Zwart, Christine M.

e15626 Background: FGFR2 fusions are found in 10-15% of intrahepatic cholangiocarcinomas. Individuals with FGFR2 fusions have a better prognosis and more indolent natural history. More recently FGFR2 fusions have been described as a predictive marker for tyrosine kinase inhibitors targeting the FGFR2 pathway. Texture analysis from CT imaging has been used in the past to estimate degree of fibrosis and angiogenesis in various tumors types; however, texture analysis has not been used in the past to detect FGFR2 rearrangements. Methods: This is a retrospective study of 33 patients with intrahepatic cholangiocarcinoma who were previously tested for FGFR2 fusions with either a FISH break apart assay or with clinically available next generation sequencing assays. All patients had a contrast enhanced CT performed. To address physiological and pathological variations, matched-size regions of interest (ROIs) over areas of non-necrotic tumor and unaffected liver during the portal venous phase were drawn. The paired ROIs for each patient were then processed via an imaging analytic pipeline for (1) ROI normalization, (2) texture panel creation, and (3) machine learning predictive model development. Results: Fifteen patients with FGFR2 fusions and 18 patients without FGFR2 fusions were included in the study. Using the developed predictive model, accurate FGFR2 fusion classification in 90% of cases was achieved (sensitivity = 87%, specificity = 94%). Conclusions: Utilizing advanced analytics with machine learning techniques, multi-textural data obtained from conventional CT images has the capability to detect genetic aberrations in intrahepatic cholangiocarcinoma, including FGFR2 gene fusions. Radiogenomic evaluation has several attractive benefits including the cost effective and expeditious detection of actionable mutations such as FGFR2 fusions as well as avoidance of invasive procedures such as percutaneous core biopsies. [Table: see text]

Abstract OBJECTIVE: Neoadjuvant endocrine therapy (NET) is increasingly used for the treatment of low and intermediate grade, hormone receptor positive, HER2 negative breast cancer. Several MRI phenotypes that may predict response to neoadjuvant chemotherapy (NAC) have been identified, but little data exists for phenotypes associated with response to NET. This study analyzed imaging phenotypes for all patients treated with NET with the aim to identify specific features that can be predictive of response to therapy. MATERIALS AND METHODS: The study was retrospective and included 21 patients with clinical stage I, II, and III breast cancer. The tumors were grade 1 or 2, estrogen receptor (ER) positive in >20% of cells, and HER2 non-amplified. MRI examinations were performed in all women before NET. MRI interpretation included mass shape, non-mass enhancement (NME) pattern, background parenchymal enhancement, and MRI phenotype (I well-defined unicentric mass; II well defined multilobulated mass; III area enhancement with nodularity; IV area enhancement without nodularity; V septal spreading). Type of neoadjuvant endocrine therapy included: tamoxifien alone, an aromatase inhibitor (AI) alone, AI + ovarian suppression, and AI + a non-chemotherapeutic agent. Patients received NET for a total duration ranging between 3 - 6 months, with one patient receiving therapy for 18 months. Clinically meaningful response was defined as stable or decreased tumor size by clinical exam and confirmed at resection by comparing final pathologic T stage with clinical T stage. RESULTS: Twenty-one patients were identified. Median age was 62 (range 36-84) years. Most were post-menopausal 17 (81%). Pre-neoadjuvant meadian tumor size on MRI was 3.9 (range 1.0-7.5) cm and comprised T1 3 (14.3%), T2 8 (38.1%), T3/4 10 (47.6%). Pre-treatment N stage was N0 14 (66.7%), N1 7 (33.3%) and pre-NET stage was I in 3 (14.3%), II in 8 (38.1%), and III in 10 (47.6%) patients. The majority 17 (81%) had some tumor reduction, and 4 (19%) had no response. No one achieved a complete response. Of the 17 responders, 7 (41%) had a good response defined as >25% decrease in tumor size. Median tumor size after NET was 3.1 (range 0.6-11) cm and the distribution of T stage was T1 7 (33.3%), T2 9 (42.9%), and T3/4 5 (23.8%). Eleven of 12 (92%) patients with well-defined phenotypes had a response as compared to 6 of 9 (67%) patients with non-well defined phenotypes. Phenotype was not predictive of a good response to therapy, 4 were in the well-defined phenotype and 3 were in the non-well defined phenotype groups. All 4 non-responders had moderate or marked background enhancement as compared to 5 of 17 responders (p = 0.02). CONCLUSION: A well-defined pre treatment MRI phenotype was significantly predictive of a positive response to NET, while a non well-defined MRI phenotype and higher degree of background enhancement was significantly predictive of negative response to NET. This warrants further prospective evaluation, especially in association with Ki-67 levels. If validated, pre treatment MRI phenotype can be applied in the clinical decision to either initiate NET or referral for upfront surgical resection. Citation Format: Hilal T, Covington M, Pockaj B, Northfelt D, Wu T, Zwart C, Li J, Patel BK. Pre-neoadjuavnt therapy MRI phenotype can predict response to neoadjuvant endocrine therapy [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P4-02-03.

ObjectiveTo determine whether machine learning can accurately classify human papillomavirus (HPV) status of oropharyngeal squamous cell carcinoma (OPSCC) using computed tomography (CT)-based texture analysis.MethodsTexture analyses were retrospectively applied to regions of interest from OPSCC primary tumors on contrast-enhanced neck CT, and machine learning was used to create a model that classified HPV status with the highest accuracy. Results were compared against the blinded review of 2 neuroradiologists.ResultsThe HPV-positive (n = 92) and -negative (n = 15) cohorts were well matched clinically. Neuroradiologist classification accuracies for HPV status (44.9%, 55.1%) were not significantly different (P= 0.13), and there was a lack of agreement between the 2 neuroradiologists (κ = −0.145). The best machine learning model had an accuracy of 75.7%, which was greater than either neuroradiologist (P< 0.001,P= 0.002).ConclusionsUseful diagnostic information regarding HPV infection can be extracted from the CT appearance of OPSCC beyond what is apparent to the trained human eye.