soft Tissue Lesions: A Two‐Center Study”. J Magn Reson Imaging 2020; 52:883-884. [DOI: 10.1002/jmri.27163] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2020] [Accepted: 03/25/2020] [Indexed: 12/13/2022] Open
|