Prognosis prediction of extremity and trunk wall soft-tissue sarcomas treated with surgical resection with radiomic analysis based on random survival forest

Machine learning-based MRI radiomics to predict postoperative complications following peripheral nerve sheath tumour excision

This study sought to establish and validate a machine learning-based multi-sequence MRI radiomics model for predicting postoperative complications in patients with peripheral nerve sheath tumours. We conducted a retrospective analysis of 303 patients with pathologically confirmed tumours, extracting features from T1-weighted and T2-weighted MRI scans. Relevant radiomic features were identified through interclass correlation coefficient analysis, t-tests and least absolute shrinkage and selection operator techniques. A multi-sequence radiomics model was developed using the Light Gradient Boosting Machine classifier, alongside a clinical-radiomics model that incorporated clinical features. The models exhibited robust diagnostic performance, with areas under the receiver operating characteristic curve reaching 0.95 in the training cohort. These findings underscore the model's potential to accurately predict postoperative complications, providing crucial support for clinicians in devising personalized treatment strategies for patients with peripheral nerve sheath tumours.Level of evidence: Prognostic III.

Deep Learning Models for Predicting the Recurrence of Idiopathic Granulomatous Mastitis

Background and Aim

Idiopathic granulomatous mastitis (IGM) is a rare chronic inflammatory breast disease that presents significant challenges in diagnosis and treatment. Predicting the recurrence of IGM is crucial for effective patient management and improved treatment outcomes. This study aims to evaluate and compare the performance of different machine learning models, including logistic regression, random forest, and neural networks, in predicting IGM recurrence using patient data.

Methods

A retrospective analysis was conducted on 212 patients diagnosed with IGM. Collected data included comprehensive serological markers, tumor characteristics, and treatment history. The dataset was divided into a training set (70%) and a testing set (30%). Data preprocessing involved normalization, feature selection, and data augmentation to ensure model robustness. Three predictive models were developed and compared: logistic regression, random forest, and neural networks. Performance metrics such as accuracy, sensitivity, specificity, and area under the ROC curve (AUC) were used to evaluate each model's ability to predict IGM recurrence.

Results

The logistic regression model achieved an AUC of 0.837, 0.725 and 0.829 in the training cohort, validation cohort and test cohort. The random forest model showed improved performance with an AUC of 0.797, 0.755 and 0.793 in the training cohort, validation cohort and test cohort. The neural network model outperformed both the logistic regression and random forest models, with an AUC of 0.938, 0.880 and 0.913 and a better F1 score. Feature importance analysis indicated that variables such as smoking, surgery and a history of oral contraceptive use were most important in predicting recurrence.

Conclusion

This study demonstrates that, compared to logistic regression and random forest models, neural networks have superior performance in predicting the recurrence of granulomatous mastitis. The high accuracy and reliability of the neural network model highlight its potential clinical application in the early and accurate prediction of IGM recurrence.

A multimodal neural network with gradient blending improves predictions of survival and metastasis in sarcoma

The objective of this study is to develop a multimodal neural network (MMNN) model that analyzes clinical variables and MRI images of a soft tissue sarcoma (STS) patient, to predict overall survival and risk of distant metastases. We compare the performance of this MMNN to models based on clinical variables alone, radiomics models, and an unimodal neural network. We include patients aged 18 or older with biopsy-proven STS who underwent primary resection between January 1st, 2005, and December 31st, 2020 with complete outcome data and a pre-treatment MRI with both a T1 post-contrast sequence and a T2 fat-sat sequence available. A total of 9380 MRI slices containing sarcomas from 287 patients are available. Our MMNN accepts the entire 3D sarcoma volume from T1 and T2 MRIs and clinical variables. Gradient blending allows the clinical and image sub-networks to optimally converge without overfitting. Heat maps were generated to visualize the salient image features. Our MMNN outperformed all other models in predicting overall survival and the risk of distant metastases. The C-Index of our MMNN for overall survival is 0.77 and the C-Index for risk of distant metastases is 0.70. The provided heat maps demonstrate areas of sarcomas deemed most salient for predictions. Our multimodal neural network with gradient blending improves predictions of overall survival and risk of distant metastases in patients with soft tissue sarcoma. Future work enabling accurate subtype-specific predictions will likely utilize similar end-to-end multimodal neural network architecture and require prospective curation of high-quality data, the inclusion of genomic data, and the involvement of multiple centers through federated learning.

Extremity and Truncal Soft Tissue Sarcoma: Risk Assessment and Multidisciplinary Management

Extremity and truncal soft tissue sarcomas are a heterogeneous group of rare cancers that arise from mesenchymal tissues. Hence, the adoption of tailored risk assessment and prognostication tools plays a crucial role in optimizing the decision-making for which of the many possible treatment strategies to select. Management of these tumors requires a multidisciplinary strategy, which has seen significant development in recent decades. Surgery has emerged as the primary treatment approach, with the main goal of achieving microscopic negative tumor margins. To reduce the likelihood of local recurrence, loco-regional treatments such as radiation therapy and isolated limb perfusion are often added to the treatment regimen in combination with surgery. This approach also enables surgeons to perform limb-sparing surgery, particularly in cases where a positive tumor margin is expected. Chemotherapy may also provide a further benefit in decreasing the probability of local recurrence or reducing distant metastasis in selected patients. Selecting the optimal treatment strategy for these rare tumors is best accomplished by an experienced multi-disciplinary team.

The impact of radiomics in the management of soft tissue sarcoma

INTRODUCTION

Soft tissue sarcomas (STSs) are rare malignancies. Pre-therapeutic tumour grading and assessment are crucial in making treatment decisions. Radiomics is a high-throughput method for analysing imaging data, providing quantitative information beyond expert assessment. This review highlights the role of radiomic texture analysis in STSs evaluation.

MATERIALS AND METHODS

We conducted a systematic review according to the Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive search was conducted in PubMed/MEDLINE and Scopus using the search terms: 'radiomics [All Fields] AND ("soft tissue sarcoma" [All Fields] OR "soft tissue sarcomas" [All Fields])'. Only original articles, referring to humans, were included.

RESULTS

A preliminary search conducted on PubMed/MEDLINE and Scopus provided 74 and 93 studies respectively. Based on the previously described criteria, 49 papers were selected, with a publication range from July 2015 to June 2023. The main domains of interest were risk stratification, histological grading prediction, technical feasibility/reproductive aspects, treatment response.

CONCLUSIONS

With an increasing interest over the last years, the use of radiomics appears to have potential for assessing STSs from initial diagnosis to predicting treatment response. However, additional and extensive research is necessary to validate the effectiveness of radiomics parameters and to integrate them into a comprehensive decision support system.

CT and MRI radiomics of bone and soft-tissue sarcomas: an updated systematic review of reproducibility and validation strategies

OBJECTIVE

To systematically review radiomic feature reproducibility and model validation strategies in recent studies dealing with CT and MRI radiomics of bone and soft-tissue sarcomas, thus updating a previous version of this review which included studies published up to 2020.

METHODS

A literature search was conducted on EMBASE and PubMed databases for papers published between January 2021 and March 2023. Data regarding radiomic feature reproducibility and model validation strategies were extracted and analyzed.

RESULTS

Out of 201 identified papers, 55 were included. They dealt with radiomics of bone (n = 23) or soft-tissue (n = 32) tumors. Thirty-two (out of 54 employing manual or semiautomatic segmentation, 59%) studies included a feature reproducibility analysis. Reproducibility was assessed based on intra/interobserver segmentation variability in 30 (55%) and geometrical transformations of the region of interest in 2 (4%) studies. At least one machine learning validation technique was used for model development in 34 (62%) papers, and K-fold cross-validation was employed most frequently. A clinical validation of the model was reported in 38 (69%) papers. It was performed using a separate dataset from the primary institution (internal test) in 22 (40%), an independent dataset from another institution (external test) in 14 (25%) and both in 2 (4%) studies.

CONCLUSIONS

Compared to papers published up to 2020, a clear improvement was noted with almost double publications reporting methodological aspects related to reproducibility and validation. Larger multicenter investigations including external clinical validation and the publication of databases in open-access repositories could further improve methodology and bring radiomics from a research area to the clinical stage.

CRITICAL RELEVANCE STATEMENT

An improvement in feature reproducibility and model validation strategies has been shown in this updated systematic review on radiomics of bone and soft-tissue sarcomas, highlighting efforts to enhance methodology and bring radiomics from a research area to the clinical stage.

KEY POINTS

• 2021-2023 radiomic studies on CT and MRI of musculoskeletal sarcomas were reviewed. • Feature reproducibility was assessed in more than half (59%) of the studies. • Model clinical validation was performed in 69% of the studies. • Internal (44%) and/or external (29%) test datasets were employed for clinical validation.

Colorectal Cancer: Current Updates and Future Perspectives

Colorectal cancer is a frequent neoplasm in western countries, mainly due to dietary and behavioral factors. Its incidence is growing in developing countries for the westernization of foods and lifestyles. An increased incidence rate is observed in patients under 45 years of age. In recent years, the mortality for CRC is decreased, but this trend is slowing. The mortality rate is reducing in those countries where prevention and treatments have been implemented. The survival is increased to over 65%. This trend reflects earlier detection of CRC through routine clinical examinations and screening, more accurate staging through advances in imaging, improvements in surgical techniques, and advances in chemotherapy and radiation. The most important predictor of survival is the stage at diagnosis. The screening programs are able to reduce incidence and mortality rates of CRC. The aim of this paper is to provide a comprehensive overview of incidence, mortality, and survival rate for CRC.

Radiomics and artificial intelligence for soft-tissue sarcomas: Current status and perspectives

This article proposes a summary of the current status of the research regarding the use of radiomics and artificial intelligence to improve the radiological assessment of patients with soft tissue sarcomas (STS), a heterogeneous group of rare and ubiquitous mesenchymal malignancies. After a first part explaining the principle of radiomics approaches, from raw image post-processing to extraction of radiomics features mined with unsupervised and supervised machine-learning algorithms, and the current research involving deep learning algorithms in STS, especially convolutional neural networks, this review details their main research developments since the formalisation of 'radiomics' in oncologic imaging in 2010. This review focuses on CT and MRI and does not involve ultrasonography. Radiomics and deep radiomics have been successfully applied to develop predictive models to discriminate between benign soft-tissue tumors and STS, to predict the histologic grade (i.e., the most important prognostic marker of STS), the response to neoadjuvant chemotherapy and/or radiotherapy, and the patients' survivals and probability for presenting distant metastases. The main findings, limitations and expectations are discussed for each of these outcomes. Overall, after a first decade of publications emphasizing the potential of radiomics through retrospective proof-of-concept studies, almost all positive but with heterogeneous and often non-replicable methods, radiomics is now at a turning point in order to provide robust demonstrations of its clinical impact through open-science, independent databases, and application of good and standardized practices in radiomics such as those provided by the Image Biomarker Standardization Initiative, without forgetting innovative research paths involving other '-omics' data to better understand the relationships between imaging of STS, gene-expression profiles and tumor microenvironment.

Pancreatic Ductal Adenocarcinoma: Update of CT-Based Radiomics Applications in the Pre-Surgical Prediction of the Risk of Post-Operative Fistula, Resectability Status and Prognosis

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) is the seventh leading cause of cancer-related deaths worldwide. Surgical resection is the main driver to improving survival in resectable tumors, while neoadjuvant treatment based on chemotherapy (and radiotherapy) is the best option-treatment for a non-primally resectable disease. CT-based imaging has a central role in detecting, staging, and managing PDAC. As several authors have proposed radiomics for risk stratification in patients undergoing surgery for PADC, in this narrative review, we have explored the actual fields of interest of radiomics tools in PDAC built on pre-surgical imaging and clinical variables, to obtain more objective and reliable predictors.

METHODS

The PubMed database was searched for papers published in the English language no earlier than January 2018.

RESULTS

We found 301 studies, and 11 satisfied our research criteria. Of those included, four were on resectability status prediction, three on preoperative pancreatic fistula (POPF) prediction, and four on survival prediction. Most of the studies were retrospective.

CONCLUSIONS

It is possible to conclude that many performing models have been developed to get predictive information in pre-surgical evaluation. However, all the studies were retrospective, lacking further external validation in prospective and multicentric cohorts. Furthermore, the radiomics models and the expression of results should be standardized and automatized to be applicable in clinical practice.

Artificial Intelligence to Early Predict Liver Metastases in Patients with Colorectal Cancer: Current Status and Future Prospectives

BACKGROUND

Artificial Intelligence (AI)-based analysis represents an evolving medical field. In the last few decades, several studies have reported the diagnostic efficiency of AI applied to Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) to early detect liver metastases (LM), mainly from colorectal cancer. Despite the increase in information and the development of different procedures in several radiological fields, an accurate method of predicting LM has not yet been found. This review aims to compare the diagnostic efficiency of different AI methods in the literature according to accuracy, sensibility, precision, and recall to identify early LM.

METHODS

A narrative review of the literature was conducted on PubMed. A total of 336 studies were screened.

RESULTS

We selected 17 studies from 2012 to 2022. In total, 14,475 patients were included, and more than 95% were affected by colorectal cancer. The most frequently used imaging tool to early detect LM was found to be CT (58%), while MRI was used in three cases. Four different AI analyses were used: deep learning, radiomics, machine learning, and fuzzy systems in seven (41.18%), five (29.41%), four (23.53%), and one (5.88%) cases, respectively. Four studies achieved an accuracy of more than 90% after MRI and CT scan acquisition, while just two reported a recall rate ≥90% (one method using MRI and CT and one CT).

CONCLUSIONS

Routinely acquired radiological images could be used for AI-based analysis to early detect LM. Simultaneous use of radiomics and machine learning analysis applied to MRI or CT images should be an effective method considering the better results achieved in the clinical scenario.

Machine learning-based radiomic computed tomography phenotyping of thymic epithelial tumors: Predicting pathological and survival outcomes

OBJECTIVE

For patients with thymic epithelial tumors, accurately predicting clinicopathological outcomes remains challenging. We aimed to investigate the performance of machine learning-based radiomic computed tomography phenotyping for predicting pathological (World Health Organization [WHO] type and TNM stage) and survival outcomes (overall and progression-free survival) in patients with thymic epithelial tumors.

METHODS

This retrospective study included patients with thymic epithelial tumors between January 2001 and January 2022. The radiomic features were extracted from preoperative unenhanced computed tomography images. After strict feature selection, random forest and random survival forest models were fitted to predict pathological and survival outcomes, respectively. The model performance was assessed by the area under the curve (AUC) and validated internally by the bootstrap method.

RESULTS

In total, 124 patients with a median age of 61 years were included. The radiomics random forest models of WHO type and TNM stage showed satisfactory performance with an AUC_WHO of 0.898 (95% CI, 0.753-1.000) and an AUC_TNM of 0.766 (95% CI, 0.642-0.886). For overall survival and progression-free survival prediction, the radiomics random survival forest models showed good performance (integrated AUCs, 0.923; 95% CI, 0.691-1.000 and 0.702; 95% CI, 0.513-0.875, respectively), and the integrated AUCs increased to 0.935 (95% CI, 0.705-1.000) and 0.811 (95% CI, 0.647-0.942), respectively, when combined with clinicopathological features.

CONCLUSIONS

Machine learning-based radiomic computed tomography phenotyping might allow for the satisfactory prediction of pathological and survival outcomes and further improve prognostic performance when integrated with clinicopathological features in patients with thymic epithelial tumors.

The diagnosis, classification, and treatment of sarcoma in this era of artificial intelligence and immunotherapy

Soft-tissue sarcomas (STS) represent a group of rare and heterogeneous tumors associated with several challenges, including incorrect or late diagnosis, the lack of clinical expertise, and limited therapeutic options. Digital pathology and radiomics represent transformative technologies that appear promising for improving the accuracy of cancer diagnosis, characterization and monitoring. Herein, we review the potential role of the application of digital pathology and radiomics in managing patients with STS. We have particularly described the main results and the limits of the studies using radiomics to refine diagnosis or predict the outcome of patients with soft-tissue sarcomas. We also discussed the current limitation of implementing radiomics in routine settings. Standard management approaches for STS have not improved since the early 1970s. Immunotherapy has revolutionized cancer treatment; nonetheless, immuno-oncology agents have not yet been approved for patients with STS. However, several lines of evidence indicate that immunotherapy may represent an efficient therapeutic strategy for this group of diseases. Thus, we emphasized the remarkable potential of immunotherapy in sarcoma treatment by focusing on recent data regarding the immune landscape of these tumors. We have particularly emphasized the fact that the development of immunotherapy for sarcomas is not an aspect of histology (except for alveolar soft-part sarcoma) but rather that of the tumor microenvironment. Future studies investigating immunotherapy strategies in sarcomas should incorporate at least the presence of tertiary lymphoid structures as a stratification factor in their design, besides including a strong translational program that will allow for a better understanding of the determinants involved in sensitivity and treatment resistance to immune-oncology agents.

Nomograms predicting local and distant recurrence and disease-specific mortality for R0/R1 soft tissue sarcomas of the extremities

Background

Prognostic models for patients with soft tissue sarcoma (STS) of the extremities have been developed from large multi-institutional datasets with mixed results. We aimed to develop predictive nomograms for sarcoma-specific survival (SSS) and, for the first time, long-term local recurrence (LR) and distant recurrence (DR) in patients with STS of the extremities treated at our institution.

Patients and methods

Data from patients treated at Humanitas Cancer Center from 1997 to 2015 were analyzed. Variable selection was based on the clinical knowledge and multivariable regression splines algorithm. Perioperative treatments were always included in the model. Prognostic models were developed using Cox proportional hazards model, and model estimates were plotted in nomograms predicting SSS at 5 and 10 years and LR and DR at 2, 5, and 10 years. Model performance was estimated internally via bootstrapping, in terms of optimism-corrected discrimination (Harrell C-index) and calibration (calibration plots).

Results

Data on 517 patients were analyzed. At 5 and 10 years, SSS was 68.1% [95% confidence interval (CI), 63.8-72.1] and 55.6% (50.5-60.3), respectively. LR was 79.1% (95% CI, 75.3-82.4), 71.1% (95% CI, 66.7-75.1), and 66.0% (95% CI, 60.7-70.7) at 2, 5, and 10 years, respectively, whereas DR was 65.9% (95% CI, 61.6-69.9), 57.5% (95% CI, 53.0-61.8), and 52.1% (95% CI, 47.1-56.8) at 2, 5, and 10 years, respectively. SSS nomogram included age, gender, margins, tumor size, grading, and histotype. LR and DR nomograms incorporated mostly the same variables, except for age for DR; LR nomogram did not include gender but included anatomic site. The optimism-corrected C-indexes were 0.73 and 0.72 for SSS at 5 and 10 years, respectively; 0.65, 0.64, and 0.64 for LR at 2, 5, and 10 years, respectively; and 0.68 for DR at 2, 5, and 10 years. Predicted probabilities were close to the observed ones for all outcomes.

Conclusions

We developed and validated three nomograms for STS of the extremities predicting the probability of SSS at 5 and 10 years and LR and DR at 2, 5, and 10 years. By accounting for the perioperative treatment, these models allow prediction for future patients who had no perioperative treatment, thus being useful in the clinical decision-making process.