Clinical features of multiply recurrent retroperitoneal liposarcoma: A single-center experience

Explainable machine learning predicts survival of retroperitoneal liposarcoma: A study based on the SEER database and external validation in China

OBJECTIVE

We have developed explainable machine learning models to predict the overall survival (OS) of retroperitoneal liposarcoma (RLPS) patients. This approach aims to enhance the explainability and transparency of our modeling results.

METHODS

We collected clinicopathological information of RLPS patients from The Surveillance, Epidemiology, and End Results (SEER) database and allocated them into training and validation sets with a 7:3 ratio. Simultaneously, we obtained an external validation cohort from The First Affiliated Hospital of Naval Medical University (Shanghai, China). We performed LASSO regression and multivariate Cox proportional hazards analysis to identify relevant risk factors, which were then combined to develop six machine learning (ML) models: Cox proportional hazards model (Coxph), random survival forest (RSF), ranger, gradient boosting with component-wise linear models (GBM), decision trees, and boosting trees. The predictive performance of these ML models was evaluated using the concordance index (C-index), the integrated cumulative/dynamic area under the curve (AUC), and the integrated Brier score, as well as the Cox-Snell residual plot. We also used time-dependent variable importance, analysis of partial dependence survival plots, and the generation of aggregated survival SHapley Additive exPlanations (SurvSHAP) plots to provide a global explanation of the optimal model. Additionally, SurvSHAP (t) and survival local interpretable model-agnostic explanations (SurvLIME) plots were used to provide a local explanation of the optimal model.

RESULTS

The final ML models are consisted of six factors: patient's age, gender, marital status, surgical history, as well as tumor's histopathological classification, histological grade, and SEER stage. Our prognostic model exhibits significant discriminative ability, particularly with the ranger model performing optimally. In the training set, validation set, and external validation set, the AUC for 1, 3, and 5 year OS are all above 0.83, and the integrated Brier scores are consistently below 0.15. The explainability analysis of the ranger model also indicates that histological grade, histopathological classification, and age are the most influential factors in predicting OS.

CONCLUSIONS

The ranger ML prognostic model exhibits optimal performance and can be utilized to predict the OS of RLPS patients, offering valuable and crucial references for clinical physicians to make informed decisions in advance.

Identification of predictors for short-term recurrence: comprehensive analysis of 296 retroperitoneal liposarcoma cases

BACKGROUND

The short-term (≤ 1 year) recurrence (STR) is the primary determinant impacting both the life quality and survival duration in patients who have undergone surgical resection for retroperitoneal liposarcoma (RPLS), a condition with intricate and ambiguous pathogenesis. The purpose of this study was to analyze the risk factors associated with STR in cases of RPLS and primary retroperitoneal liposarcoma (PRPLS).

METHODS

For this retrospective observational study, a total of 296 RPLS cases were selected as research subjects, who experienced tumor recurrence during the follow-up period. The Local recurrence-free survival (LRFS) rates were estimated using the Kaplan-Meier method and subsequently compared between groups utilizing the log-rank test. The subsequent analyses involved univariate and multivariate logistic regression to identify predictors of STR in RPLS cases. Additionally, a logistic regression model was constructed for PRPLS.

RESULTS

The 1-, 3-, and 5-year LRFS rates of the 296 RPLS cases were 51.7%, 16.9%, and 7.1%, respectively. In the univariate analysis, several factors were found to be associated with STR, including preoperative neutrophil/lymphocyte ratio (NLR), smoking history, surgical frequency, combined organ excision, operative time, intraoperative bleeding, transfer to the intensive care unit (ICU), multiple primary tumors, tumor shape and capsule characteristics, histological subtype, and presence of tumor necrosis. The elevated preoperative NLR, surgical frequency of ≥ 3 times, transfer to the ICU, presence of multiple primary tumors, and tumor necrosis were identified as independent risk factors for STR in surgically resected RPLS. Conversely, diabetes, intact tumor capsule, and well-differentiated histological subtype appeared to be independent protective factors. Analysis for PRPLS revealed that tumor capsule and tumor necrosis were independent predictors of STR.

CONCLUSIONS

The elevated preoperative NLR, surgical frequency of ≥ 3 times, transfer to the ICU, presence of multiple primary tumors, tumor necrosis, and tumor capsule were expected to serve as predictive factors of STR for surgical resected RPLS and PRPLS.

Predictors and outcomes of recurrent retroperitoneal liposarcoma: new insights into its recurrence patterns

BACKGROUND

The clinical profiles of recurrent retroperitoneal liposarcoma (RLS) need to be explored. The recurrence patterns of RLS are controversial and ambiguous.

METHODS

A total of 138 patients with recurrent RLS were finally recruited in the study. The analysis of overall survival (OS) and recurrence-free survival (RFS) was performed by Kaplan‒Meier analysis. To identify independent prognostic factors, all significant variables on univariate Cox regression analysis (P ≤ 0.05) were subjected to multivariate Cox regression analysis. The corresponding nomogram model was further built to predict the survival status of patients.

RESULTS

Among patients, the 1-, 3-, and 5-year OS rates were 70.7%, 35.9% and 30.9%, respectively. The 1-, 3- and 5-year RFS rates of the 55 patients who underwent R0 resection were 76.1%, 50.8% and 34.4%, respectively. The multivariate analysis revealed that resection method, tumor size, status of pathological differentiation, pathological subtypes and recurrence pattern were independent risk factors for OS or RFS. Patients with distant recurrence (DR) pattern usually had multifocal tumors (90.5% vs. 74.7%, P < 0.05); they were prone to experience changes of pathological differentiation (69.9% vs. 33.3%, P < 0.05) and had a better prognosis than those with local recurrence (LR) pattern. R0 resection and combined organ resection favored the survival of patients with DR pattern in some cases.

CONCLUSIONS

Patients with DR pattern had better prognosis, and they may benefit more from aggressive combined resection than those with LR pattern. Classifying the recurrence patterns of RLS provides guidance for individualized clinical management of recurrent RLS.

Clinical and Pathological Features of Primary Orbital Liposarcoma in Chinese Patients

PURPOSE

Liposarcomas are rare in the orbit. We analyzed a series of primary liposarcomas to determine the features unique to the orbit.

METHODS

Records from 10 Chinese patients treated for primary orbital liposarcoma at Beijing Tongren Hospital, Capital Medical University, between September 2009 and September 2020 were reviewed.

RESULTS

This cohort included four men and six women with age of onset ranging from 18 to 80 years. The pathology was myxoid liposarcoma in five patients, dedifferentiated liposarcoma in two patients, well-differentiated liposarcoma and pleomorphic liposarcoma in one patient each, and dedifferentiated liposarcoma and well-differentiated liposarcoma co-existing in one case. Magnetic resonance imaging (MRI) revealed a well-defined, irregular, or lobulated mass in the orbit, which contained components that were suppressible in the fat-suppression sequence, as well as components that were enhanced by gadolinium enhancement. Nine patients relapsed after surgery, with a mean recurrence of 2.44, and one patient was lost to follow-up. The interval between treatment and first recurrence ranged from 4 months to 16 years; 55.6% of patients with orbital liposarcoma relapsed within one year. Three patients underwent local excision alone, four patients underwent excision combined with radiotherapy, and three patients underwent exenteration. Half of the patients were misdiagnosed in the pathologic diagnosis after their first or multiple surgeries. No distant metastasis, death from tumors, or invasion of adjacent organs was observed after 21-150 months of follow-up.

CONCLUSION

Orbital liposarcoma is easily misdiagnosed and prone to recurrence; however, MRI findings may help identify orbital liposarcoma prior to surgery. The optimal treatment choice remains to be discussed.

Primary dedifferentiated liposarcoma of the pancreas: A case report and literature review

BACKGROUND

Dedifferentiated liposarcoma (DDLPS) is a high-grade invasive tumor that more commonly occurs in the retroperitoneum, followed by the thighs and groin. DDLPS in the pancreas is very rare.

CASE SUMMARY

A patient underwent CT examination due to hidden pain in the upper abdomen, which revealed a pancreatic space occupying lesion of unknown nature. Based on the patient's preoperative medical history, physical examination, and auxiliary examination, it was considered that there was a huge space occupying lesion in the head and neck of the pancreas, with clear boundaries and surgical indications. The patient underwent pancreaticoduodenectomy at our hospital, and the postoperative pathology revealed a DDLPS of the pancreas. Three months after the surgery, tumor recurrence occurred. Dacarbazine combined with epirubicin chemotherapy had a poor effect, and the patient passed away 18 mo later.

CONCLUSION

Due to the fact that DDLPS of the pancreas is usually not significantly responsive to radiotherapy and chemotherapy, the currently most effective treatment method for DDLPS of the pancreas is resection with negative margin under a microscope. However, due to the deep location of liposarcoma in the pancreas and its proximity to many surrounding organs, it is difficult to completely remove the tumor, and many patients may develop regional recurrence.

Correlation Analysis Between Demographic, Surgical, and Pathological Characteristics with Local Recurrence-Free Survival for Surgical Resected Retroperitoneal Liposarcoma

BACKGROUND

As the leading cause of mortality for retroperitoneal liposarcoma (RPLS) cases, postoperative recurrence has complicated and unclear risk factors. This study was conducted to explore the correlations between demographic, surgical, and pathological characteristics with local recurrence-free survival (LRFS) for surgical resected RPLS.

METHODS

RPLS cases that underwent radical operation were considered to be included in this analysis. LRFS rates were estimated based on the Kaplan-Meier method and were compared between groups by the log-rank test. Cox proportional hazard regression models were constructed to identified the predictors of LRFS. Subsequently, the independent predictors acquired from multivariate analyses were used to construct a nomogram.

RESULTS

348 RPLS cases who underwent radical operation were included. Of the 348 cases, 333 had tumor recurrence or with a follow-up period ≥5 years. Thus, 296 (88.9%) of the 333 cases had recurrent disease, and the median LRFS duration of 296 recurrence cases was 17.0 (95% confidence interval (CI) 13.2-20.8) months. Multivariate analysis identified the preoperative neutrophil/lymphocyte ratio (NLR), surgical frequency, operative time, tumor shape, histological subtype, and tumor necrosis as independent predictors of LRFS. Based on above independent predictors, a nomogram was constructed to predict the 1-, 3-, and 5-year LRFS of surgical resected RPLS.

CONCLUSION

Elevated preoperative NLR, ≥2nd time surgical frequency, extended operation time, irregular tumor shape, no well-differentiated histological subtype, and tumor necrosis could be used as predictors of LRFS for surgical resected RPLS.

Recurrent metastatic retroperitoneal dedifferentiated liposarcoma: a case report and literature review

BACKGROUND

Retroperitoneal liposarcoma (RPLPS), a rare tumor, is often treated using surgical procedures as the first choice for treatment. However, there is no consensus on the scope of surgical resection. In addition, the treatment outcomes of conventional radiotherapy and chemotherapy have not been satisfactory, particularly for specific types of LPS, such as dedifferentiated LPS. In this case study, we present a brief review of other cases of RPLPS, highlighting the selection of surgical scope for RPLPS and related adjuvant treatment for advanced RPLPS.

CASE PRESENTATION

A case study is reported regarding an extremely rare recurrent and metastatic retroperitoneal dedifferentiated LPS. The primary RPLPS tumor, with a diameter of 20 cm and a weight of 2.5 kg, occupied the whole left abdomen and adhered to the left kidney. A surgical tumor resection combined with a left nephrectomy is performed. During the 6th -month postoperative follow-up examination, we observed the local recurrence of the tumor in the operation area, in addition to multiple metastatic tumors in both lungs. Further, the prescribed 3-month targeted treatment with anlotinib significantly reduced the size of the metastatic pulmonary tumors. However, the recurrent retroperitoneal tumors showed no significant change in size. Eventually, we observed no substantial evidence of tumor progression, with the patient's condition under control.

CONCLUSION

The case demonstrated that the postoperative recurrence of widespread RPLPS required R0 resection to cure the disease, considering targeted therapy for advanced RPLPS control.

Development and Validation of a Prognostic Model to Predict the Prognosis of Patients With Retroperitoneal Liposarcoma: A Large International Population-Based Cohort Study

Background

Retroperitoneal liposarcomas (RPLs), sarcoma of mesenchymal origin, are the most common soft tissue sarcomas (STS) of the retroperitoneum. Given the rarity of RPLs, the prognostic values of clinicopathological features in the patients remain unclear. The nomogram can provide a visual interface to aid in calculating the predicted probability that a patient will achieve a particular clinical endpoint and communication with patients.

Methods

We included a total of 1,392 RPLs patients diagnosed between 2004 and 2015 from the Surveillance, Epidemiology, and End Results (SEER) database. For nomogram construction and validation, patients in the SEER database were divided randomly into the training cohort and internal validation cohort at a ratio of 7:3, while 65 patients with RPLs from our center between 2010 and 2016 served as the external validation cohort. The OS curves were drawn using the Kaplan-Meier method and assessed using the log-rank test. Moreover, Fine and Gray's competing-risk regression models were conducted to assess CSS. Univariate and multivariate analyses were performed to select the prognostic factors for survival time. We constructed a predictive nomogram based on the results of the multivariate analyses.

Results

Through univariate and multivariate analyses, it is found that age, histological grade, classification, SEER stage, surgery constitute significant risk factors for OS, and age, classification, SEER stage, AJCC M stage, surgery, and tumor size constitute risk factors for CSS. We found that the nomogram provided a good assessment of OS and CSS at 1, 3, and 5 years in patients with RPLs (1-year OS: (training cohort: AUC = 0.755 (95% CI, 0.714, 0.796); internal validation cohort: AUC = 0.754 (95% CI, 0.681, 0.827); external validation cohort: AUC = 0.793 (95% CI, 0.651, 0.935)); 3-year OS: (training cohort: AUC = 0.782 (95% CI, 0.752, 0.811); internal validation cohort: AUC = 0.788 (95% CI, 0.736, 0.841); external validation cohort: AUC = 0.863 (95% CI, 0.773, 0.954)); 5-year OS: (training cohort: AUC = 0.780 (95% CI, 0.752, 0.808); internal validation cohort: AUC = 0.783 (95% CI, 0.732, 0.834); external validation cohort: AUC = 0.854 (95% CI, 0.762, 0.945)); 1-year CSS: (training cohort: AUC = 0.769 (95% CI, 0.717, 0.821); internal validation cohort: AUC = 0.753 (95% CI, 0.668, 0.838); external validation cohort: AUC = 0.799 (95% CI, 0.616, 0.981)); 3-year CSS: (training cohort: AUC = 0.777 (95% CI, 0.742, 0.811); internal validation cohort: AUC = 0.787 (95% CI, 0.726, 0.849); external validation cohort: AUC = 0.808 (95% CI, 0.673, 0.943)); 5-year CSS: (training cohort: AUC = 0.773 (95% CI, 0.741, 0.805); internal validation cohort: AUC = 0.768 (95% CI, 0.709, 0.827); external validation cohort: AUC = 0.829 (95% CI, 0.712, 0.945))). The calibration plots for the training, internal validation, and external validation cohorts at 1-, 3-, and 5-year OS and CSS indicated that the predicted survival rates closely correspond to the actual survival rates.

Conclusion

We constructed and externally validated an unprecedented nomogram prognostic model for patients with RPLs. The nomogram can be used as a potential, objective, and supplementary tool for clinicians to predict the prognosis of RPLs patients around the world.

Management of retroperitoneal sarcoma involving the iliac artery: Single-center surgical experience

BACKGROUND

Management of retroperitoneal sarcoma (RPS) involving the iliac artery is challenging and requires the concerted efforts of multidisciplinary team (MDT) members during surgical treatment.

AIM

To summarize the clinicopathologic features of RPS involving the iliac artery and our retroperitoneal soft tissue tumor MDT surgical experience.

METHODS

In this retrospective study, 15 patients with RPS involving the iliac artery who underwent surgery at our retroperitoneal soft tissue tumor center from July 2004 to June 2020 were analyzed. Statistical analyses were performed by Student’s t-test with SPSS 16.0.

RESULTS

Complete tumor resection (R0/R1) and iliac artery reconstruction were achieved in all 15 patients. All the operations were successful, with no serious complications or perioperative death. Resection with bilateral iliac artery reconstruction required a higher intraoperative blood transfusion volume than resection with unilateral iliac artery reconstruction. Recurrent cases were more likely to bleed and required a higher blood transfusion volume than primary cases. As of January 2021, 11 patients were alive, and 4 had died. Local recurrence occurred in two patients, one of whom developed liver metastasis.

CONCLUSION

Resection of RPS involving iliac vessels is feasible and effective when performed by MDT members. Iliac artery oncovascular resection and reconstruction are key to a successful operation. Adequate blood preparation is important for successful completion of surgery.

Recurrent retroperitoneal liposarcoma: A case report and literature review

Retroperitoneal liposarcoma frequently recurs within 2 years of the initial surgical resection. For the early detection of recurrent retroperitoneal liposarcomas, a shorter follow-up interval with CT or MRI would be helpful.