Rakheja, Dinesh

PURPOSE Monoclonal antibodies directed against insulin-like growth factor-1 receptor (IGF-1R) have shown activity in patients with relapsed Ewing sarcoma. The primary objective of Children's Oncology Group trial AEWS1221 was to determine if the addition of the IGF-1R monoclonal antibody ganitumab to interval-compressed chemotherapy improves event-free survival (EFS) in patients with newly diagnosed metastatic Ewing sarcoma. METHODS Patients were randomly assigned 1:1 at enrollment to standard arm (interval-compressed vincristine/doxorubicin/cyclophosphamide alternating once every 2 weeks with ifosfamide/etoposide = VDC/IE) or to experimental arm (VDC/IE with ganitumab at cycle starts and as monotherapy once every 3 weeks for 6 months after conventional therapy). A planned sample size of 300 patients was projected to provide 81% power to detect an EFS hazard ratio of 0.67 or smaller for the experimental arm compared with the standard arm with a one-sided α of .025. RESULTS Two hundred ninety-eight eligible patients enrolled (148 in standard arm; 150 in experimental arm). The 3-year EFS estimates were 37.4% (95% CI, 29.3 to 45.5) for the standard arm and 39.1% (95% CI, 31.3 to 46.7) for the experimental arm (stratified EFS-event hazard ratio for experimental arm 1.00; 95% CI, 0.76 to 1.33; 1-sided, P = .50). The 3-year overall survival estimates were 59.5% (95% CI, 50.8 to 67.3) for the standard arm and 56.7% (95% CI, 48.3 to 64.2) for the experimental arm. More cases of pneumonitis after radiation involving thoracic fields and nominally higher rates of febrile neutropenia and ALT elevation were reported on the experimental arm. CONCLUSION Ganitumab added to interval-compressed chemotherapy did not significantly reduce the risk of EFS event in patients with newly diagnosed metastatic Ewing sarcoma, with outcomes similar to prior trials without IGF-1R inhibition or interval compression. The addition of ganitumab may be associated with increased toxicity.

Abstract Intratumoral heterogeneity arising from tumor evolution poses significant challenges biologically and clinically. Dissecting this complexity may benefit from deep learning (DL) algorithms, which can infer molecular features from ubiquitous hematoxylin and eosin (H&E)–stained tissue sections. Although DL algorithms have been developed to predict some driver mutations from H&E images, the ability of these DL algorithms to resolve intratumoral mutation heterogeneity at subclonal spatial resolution is unexplored. Here, we apply DL to a paradigm of intratumoral heterogeneity, clear cell renal cell carcinoma (ccRCC), the most common type of kidney cancer. Matched IHC and H&E images were leveraged to develop DL models for predicting intratumoral genetic heterogeneity of the three most frequently mutated ccRCC genes, BAP1, PBRM1, and SETD2. DL models were generated on a large cohort (N = 1,282) and tested on several independent cohorts, including a TCGA cohort (N = 363 patients) and two tissue microarray (TMA) cohorts (N = 118 and 365 patients). These models were also expanded to a patient-derived xenograft (PDX) TMA, affording analysis of homotopic and heterotopic interactions of tumor and stroma. The status of all three genes could be inferred by DL, with BAP1 showing the highest sensitivity and performance within and across tissue samples (AUC = 0.87–0.89 on holdout). BAP1 results were validated on independent human (AUC = 0.77–0.84) and PDX (AUC = 0.80) cohorts. Finally, BAP1 predictions correlated with clinical outputs such as disease-specific survival. Overall, these data show that DL models can resolve intratumoral heterogeneity in cancer with potential diagnostic, prognostic, and biological implications. Significance: This work demonstrates the potential for deep learning analysis of histopathologic images to serve as a fast, low-cost method to assess genetic intratumoral heterogeneity. See related commentary by Song et al., p. 2672