Tumor grading of soft tissue sarcomas using MRI-based radiomics

Imaging at the nexus: how state of the art imaging techniques can enhance our understanding of cancer and fibrosis

Both cancer and fibrosis are diseases involving dysregulation of cell signaling pathways resulting in an altered cellular microenvironment which ultimately leads to progression of the condition. The two disease entities share common molecular pathophysiology and recent research has illuminated the how each promotes the other. Multiple imaging techniques have been developed to aid in the early and accurate diagnosis of each disease, and given the commonalities between the pathophysiology of the conditions, advances in imaging one disease have opened new avenues to study the other. Here, we detail the most up-to-date advances in imaging techniques for each disease and how they have crossed over to improve detection and monitoring of the other. We explore techniques in positron emission tomography (PET), magnetic resonance imaging (MRI), second generation harmonic Imaging (SGHI), ultrasound (US), radiomics, and artificial intelligence (AI). A new diagnostic imaging tool in PET/computed tomography (CT) is the use of radiolabeled fibroblast activation protein inhibitor (FAPI). SGHI uses high-frequency sound waves to penetrate deeper into the tissue, providing a more detailed view of the tumor microenvironment. Artificial intelligence with the aid of advanced deep learning (DL) algorithms has been highly effective in training computer systems to diagnose and classify neoplastic lesions in multiple organs. Ultimately, advancing imaging techniques in cancer and fibrosis can lead to significantly more timely and accurate diagnoses of both diseases resulting in better patient outcomes.

Integration of pre-treatment computational radiomics, deep radiomics, and transcriptomics enhances soft-tissue sarcoma patient prognosis

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.

Inferring malignancy grade of soft tissue sarcomas from magnetic resonance imaging features: A systematic review

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.

MRI- and DWI-Based Radiomics Features for Preoperatively Predicting Meningioma Sinus Invasion

The aim of this study was to use multimodal imaging (contrast-enhanced T1-weighted (T1C), T2-weighted (T2), and diffusion-weighted imaging (DWI)) to develop a radiomics model for preoperatively predicting venous sinus invasion in meningiomas. This prediction would assist in selecting the appropriate surgical approach and forecasting the prognosis of meningiomas. A retrospective analysis was conducted on 331 participants who had been pathologically diagnosed with meningiomas. For each participant, 3948 radiomics features were acquired from the T1C, T2, and DWI images. Minimum redundancy maximum correlation, rank sum test, and multi-factor recursive elimination were used to extract the most significant features of different models. Then, multivariate logistic regression was used to build classification models to predict meningioma venous sinus invasion. The diagnostic capabilities were assessed using receiver operating characteristic (ROC) analysis. In addition, a nomogram was constructed by incorporating clinical and radiological characteristics and a radiomics signature. To assess the clinical usefulness of the nomogram, a decision curve analysis (DCA) was performed. Tumor shape, boundary, and enhancement features were independent predictors of meningioma venous sinus invasion (p = 0.013, p = 0.013, p = 0.005, respectively). Eleven (T2:1, T1C:4, DWI:6) of the 3948 radiomics features were screened for strong association with meningioma sinus invasion. The areas under the ROC curves for the training and external test sets were 0.946 and 0.874, respectively. The clinicoradiomic model showed excellent predictive performance for invasive meningioma, which may help to guide surgical approaches and predict prognosis.

Preoperative Classification of Peripheral Nerve Sheath Tumors on MRI Using Radiomics

Malignant peripheral nerve sheath tumors (MPNSTs) are aggressive soft-tissue tumors prevalent in neurofibromatosis type 1 (NF1) patients, posing a significant risk of metastasis and recurrence. Current magnetic resonance imaging (MRI) imaging lacks decisiveness in distinguishing benign peripheral nerve sheath tumors (BPNSTs) and MPNSTs, necessitating invasive biopsies. This study aims to develop a radiomics model using quantitative imaging features and machine learning to distinguish MPNSTs from BPNSTs. Clinical data and MRIs from MPNST and BPNST patients (2000-2019) were collected at a tertiary sarcoma referral center. Lesions were manually and semi-automatically segmented on MRI scans, and radiomics features were extracted using the Workflow for Optimal Radiomics Classification (WORC) algorithm, employing automated machine learning. The evaluation was conducted using a 100× random-split cross-validation. A total of 35 MPNSTs and 74 BPNSTs were included. The T1-weighted (T1w) MRI radiomics model outperformed others with an area under the curve (AUC) of 0.71. The incorporation of additional MRI scans did not enhance performance. Combining T1w MRI with clinical features achieved an AUC of 0.74. Experienced radiologists achieved AUCs of 0.75 and 0.66, respectively. Radiomics based on T1w MRI scans and clinical features show some ability to distinguish MPNSTs from BPNSTs, potentially aiding in the management of these tumors.

Development and benchmarking of a Deep Learning-based MRI-guided gross tumor segmentation algorithm for Radiomics analyses in extremity soft tissue sarcomas

BACKGROUND

Volume of interest (VOI) segmentation is a crucial step for Radiomics analyses and radiotherapy (RT) treatment planning. Because it can be time-consuming and subject to inter-observer variability, we developed and tested a Deep Learning-based automatic segmentation (DLBAS) algorithm to reproducibly predict the primary gross tumor as VOI for Radiomics analyses in extremity soft tissue sarcomas (STS).

METHODS

A DLBAS algorithm was trained on a cohort of 157 patients and externally tested on an independent cohort of 87 patients using contrast-enhanced MRI. Manual tumor delineations by a radiation oncologist served as ground truths (GTs). A benchmark study with 20 cases from the test cohort compared the DLBAS predictions against manual VOI segmentations of two residents (ERs) and clinical delineations of two radiation oncologists (ROs). The ROs rated DLBAS predictions regarding their direct applicability.

RESULTS

The DLBAS achieved a median dice similarity coefficient (DSC) of 0.88 against the GTs in the entire test cohort (interquartile range (IQR): 0.11) and a median DSC of 0.89 (IQR 0.07) and 0.82 (IQR 0.10) in comparison to ERs and ROs, respectively. Radiomics feature stability was high with a median intraclass correlation coefficient of 0.97, 0.95 and 0.94 for GTs, ERs, and ROs, respectively. DLBAS predictions were deemed clinically suitable by the two ROs in 35% and 20% of cases, respectively.

CONCLUSION

The results demonstrate that the DLBAS algorithm provides reproducible VOI predictions for radiomics feature extraction. Variability remains regarding direct clinical applicability of predictions for RT treatment planning.

Radiomics in Diagnosis, Grading, and Treatment Response Assessment of Soft Tissue Sarcomas: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance.

METHODS

In this diagnostic accuracy study, radiomics was applied using multiple MRI sequences and AI classifiers, with histopathological diagnosis as the reference standard. Statistical analysis involved meta-analysis, random-effects model, and Deeks' funnel plot asymmetry test.

RESULTS

Among 579 unique titles and abstracts, 24 articles were included in the systematic review, with 21 used for meta-analysis. Radiomics demonstrated a pooled sensitivity of 84% (95% CI: 80-87) and specificity of 63% (95% CI: 56-70), AUC of 0.93 for diagnosis, sensitivity of 84% (95% CI: 82-87) and specificity of 73% (95% CI: 68-77), AUC of 0.91 for grading, and sensitivity of 83% (95% CI: 67-94) and specificity of 67% (95% CI: 59-74), AUC of 0.87 for treatment response assessment.

CONCLUSION

Radiomics exhibits potential for accurate diagnosis, grading, and treatment response assessment in STSs, emphasizing the need for standardization and prospective trials.

CLINICAL RELEVANCE STATEMENT

Radiomics offers precise tools for STS diagnosis, grading, and treatment response assessment, with implications for optimizing patient care and treatment strategies in this complex malignancy.

Multi-institutional validation of a radiomics signature for identification of postoperative progression of soft tissue sarcoma

BACKGROUND

To develop a magnetic resonance imaging (MRI)-based radiomics signature for evaluating the risk of soft tissue sarcoma (STS) disease progression.

METHODS

We retrospectively enrolled 335 patients with STS (training, validation, and The Cancer Imaging Archive sets, n = 168, n = 123, and n = 44, respectively) who underwent surgical resection. Regions of interest were manually delineated using two MRI sequences. Among 12 machine learning-predicted signatures, the best signature was selected, and its prediction score was inputted into Cox regression analysis to build the radiomics signature. A nomogram was created by combining the radiomics signature with a clinical model constructed using MRI and clinical features. Progression-free survival was analyzed in all patients. We assessed performance and clinical utility of the models with reference to the time-dependent receiver operating characteristic curve, area under the curve, concordance index, integrated Brier score, decision curve analysis.

RESULTS

For the combined features subset, the minimum redundancy maximum relevance-least absolute shrinkage and selection operator regression algorithm + decision tree classifier had the best prediction performance. The radiomics signature based on the optimal machine learning-predicted signature, and built using Cox regression analysis, had greater prognostic capability and lower error than the nomogram and clinical model (concordance index, 0.758 and 0.812; area under the curve, 0.724 and 0.757; integrated Brier score, 0.080 and 0.143, in the validation and The Cancer Imaging Archive sets, respectively). The optimal cutoff was - 0.03 and cumulative risk rates were calculated.

DATA CONCLUSION

To assess the risk of STS progression, the radiomics signature may have better prognostic power than a nomogram/clinical model.

Evaluation of AJCC staging system and proposal of a novel stage grouping system in retroperitoneal liposarcoma: the Fudan Zhongshan experience

Background

Overall survival (OS) varies significantly among individuals with heterogeneous retroperitoneal liposarcoma (RPLS), even among those with the same clinical stage. Improved staging of RPLS is a critical unmet need, given the disappointing results of external validations of the 8th American Joint Committee on Cancer (AJCC) TNM staging system.

Methods

The cohort study included 220 consecutive patients who underwent surgical resection for primary RPLS at the largest sarcoma centre of Fudan University in China from September 2009 to August 2021, combined with 277 adult patients with RPLS in the SEER database from 1975 to 2020. Data analysis was performed from December 2021 to December 2022. Patients were retrospectively restaged according to the 8th and 7th editions of the TNM staging system as well as the new TNM (nTNM) staging system. The primary endpoint was overall survival (OS). Comparative analysis of postoperative survival was performed using the Kaplan-Meier method, and differences between subgroups were tested using the log-rank test. The OS prediction nomogram was generated based on baseline variables and tumour characteristics. Harrell's consistency index (C-index), area under the curve (AUC) of receiver operating characteristic curves (ROC), and calibration curves were used to evaluate the performance of the nomogram.

Results

A total of 497 patients were enrolled in the study, including 282 (56.7%) male patients. The median follow-up was 51 months (interquartile range, IQR, 23-83), and the OS rates at 1, 3, and 5 years were 87.9%, 75.3%, and 64.9%, respectively. According to the staging distribution of the AJCC 7th edition, 6 patients were stage IA (1.2%), 189 patients were stage IB (38%), 12 patients were stage IIA (2.4%), 150 patients were stage IIB (30.1%), 131 patients were stage III (26.3%), and 9 patients were stage IV (1.8%). With the 8th edition staging, this distribution changed: 6 patients (1.2%) were stage IA, 189 patients (38%) were stage IB, 12 patients (2.4%) were stage II, 24 patients (4.8%) were stage IIIA, 257 patients (51.7%) were stage IIIB, and 9 patients (1.8%) were stage IV. 182 patients (36.6%) were reclassified according to the nTNM staging system with the new T stage classification. The C-index and log-rank score improved after implementation of nTNM implementation. The nTNM system was associated with improved identification of high-risk patients compared with the AJCC 7th and 8th TNM. The FNCLCC stage proved to be highly prognostic with significant intergroup differences in OS. The calibration curve shows a high degree of agreement between the actual OS rate and the nomogram estimated OS rate.

Conclusion

Compared with 8th AJCC TNM, 7th AJCC TNM staging system showed a more homogeneous staging distribution and a slight improvement in the prognostic accuracy of RPLS. The revised T-stage and nTNM systems showed better risk stratification performance. The FNCLCC stage was found to have high prognostic value, further emphasising histological grade is the least negligible prognostic factor in predicting patient survival. The constructed nomogram model enables individualized prognostic analysis and helps to develop risk-adapted therapy for RPLS patients.

The impact of radiomics in the management of soft tissue sarcoma

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.

MRI-Based Radiomics Methods for Predicting Ki-67 Expression in Breast Cancer: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

The purpose of this systematic review and meta-analysis was to assess the quality and diagnostic accuracy of MRI-based radiomics for predicting Ki-67 expression in breast cancer.

MATERIALS AND METHODS

A systematic literature search was performed to find relevant studies published in different databases, including PubMed, Web of Science, and Embase up until March 10, 2023. All papers were independently evaluated for eligibility by two reviewers. Studies that matched research questions and provided sufficient data for quantitative synthesis were included in the systematic review and meta-analysis, respectively. The quality of the articles was assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) and Radiomics Quality Score (RQS) tools. The predictive value of MRI-based radiomics for Ki-67 antigen in patients with breast cancer was assessed using pooled sensitivity (SEN), specificity, and area under the curve (AUC). Meta-regression was performed to explore the cause of heterogeneity. Different covariates were used for subgroup analysis.

RESULTS

31 studies were included in the systematic review; among them, 21 reported sufficient data for meta-analysis. 20 training cohorts and five validation cohorts were pooled separately. The pooled sensitivity, specificity, and AUC of MRI-based radiomics for predicting Ki-67 expression in training cohorts were 0.80 [95% CI, 0.73-0.86], 0.82 [95% CI, 0.78-0.86], and 0.88 [95%CI, 0.85-0.91], respectively. The corresponding values for validation cohorts were 0.81 [95% CI, 0.72-0.87], 0.73 [95% CI, 0.62-0.82], and 0.84 [95%CI, 0.80-0.87], respectively. Based on QUADAS-2, some risks of bias were detected for reference standard and flow and timing domains. However, the quality of the included article was acceptable. The mean RQS score of the included articles was close to 6, corresponding to 16.6% of the maximum possible score. Significant heterogeneity was observed in pooled sensitivity and specificity of training cohorts (I2 > 75%). We found that using deep learning radiomic methods, magnetic field strength (3 T vs. 1.5 T), scanner manufacturer, region of interest structure (2D vs. 3D), route of tissue sampling, Ki-67 cut-off, logistic regression for model construction, and LASSO for feature reduction as well as PyRadiomics software for feature extraction had a great impact on heterogeneity according to our joint model analysis. Diagnostic performance in studies that used deep learning-based radiomics and multiple MRI sequences (e.g., DWI+DCE) was slightly higher. In addition, radiomic features derived from DWI sequences performed better than contrast-enhanced sequences in terms of specificity and sensitivity. No publication bias was found based on Deeks' funnel plot. Sensitivity analysis showed that eliminating every study one by one does not impact overall results.

CONCLUSION

This meta-analysis showed that MRI-based radiomics has a good diagnostic accuracy in differentiating breast cancer patients with high Ki-67 expression from low-expressing groups. However, the sensitivity and specificity of these methods still do not surpass 90%, restricting them from being used as a supplement to current pathological assessments (e.g., biopsy or surgery) to predict Ki-67 expression accurately.

Dosiomics and radiomics-based prediction of pneumonitis after radiotherapy and immune checkpoint inhibition: The relevance of fractionation

OBJECTIVES

Post-therapy pneumonitis (PTP) is a relevant side effect of thoracic radiotherapy and immunotherapy with checkpoint inhibitors (ICI). The influence of the combination of both, including dose fractionation schemes on PTP development is still unclear. This study aims to improve the PTP risk estimation after radio(chemo)therapy (R(C)T) for lung cancer with and without ICI by investigation of the impact of dose fractionation on machine learning (ML)-based prediction.

MATERIALS AND METHODS

Data from 100 patients who received fractionated R(C)T were collected. 39 patients received additional ICI therapy. Computed Tomography (CT), RT segmentation and dose data were extracted and physical doses were converted to 2-Gy equivalent doses (EQD2) to account for different fractionation schemes. Features were reduced using Pearson intercorrelation and the Boruta algorithm within 1000-fold bootstrapping. Six single (clinics, Dose Volume Histogram (DVH), ICI, chemotherapy, radiomics, dosiomics) and four combined models (radiomics + dosiomics, radiomics + DVH + Clinics, dosiomics + DVH + Clinics, radiomics + dosiomics + DVH + Clinics) were trained to predict PTP. Dose-based models were tested using physical dose and EQD2. Four ML-algorithms (random forest (rf), logistic elastic net regression, support vector machine, logitBoost) were trained and tested using 5-fold nested cross validation and Synthetic Minority Oversampling Technique (SMOTE) for resampling in R. Prediction was evaluated using the area under the receiver operating characteristic curve (AUC) on the test sets of the outer folds.

RESULTS

The combined model of all features using EQD2 surpassed all other models (AUC = 0.77, Confidence Interval CI 0.76-0.78). DVH, clinical data and ICI therapy had minor impact on PTP prediction with AUC values between 0.42 and 0.57. All EQD2-based models outperformed models based on physical dose.

CONCLUSIONS

Radiomics + dosiomics based ML models combined with clinical and dosimetric models were found to be suited best for PTP prediction after R(C)T and could improve pre-treatment decision making. Different RT dose fractionation schemes should be considered for dose-based ML approaches.

AI applications in musculoskeletal imaging: a narrative review

This narrative review focuses on clinical applications of artificial intelligence (AI) in musculoskeletal imaging. A range of musculoskeletal disorders are discussed using a clinical-based approach, including trauma, bone age estimation, osteoarthritis, bone and soft-tissue tumors, and orthopedic implant-related pathology. Several AI algorithms have been applied to fracture detection and classification, which are potentially helpful tools for radiologists and clinicians. In bone age assessment, AI methods have been applied to assist radiologists by automatizing workflow, thus reducing workload and inter-observer variability. AI may potentially aid radiologists in identifying and grading abnormal findings of osteoarthritis as well as predicting the onset or progression of this disease. Either alone or combined with radiomics, AI algorithms may potentially improve diagnosis and outcome prediction of bone and soft-tissue tumors. Finally, information regarding appropriate positioning of orthopedic implants and related complications may be obtained using AI algorithms. In conclusion, rather than replacing radiologists, the use of AI should instead help them to optimize workflow, augment diagnostic performance, and keep up with ever-increasing workload.Relevance statement This narrative review provides an overview of AI applications in musculoskeletal imaging. As the number of AI technologies continues to increase, it will be crucial for radiologists to play a role in their selection and application as well as to fully understand their potential value in clinical practice. Key points • AI may potentially assist musculoskeletal radiologists in several interpretative tasks.• AI applications to trauma, age estimation, osteoarthritis, tumors, and orthopedic implants are discussed.• AI should help radiologists to optimize workflow and augment diagnostic performance.

Prediction of postoperative liver metastasis in pancreatic ductal adenocarcinoma based on multiparametric magnetic resonance radiomics combined with serological markers: a cohort study of machine learning

OBJECTIVE

To construct and validate a multi-dimensional model based on multiple machine leaning algorithms to predict PCLM using multi-parameter magnetic resonance (MRI) sequences with clinical and imaging parameters.

METHODS

A total of 148 PDAC retrospectively examined patients were classified as metastatic or non-metastatic based on results at 3 months after surgery. The radiomics features of the primary tumor were extracted from T2WI images, followed by dimension reduction. Then, multiple machine learning methods were used to construct models. Independent predictors were also screened using multifactor logistic regression and a nomogram was constructed in combination with the radiomics model. Area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used to assess the accuracy and reliability of the nomogram.

RESULTS

The diagnostic efficacy of the radiomics model in the training and test set was 0.822 and 0.803, sensitivity was 0.742 and 0.692, and specificity was 0.792 and 0.875, respectively. The diagnostic efficacy of the nomogram in the training and test set was 0.866 and 0.832.

CONCLUSION

A radiomics nomogram based on machine learning improved the accuracy of predicting PCLM and may be useful for early preoperative diagnosis.

Prediction of high-grade soft-tissue sarcoma using a combined intratumoural and peritumoural MRI-based radiomics nomogram

AIM

To develop an intratumoural and peritumoural magnetic resonance imaging (MRI)-based radiomics nomogram for predicting tumour grade to improve clinical treatment and long-term prognosis.

MATERIALS AND METHODS

MRI (3 T) features and T2-weighted imaging with fat-saturation (T2WI-FS)-based radiomics features of 57 patients with soft-tissue sarcoma (STS) were analysed retrospectively. Tumour size, ratio of width and length, relative depth to the peripheral fascia, peritumoural oedema, heterogeneity on T2WI, necrosis signal, enhancement model, and peritumoural enhancement were obtained. Independent risk factors were screened to construct an MRI feature nomogram. Radiomics features were obtained from intratumoural and peritumoural images on T2WI-FS. The optimal radiomics model was selected by the four-step dimensionality reduction method of minimum and maximum normalisation, optimal feature selection, selection based on support vector machine with L1-norm regularisation model, and iterative feature selection. MRI features and optimal radiomics features were used to construct a radiomics nomogram. The MRI feature nomogram model, the radiomics model, and the radiomics nomogram model were assessed by receiver operating characteristic (ROC) curves and calibration curves of the training and validation sets.

RESULTS

Heterogeneity on T2WI and peritumoural enhancement were independent risk factors for predicting high-grade STS. The areas under the curves of the training set and verification set of the three models were as follows: MRI feature nomogram, 0.86 and 0.83, respectively; intratumoural and peritumoural combined radiomics model, 0.99 and 0.86, respectively; and radiomics nomogram model, 0.98 and 0.96, respectively.

CONCLUSION

The radiomics nomogram model based on MRI features and combined intratumoural and peritumoural radiomic features was best able to predict high-grade STS.

Radiomics and artificial intelligence for soft-tissue sarcomas: Current status and perspectives

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.

Research status and progress of radiomics in bone and soft tissue tumors: A review

Bone and soft tissue tumors are diverse, accompanying by complex histological components and significantly divergent biological behaviors. It is a challenge to address the demand for qualitative imaging as traditional imaging is restricted to the detection of anatomical structures and aberrant signals. With the improvement of digitalization in hospitals and medical centers, the introduction of electronic medical records and easier access to large amounts of information coupled with the improved computational power, traditional medicine has evolved into the combination of human brain, minimal data, and artificial intelligence. Scholars are committed to mining deeper levels of imaging data, and radiomics is worthy of promotion. Radiomics extracts subvisual quantitative features, analyzes them based on medical images, and quantifies tumor heterogeneity by outlining the region of interest and modeling. Two observers separately examined PubMed, Web of Science and CNKI to find existing studies, case reports, and clinical guidelines about research status and progress of radiomics in bone and soft tissue tumors from January 2010 to February 2023. When evaluating the literature, factors such as patient age, medical history, and severity of the condition will be considered. This narrative review summarizes the application and progress of radiomics in bone and soft tissue tumors.

The importance of planning CT-based imaging features for machine learning-based prediction of pain response

Patients suffering from painful spinal bone metastases (PSBMs) often undergo palliative radiation therapy (RT), with an efficacy of approximately two thirds of patients. In this exploratory investigation, we assessed the effectiveness of machine learning (ML) models trained on radiomics, semantic and clinical features to estimate complete pain response. Gross tumour volumes (GTV) and clinical target volumes (CTV) of 261 PSBMs were segmented on planning computed tomography (CT) scans. Radiomics, semantic and clinical features were collected for all patients. Random forest (RFC) and support vector machine (SVM) classifiers were compared using repeated nested cross-validation. The best radiomics classifier was trained on CTV with an area under the receiver-operator curve (AUROC) of 0.62 ± 0.01 (RFC; 95% confidence interval). The semantic model achieved a comparable AUROC of 0.63 ± 0.01 (RFC), significantly below the clinical model (SVM, AUROC: 0.80 ± 0.01); and slightly lower than the spinal instability neoplastic score (SINS; LR, AUROC: 0.65 ± 0.01). A combined model did not improve performance (AUROC: 0,74 ± 0,01). We could demonstrate that radiomics and semantic analyses of planning CTs allowed for limited prediction of therapy response to palliative RT. ML predictions based on established clinical parameters achieved the best results.

Prediction of histopathologic grades of myxofibrosarcoma with radiomics based on magnetic resonance imaging

PURPOSE

To develop a radiomics-based model from preoperative magnetic resonance imaging (MRI) for predicting the histopathological grades of myxofibrosarcoma.

METHODS

This retrospective study included 54 patients. The tumors were classified into high-grade and low-grade myxofibrosarcoma. The tumor size, signal intensity heterogeneity, margin, and surrounding tissue were evaluated on MRI. Using the least absolute shrinkage and selection operator (LASSO) algorithms, 1037 radiomics features were obtained from fat-suppressed T2-weighted images (T2WI), and a radiomics signature was established. Using multivariable logistic regression analysis, three models were built to predict the histopathologic grade of myxofibrosarcoma. A radiomics nomogram represents the integrative model. The three models' performance was evaluated using the receiver operating characteristics (ROC) and calibration curves.

RESULTS

The high-grade myxofibrosarcoma had greater depth (P = 0.027), more frequent heterogeneous signal intensity at T2WI (P = 0.015), and tail sign (P = 0.014) than the low-grade tumor. The area under curve (AUC) of these conventional MRI features models was 0.648, 0.656, and 0.668, respectively. Seven radiomic features were selected by LASSO to construct the radiomics signature model, with an AUC of 0.791. The AUC of the integrative model based on radiomics signature and conventional MRI features was 0.875. The integrative model's calibration curve and insignificant Hosmer-Lemeshow test statistic (P = 0.606) revealed good calibration.

CONCLUSION

An integrative model using radiomics signature and three conventional MRI features can preoperatively predict low- or high-grade myxofibrosarcoma.

Lifestyle, clinical and histological indices-based prediction models for survival in cancer patients: a city-wide prospective cohort study in China

PURPOSE

We developed a nomogram to predict 3-year, 5-year and 7-year cancer survival rates of cancer patients.

METHODS

This prospective cohort study included 20,491 surviving patients first diagnosed with cancer in Guangzhou from 2010 to 2019. They were divided into a training and a validation group. Lifestyle, clinical and histological parameters (LCH) were included in multivariable Cox regression. Akaike information criterion was used to select prediction factors for the nomogram. The discrimination and calibration of models were assessed by concordance index (C-index), area under time-dependent receiver operating characteristic curve (time-dependent AUC), and calibration plots. We used net reclassification index (NRI) and integrated discrimination improvement (IDI) to compare the clinical utility of LCH prediction model with the prediction model based on lifestyle factors (LF).

RESULTS

13 prediction factors including age, sex, BMI, smoking status, physical activity, sleep duration, regular diet, tumor grading, TNM stage, multiple primary cancer and anatomical site were included in the LCH model. The LCH model showed satisfactory discrimination and calibration (C-index = 0.81 (95% CI 0.80-0.82) for training group and 0.80 (0.79-0.81) for validation group, both time-dependent AUC > 0.70). The LF model including smoking status, physical activity, sleep duration, regular diet, and BMI showed less satisfactory discrimination (C-index = 0.60 (95% CI 0.59-0.61) for training and 0.60 (0.58-0.62) for validation group). The LCH model had better accuracy and discriminative ability than the LF model, as indicated by positive NRI and IDI values.

CONCLUSIONS

The LCH model shows good accuracy, clinical utility and precise prognosis prediction, and may serve as a tool to predict cancer survival of cancer patients.

ComBat Harmonization of Myocardial Radiomic Features Sensitive to Cardiac MRI Acquisition Parameters

Purpose

To investigate the effect of ComBat harmonization methods on the robustness of cardiac MRI-derived radiomic features to variations in imaging parameters.

Materials and Methods

This Health Insurance Portability and Accountability Act-compliant retrospective study used a publicly available data set of 11 healthy controls (mean age, 33 years ± 16 [SD]; six men) and five patients (mean age, 52 years ± 16; four men). A single midventricular short-axis section was acquired with 3-T MRI using cine balanced steady-state free precision, T1-weighted, T2-weighted, T1 mapping, and T2 mapping imaging sequences. Each sequence was acquired using baseline parameters and after variations in flip angle, spatial resolution, section thickness, and parallel imaging. Image registration was performed for all sequences at a per-individual level. Manual myocardial contouring was performed, and 1652 radiomic features per sequence were extracted using baseline and variations in imaging parameters. Radiomic feature stability to change in imaging parameters was assessed using Cohen d sensitivity. The stability of radiomic features was assessed both without and after ComBat harmonization of radiomic features. Three ComBat methods were studied: parametric, nonparametric, and Gaussian mixture model (GMM).

Results

For all sequences combined, 51.4% of features were robust to changes in imaging parameters when no ComBat method was applied. ComBat harmonization substantially increased the number of stable features to 95.1% (95% CI: 94.9, 95.3) when parametric ComBat was used and 90.9% (95% CI: 90.6, 91.2) when nonparametric ComBat was used. GMM combat resulted in only 52.6% stable features.

Conclusion

ComBat harmonization improved the stability of radiomic features to changes in imaging parameters across all cardiac MRI sequences.Keywords: Cardiac MRI, Radiomics, ComBat, Harmonization Supplemental material is available for this article. © RSNA, 2023.

Ensemble learning-based radiomics with multi-sequence magnetic resonance imaging for benign and malignant soft tissue tumor differentiation

Many previous studies focused on differentiating between benign and malignant soft tissue tumors using radiomics model based on various magnetic resonance imaging (MRI) sequences, but it is still unclear how to set up the input radiomic features from multiple MRI sequences. Here, we evaluated two types of radiomics models generated using different feature incorporation strategies. In order to differentiate between benign and malignant soft tissue tumors (STTs), we compared the diagnostic performance of an ensemble of random forest (R) models with single-sequence MRI inputs to R models with pooled multi-sequence MRI inputs. One-hundred twenty-five STT patients with preoperative MRI were retrospectively included and consisted of training (n = 100) and test (n = 25) sets. MRI included T1-weighted (T1-WI), T2-weighted (T2-WI), contrast-enhanced (CE)-T1-WI, diffusion-weighted images (DWIs, b = 800 sec/mm2) and apparent diffusion coefficient (ADC) maps. After tumor segmentation on each sequence, 100 original radiomic features were extracted from each sequence image and divided into three-feature sets: T features from T1- and T2-WI, CE features from CE-T1-WI, and D features from DWI and ADC maps. Four radiomics models were built using Lasso and R with four combinations of three-feature sets as inputs: T features (R-T), T+CE features (R-C), T+D features (R-D), and T+CE+D features (R-A) (Type-1 model). An ensemble model was built by soft voting of five, single-sequence-based R models (Type-2 model). AUC, sensitivity, specificity, and accuracy of each model was calculated with five-fold cross validation. In Type-1 model, AUC, sensitivity, specificity, and accuracy were 0.752, 71.8%, 61.1%, and 67.2% in R-T; 0.756, 76.1%, 70.4%, and 73.6% in R-C; 0.750, 77.5%, 63.0%, and 71.2% in R-D; and 0.749, 74.6%, 61.1%, and 68.8% R-A models, respectively. AUC, sensitivity, specificity, and accuracy of Type-2 model were 0.774, 76.1%, 68.5%, and 72.8%. In conclusion, an ensemble method is beneficial to incorporate features from multi-sequence MRI and showed diagnostic robustness for differentiating malignant STTs.

Dosiomics and radiomics to predict pneumonitis after thoracic stereotactic body radiotherapy and immune checkpoint inhibition

Introduction

Pneumonitis is a relevant side effect after radiotherapy (RT) and immunotherapy with checkpoint inhibitors (ICIs). Since the effect is radiation dose dependent, the risk increases for high fractional doses as applied for stereotactic body radiation therapy (SBRT) and might even be enhanced for the combination of SBRT with ICI therapy. Hence, patient individual pre-treatment prediction of post-treatment pneumonitis (PTP) might be able to support clinical decision making. Dosimetric factors, however, use limited information and, thus, cannot exploit the full potential of pneumonitis prediction.

Methods

We investigated dosiomics and radiomics model based approaches for PTP prediction after thoracic SBRT with and without ICI therapy. To overcome potential influences of different fractionation schemes, we converted physical doses to 2 Gy equivalent doses (EQD2) and compared both results. In total, four single feature models (dosiomics, radiomics, dosimetric, clinical factors) were tested and five combinations of those (dosimetric+clinical factors, dosiomics+radiomics, dosiomics+dosimetric+clinical factors, radiomics+dosimetric+clinical factors, radiomics+dosiomics+dosimetric+clinical factors). After feature extraction, a feature reduction was performed using pearson intercorrelation coefficient and the Boruta algorithm within 1000-fold bootstrapping runs. Four different machine learning models and the combination of those were trained and tested within 100 iterations of 5-fold nested cross validation.

Results

Results were analysed using the area under the receiver operating characteristic curve (AUC). We found the combination of dosiomics and radiomics features to outperform all other models with AUCradiomics+dosiomics, D = 0.79 (95% confidence interval 0.78-0.80) and AUCradiomics+dosiomics, EQD2 = 0.77 (0.76-0.78) for physical dose and EQD2, respectively. ICI therapy did not impact the prediction result (AUC ≤ 0.5). Clinical and dosimetric features for the total lung did not improve the prediction outcome.

Conclusion

Our results suggest that combined dosiomics and radiomics analysis can improve PTP prediction in patients treated with lung SBRT. We conclude that pre-treatment prediction could support clinical decision making on an individual patient basis with or without ICI therapy.

Diagnosis of Marginal Infiltration in Soft Tissue Sarcoma by Radiomics Approach Using T2-Weighted Dixon Sequence

BACKGROUND

Determination of preoperative soft tissue sarcoma (STS) margin is crucial for patient prognosis.

PURPOSE

To evaluate diagnostic performance of radiomics model using T2-weighted Dixon sequence for infiltration degree of STS margin.

STUDY TYPE

Retrospective.

POPULATION

Seventy-two STS patients consisted of training (n = 58) and test (n = 14) sets.

FIELD STRENGTH/SEQUENCE

A 3.0 T; T2-weighted Dixon images.

ASSESSMENT

Pathologic result of marginal infiltration in STS (circumscribed margin; n = 27, group 1, focally infiltrative margin; n = 31, group 2-A, diffusely infiltrative margin; n = 14, group 2-B) was the reference standard. Radiomic volume and shape (VS) and other (T2) features were extracted from entire tumor volume and margin, respectively. Twelve radiomics models were generated using four combinations of classifier algorithms (R, SR, LR, LSR) and three different inputs (VS, T2, VS + T2 [VST2] features) to differentiate the three groups. Three radiologists (reader 1, 2, 3) analyzed the marginal infiltration with 6-scale confidence score.

STATISTICAL TESTS

Area under the receiver operating characteristic curve (AUC) and concordance rate.

RESULTS

Averaged AUCs of R, SR, LR, LSR models were 0.438, 0.466, 0.438, 0.466 using VS features, 0.596, 0.584, 0.814, 0.815 using T2 features, and 0.581, 0.587, 0.821, 0.821 using VST2 features, respectively. The LR and LSR models constructed with T2 or VST2 features showed higher AUC and concordance rate compared to radiologists' analysis (AUC; 0.730, 0.675, 0.706, concordance rate; 0.46, 0.43, 0.47 in reader 1, 2, 3).

DATA CONCLUSION

Radiomics model constructed with features from tumor margin on T2-weighted Dixon sequence is a promising method for differentiating infiltration degree of STS margin.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Imaging presentation of extraskeletal osteosarcomas on CT and MRI and correlation with patients outcome: A two-center retrospective study of 54 patients

PURPOSE

The purpose of this study was to analyze the imaging features of extraskeletal osteosarcomas (ESOS) on computed tomography (CT) and magnetic resonance imaging (MRI) and to investigate their associations with overall survival (OS) using uni- and multivariable survival analyses.

MATERIALS AND METHODS

This two-center retrospective study included all consecutive adult patients between 2008 and 2021 with histopathologically-proven ESOS who underwent pre-treatment CT and/or MRI. Clinical and histological characteristics, ESOS presentation on CT and MRI, treatment and outcomes were reported. Survival analyses were performed using Kaplan-Meier analysis and Cox regressions. Associations between imaging features and OS were searched using uni- and multivariable analyses.

RESULTS

Fifty-four patients were included (30/54 [56%] men, median age: 67.5 years). Twenty-four died of ESOS (median OS: 18 months). ESOS were mostly deep-seated (46/54, 85%) in the lower limb (27/54, 50%) with a median size of 95 mm (interquartile range: 64, 142; range: 21-289 mm). Mineralization was seen on 26/42 (62%) patients, mainly gross-amorphous (18/26; 69%). ESOS were generally highly heterogeneous on T2-weighted images (38/48; 79%) and contrast-enhanced (CE) T1-weighted images (29/40; 72%), with necrosis (39/40; 97%), well-defined or focally infiltrative margins (39/47; 83%), with moderate peritumoral edema (39/47; 83%) and rim-like peripheral enhancement (17/40; 42%). Size, location, mineralization on CT, signal intensity heterogeneity on T1-, T2- and CE-T1-weighted images and hemorragic signal on MRI were associated with poorer OS (range of log-rank P = 0.0069-0.0485). At multivariable analysis, hemorragic signal and signal intensity heterogeneity on T2-weighted images remained predictive for poorer OS (hazard ratio [HR] = 2.68, P = 0.0299; HR = 9.85, P = 0.0262, respectively) CONCLUSION: ESOS typically presents as mineralized heterogeneous and necrotic soft tissue tumor with a possible rim-like enhancement and limited peritumoral abnormalities. MRI may help estimate outcome of patients with ESOS.

Role of Imaging in Initial Prognostication of Locally Advanced Soft Tissue Sarcomas

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.

Nearest Neighbor-Based Strategy to Optimize Multi-View Triplet Network for Classification of Small-Sample Medical Imaging Data

Multi-view classification with limited sample size and data augmentation is a very common machine learning (ML) problem in medicine. With limited data, a triplet network approach for two-stage representation learning has been proposed. However, effective training and verifying the features from the representation network for their suitability in subsequent classifiers are still unsolved problems. Although typical distance-based metrics for the training capture the overall class separability of the features, the performance according to these metrics does not always lead to an optimal classification. Consequently, an exhaustive tuning with all feature-classifier combinations is required to search for the best end result. To overcome this challenge, we developed a novel nearest-neighbor (NN) validation strategy based on the triplet metric. This strategy is supported by a theoretical foundation to provide the best selection of the features with a lower bound of the highest end performance. The proposed strategy is a transparent approach to identify whether to improve the features or the classifier. This avoids the need for repeated tuning. Our evaluations on real-world medical imaging tasks (i.e., radiation therapy delivery error prediction and sarcoma survival prediction) show that our strategy is superior to other common deep representation learning baselines [i.e., autoencoder (AE) and softmax]. The strategy addresses the issue of feature's interpretability which enables more holistic feature creation such that the medical experts can focus on specifying relevant data as opposed to tedious feature engineering.

Distinct patterns of the natural evolution of soft tissue sarcomas on pre-treatment MRIs captured with delta-radiomics correlate with gene expression profiles

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.

Controversies in the management of patients with soft tissue sarcoma: Recommendations of the Conference on State of Science in Sarcoma 2022

BACKGROUND

Owing to the rarity and heterogeneity in biology and presentation, there are multiple areas in the diagnosis, treatment and follow-up of soft tissue sarcoma (STS), with no, low-level or conflicting evidence.

METHODS

During the first Consensus Conference on the State of Science in Sarcoma (CSSS), we used a modified Delphi process to identify areas of controversy in the field of sarcoma, to name topics with limited evidence-based data in which a scientific and knowledge gap may remain and a consensus statement will help to guide patient management. We determined scientific questions which need to be addressed in the future in order to generate evidence and to inform physicians and caregivers in daily clinical practice in order to improve the outcomes of patients with sarcoma. We conducted a vote on STS key questions and controversies prior to the CSSS meeting, which took place in May 2022.

RESULTS

Sixty-two European sarcoma experts participated in the survey. Sixteen strong consensus (≥95%) items were identified by the experts, as well as 30 items with a ≥75% consensus on diagnostic and therapeutic questions. Ultimately, many controversy topics remained without consensus.

CONCLUSIONS

In this manuscript, we summarise the voting results and the discussion during the CSSS meeting. Future scientific questions, priorities for clinical trials, registries, quality assurance, and action by stakeholders are proposed. Platforms and partnerships can support innovative approaches to improve management and clinical research in STS.

MRI-Based Computer-Aided Diagnostic Model to Predict Tumor Grading and Clinical Outcomes in Patients With Soft Tissue Sarcoma

BACKGROUND

MRI acts as a potential resource for exploration and interpretation to identify tumor characterization by advanced computer-aided diagnostic (CAD) methods.

PURPOSE

To evaluate and validate the performance of MRI-based CAD models for identifying low-grade and high-grade soft tissue sarcoma (STS) and for investigating survival prognostication.

STUDY TYPE

Retrospective.

SUBJECTS

A total of 540 patients (295 male/female: 295/245, median age: 42 years) with STSs.

FIELD SEQUENCE

5-T MRI with T₁ WI sequence and fat-suppressed T₂ -weighted (T₂ FS) sequence.

ASSESSMENT

Manual regions of interests (ROIs) were delineated for generation of radiomic features. Automatic segmentation and pretrained convolutional neural networks (CNNs) were performed for deep learning (DL) analysis. The last fully connected layer at the top of CNNs was removed, and the global max pooling was added to transform feature maps to numeric values. Tumor grade was determined on histological specimens.

STATISTICAL TESTS

The support vector machine was adopted as the classifier for all MRI-based models. The DL signature was derived from the DL-MRI model with the highest area under the curve (AUC). The significant clinical variables, tumor location and size, integrated with radiomics and DL signatures were ready for construction of clinical-MRI nomogram to identify tumor grading. The prognostic value of clinical variables and these MRI-based signatures for overall survival (OS) was evaluated via Cox proportional hazard.

RESULTS

The clinical-MRI differentiation nomogram represented an AUC of 0.870 in the training cohort, and an AUC of 0.855, accuracy of 79.01%, sensitivity of 79.03%, and specificity of 78.95% in the validation cohort. The prognostic model showed good performance for OS with 3-year C-index of 0.681 and 0.642 and 5-year C-index of 0.722 and 0.676 in the training and validation cohorts.

DATA CONCLUSION

MRI-based CAD nomogram represents effective abilities in classification of low-grade and high-grade STSs. The MRI-based prognostic model yields favorable preoperative capacities to identify long-term survivals for STSs.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 4.

Harmonization Strategies in Multicenter MRI-Based Radiomics

Radiomics analysis is a powerful tool aiming to provide diagnostic and prognostic patient information directly from images that are decoded into handcrafted features, comprising descriptors of shape, size and textural patterns. Although radiomics is gaining momentum since it holds great promise for accelerating digital diagnostics, it is susceptible to bias and variation due to numerous inter-patient factors (e.g., patient age and gender) as well as inter-scanner ones (different protocol acquisition depending on the scanner center). A variety of image and feature based harmonization methods has been developed to compensate for these effects; however, to the best of our knowledge, none of these techniques has been established as the most effective in the analysis pipeline so far. To this end, this review provides an overview of the challenges in optimizing radiomics analysis, and a concise summary of the most relevant harmonization techniques, aiming to provide a thorough guide to the radiomics harmonization process.

The diagnosis, classification, and treatment of sarcoma in this era of artificial intelligence and immunotherapy

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.

Concordance of histopathological and radiological grading in soft tissue sarcomas

Aim: The grade of the tumor is essential for planning the treatment strategy in soft-tissue sarcomas (STS). The goal of this study is to determine magnetic resonance imaging features related to histopathological grade and aggressiveness of STS. Material and Method: This retrospective single-center study involved preoperative contrast-enhanced MRI examinations of 64 patients with STS. MRI findings evaluated were; heterogeneity, necrosis, hemorrhage, and relationship with surrounding tissue in T1-weighted (T1W), T2-weighted (T2W), and T1W post-contrast sequences of the lesion. Histological grade was determined with the Fédération Nationale des Centres de Lutte Contre Le Cancer (FNCLCC) grading system, and the aggressiveness of the lesion was measured with the Ki-67 index. Results: Sixty-four patients (mean age 45.5±21.6, M/F ratio 34/30) with STS were included. 33 (51.6%) patients graded as FNCLCC grade 3. On MRI examinations, the absence of necrosis was significantly associated with FNCLCC grade 1 and a low Ki-67 index (p

Comparing Apparent Diffusion Coefficient and FNCLCC Grading to Improve Pretreatment Grading of Soft Tissue Sarcoma-A Translational Feasibility Study on Fusion Imaging

Simple Summary

Histological subtype and grading are essential for the planning of soft tissue sarcoma. Pretherapeutic grading based on core needle biopsies is frequently not reliable due to intratumoral heterogeneity. This pilot study assessed the ability of functional radiological imaging to improve histopathological grading. Multiple biopsies were taken from the sarcoma specimens during tumor resection and radiopaque markers were placed. Subsequently, fusion of preoperative magnetic resonance imaging and postoperative computed tomography of the specimen allowed for comparison of histopathological grading and diffusion-weighted imaging. The apparent diffusion coefficient appears to correlate with FNCLCC criteria and may supplement pretreatment assessment and multimodal treatment allocation in soft tissue sarcoma.

Abstract

Histological subtype and grading are cornerstones of treatment decisions in soft tissue sarcoma (STS). Due to intratumoral heterogeneity, pretreatment grading assessment is frequently unreliable and may be improved through functional imaging. In this pilot study, 12 patients with histologically confirmed STS were included. Preoperative functional magnetic resonance imaging was fused with a computed tomography scan of the resected specimen after collecting core needle biopsies and placing radiopaque markers at distinct tumor sites. The Fédération Nationale des Centres de Lutte Contre le Cancer (FNCLCC) grading criteria of the biopsies and apparent diffusion coefficients (ADCs) of the biopsy sites were correlated. Concordance in grading between the specimen and at least one biopsy was achieved in 9 of 11 cases (81.8%). In 7 of 12 cases, fusion imaging was feasible without relevant contour deviation. Functional analysis revealed a tendency for high-grade regions (Grade 2/3 (G2/G3)) (median (range) ± standard deviation: 1.13 (0.78–1.70) ± 0.23 × 10⁻³ mm²/s) to have lower ADC values than low-grade regions (G1; 1.43 (0.64–2.03) ± 0.46 × 10⁻³ mm²/s). In addition, FNCLCC scoring of multiple tumor biopsies proved intratumoral heterogeneity as expected. The ADC appears to correlate with the FNCLCC grading criteria. Further studies are needed to determine whether functional imaging may supplement histopathological grading.

T2-weighted MRI-based radiomics for discriminating between benign and borderline epithelial ovarian tumors: a multicenter study

Background

Preoperative differentiation between benign and borderline epithelial ovarian tumors (EOTs) is challenging and can significantly impact clinical decision making. The purpose was to investigate whether radiomics based on T2-weighted MRI can discriminate between benign and borderline EOTs preoperatively.

Methods

A total of 417 patients (309, 78, and 30 samples in the training and internal and external validation sets) with pathologically proven benign and borderline EOTs were included in this multicenter study. In total, 1130 radiomics features were extracted from manually delineated tumor volumes of interest on images. The following three different models were constructed and evaluated: radiomics features only (radiomics model); clinical and radiological characteristics only (clinic-radiological model); and a combination of them all (combined model). The diagnostic performances of models were assessed using receiver operating characteristic (ROC) analysis, and area under the ROC curves (AUCs) were compared using the DeLong test.

Results

The best machine learning algorithm to distinguish borderline from benign EOTs was the logistic regression. The combined model achieved the best performance in discriminating between benign and borderline EOTs, with an AUC of 0.86 ± 0.07. The radiomics model showed a moderate AUC of 0.82 ± 0.07, outperforming the clinic-radiological model (AUC of 0.79 ± 0.06). In the external validation set, the combined model performed significantly better than the clinic-radiological model (AUCs of 0.86 vs. 0.63, p = 0.021 [DeLong test]).

Conclusions

Radiomics, based on T2-weighted MRI, can provide critical diagnostic information for discriminating between benign and borderline EOTs, thus having the potential to aid personalized treatment options.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01264-x.

Virtual Biopsy in Soft Tissue Sarcoma. How Close Are We?

A shift in radiology to a data-driven specialty has been unlocked by synergistic developments in imaging biomarkers (IB) and computational science. This is advancing the capability to deliver “virtual biopsies” within oncology. The ability to non-invasively probe tumour biology both spatially and temporally would fulfil the potential of imaging to inform management of complex tumours; improving diagnostic accuracy, providing new insights into inter- and intra-tumoral heterogeneity and individualised treatment planning and monitoring. Soft tissue sarcomas (STS) are rare tumours of mesenchymal origin with over 150 histological subtypes and notorious heterogeneity. The combination of inter- and intra-tumoural heterogeneity and the rarity of the disease remain major barriers to effective treatments. We provide an overview of the process of successful IB development, the key imaging and computational advancements in STS including quantitative magnetic resonance imaging, radiomics and artificial intelligence, and the studies to date that have explored the potential biological surrogates to imaging metrics. We discuss the promising future directions of IBs in STS and illustrate how the routine clinical implementation of a virtual biopsy has the potential to revolutionise the management of this group of complex cancers and improve clinical 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.

Deep Learning Radiomics Nomogram to Predict Lung Metastasis in Soft-Tissue Sarcoma: A Multi-Center Study

Objectives

To build and evaluate a deep learning radiomics nomogram (DLRN) for preoperative prediction of lung metastasis (LM) status in patients with soft tissue sarcoma (STS).

Methods

In total, 242 patients with STS (training set, n=116; external validation set, n=126) who underwent magnetic resonance imaging were retrospectively enrolled in this study. We identified independent predictors for LM-status and evaluated their performance. The minimum redundancy maximum relevance (mRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm were adopted to screen radiomics features. Logistic regression, decision tree, random forest, support vector machine (SVM), and adaptive boosting classifiers were compared for their ability to predict LM. To overcome the imbalanced distribution of the LM data, we retrained each machine-learning classifier using the synthetic minority over-sampling technique (SMOTE). A DLRN combining the independent clinical predictors with the best performing radiomics prediction signature (mRMR+LASSO+SVM+SMOTE) was established. Area under the receiver operating characteristics curve (AUC), calibration curves, and decision curve analysis (DCA) were used to assess the performance and clinical applicability of the models.

Result

Comparisons of the AUC values applied to the external validation set revealed that the DLRN model (AUC=0.833) showed better prediction performance than the clinical model (AUC=0.664) and radiomics model (AUC=0.799). The calibration curves indicated good calibration efficiency and the DCA showed the DLRN model to have greater clinical applicability than the other two models.

Conclusion

The DLRN was shown to be an accurate and efficient tool for LM-status prediction in STS.

Use of automated artificial intelligence to predict the need for orthodontic extractions

Objective

To develop and explore the usefulness of an artificial intelligence system for the prediction of the need for dental extractions during orthodontic treatments based on gender, model variables, and cephalometric records.

Methods

The gender, model variables, and radiographic records of 214 patients were obtained from an anonymized data bank containing 314 cases treated by two experienced orthodontists. The data were processed using an automated machine learning software (Auto-WEKA) and used to predict the need for extractions.

Results

By generating and comparing several prediction models, an accuracy of 93.9% was achieved for determining whether extraction is required or not based on the model and radiographic data. When only model variables were used, an accuracy of 87.4% was attained, whereas a 72.7% accuracy was achieved if only cephalometric information was used.

Conclusions

The use of an automated machine learning system allows the generation of orthodontic extraction prediction models. The accuracy of the optimal extraction prediction models increases with the combination of model and cephalometric data for the analytical process.

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.

Multi-Parametric Magnetic Resonance Imaging-Based Radiomics Analysis of Cervical Cancer for Preoperative Prediction of Lymphovascular Space Invasion

Background

Detection of lymphovascular space invasion (LVSI) in early cervical cancer (CC) is challenging. To date, no standard clinical markers or screening tests have been used to detect LVSI preoperatively. Therefore, non-invasive risk stratification tools are highly desirable.

Objective

To train and validate a multi-parametric magnetic resonance imaging (mpMRI)-based radiomics model to detect LVSI in patients with CC and investigate its potential as a complementary tool to enhance the efficiency of risk assessment strategies.

Materials and Methods

The model was developed from the tumor volume of interest (VOI) of 125 patients with CC. A total of 1037 radiomics features obtained from conventional magnetic resonance imaging (MRI), including a small field-of-view (sFOV) high-resolution (HR)-T2-weighted MRI (T2WI), apparent diffusion coefficient (ADC), T2WI, fat-suppressed (FS)-T2WI, as well as axial and sagittal contrast-enhanced T1-weighted MRI (T1c). We conducted a radiomics-based characterization of each tumor region using pretreatment image data. Feature selection was performed using the least absolute shrinkage and selection operator method on the training set. The predictive performance was compared with single variates (clinical data and single-layer radiomics signatures) analyzed using a receiver operating characteristic (ROC) curve. Three-fold cross-validation performed 20 times was used to evaluate the accuracy of the trained classifiers and the stability of the selected features. The models were validated by using a validation set.

Results

Feature selection extracted the six most important features (3 from sFOV HR-T2WI, 1 T2WI, 1 FS-T2WI, and 1 T1c) for model construction. The mpMRI-combined radiomics model (area under the curve [AUC]: 0.940) reached a significantly higher performance (better than the clinical parameters [AUC: 0.730]), including any single-layer model using sFOV HR-T2WI (AUC: 0.840), T2WI (AUC: 0.770), FS-T2WI (AUC: 0.710), ADC maps (AUC: 0.650), sagittal, and axial T1c values (AUC: 0.710, 0.680) in the validation set.

Conclusion

Biomarkers using multi-parametric radiomics features derived from preoperative MR images could predict LVSI in patients with CC.

What morphological MRI features enable differentiation of low-grade from high-grade soft tissue sarcoma?

Objective:

To assess the diagnostic performance of morphological MRI features separately and in combination for distinguishing low- from high-grade soft tissue sarcoma (STS).

Methods and materials:

We retrospectively analysed pre-treatment MRI examinations with T1, T2 with and without fat suppression (FS) and contrast-enhanced T1 obtained in 64 patients with STS categorized histologically as low (n = 21) versus high grade (n = 43). Two musculoskeletal radiologists blinded to histology evaluated MRI features. Diagnostic performance was calculated for each reader and for MRI features showing significant association with histology (p < 0.05). Logistic regression analysis was performed to develop a diagnostic model to identify high-grade STS.

Results:

Among all evaluated MRI features, only six features had adequate interobserver reproducibility (kappa>0.5). Multivariate logistic regression analysis revealed a significant association with tumour grade for lesion heterogeneity on FS images, intratumoural enhancement≥51% of tumour volume and peritumoural enhancement for both readers (p < 0.05). For both readers, the presence of each of the three features yielded odds ratios for high grade versus low grade from 4.4 to 9.1 (p < 0.05). The sum of the positive features for each reader independent of reader expertise yielded areas under the curve (AUCs) > 0.8. The presence of ≥2 positive features indicated a high risk for high-grade sarcoma, whereas ≤1 positive feature indicated a low-to-moderate risk

Conclusion:

A diagnostic MRI score based on tumour heterogeneity, intratumoural and peritumoural enhancement enables identification of lesions that are likely to be high-grade as opposed to low-grade STS.

Advances in knowledge:

Tumour heterogeneity in Fat Suppression sequence, intratumoural and peritumoural enhancement is identified as signs of high-grade sarcoma.

A CT-based radiomics nomogram for predicting early recurrence in patients with high-grade serous ovarian cancer

PURPOSE

To develop and validate a radiomics nomogram for predicting early recurrence in high-grade serous ovarian cancer (HGSOC) patients.

MATERIALS AND METHODS

From May 2008 to December 2019, 256 eligible HGSOC patients were enrolled and divided into training (n = 179) and test cohorts (n = 77) in a 7:3 ratio. A radiomics signature (Radscore) was selected by using recursive feature elimination based on a support vector machine (SVM-RFE) and building a radiomics model for recurrence prediction. Independent clinical risk factors were generated by univariable and multivariable Cox regression analyses. A combined model was developed based on the Radscore and independent clinical risk factors and presented as a radiomics nomogram. Its performance was assessed by AUC, Kaplan-Meier survival analysis and decision curve analysis.

RESULTS

Seven radiomics features were selected. The radiomics model yielded AUCs of 0.715 (95% CI: 0.640, 0.790) and 0.717 (95% CI: 0.600, 0.834) in the training and test cohorts, respectively. The clinical model (FIGO stage and residual disease) yielded AUCs of 0.632 and 0.691 in the training and test cohorts, respectively. The combined model demonstrated AUCs of 0.749 (95% CI: 0.678, 0.821) and 0.769 (95% CI: 0.662, 0.877) in the training and test cohorts, respectively. In the combined model, PFS was significantly shorter in the high-risk group than in the low-risk group (P < 0.0001).

CONCLUSIONS

The radiomics nomogram performed well for early individualized recurrence prediction in patients with HGSOC and can also be used to differentiate high-risk patients from low-risk patients.

Evaluation of two modalities of perioperative treatment in the management of extremity and truncal soft tissue sarcomas: neoadjuvant concurrent chemoradiotherapy and sequential treatment

PURPOSE

Patients with locally advanced grade 2-3 extremity/truncal soft tissue sarcomas (STS) are at high risk of recurrence. The objective of this study was to assess the efficacy and feasibility of neoadjuvant concurrent chemoradiotherapy (cCRT) in selected grade 2-3 patients with limb or trunk wall STS, and to compare this schedule to a sequential approach combining neoadjuvant chemotherapy and adjuvant radiotherapy.

METHODS

We retrospectively included patients who underwent neoadjuvant cCRT at two comprehensive cancer centers from 1992-2016. We then compared these results to those of patients treated with preoperative chemotherapy and postoperative radiotherapy from a third comprehensive cancer center with a propensity score matched analysis.

RESULTS

A total of 53 patients were treated by neoadjuvant cCRT; 58 patients could be matched with 29 patients in each treatment group after propensity score matching. Disease-free survival and overall survival at 5 years were 54.9 and 63.5%, respectively with neoadjuvant cCRT, with no significant difference when compared to the sequential treatment group. R0 resection rate was higher (90.9 vs 44.8%, p < 0.01) in the cCRT group than in the sequential treatment group during a shorter therapeutic sequence (118 vs 210.5 days, p < 0.01), with no impact on the surgical procedure or postoperative complications.

CONCLUSION

cCRT is feasible with acceptable immediate and late toxicities. It could facilitate surgery by increasing the R0 resection rate and improve patient compliance by shortening the therapeutic sequence.

An Update in Imaging Evaluation of Histopathological Grade of Soft Tissue Sarcomas Using Structural and Quantitative Imaging and Radiomics

Over the past two decades, considerable efforts have been made to develop non-invasive methods for determining tumor grade or surrogates for predicting the biological behavior, aiding early treatment decisions, and providing prognostic information. The development of new imaging tools, such as diffusion-weighted imaging, diffusion kurtosis imaging, perfusion imaging, and magnetic resonance spectroscopy have provided leverage in the diagnosis of soft tissue sarcomas. Artificial intelligence is a new technology used to study and simulate human thinking and abilities, which can extract and analyze advanced and quantitative image features from medical images with high throughput for an in-depth characterization of the spatial heterogeneity of tumor tissues. This article reviews the current imaging modalities used to predict the histopathological grade of soft tissue sarcomas and highlights the advantages and limitations of each modality. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

MRI-based delta-radiomics predicts pathologic complete response in high-grade soft-tissue sarcoma patients treated with neoadjuvant therapy

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.