The Utility of Chest Imaging for Surveillance of Atypical Lipomatous Tumors

Low local recurrence rates following marginal surgical resection of non-coelomic Atypical Lipomatous Tumours/Well-differentiated Liposarcomas

INTRODUCTION

High rates of local recurrence (LR) have been reported following resection of extremity Atypical lipomatous tumours/Well-differentiated liposarcomas (ALTs). This retrospective study of patients who underwent resection of primary deep extremity and trunk ALTs at a specialist sarcoma centre aims to assess morbidity and factors associated with low local recurrence rates (LRR).

METHODS

To review a homogeneous cohort of patients with low-grade disease, tumours with known high-risk histological features were excluded. Prognostic variables potentially influencing local recurrence (LR) (age, size, site, margin status, and histological findings) were analysed. Endpoints were LR, distant recurrence (DR) and local disease-free survival (LDFS).

RESULTS

127 patients were identified, with median follow-up of 54 months (0-235). Median tumour size was 17.5 cm (5-36). 85 % occurred in the lower limb. 93.7 % underwent marginal resection. No patients received radiotherapy. Median hospital stay was 3 days (0-16). 7.9 % returned to theatre for evacuation of haematoma or infected seroma and 18.1 % had outpatient seroma aspiration. Surgical margins were R0/R1 in 93.7 % of patients and R2 in 6.3 % with a LR rate of 8.4 % and 75 % respectively at median time of 54 months. One- and 5-year LDFS was 100 % and 88.4 %, respectively. DR rate was 0.8 % (1/127) this patient had pleomorphic liposarcomatous transformation on recurrence and subsequently developed distant metastases. No patients died of disease.

CONCLUSION

Function-preserving marginal resection of non-coelomic ALTs has low morbidity, low LR and extremely low rates of distant relapse. Patients with lower limb ALT were found to have significantly lower LR, which may impact follow-up protocols.

Tumor-to-bone distance and radiomic features on MRI distinguish intramuscular lipomas from well-differentiated liposarcomas

Background

To develop a machine learning model based on tumor-to-bone distance and radiomic features derived from preoperative MRI images to distinguish intramuscular (IM) lipomas and atypical lipomatous tumors/well-differentiated liposarcomas (ALTs/WDLSs) and compared with radiologists.

Methods

The study included patients with IM lipomas and ALTs/WDLSs diagnosed between 2010 and 2022, and with MRI scans (sequence/field strength: T1-weighted (T1W) imaging at 1.5 or 3.0 Tesla MRI). Manual segmentation of tumors based on the three-dimensional T1W images was performed by two observers to appraise the intra- and interobserver variability. After radiomic features and tumor-to-bone distance were extracted, it was used to train a machine learning model to distinguish IM lipomas and ALTs/WDLSs. Both feature selection and classification steps were performed using Least Absolute Shrinkage and Selection Operator logistic regression. The performance of the classification model was assessed using a tenfold cross-validation strategy and subsequently evaluated using the receiver operating characteristic curve (ROC) analysis. The classification agreement of two experienced musculoskeletal (MSK) radiologists was assessed using the kappa statistics. The diagnosis accuracy of each radiologist was evaluated using the final pathological results as the gold standard. Additionally, we compared the performance of the model and two radiologists in terms of the area under the receiver operator characteristic curves (AUCs) using the Delong’s test.

Results

There were 68 tumors (38 IM lipomas and 30 ALTs/WDLSs). The AUC of the machine learning model was 0.88 [95% CI 0.72–1] (sensitivity, 91.6%; specificity, 85.7%; and accuracy, 89.0%). For Radiologist 1, the AUC was 0.94 [95% CI 0.87–1] (sensitivity, 97.4%; specificity, 90.9%; and accuracy, 95.0%), and as to Radiologist 2, the AUC was 0.91 [95% CI 0.83–0.99] (sensitivity, 100%; specificity, 81.8%; and accuracy, 93.3%). The classification agreement of the radiologists was 0.89 of kappa value (95% CI 0.76–1). Although the AUC of the model was lower than of two experienced MSK radiologists, there was no statistically significant difference between the model and two radiologists (all P > 0.05).

Conclusions

The novel machine learning model based on tumor-to-bone distance and radiomic features is a noninvasive procedure that has the potential for distinguishing IM lipomas from ALTs/WDLSs. The predictive features that suggested malignancy were size, shape, depth, texture, histogram, and tumor-to-bone distance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13018-023-03718-4.

Robustness of Radiomic Features: Two-Dimensional versus Three-Dimensional MRI-Based Feature Reproducibility in Lipomatous Soft-Tissue Tumors

This retrospective study aimed to compare the intra- and inter-observer manual-segmentation variability in the feature reproducibility between two-dimensional (2D) and three-dimensional (3D) magnetic-resonance imaging (MRI)-based radiomic features. The study included patients with lipomatous soft-tissue tumors that were diagnosed with histopathology and underwent MRI scans. Tumor segmentation based on the 2D and 3D MRI images was performed by two observers to assess the intra- and inter-observer variability. In both the 2D and the 3D segmentations, the radiomic features were extracted from the normalized images. Regarding the stability of the features, the intraclass correlation coefficient (ICC) was used to evaluate the intra- and inter-observer segmentation variability. Features with ICC > 0.75 were considered reproducible. The degree of feature robustness was classified as low, moderate, or high. Additionally, we compared the efficacy of 2D and 3D contour-focused segmentation in terms of the effects of the stable feature rate, sensitivity, specificity, and diagnostic accuracy of machine learning on the reproducible features. In total, 93 and 107 features were extracted from the 2D and 3D images, respectively. Only 35 features from the 2D images and 63 features from the 3D images were reproducible. The stable feature rate for the 3D segmentation was more significant than for the 2D segmentation (58.9% vs. 37.6%, p = 0.002). The majority of the features for the 3D segmentation had moderate-to-high robustness, while 40.9% of the features for the 2D segmentation had low robustness. The diagnostic accuracy of the machine-learning model for the 2D segmentation was close to that for the 3D segmentation (88% vs. 90%). In both the 2D and the 3D segmentation, the specificity values were equal to 100%. However, the sensitivity for the 2D segmentation was lower than for the 3D segmentation (75% vs. 83%). For the 2D + 3D radiomic features, the model achieved a diagnostic accuracy of 87% (sensitivity, 100%, and specificity, 80%). Both 2D and 3D MRI-based radiomic features of lipomatous soft-tissue tumors are reproducible. With a higher stable feature rate, 3D contour-focused segmentation should be selected for the feature-extraction process.

Adjuvant Radiation after Primary Resection of Atypical Lipomatous Tumors of the Extremity Reduces Local Recurrence but Increases Complications: A Multicenter Evaluation

Background

Radiation after resection of an atypical lipomatous tumor (ALT) is controversial. This study evaluates local control and complications after the first resection of ALTs of the extremity with or without adjuvant radiation.

Methods

A dual institution, retrospective review of patients treated from 1995 to 2020 with first-time resection of an ALT in the extremity was performed. In total, 102 patients underwent adjuvant radiation (XRT group) and 68 patients were treated with surgery alone (no-XRT group). The median follow-up time was 4.6 years (interquartile range (IQR) 2.0–7.3 years). The median radiation dose was 60 Gy (IQR 55–66 Gy). Univariable and multivariable analyses evaluated the association of patient, tumor, and treatment variables with recurrence and complications. Kaplan–Meier analysis evaluated local recurrence-free survival (LRFS) and time to complication.

Results

The overall incidence of local recurrence was 1% (1/102) in the XRT group and 24% (16/68) in the no-XRT group (p < 0.001). The median time-to-recurrence was 8.2 years (IQR 6.5–10.5 years). In the XRT and the no-XRT groups, 5-yr LRFS was 98% and 92% (p=0.21) and 10-yr LRFS was 98% and 41% (p < 0.001), respectively. The absence of radiation (HR = 23.63, 95% CI (3.09–180.48); p < 0.001) and R2 surgical resection margins (HR = 11.04, 95% CI (2.07–59.03); p < 0.001) incurred a 23-fold and 11-fold increased risk of local recurrence, respectively, while tumor size, depth, location, and neurovascular involvement were not found to be independent predictors of recurrence. The complication rate was 37% (38/102) in the XRT group and 10% (7/68) in the no-XRT group (p < 0.001). Eight patients (8/102, 8%) required surgical management for complication in the XRT group compared with two patients (2/68, 3%) in the no-XRT group (p=0.10). Higher radiation dose had a modest correlation with increased severity of complication (ρ=0.24; p=0.02).

Conclusions

Adjuvant radiation after first-time resection of an ALT of the extremity was associated with a significantly reduced risk of local recurrence but a three-fold increase in complication rate. These data support a 10-year follow-up for these patients and inform a notable clinical trade-off if considering adjuvant radiation for this tumor with recurrent potential.