High-grade soft-tissue sarcoma: optimizing injection improves MRI evaluation of tumor response

Predicting Soft Tissue Sarcoma Response to Neoadjuvant Chemotherapy Using an MRI-Based Delta-Radiomics Approach

OBJECTIVES

To evaluate the performance of machine learning-augmented MRI-based radiomics models for predicting response to neoadjuvant chemotherapy (NAC) in soft tissue sarcomas.

METHODS

Forty-four subjects were identified retrospectively from patients who received NAC at our institution for pathologically proven soft tissue sarcomas. Only subjects who had both a baseline MRI prior to initiating chemotherapy and a post-treatment scan at least 2 months after initiating chemotherapy and prior to surgical resection were included. 3D ROIs were used to delineate whole-tumor volumes on pre- and post-treatment scans, from which 1708 radiomics features were extracted. Delta-radiomics features were calculated by subtraction of baseline from post-treatment values and used to distinguish treatment response through univariate analyses as well as machine learning-augmented radiomics analyses.

RESULTS

Though only 4.74% of variables overall reached significance at p ≤ 0.05 in univariate analyses, Laws Texture Energy (LTE)-derived metrics represented 46.04% of all such features reaching statistical significance. ROC analyses similarly failed to predict NAC response, with AUCs of 0.40 (95% CI 0.22-0.58) and 0.44 (95% CI 0.26-0.62) for RF and AdaBoost, respectively.

CONCLUSION

Overall, while our result was not able to separate NAC responders from non-responders, our analyses did identify a subset of LTE-derived metrics that show promise for further investigations. Future studies will likely benefit from larger sample size constructions so as to avoid the need for data filtering and feature selection techniques, which have the potential to significantly bias the machine learning procedures.

Correlation of radiological and histopathological response after neoadjuvant radiotherapy in soft tissue sarcoma

BACKGROUND

The aim of this study was to assess the association between radiological and histopathological response after neoadjuvant radiotherapy (nRT) in soft tissue sarcoma (STS), as well as the prognostic value of the different response evaluation methods on the oncological outcome.

METHODS

A retrospective cohort of patients with localized STS of the extremity and trunk wall, treated with nRT followed by resection were included. The radiological response was assessed by RECIST 1.1 (RECIST) and MR-adapted Choi (Choi), histopathologic response was evaluated according to the EORTC-STBSG recommendations. Oncological outcome parameters of interest were local recurrence-free survival (LRFS), disease metastases-free survival (DMFS), and overall survival (OS).

RESULTS

For 107 patients, complete pre- and postoperative pathology and imaging datasets were available. Most tumors were high-grade (77%) and the most common histological subtypes were undifferentiated pleomorphic sarcoma/not otherwise specified (UPS/NOS, 40%), myxoid liposarcoma (MLS, 21%) and myxofibrosarcoma (MFS, 16%). When comparing RECIST to Choi, the response was differently categorized in 58%, with a higher response rate (CR + PR) with Choi. Radiological responders showed a significant lower median percentage of viable cells (RECIST p = .050, Choi p = .015) and necrosis (RECIST p < .001), and a higher median percentage of fibrosis (RECIST p = .005, Choi p = .008), compared to radiological non-responders (SD + PD). RECIST, Choi, fibrosis, and viable cells were not significantly associated with altered oncological outcome, more necrosis was associated with poorer OS (p = .038).

CONCLUSION

RECIST, Choi and the EORTC-STBSG response score show incongruent results in response evaluation. The radiological response was significantly correlated with a lower percentage of viable cells and necrosis, but a higher percentage of fibrosis. Apart from necrosis, radiological nor other histopathological parameters were associated with oncologic outcomes.

Soft Tissue Sarcomas: The Role of Quantitative MRI in Treatment Response Evaluation

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.

Radiomics of Musculoskeletal Sarcomas: A Narrative Review

Bone and soft-tissue primary malignant tumors or sarcomas are a large, diverse group of mesenchymal-derived malignancies. They represent a model for intra- and intertumoral heterogeneities, making them particularly suitable for radiomics analyses. Radiomic features offer information on cancer phenotype as well as the tumor microenvironment which, combined with other pertinent data such as genomics and proteomics and correlated with outcomes data, can produce accurate, robust, evidence-based, clinical-decision support systems. Our purpose in this narrative review is to offer an overview of radiomics studies dealing with Magnetic Resonance Imaging (MRI)-based radiomics models of bone and soft-tissue sarcomas that could help distinguish different histotypes, low-grade from high-grade sarcomas, predict response to multimodality therapy, and thus better tailor patients’ treatments and finally improve their survivals. Although showing promising results, interobserver segmentation variability, feature reproducibility, and model validation are three main challenges of radiomics that need to be addressed in order to translate radiomics studies to clinical applications. These efforts, together with a better knowledge and application of the “Radiomics Quality Score” and Image Biomarker Standardization Initiative reporting guidelines, could improve the quality of sarcoma radiomics studies and facilitate radiomics towards clinical translation.

Implementing a Machine Learning Strategy to Predict Pathologic Response in Patients With Soft Tissue Sarcomas Treated With Neoadjuvant Chemotherapy

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.

Imaging response evaluation after neoadjuvant treatment in soft tissue sarcomas: Where do we stand?

Soft tissue sarcomas (STS) represent a broad family of rare tumours for which surgery with radiotherapy represents first-line treatment. Recently, neoadjuvant chemo-radiotherapy has been increasingly used in high-risk patients in an effort to reduce surgical morbidity and improve clinical outcomes. An adequate understanding of the efficacy of neoadjuvant therapies would optimise patient care, allowing a tailored approach. Although response evaluation criteria in solid tumours (RECIST) is the most common imaging method to assess tumour response, Choi criteria and functional and molecular imaging (DWI, DCE-MRI and ¹⁸F-FDG-PET) seem to outperform it in the discrimination between responders and non-responders. Moreover, the radiologic-pathology correlation of treatment-related changes remains poorly understood. In this review, we provide an overview of the imaging assessment of tumour response in STS undergoing neoadjuvant treatment, including conventional imaging (CT, MRI, PET) and advanced imaging analysis. Future directions will be presented to shed light on potential advances in pre-surgical imaging assessments that have clinical implications for sarcoma patients.

Magnetic resonance imaging assessment of chemotherapy-related adipocytic maturation in myxoid/round cell liposarcomas: specificity and prognostic value

OBJECTIVE

To investigate the specificity, clinical implication and prognostic value of MRI adipocytic maturation (MAM) in myxoid/round cells liposarcomas (MRC-LPS) treated with neoadjuvant chemotherapy (NAC).

METHODS

Of the 89 patients diagnosed with MRC-LPS at our sarcoma reference center between 2008 and 2018, 28 were included as they were treated with NAC, surgery and radiotherapy. All patients underwent contrast-enhanced MRIs at baseline and late evaluation. A control cohort of 13 high-grade pleomorphic and dedifferentiated LPS with same inclusion criteria was used to evaluate the specificity of MAM in MRC-LPS. Two radiologists analyzed the occurrence of MAM, changes in the tumor architecture, shape and surrounding tissues during NAC. Pathological features of tumor samples were reviewed and correlated with MRI. Metastatic relapse-free survival was estimated with Kaplan-Meier curves and Cox models. Associations between prognostic T1-based delta-radiomics features and MAM were investigated with Student t-test.

RESULTS

MAM was more frequent in MRC-LPS (p = 0.045) and not specific of any type of chemotherapy (p = 0.7). Regarding MRC-LPS, 14 out of 28 patients (50%) demonstrated MAM. Eight patients showed metastatic relapses. MAM was not associated with metastatic relapse-free survival (p = 0.9). MAM correlated strongly with the percentage of histological adipocytic differentiation on surgical specimen (p < 0.001), which still expressed the tumor marker NY-ESO-1. None of the prognostic T1-based delta-radiomics features was associated with MAM.

CONCLUSION

MAM seems a neutral event during NAC.

ADVANCES IN KNOWLEDGE

MAM predominated in MRC-LPS and was not specific of a type of chemotherapy. Occurrence of MAM was not associated with better patients' metastasis free survival.

Can radiomics improve the prediction of metastatic relapse of myxoid/round cell liposarcomas?

OBJECTIVE

The strongest adverse prognostic factor in myxoid/round cell liposarcomas (MRC-LPS) is the presence of a round cell component above 5% within the tumor bulk. Its identification is underestimated on biopsies and in the neoadjuvant setting. The aim was to improve the prediction of patients' prognosis through a radiomics approach.

METHODS

Thirty-five out of 89 patients with MRC-LPS managed at our sarcoma reference center from 2008 to 2017 were included in this IRB-approved retrospective study as they presented with a pre-treatment contrast-enhanced MRI (median age, 49 years old). Two radiologists reported usual conventional/semantic radiological variables. After signal intensity (SI) normalization, voxel size standardization of T2-WI, and whole tumor volume segmentation, 44 3D-radiomics features were extracted. Using least absolute shrinkage and selection operator penalized Cox regression on prefiltered features, a radiomics score based on 3 weighted radiomics features was generated. Four prognostic multivariate models for MRFS were compared using concordance index: (1) clinical model, (2) semantic radiological model, (3) radiomics model, and (4) radiomics + semantic radiological model.

RESULTS

Twelve patients showed a metastatic relapse. The radiomics score included FOS_Skewness, GLRLM_LRHGE, and SHAPE_Volume and correlated with MRFS (hazard ratio = 19.37, p = 0.0009) and visual heterogeneity on T2-WI (p < 0.0001). A high score indicated a poorer prognosis. After adjustment, the best predictive performances were obtained with model (4) (concordance index = 0.937) and the lowest with model (1) (concordance index = 0.637).

CONCLUSION

Adding selected radiomics features that quantify tumor heterogeneity and shape at baseline to a conventional radiological analysis improves prediction of MRC-LPS patients' prognosis.

KEY POINTS

• Fourteen radiomics features quantifying shape and heterogeneity of myxoid/round cell liposarcomas on T2-WI were associated with metastatic relapse in univariate analysis. • A radiomics score based on 3 selected and weighted radiomics features was a strong and independent prognostic factor for metastatic relapse-free survival. • The best prediction of metastatic relapse-free survival for myxoid/round cell liposarcomas was achieved by combining the radiomics score to relevant radiological features.