scholarly journals Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics

Cancers ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1929
Author(s):  
Jan C. Peeken ◽  
Jan Neumann ◽  
Rebecca Asadpour ◽  
Yannik Leonhardt ◽  
Joao R. Moreira ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Soft Tissue Sarcomas ◽  
Treatment Decision ◽  
Staging System ◽  
Predictive Performance ◽  
Machine Learning Techniques ◽  
Clinical Staging ◽  
Imaging Features ◽  
Prognostic Assessment ◽  
Selection Operator

Background: In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients’ risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS). Methods: Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS. Results: ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification. Conclusions: T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.

Myxofibrosarcoma: clinical and prognostic value of MRI features

2020 ◽  
Vol 16 ◽  
Author(s):  
Paolo Spinnato ◽  
Andrea Sambri ◽  
Tomohiro Fujiwara ◽  
Luca Ceccarelli ◽  
Roberta Clinca ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Local Recurrence ◽  
Contrast Enhancement ◽  
Imaging Modality ◽  
Soft Tissue Sarcomas ◽  
The Elderly ◽  
High Rate ◽  
Imaging Features ◽  
High Grade ◽  
Mri Features

: Myxofibrosarcoma is one of the most common soft tissue sarcomas in the elderly. It is characterized by an extremely high rate of local recurrence, higher than other soft tissue tumors, and a relatively low risk of distant metastases.Magnetic resonance imaging (MRI) is the imaging modality of choice for the assessment of myxofibrosarcoma and plays a key role in the preoperative setting of these patients.MRI features associated with high risk of local recurrence are: high myxoid matrix content (water-like appearance of the lesions), high grade of contrast enhancement, presence of an infiltrative pattern (“tail sign”). On the other hand, MRI features associated with worse sarcoma specific survival are: large size of the lesion, deep location, high grade of contrast enhancement. Recognizing the above-mentioned imaging features of myxofibrosarcoma may be helpful to stratify the risk for local recurrence and disease-specific survival. Moreover, the surgical planning should be adjusted according to the MRI features

scholarly journals Development and External Validation of Deep-Learning-Based Tumor Grading Models in Soft-Tissue Sarcoma Patients Using MR Imaging

Cancers ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2866
Author(s):  
Fernando Navarro ◽  
Hendrik Dapper ◽  
Rebecca Asadpour ◽  
Carolin Knebel ◽  
Matthew B. Spraker ◽  
...  
Keyword(s):  
Deep Learning ◽  
Soft Tissue ◽  
Mr Imaging ◽  
Characteristic Curve ◽  
External Validation ◽  
Soft Tissue Sarcomas ◽  
Treatment Decision ◽  
Receiver Operator Characteristic Curve ◽  
Low Grade ◽  
Tumor Grading

Background: In patients with soft-tissue sarcomas, tumor grading constitutes a decisive factor to determine the best treatment decision. Tumor grading is obtained by pathological work-up after focal biopsies. Deep learning (DL)-based imaging analysis may pose an alternative way to characterize STS tissue. In this work, we sought to non-invasively differentiate tumor grading into low-grade (G1) and high-grade (G2/G3) STS using DL techniques based on MR-imaging. Methods: Contrast-enhanced T1-weighted fat-saturated (T1FSGd) MRI sequences and fat-saturated T2-weighted (T2FS) sequences were collected from two independent retrospective cohorts (training: 148 patients, testing: 158 patients). Tumor grading was determined following the French Federation of Cancer Centers Sarcoma Group in pre-therapeutic biopsies. DL models were developed using transfer learning based on the DenseNet 161 architecture. Results: The T1FSGd and T2FS-based DL models achieved area under the receiver operator characteristic curve (AUC) values of 0.75 and 0.76 on the test cohort, respectively. T1FSGd achieved the best F1-score of all models (0.90). The T2FS-based DL model was able to significantly risk-stratify for overall survival. Attention maps revealed relevant features within the tumor volume and in border regions. Conclusions: MRI-based DL models are capable of predicting tumor grading with good reproducibility in external validation.

scholarly journals DNA methylation patterns–based subtype distinction and identification of soft tissue sarcoma prognosis

2020 ◽  
Author(s):  
Zhengyuan Wu ◽  
Miao Yu ◽  
Jing-yuan Fan ◽  
Zhen-pei Wen ◽  
Tian-yu Ren ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Soft Tissue ◽  
Clinical Features ◽  
Soft Tissue Sarcomas ◽  
Survival Prediction ◽  
Biological Functions ◽  
Promoter Regions ◽  
Patient Prognosis ◽  
Selection Operator ◽  
Methylation Patterns

Abstract Background: Soft tissue sarcomas (STSs) are heterogeneous at the clinical with a variable tendency of aggressive behavior. Methods: In this study, we constructed a specific DNA methylation-based classification to identify the distinct prognosis-subtypes of STSs based on the DNA methylation spectrum from the TCGA database.Results: Eventually, samples were clustered into four subgroups, and their survival curves were distinct from each other. Meanwhile, the samples in each subgroup reflected differentially in several clinical features. Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis was also conducted on the genes of the corresponding promoter regions of the above‐described specific methylation sites, revealing that these genes were mainly concentrated in certain cancer‑associated biological functions and pathways. In addition, we calculated the differences among clustered methylation sites and performed the specific methylation sites with LASSO algorithm. The selection operator algorithm was employed to derive a risk signature model, and a prognostic signature based on these methylation sites performed well for risk stratification in STSs patients. At last, a nomogram consisted of clinical features and risk score was developed for the survival prediction. Conclusion: In conclusion, this study declares that DNA methylation-based STSs subtype classification is highly relevant for future development of personalized therapy as it identifies the prediction value of patient prognosis.

The diagnostic value of multimodality MRI in endometrial carcinoma staging

2016 ◽  
Vol 58 (5) ◽  
pp. 609-616 ◽  
Author(s):  
Lixin Du ◽  
Yongqiang Yu ◽  
Yuli Wang ◽  
Jun Xia ◽  
Xixiong Qiu ◽  
...  
Keyword(s):  
Endometrial Carcinoma ◽  
Stage Iv ◽  
Staging System ◽  
Diagnostic Value ◽  
Clinical Staging ◽  
Prognostic Assessment ◽  
Imaging Tool ◽  
Mri Staging ◽  
Gynecology And Obstetrics ◽  
Staging Accuracy

Background Multimodality magnetic resonance imaging (MRI) is an imaging technology that is used to integrate the structural and functional information of lesions. MRI can determine the staging of endometrial carcinoma, provide guidance for selection of surgical treatment and postoperative prognostic assessment, and has an important role in improving the survival of patients with endometrial carcinoma. Purpose To evaluate multimodality MRI staging accuracy for endometrial carcinoma based on the International Federation of Gynecology and Obstetrics (FIGO 2009) staging system. Material and Methods This is a retrospective study of the complete clinical and surgical pathology data from 83 patients with endometrial carcinoma treated between June 2011 and August 2015. Using a blind design, the preoperative clinical staging according to the current FIGO2009 MRI-based staging for each endometrial carcinoma was analyzed and corrected by postoperative histopathological results, which served as the staging standard. The role of multimodality MRI on clinical staging accuracy for endometrial carcinoma was studied. Results Based on the pathological evaluation after surgery, the 83 endometrial carcinoma patients were staged according to the current FIGO2009 staging criteria as: stage I, n = 56; stage II, n = 17; stage III, n = 7; and stage IV, n = 3. The multimodality MRI staging accuracy for endometrial carcinoma stages I–IV by FIGO2009 were 91.6% (76/83), 91.6% (76/83), 92.8% (77/83), and 97.6% (81/83), respectively. Conclusion Multimodality MRI is an important imaging tool in the pre-operative clinical staging of endometrial carcinoma. The current FIGO staging system appears to be a concise, reasonable, and practical set of criteria for the clinical management of endometrial carcinoma.

scholarly journals Predicting distant metastases in soft-tissue sarcomas from PET-CT scans using constrained hierarchical multi-modality feature learning

2021 ◽  
Author(s):  
Yige Peng ◽  
Lei Bi ◽  
Ashnil Kumar ◽  
Michael Fulham ◽  
David Dagan Feng ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Imaging Modality ◽  
Soft Tissue Sarcomas ◽  
Feature Learning ◽  
Distant Metastases ◽  
P Value ◽  
Imaging Features ◽  
Tumor Delineation ◽  
Positron Emission ◽  
Pet Ct

Abstract Objective: Positron emission tomography-computed tomography (PET-CT) is regarded as the imaging modality of choice for the management of soft-tissue sarcomas (STSs). Distant metastases (DM) are the leading cause of death in STS patients and early detection is important to effectively manage tumors with surgery, radiotherapy and chemotherapy. In this study, we aim to early detect DM in patients with STS using their PET-CT data. Approach: We derive a new convolutional neural network (CNN) method for early DM detection. The novelty of our method is the introduction of a constrained hierarchical multi-modality feature learning approach to integrate functional imaging (PET) features with anatomical imaging (CT) features. In addition, we removed the reliance on manual input, e.g., tumor delineation, for extracting imaging features. Main results: Our experimental results on a well-established benchmark PET-CT dataset show that our method achieved the highest accuracy (0.896) and AUC (0.903) scores when compared to the state-of-the-art methods (unpaired student’s t-test p-value < 0.05). Significance: Our method could be an effective and supportive tool to aid physicians in tumor quantification and in identifying image biomarkers for cancer treatment.

How well do we communicate risk? An evaluation of AJCC version 6 and 7 staging systems for soft tissue sarcomas.

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 10001-10001
Author(s):  
Robert G. Maki ◽  
Cristina R. Antonescu ◽  
Meera Hameed ◽  
Nicole H. Moraco ◽  
Samuel Singer ◽  
...  
Keyword(s):  
Soft Tissue ◽  
Soft Tissue Sarcomas ◽  
Staging System ◽  
Cancer Staging ◽  
Clinical Situation ◽  
Nodal Metastasis ◽  
Patient Specific ◽  
Cancer Center ◽  
Anatomic Site ◽  
Staging Systems

10001 Background: Cancer staging systems allow physicians to communicate risks of a particular clinical situation with one another and with patients. Few data have been presented to support the update of a commonly employed staging system for soft tissue sarcoma (STS). We examined American Joint Committee on Cancer (AJCC) versions 6 (2002) and 7 (2010) staging systems for patients with primary STS using a single institution clinically annotated prospective database. Methods: Subsets of the prospectively collected Memorial Sloan-Kettering Cancer Center STS database of 8647 patients from 1982 to 2010 were examined with respect to criteria of the AJCC versions 6 and 7 staging systems. Results: Tumor size does not appear to be adequately addressed in version 6 or 7. Relapse-free survival was statistically worse for increasing size of primary STS <5, 5-10, 10-15, and >15 cm; in comparison, overall survival decreased over three size categories (<5, 5-10, >10 cm). Tumor depth, a statistically significant factor in patient outcomes that is included in version 6, is functionally omitted in version 7. Patients with node involvement without other metastases fare statistically worse than patients with large, high grade tumors without nodal metastasis, as shown previously. Version 6 and 7 criteria do not address effects of primary anatomic site and histology, even for tumors with same FNCLCC grade. Sarcoma subtypes defined after publication of FNCLCC criteria are difficult to incorporate into existing guidelines. Conclusions: Improved prognostication of STS outcomes is better achieved by staging according to anatomic primary site, depth, and a larger number of size categories. Histology-specific nomograms improve prognostic accuracy, such as those for liposarcoma, GIST, or rhabdomyosarcoma. Staging accuracy increases at the cost of portability and simplicity. The increasing difficulties with use of a single STS staging system highlight the potential benefit of newer techniques, such as patient-specific nomograms or Bayesian networks. Staging systems will require significant modifications to incorporate increasingly sophisticated molecular diagnostics.

scholarly journals Leiomyosarcoma of the extremity deep soft tissues: analysis of factors predictive of survival and imaging features

2020 ◽  
Vol 7 (9) ◽  
pp. 647-651
Author(s):  
Osman Ciloglu ◽  
Rana Kapukaya
Keyword(s):  
Overall Survival ◽  
Survival Rate ◽  
Soft Tissue ◽  
Neoadjuvant Chemotherapy ◽  
Soft Tissues ◽  
Soft Tissue Sarcomas ◽  
Disease Free Survival ◽  
Magnetic Resonance Images ◽  
Tumor Type ◽  
Imaging Features

Objective:  This study aimed to report the visual outcomes of deeply located Leiomyosarcoma (LMS) in the extremities and treatment results. Methods: The histological diagnosis of each case was confirmed by the pathology council and only cases with LMS localized in the deep soft tissue of the limb were included in this study. Treatment-related factors such as all the visual features of the tumor, type of therapy, local and distant recurrence, follow-up time, and outcome were analyzed. Overall survival time was determined. Results: Evaluation was made of 17 patients, comprising 11 females and 6 males with a mean age of 64.35 years (range, 52-75 years). The localization of the primary lesion was the lower extremity in 14 patients (82.34%), and the upper extremity in 3 (17.34%). The average size of the lesions was 8.23 cm (range, 3-22 cm). All lesions were staged according to the TNM Classification of soft tissue sarcomas, as 3 (17.64%) patients in stage IIA, 9 (52.94%) in stage IIB, and 5 (29.41%) in stage IV. In the radiological features of the lesions, only two patients had scattered calcification and osseous pathology in the tumor tissue. The signal properties obtained in other soft tissue sarcomas on magnetic resonance images (MRI) were also present in these lesions. Neoadjuvant chemotherapy was applied to 5 of 17 patients, and surgical and adjuvant radiotherapy was applied to the remaining 12 patients. These patients were followed up for an average of 66 (23-111) months. Local recurrence occurred in 3 patients. The five-year disease-free survival rate was 58.8%, and the disease-survival rate was 64.7%. Conclusion: The most important result of this study was that the only effective factor on overall survival is tumor size (p <0.001). Neoadjuvant chemotherapy was not seen to have any significant effect on this disease.

Sign in / Sign up

Export Citation Format

Share Document