Quantitative magnetic resonance imaging (q-MRI) for the assessment of soft-tissue sarcoma treatment response: a narrative case review of technique development

A magnetic resonance imaging (MRI)-based deep learning radiomics model predicts recurrence-free survival in lung cancer patients after surgical resection of brain metastases

AIM

To develop and validate a magnetic resonance imaging (MRI)-based deep learning radiomics model (DLRM) to predict recurrence-free survival (RFS) in lung cancer patients after surgical resection of brain metastases (BrMs).

MATERIALS AND METHODS

A total of 215 lung cancer patients with BrMs confirmed by surgical pathology were retrospectively included in five centres, 167 patients were assigned to the training cohort, and 48 to the external test cohort. All patients underwent regular follow-up brain MRIs. Clinical and morphological MRI models for predicting RFS were built using univariate and multivariate Cox regressions, respectively. Handcrafted and deep learning (DL) signatures were constructed from BrMs pretreatment MR images using the least absolute shrinkage and selection operator (LASSO) method, respectively. A DLRM was established by integrating the clinical and morphological MRI predictors, handcrafted and DL signatures based on the multivariate Cox regression coefficients. The Harrell C-index, area under the receiver operating characteristic curve (AUC), and Kaplan-Meier's survival analysis were used to evaluate model performance.

RESULTS

The DLRM showed satisfactory performance in predicting RFS and 6- to 18-month intracranial recurrence in lung cancer patients after BrMs resection, achieving a C-index of 0.79 and AUCs of 0.84-0.90 in the training set and a C-index of 0.74 and AUCs of 0.71-0.85 in the external test set. The DLRM outperformed the clinical model, morphological MRI model, handcrafted signature, DL signature, and clinical-morphological MRI model in predicting RFS (P < 0.05). The DLRM successfully classified patients into high-risk and low-risk intracranial recurrence groups (P < 0.001).

CONCLUSION

This MRI-based DLRM could predict RFS in lung cancer patients after surgical resection of BrMs.

Novel Use and Value of Contrast-Enhanced Susceptibility-Weighted Imaging Morphologic and Radiomic Features in Predicting Extremity Soft Tissue Undifferentiated Pleomorphic Sarcoma Treatment Response

PURPOSE

Undifferentiated pleomorphic sarcomas (UPSs) demonstrate therapy-induced hemosiderin deposition, granulation tissue formation, fibrosis, and calcification. We aimed to determine the treatment-assessment value of morphologic tumoral hemorrhage patterns and first- and high-order radiomic features extracted from contrast-enhanced susceptibility-weighted imaging (CE-SWI).

MATERIALS AND METHODS

This retrospective institutional review board-authorized study included 33 patients with extremity UPS with magnetic resonance imaging and resection performed from February 2021 to May 2023. Volumetric tumor segmentation was obtained at baseline, postsystemic chemotherapy (PC), and postradiation therapy (PRT). The pathology-assessed treatment effect (PATE) in surgical specimens separated patients into responders (R; ≥90%, n = 16), partial responders (PR; 89%-31%, n = 10), and nonresponders (NR; ≤30%, n = 7). RECIST, WHO, and volume were assessed for all time points. CE-SWI T2* morphologic patterns and 107 radiomic features were analyzed.

RESULTS

A Complete-Ring (CR) pattern was observed in PRT in 71.4% of R (P = 7.71 × 10-6), an Incomplete-Ring pattern in 33.3% of PR (P = .2751), and a Globular pattern in 50% of NR (P = .1562). The first-order radiomic analysis from the CE-SWI intensity histogram outlined the values of the 10th and 90th percentiles and their skewness. R showed a 280% increase in 10th percentile voxels (P = .061) and a 241% increase in skewness (P = .0449) at PC. PR/NR showed a 690% increase in the 90th percentile voxels (P = .03) at PC. Multiple high-order radiomic texture features observed at PRT discriminated better R versus PR/NR than the first-order features.

CONCLUSION

CE-SWI morphologic patterns strongly correlate with PATE. The CR morphology pattern was the most frequent in R and had the highest statistical association predicting response at PRT, easily recognized by a radiologist not requiring postprocessing software. It can potentially outperform size-based metrics, such as RECIST. The first- and high-order radiomic analysis found several features separating R versus PR/NR.

Diagnostic Performance of Radiomics and Deep Learning to Identify Benign and Malignant Soft Tissue Tumors: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

To systematically evaluate the application value of radiomics and deep learning (DL) in the differential diagnosis of benign and malignant soft tissue tumors (STTs).

MATERIALS AND METHODS

A systematic review was conducted on studies published up to December 11, 2023, that utilized radiomics and DL methods for the diagnosis of STTs. The methodological quality and risk of bias were evaluated using the Radiomics Quality Score (RQS) 2.0 system and Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool, respectively. A bivariate random-effects model was used to calculate the summarized sensitivity and specificity. To identify factors contributing to heterogeneity, meta-regression and subgroup analyses were performed to assess the following covariates: diagnostic modality, region/volume of interest, imaging examination, study design, and pathology type. The asymmetry of Deeks' funnel plot was used to assess publication bias.

RESULTS

A total of 21 studies involving 3866 patients were included, with 13 studies using independent test/validation sets included in the quantitative statistical analysis. The average RQS was 21.31, with substantial or near-perfect inter-rater agreement. The combined sensitivity and specificity were 0.84 (95% CI: 0.76-0.89) and 0.88 (95% CI: 0.69-0.96), respectively. Meta-regression and subgroup analyses showed that study design and the region/volume of interest were significant factors affecting study heterogeneity (P < 0.05). No publication bias was observed.

CONCLUSION

Radiomics and DL can accurately distinguish between benign and malignant STTs. Future research should concentrate on enhancing the rigor of study designs, conducting multicenter prospective validations, amplifying the interpretability of DL models, and integrating multimodal data to elevate the diagnostic accuracy and clinical utility of soft tissue tumor assessments.

Perfusion-weighted imaging with dynamic contrast enhancement (PWI/DCE) morphologic, qualitative, semiquantitative, and radiomics features predicting undifferentiated pleomorphic sarcoma (UPS) treatment response

Undifferentiated pleomorphic sarcoma (UPS) is the largest subgroup of soft tissue sarcomas. This study determined the value of perfusion-weighted imaging with dynamic-contrast-enhancement (PWI/DCE) morphologic, qualitative, and semiquantitative features for predicting UPS pathology-assessed treatment effect (PATE). This retrospective study included 33 surgically excised extremity UPS patients with pre-surgical MRI. Volumetric tumor segmentation from PWI/DCE was obtained at Baseline (BL), Post-Chemotherapy (PC), and Post-Radiation Therapy (PRT). The surgical specimens' PATE separated cases into Responders (R) (≥ 90%, 16 patients), Partial-Responders (PR) (89 - 31%, 10 patients), and Non-Responders (NR) (≤ 30%, seven patients). Seven semiquantitative kinetic parameters and maps were extracted from time-intensity curves (TICs), and 107 radiomic features were derived. Statistical analyses compared R vs. PR/NR. At PRT, 79% of R displayed a "Capsular" morphology (P = 1.49 × 10-7), and 100% demonstrated a TIC-type II (P = 8.32 × 10-7). 80% of PR showed "Unipolar" morphology (P = 1.03 × 10-5), and 60% expressed a TIC-type V (P = 0.06). Semiquantitative wash-in rate (WiR) was able to separate R vs. PR/NR (P = 0.0078). The WiR radiomics displayed significant differences in the first_order_10 percentile (P = 0.0178) comparing R vs. PR/NR at PRT. The PWI/DCE TIC-type II curve, low WiR, and "Capsular" enhancement represent PRT patterns typically observed in successfully treated UPS and demonstrate potential for UPS treatment response assessment.

Artificial intelligence and machine learning applications for the imaging of bone and soft tissue tumors

Recent advancements in artificial intelligence (AI) and machine learning offer numerous opportunities in musculoskeletal radiology to potentially bolster diagnostic accuracy, workflow efficiency, and predictive modeling. AI tools have the capability to assist radiologists in many tasks ranging from image segmentation, lesion detection, and more. In bone and soft tissue tumor imaging, radiomics and deep learning show promise for malignancy stratification, grading, prognostication, and treatment planning. However, challenges such as standardization, data integration, and ethical concerns regarding patient data need to be addressed ahead of clinical translation. In the realm of musculoskeletal oncology, AI also faces obstacles in robust algorithm development due to limited disease incidence. While many initiatives aim to develop multitasking AI systems, multidisciplinary collaboration is crucial for successful AI integration into clinical practice. Robust approaches addressing challenges and embodying ethical practices are warranted to fully realize AI's potential for enhancing diagnostic accuracy and advancing patient care.

Spatial assessments in texture analysis: what the radiologist needs to know

To date, studies investigating radiomics-based predictive models have tended to err on the side of data-driven or exploratory analysis of many thousands of extracted features. In particular, spatial assessments of texture have proven to be especially adept at assessing for features of intratumoral heterogeneity in oncologic imaging, which likewise may correspond with tumor biology and behavior. These spatial assessments can be generally classified as spatial filters, which detect areas of rapid change within the grayscale in order to enhance edges and/or textures within an image, or neighborhood-based methods, which quantify gray-level differences of neighboring pixels/voxels within a set distance. Given the high dimensionality of radiomics datasets, data dimensionality reduction methods have been proposed in an attempt to optimize model performance in machine learning studies; however, it should be noted that these approaches should only be applied to training data in order to avoid information leakage and model overfitting. While area under the curve of the receiver operating characteristic is perhaps the most commonly reported assessment of model performance, it is prone to overestimation when output classifications are unbalanced. In such cases, confusion matrices may be additionally reported, whereby diagnostic cut points for model predicted probability may hold more clinical significance to clinical colleagues with respect to related forms of diagnostic testing.

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.

Predicting pathological complete response of neoadjuvant radiotherapy and targeted therapy for soft tissue sarcoma by whole-tumor texture analysis of multisequence MRI imaging

OBJECTIVES

To construct effective prediction models for neoadjuvant radiotherapy (RT) and targeted therapy based on whole-tumor texture analysis of multisequence MRI for soft tissue sarcoma (STS) patients.

METHODS

Thirty patients with STS of the extremities or trunk from a prospective phase II trial were enrolled for this analysis. All patients underwent pre- and post-neoadjuvant RT MRI examinations from which whole-tumor texture features were extracted, including T₁-weighted with fat saturation and contrast enhancement (T₁FSGd), T₂-weighted with fat saturation (T₂FS), and diffusion-weighted imaging (DWI) sequences and their corresponding apparent diffusion coefficient (ADC) maps. According to the postoperative pathological results, the patients were divided into pathological complete response (pCR) and non-pCR (N-pCR) groups. pCR was defined as less than 5% of residual tumor cells by postoperative pathology. Delta features were defined as the percentage change in a texture feature from pre- to post-neoadjuvant RT MRI. After data reduction and feature selection, logistic regression was used to build prediction models. ROC analysis was performed to assess the diagnostic performance.

RESULTS

Five of 30 patients (16.7%) achieved pCR. The Delta_Model (AUC 0.92) had a better predictive ability than the Pre_Model (AUC 0.78) and Post_Model (AUC 0.76) and was better than AJCC staging (AUC 0.52) and RECIST 1.1 criteria (AUC 0.52). The Combined_Model (pre, post, and delta features) had the best predictive performance (AUC 0.95).

CONCLUSION

Whole-tumor texture analysis of multisequence MRI can well predict pCR status after neoadjuvant RT and targeted therapy in STS patients, with better performance than RECIST 1.1 and AJCC staging.

KEY POINTS

• MRI multisequence texture analysis could predict the efficacy of neoadjuvant RT and targeted therapy for STS patients. • Texture features showed incremental value beyond routine clinical factors. • The Combined_Model with features at multiple time points showed the best performance.

Experience in utilizing a novel 3D digital model with CT and MRI fusion data in sarcoma evaluation and surgical planning

OBJECTIVE

To assess sarcoma margins with more accuracy and aid surgical planning, we constructed three-dimensional (3D) digital models with computed tomography(CT) and magnetic resonance imaging (MRI) image fusion data and validated the preciseness of the models by comparing them with 3D models constructed with CT only data.

MATERIALS AND METHODS

We retrospectively reviewed a consecutive set of patients treated in our center who were preoperatively evaluated with the fusion image model. Models based on fusion images or CT-only data were constructed. Volumes of both tumors were calculated and the tumors were overlapped to see the location of differences between the two models.

RESULTS

A consecutive 12 cases (4 male vs. 8 female) were included in this study. Most of the tumors were located in the pelvic bone or spine. The volume of the two tumor models was different and the differences were mainly in the peripheral region of the tumor.

CONCLUSION

CT and MRI fusion image 3D models are more accurate than models with CT-only data and can be very helpful in preoperative planning of sarcoma patients.

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.

Target-switchable Gd(III)-DOTA/protein cage nanoparticle conjugates with multiple targeting affibody molecules as target selective T1 contrast agents for high-field MRI

Magnetic resonance imaging (MRI) is a non-invasive in vivo imaging tool, providing high enough spatial resolution to obtain both the anatomical and the physiological information of patients. However, MRI generally suffers from relatively low sensitivity often requiring the aid of contrast agents (CA) to enhance the contrast of vessels and/or the tissues of interest from the background. The targeted delivery of diagnostic probes to the specific lesion is a powerful approach for early diagnosis and signal enhancement leading to the effective treatment of various diseases. Here, we established targeting ligand switchable nanoplatforms using lumazine synthase protein cage nanoparticles derived from Aquifex aeolicus (AaLS) by genetically introducing the SpyTag peptide (ST) to the C-terminus of the AaLS subunits to form an ST-displaying AaLS (AaLS-ST). Conversely, multiple targeting ligands were constructed by genetically fusing SpyCatcher protein (SC) to either HER2 or EGFR targeting affibody molecules (SC-HER2Afb or SC-EGFRAfb). Gd(III)-DOTA complexes were chemically attached to the AaLS-ST and the external surface of the Gd(III)-DOTA conjugated AaLS-ST (Gd(III)-DOTA-AaLS-ST) were successfully decorated with either the HER2Afb or the EGFRAfb. The resulting Gd(III)-DOTA-AaLS/HER2Afb and Gd(III)-DOTA-AaLS/EGFR2Afb exhibited high r₁ relaxivity values of 57 and 25 mM^-1 s^-1 at 1.4 and 7 T, respectively, which were 10-fold or higher than those of the clinically used Dotarem. Their target-selective contrast enhancements were confirmed with in vitro cell-based MRI scans and the in vivo MR imaging of tumor-bearing mouse models at 7 T. A target-switchable AaLS-based nanoplatform that was developed in this study might serve as a promising T₁ CA developing platform at a high magnetic field to detect various tumor sites in a target-specific manner in future clinical applications.

Whole-tumor 3D volumetric MRI-based radiomics approach for distinguishing between benign and malignant soft tissue tumors

OBJECTIVES

Our purpose was to differentiate between malignant from benign soft tissue neoplasms using a combination of MRI-based radiomics metrics and machine learning.

METHODS

Our retrospective study identified 128 histologically diagnosed benign (n = 36) and malignant (n = 92) soft tissue lesions. 3D ROIs were manually drawn on 1 sequence of interest and co-registered to other sequences obtained during the same study. One thousand seven hundred eight radiomics features were extracted from each ROI. Univariate analyses with supportive ROC analyses were conducted to evaluate the discriminative power of predictive models constructed using Real Adaptive Boosting (Adaboost) and Random Forest (RF) machine learning approaches.

RESULTS

Univariate analyses demonstrated that 36.89% of individual radiomics varied significantly between benign and malignant lesions at the p ≤ 0.05 level. Adaboost and RF performed similarly well, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81), respectively, after 10-fold cross-validation. Restricting the machine learning models to only sequences extracted from T2FS and STIR sequences maintained comparable performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84), respectively.

CONCLUSION

Machine learning decision classifiers constructed from MRI-based radiomics features show promising ability to preoperatively discriminate between benign and malignant soft tissue masses. Our approach maintains applicability even when the dataset is restricted to T2FS and STIR fluid-sensitive sequences, which may bolster practicality in clinical application scenarios by eliminating the need for complex co-registrations for multisequence analysis.

KEY POINTS

• Predictive models constructed from MRI-based radiomics data and machine learning-augmented approaches yielded good discriminative power to correctly classify benign and malignant lesions on preoperative scans, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81) for Real Adaptive Boosting (Adaboost) and Random Forest (RF), respectively. • Restricting the models to only use metrics extracted from T2 fat-saturated (T2FS) and Short-Tau Inversion Recovery (STIR) sequences yielded similar performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84) for Adaboost and RF, respectively. • Radiomics-based machine learning decision classifiers constructed from multicentric data more closely mimic the real-world practice environment and warrant additional validation ahead of prospective implementation into clinical workflows.

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.

Coronavirus Disease 2019 (COVID-19) diagnostic technologies: A country-based retrospective analysis of screening and containment procedures during the first wave of the pandemic

Since first report of a novel coronavirus in December of 2019, the Coronavirus Disease 2019 (COVID-19) pandemic has crippled healthcare systems around the world. While many initial screening protocols centered around laboratory detection of the virus, early testing assays were thought to be poorly sensitive in comparison to chest computed tomography, especially in asymptomatic disease. Coupled with shortages of reverse transcription polymerase chain reaction (RT-PCR) testing kits in many parts of the world, these regions instead turned to the use of advanced imaging as a first-line screening modality. However, in contrast to previous Severe Acute Respiratory Syndrome and Middle East Respiratory Syndrome coronavirus epidemics, chest X-ray has not demonstrated optimal sensitivity to be of much utility in first-line screening protocols. Though current national and international guidelines recommend for the use of RT-PCR as the primary screening tool for suspected cases of COVID-19, institutional and regional protocols must consider local availability of resources when issuing universal recommendations. Successful containment and social mitigation strategies worldwide have been thus far predicated on unified governmental responses, though the underlying ideologies of these practices may not be widely applicable in many Western nations. As the strain on the radiology workforce continues to mount, early results indicate a promising role for the use of machine-learning algorithms as risk stratification schema in the months to come.