Sarcoma nomograms: a light over the darkness

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.

Deep Learning and Multimodal Artificial Intelligence in Orthopaedic Surgery

This review article focuses on the applications of deep learning with neural networks and multimodal neural networks in the orthopaedic domain. By providing practical examples of how artificial intelligence (AI) is being applied successfully in orthopaedic surgery, particularly in the realm of imaging data sets and the integration of clinical data, this study aims to provide orthopaedic surgeons with the necessary tools to not only evaluate existing literature but also to consider AI's potential in their own clinical or research pursuits. We first review standard deep neural networks which can analyze numerical clinical variables, then describe convolutional neural networks which can analyze image data, and then introduce multimodal AI models which analyze various types of different data. Then, we contrast these deep learning techniques with related but more limited techniques such as radiomics, describe how to interpret deep learning studies, and how to initiate such studies at your institution. Ultimately, by empowering orthopaedic surgeons with the knowledge and know-how of deep learning, this review aspires to facilitate the translation of research into clinical practice, thereby enhancing the efficacy and precision of real-world orthopaedic care for patients.

An updated incidence trends of soft-tissue sarcoma and cancer-specific survival of patients with primary soft-tissue sarcoma of liver: a population-based study

Objectives: This study aimed to evaluate and update incidence trends of soft-tissue sarcoma (STS) and to develop a nomogram to predict cancer-specific survival (CSS) in patients diagnosed with primary STS of the liver.Methods: Patients with hepatic STS were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Joinpoint regression analyses were performed to assess the incidence trends of STS. A nomogram was developed based on the independent risk factors chosen by Cox regression models. The calibration curve, area under the receiver operating characteristic curve (AUC), C-index, and decision curve analysis (DCA) were used to assess the predictive performance of the nomogram.Results: The incidence of STS increased between 1994 and 2012. There was a sudden decline in the incidence of STS from 2013. The incidence of STS was different in distinct races and genders. The nomogram for predicting the CSS of hepatic STS according to the independent factors was well calibrated and it displayed optimal discrimination power.Conclusion: This study highlights that age, sex, tumor size, quality of surgery, and histologic subtypes may contribute to the prognosis of hepatic STS, and STS may be etiologically distinct and should be considered separately in different races and genders.

Soft-tissue sarcoma in adults: An update on the current state of histiotype-specific management in an era of personalized medicine

Soft-tissue sarcomas (STS) are rare tumors that account for 1% of all adult malignancies, with over 100 different histologic subtypes occurring predominately in the trunk, extremity, and retroperitoneum. This low incidence is further complicated by their variable presentation, behavior, and long-term outcomes, which emphasize the importance of centralized care in specialized centers with a multidisciplinary team approach. In the last decade, there has been an effort to improve the quality of care for patients with STS based on anatomic site and histology, and multiple ongoing clinical trials are focusing on tailoring therapy to histologic subtype. This report summarizes the latest evidence guiding the histiotype-specific management of extremity/truncal and retroperitoneal STS with regard to surgery, radiation, and chemotherapy.

Completion surgery of residual disease after primary inadequate surgery of retroperitoneal sarcomas can salvage a selected subgroup of patients-A propensity score analysis

BACKGROUND

Patients with retroperitoneal sarcoma (RPSs) who undergo primary inadequate surgery before referral to specialized sarcoma centers may be considered for completion surgery (CS). We wanted to compare the outcome of these patients to those who underwent primary adequate surgery (PAS) at a single referral institution.

METHODS

We identified 34 patients who were referred for CS after primary inadequate surgery. Using a propensity score based on validated RPS outcome risk factors, we managed to match 28 patients to patients with PAS.

RESULTS

Median time lag between the first and second operation in CS patients was 5 months (2-15). Surgical extent was similar among groups (median number of organs resected = 3; P = 0.08), and macroscopically complete excision was achieved in all patients. The rate of severe complications did not differ between the groups (1 of 28 vs 3 of 28, respectively; P = 0.35) and no perioperative mortality was documented. Median follow-up was 43.5 months. Patients in the CS group had similar local recurrence-free survival (mean, 92.1 ± 9.7 vs 99.8 ± 12.4; P = 0.85) and relapse-free survival (mean, 88.7 ± 9.8 vs 80.9 ± 12.3; P = 0.3) to those with PAS.

CONCLUSIONS

CS has short- and long-term outcomes comparable to PAS. While primary surgery should always be carried out at a referral institution, some of the patients who undergo an initial incomplete resection at a non specialist center can still be offered a salvage procedure at a referral institution with comparable results.