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

2021 ◽  
pp. 958-972
Author(s):  
Amandine Crombé ◽  
Sophie Cousin ◽  
Mariella Spalato-Ceruso ◽  
François Le Loarer ◽  
Maud Toulmonde ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Standard Model ◽  
Cox Regression ◽  
Soft Tissue Sarcomas ◽  
Histologic Response ◽  
Surgical Specimen ◽  
Metastatic Relapse ◽  
The Standard Model

PURPOSE Neoadjuvant chemotherapy (NAC) has been increasingly used in patients with locally advanced high-risk soft tissue sarcomas in the past decade, but definition and prognostic impact of a good histologic response (GHR) are lacking. Our aim was to investigate which histologic feature from the post-NAC surgical specimen independently correlated with metastatic relapse-free survival (MFS) in combination with clinical, radiologic, and pathologic features using a machine learning approach. METHODS This retrospective study included 175 consecutive patients (median age: 59 years, 75 women) with resectable disease, treated with anthracycline-based NAC between 1989 and 2015 in our sarcoma reference center, and with quantitative histopathologic analysis of the surgical specimen. The outcome of interest was the MFS. A multimodel, multivariate survival analysis was used to define GHR. The added prognostic value of GHR was investigated through the comparisons with the standard model (including histologic grade, size, and depth) and SARCULATOR nomogram using concordance indices (c-index) and Monte-Carlo cross-validation. RESULTS Seventy-two patients (72 of 175, 41.1%) had a metastatic relapse. Stepwise Cox regression, random survival forests, and least absolute shrinkage and selection operator–penalized Cox regression all converged toward the same definition for GHR, ie, < 5% stainable tumor cells. The five-year MFS probability was 1 (95% CI, 1 to 1) in patients with GHR versus 0.73 (95% CI, 0.65 to 0.81) in patients without GHR (log-rank P = .0122). The final prognostic model incorporating the GHR was significantly better than the standard model and SARCULATOR (average c-index in testing sets = 0.72 [95% CI, 0.61 to 0.82] v 0.57 [95% CI, 0.44 to 0.70] and 0.54 [95% CI, 0.45 to 0.64], respectively; P = .0414 and .0091). CONCLUSION Histologic response to NAC improves the prediction of MFS in patients with soft tissue sarcoma and represents a possible end point in future studies exploring innovative regimens in the neoadjuvant setting.

Nuclear SMAD4 as a predictor of survival in patientes with extremity soft tissue sarcomas submitted to neoadjuvant chemotherapy.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 10586-10586
Author(s):  
Isabela Werneck Cunha ◽  
Ranyell Spencer Sobreira Batista ◽  
Paulo Roberto Stevanato ◽  
Samuel Aguiar ◽  
Ademar Lopes ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Locally Advanced ◽  
Neoadjuvant Treatment ◽  
Soft Tissue Sarcomas ◽  
Disease Free Survival ◽  
Chemotherapy Response ◽  
Surgical Specimen ◽  
Viable Cells ◽  
Low Expression

10586 Background: Neoadjuvant chemotherapy for locally advanced soft tissue sarcomas, although not standard, represents a promising option for resectable tumours. The discovery of biological predictors of chemotherapy response highlights the possibility to develop individualised therapeutic approaches in selected group of patients or predict survival also. The SMAD4 protein, a member of TGFβ superfamily has a role in progression and tumor metastasis and may be involved sarcomas recurrence. Methods: 30 patients with soft tissue sarcomas (STS) of high-grade located in extremities treated with neoadjuvant doxorubicin and ifosfamide chemotherapy were observed prospectively since January 2005 to June 2011. All patients were submitted to radiation therapy adjuvant. Surgical specimens after neoadjuvant treatment were evaluated of SMAD4 nuclear expression by immuno-histochemistry and percentage of viable cells Results: The median follow-up time was 42 months. The overall survival (OS) was 91.7% in patients with low expression SMAD4 nuclear protein associated with ≤10% of viable cells (n=12) in the surgical specimen and 68.9% in the remaining patients. Likewise, the disease free survival (DSF) was 91.7% versus 38.6% (p 0.01) respectively. Conclusions: The combination of nuclear SMAD4 low expression and 10% or less of viable cells in the surgical specimen was statistically significant in better DFS in patients with locally advanced extremity STS treated with neoajuvant chemotherapy with benefit in OS.

53 Neoadjuvant chemotherapy and radiotherapy for large soft tissue sarcomas

1996 ◽  
Vol 36 (1) ◽  
pp. 185 ◽  
Author(s):  
Ira J. Spiro ◽  
Damian Dupuis ◽  
Herman Suit ◽  
Henry Mankin ◽  
Candace Jennings ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Soft Tissue Sarcomas

MR-imaging changes of musculoskeletal soft-tissue sarcomas associated with neoadjuvant chemotherapy and hyperthermia

2003 ◽  
Vol 19 (4) ◽  
pp. 391-401 ◽  
Author(s):  
A. Baur ◽  
A. Stäbler ◽  
C. M. Wendtner ◽  
S. Arbogast ◽  
S. A. Rahman ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Mr Imaging ◽  
Soft Tissue Sarcomas

scholarly journals T2 -based MRI Delta-radiomics improve response prediction in soft-tissue sarcomas treated by neoadjuvant chemotherapy.

2018 ◽  
Vol 50 (2) ◽  
pp. 497-510 ◽  
Author(s):  
Amandine Crombé ◽  
Cynthia Périer ◽  
Michèle Kind ◽  
Baudouin Denis De Senneville ◽  
François Le Loarer ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Soft Tissue Sarcomas ◽  
Response Prediction

scholarly journals A Novel Four-Gene Prognostic Signature for Prediction of Survival in Patients with Soft Tissue Sarcoma

Cancers ◽  
2021 ◽  
Vol 13 (22) ◽  
pp. 5837
Author(s):  
Changwu Wu ◽  
Siming Gong ◽  
Georg Osterhoff ◽  
Nikolas Schopow
Keyword(s):  
Soft Tissue ◽  
Risk Score ◽  
Cox Regression ◽  
Soft Tissue Sarcomas ◽  
Gene Signature ◽  
Gene Set Enrichment Analysis ◽  
The Cancer Genome Atlas ◽  
Prognostic Models ◽  
Malignant Tumours ◽  
Free Survival

Soft tissue sarcomas (STS), a group of rare malignant tumours with high tissue heterogeneity, still lack effective clinical stratification and prognostic models. Therefore, we conducted this study to establish a reliable prognostic gene signature. Using 189 STS patients’ data from The Cancer Genome Atlas database, a four-gene signature including DHRS3, JRK, TARDBP and TTC3 was established. A risk score based on this gene signature was able to divide STS patients into a low-risk and a high-risk group. The latter had significantly worse overall survival (OS) and relapse free survival (RFS), and Cox regression analyses showed that the risk score is an independent prognostic factor. Nomograms containing the four-gene signature have also been established and have been verified through calibration curves. In addition, the predictive ability of this four-gene signature for STS metastasis free survival was verified in an independent cohort (309 STS patients from the Gene Expression Omnibus database). Finally, Gene Set Enrichment Analysis indicated that the four-gene signature may be related to some pathways associated with tumorigenesis, growth, and metastasis. In conclusion, our study establishes a novel four-gene signature and clinically feasible nomograms to predict the OS and RFS. This can help personalized treatment decisions, long-term patient management, and possible future development of targeted therapy.

scholarly journals Machine learning analysis of gene expression data reveals novel diagnostic and prognostic biomarkers and identifies therapeutic targets for soft tissue sarcomas

2019 ◽  
Vol 15 (2) ◽  
pp. e1006826 ◽  
Author(s):  
David G. P. van IJzendoorn ◽  
Karoly Szuhai ◽  
Inge H. Briaire-de Bruijn ◽  
Marie Kostine ◽  
Marieke L. Kuijjer ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Soft Tissue ◽  
Gene Expression Data ◽  
Therapeutic Targets ◽  
Soft Tissue Sarcomas ◽  
Prognostic Biomarkers ◽  
Expression Data ◽  
Learning Analysis

Risk assessment in high grade sarcoma patients during neoadjuvant chemotherapy using multiple tracer PET

2006 ◽  
Vol 24 (18_suppl) ◽  
pp. 20006-20006
Author(s):  
J. F. Eary ◽  
E. Conrad ◽  
J. Link ◽  
A. Cizik ◽  
D. Mankoff ◽  
...  
Keyword(s):  
Drug Resistance ◽  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Soft Tissue Sarcoma ◽  
Pet Imaging ◽  
Cellular Proliferation ◽  
Soft Tissue Sarcomas ◽  
Response To Treatment ◽  
High Grade ◽  
Hypoxic Volume

20006 Background: Patients with high grade soft tissue sarcomas are treated with neoadjuvant chemotherapy. Sarcomas have biological features that may predict for poor outcome. Some of these features are tumor proliferation rate, level of tumor hypoxia, and upregulation of tumor drug resistance mechanisms. Methods: We have a group of specific PET imaging agents to quantify the level of activity of these tumor processes. Patients with soft tissue sarcomas receive [C-11]Thymidine (TdR) to assess cellular proliferation, [O-15] Water to quantify tumor blood flow and to serve as the input function for quantification of the other tracers, [C-11]Verapamil to assess drug resistance mechanism activity, and [F-18]Fluoromisonidazole) FMISO to quantify changes in tumor hypoxic volume in response to treatment. These studies are performed in a single PET imaging session prior to neoadjuvant chemotherapy, after the second of four cycles of therapy and in the week prior to resection. Results: An example of this complex study result, is demonstrated by a recent patient with a high grade soft tissue sarcoma. The tumor showed increased TdR uptake, a moderate hypoxic volume, and [C-11] verapamil uptake prior to initiation of neoadjuvant adriamycin based chemotherapy. After 2 cycles of therapy, there was a significant decrease in the maximum level and volume of TdR uptake and a large reduction in tumor hypoxic volume. Conclusions: These data would imply a high risk soft tissue sarcoma due the presence of increased cellular proliferation, a significant hypoxic volume and the absence of p-glycoprotein activity determined by the presence of [C-11]Verapamil uptake. However, early response is also suggested by the findings above. Patient outcome will be assessed and correlated with these tumor parameters to further understand what tumor biological risk factors can be quantified non-invasively and repeated throughout the clinical course in soft tissue sarcoma patients. Supported by NIH NCI PO1 42045–18 and S10 RR017229–01 [Table: see text] No significant financial relationships to disclose.

Correlation of FDG PET-CT with histologic response after neoadjuvant chemotherapy for soft tissue sarcomas

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. 10583-10583
Author(s):  
E. Y. Cheng ◽  
J. W. Froelich ◽  
J. C. Manivel ◽  
B. J. Weigel ◽  
K. M. Skubitz
Keyword(s):  
Soft Tissue ◽  
Fdg Pet ◽  
Soft Tissue Sarcomas ◽  
Response To Treatment ◽  
Additional Patient ◽  
High Grade ◽  
Continuous Variables ◽  
Histologic Response ◽  
Pet Ct ◽  
Fdg Pet Ct

10583 Background: Surrogate endpoints for survival are needed to allow rapid assessment of new therapies without doing lengthy studies using a survival endpoint. Non-invasive assessment of treatment response is also needed to guide chemotherapy. FDG- PET-CT has potential for assessing response to treatment in sarcoma. This study's goal was to correlate FDG-PET-CT, along with standard CT, with histologic response after chemotherapy for high grade soft tissue sarcomas before resection. Methods: Patients with high grade soft tissue sarcomas > 5 cm were enrolled in a prospective clinical trial and given ifosfamide/doxorubicin before tumor excision. FDG-PET-CT was performed at baseline before treatment, after cycle 1, & just before surgery. Differences in both SUVmax (baseline to cycle 1 [B-1], baseline to surgery [B-3]) and CT criteria (RECIST 1 dimension [1D], RECIST 2D & Choi) were compared to histologic response (> or < 90%) upon excision. Results: 25 patients were enrolled and 4 had disease progression prior to completing all 3 PET-CT's yielding 21 evaluable cases. 5 patients had SUVmax change of <40%: 4/5 (80%) had histologic response < 90% & 1/5 (20%) had histologic response >90%. 16 patients had SUVmax change of >40%: 12/16 (75%) had histologic response >90% & 4/16 (25%) had histologic response <90%. A scatterplot of SUVmax change (baseline to surgery), & histologic response as continuous variables revealed a Spearman's correlation coefficient = 0.55 (p<0.01). Conclusions: A cutoff value of 40% reduction in SUVmax from baseline to surgery appeared to differentiate histologic responders. Using this to define PET response, a correlation between PET response, as well as RECIST 1D and 2D, and histologic response was observed. Additional patient follow-up & further study of FDG-PET-CT as a surrogate endpoint for histologic response and survival is warranted. [Table: see text] [Table: see text]

Sign in / Sign up

Export Citation Format

Share Document