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.

Hepatocellular carcinoma is the fourth leading cause of cancer-related death worldwide. Depending on the extent of disease and competing comorbidities for mortality, multiple liver-directed therapy options exist for the treatment of hepatocellular carcinoma. Advancements in radiation oncology have led to the emergence of stereotactic body radiation therapy as a promising liver-directed therapy, which delivers high doses of radiation with a steep dose gradient to maximize local tumor control and minimize radiation-induced treatment toxicity. In this study, we review the current clinical data as well as the unresolved issues and controversies regarding stereotactic body radiation therapy for hepatocellular carcinoma: (1) Is there a radiation dose–response relationship with hepatocellular carcinoma? (2) What are the optimal dosimetric predictors of radiation-induced liver disease, and do they differ for patients with varying liver function? (3) How do we assess treatment response on imaging? (4) How does stereotactic body radiation therapy compare to other liver-directed therapy modalities, including proton beam therapy? Based on the current literature discussed, this review highlights future possible research and clinical directions.

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.

Purpose: To characterize changes in the soft-tissue sarcoma (STS) tumor immune microenvironment induced by standard neoadjuvant therapy with the goal of informing neoadjuvant immunotherapy trial design. Experimental Design: Paired pre- and postneoadjuvant therapy specimens were retrospectively identified for 32 patients with STSs and analyzed by three modalities: multiplexed IHC, NanoString, and RNA sequencing with ImmunoPrism analysis. Results: All 32 patients, representing a variety of STS histologic subtypes, received neoadjuvant radiotherapy and 21 (66%) received chemotherapy prior to radiotherapy. The most prevalent immune cells in the tumor before neoadjuvant therapy were myeloid cells (45% of all immune cells) and B cells (37%), with T (13%) and natural killer (NK) cells (5%) also present. Neoadjuvant therapy significantly increased the total immune cells infiltrating the tumors across all histologic subtypes for patients receiving neoadjuvant radiotherapy with or without chemotherapy. An increase in the percentage of monocytes and macrophages, particularly M2 macrophages, B cells, and CD4+ T cells was observed postneoadjuvant therapy. Upregulation of genes and cytokines associated with antigen presentation was also observed, and a favorable pathologic response (≥90% necrosis postneoadjuvant therapy) was associated with an increase in monocytic infiltrate. Upregulation of the T-cell checkpoint TIM3 and downregulation of OX40 were observed posttreatment. Conclusions: Standard neoadjuvant therapy induces both immunostimulatory and immunosuppressive effects within a complex sarcoma microenvironment dominated by myeloid and B cells. This work informs ongoing efforts to incorporate immune checkpoint inhibitors and novel immunotherapies into the neoadjuvant setting for STSs.