Faculty Bibliography

Background: Early-Stage non-small cell lung cancer (ES-NSCLC) accounts for approximately 40% of NSCLC cases, with 5-year survival rates varying between 31-49%. Radiomic textural features from pre-treatment CT scans and QH features from H&E stained WSIs have been shown to be independently prognostic of outcome. With diagnostic CT scans and surgical resection, the standard of care in ES-NSCLC, in this work we seek to take a multimodality approach using routine imaging to improve the predictive performance in determining DFS following resection.
Method(s): A retrospective chart review of Stage I and II (ES-NSCLC) pts undergoing surgical resection between 2005-14 with available CT and resected tissue yielded 70 pts. A total of 248 radiomic CT textural features from inside the tumor (Intratumoral -IT) and outside the tumor (Peritumoral - PT) and 242 QH features related to the nuclear shape, texture and spatial orientation and architecture from H&E WSI were extracted. We developed two risk models, Radiomic and QH using the most stable, discriminative and uncorrelated features from CT and WSI respectively determined by Lasso-regularized Cox regression to predict Disease free survival (DFS). Model performances were analyzed using Hazard Ratios (HR), Concordance Index (C-index) and Decision curve analysis. We built a nomogram to calculate the DFS based around the individual models as well as an integration of the QH and Radiomic models.
Result(s): Top 6 Radiomic features included 2 IT and 4 PT features from the Haralick and Collage families. The QH model comprised 6 nuclear shape and graph features. In predicting DFS, While the Radiomic model had a HR of 2.4 (p <0.01) with C-index - 0.67, the QH model had

Background: Early stage non-small cell lung cancer (ES-NSCLC) comprises about 45% of all NSCLC patients, with 5-year survival ranging between 30-49%. Surgical resection is the standard of care curative modality in these patients but about 30-55% of patients often recur following surgery within the first 3 years. There is currently no validated method to stratify patients based on their risk of recurrence following surgery in these patients. In this project, we develop and validate a nomogram using a combination of CT-derived radiomic textural features and clinco-pathologic factors, in order to predict DFS in ES-NSCLC.
Method(s): This study comprised 350 ES-NSCLC patients from two different institutions who underwent surgery (75 patients relapsed). Radiomic textural features were extracted from tumor region (Intratumoral - IT) as well as from the annular ring shaped peritumoral region (PT) with 3mm as a ring thickness and extending 9 mm outside the nodule. A total of 124 features from Gabor, Laws, Laplace, Haralick and Collage feature families were extracted from IT and each PT ring for all patients. The most stable, significant and uncorrelated features were selected from D1 (N=221) and used to build a Lasso-regularized multivariate Cox-regression model to generate a Radiomic Risk Score (RRS) derived from weighted Lasso coefficients. Further, RRS was integrated with clinic-pathologic variables (Lympho-vascular invasion LVI and AJCC stage) which were independently predictive on DFS in multivariate analysis to build a clinical-radiomics score (CRS). A nomogram was constructed to visually assess the CRS and RRS on DFS. Performances were evaluated using hazard ratios (HR), concordance index (C-Index) along with decision and calibration curves to show the differences between the individual and integrated risk scores.
Result(s): Top 14 radiomic features included 6 from IT and 8 from 0-9 mm PT distance. The constructed RRS could predict DFS (n=221, C-index=0.69, HR = 3.8; 95% CI- 2.7-5.6, p<0.05) on training (D1) and (n=129, C-index=0.69,

Background: Osimertinib, a third-generation EGFR inhibitor, has become the first-line therapy for patients with metastatic EGFR-mutant NSCLCs since 2018. Osimertinib is well-tolerated, therefore, it opens opportunities to be combined with other therapeutic agents to enhance the treatment outcome. In preclinical models, it has been shown that upregulated VEGF signaling mediates acquired resistance to EGFR therapies. In xenograft models, combination of anti-VEGF medications with EGFR inhibitors were significantly more effective than erlotinib or gefitinib alone. Ramucirumab, a monoclonal antibody targeting VEGF receptor 2, is approved with docetaxel in as second line treatment for NSCLCs. In clinical trial evaluations, the phase 3 RELAY trial (NCT02411448) studying ramucirumab plus erlotinib in patients with metastatic untreated EGFR-mutant NSCLC patients showed a statistically significant improvement in progression-free survival in the combination group compared to erlotinib alone. A phase I study of osimertinib with ramucirumab (NCT02789345) demonstrated safety and feasibility of this combination. With strong preclinical and clinical evidence showing dual inhibition of VEGF/EGFR signaling prolongs progression-free survival for EGFR-mutant lung cancers, and demonstrated safety, we are conducting a phase 2 trial to evaluate the osimertinib ramucirumab combination's efficacy in treatment-naive EGFR-mutant NSCLC.
Method(s): The OSI+RAM trial is a randomized phase 2 study with the primary endpoint being progression-free survival in osi+ram group as compared to osimertinib monotherapy group. The major inclusion criteria include patients with metastatic NSCLC harboring EGFR mutations (L858R/Exon 19 del). The major exclusion criteria include prior anti-EGFR or anti-VEGF treatments. Patients with stable CNS metastasis are allowed. Based on the results from erlotinib bevacizumab (NEJ026) study, we expect an improvement of PFS from 18.9 months to 29.7 months, corresponding to a hazard ratio of 0.65. The trial plans to enroll total of 150 patients, with 100 allocating to osi+ram arm and 50 to osimertinib monotherapy. Total of 9 study sites in the USA are planned. Hoosier Cancer Research Network will facilitate the execution of the trial. The trial protocol has received IND exemption from US FDA and has been approved by IRB at MD Anderson Cancer Center. The first subject is expected to be enrolled in May 2019. A planned interim analysis will be performed after the first 75 subjects are enrolled. NCT03909334.
Result(s): Section not applicable
Conclusion(s): Section not applicable Keywords: Ramucirumab, CNS metastasis, EGFR
Copyright

Background: No targeted therapy is currently approved for patients with RET fusion-positive non-small cell lung cancer (NSCLC). LOXO-292 is a highly selective RET inhibitor with activity against diverse RET fusions, activating RET mutations and brain metastases. Based on initial data from LIBRETTO-001, LOXO-292 received FDA Breakthrough Designation for the treatment of RET fusion-positive NSCLC in August 2018.
Method(s): This global phase 1/2 study (87 sites, 15 countries) enrolled patients with advanced RET-altered solid tumors including RET fusion-positive NSCLC (NCT03157128). LOXO-292 was dosed orally in 28-day cycles. The phase 1 portion established the MTD/RP2D (160 mg BID). The phase 2 portion enrolled patients to one of six cohorts based on tumor type, RET alteration, and prior therapies. The primary endpoint was ORR (RECIST 1.1). Secondary endpoints included DoR, CNS ORR, CNS DoR, PFS, OS, safety and PK.
Result(s): As of 17-June 2019, 247 RET fusion-positive NSCLC patients were treated. The primary analysis set (PAS) for LOXO-292 registration, as defined with the US FDA, consists of the first 105 consecutively enrolled RET fusion-positive NSCLC patients who received prior platinum-based chemotherapy; 54 patients (51%) also received prior immune checkpoint inhibitors (ICIs). The majority of PAS responders have been followed for >=6 months from first response. Of the remaining 142 patients, 74 previously treated with platinum-based chemotherapy have not had sufficient follow-up, 56 did not receive prior platinum-based chemotherapy and 12 did not have measurable disease at baseline. Among PAS patients, the investigator-assessed ORR was 70% (95% CI 60-78%, n=73/105, 3 PRs pending confirmation). Responses did not differ by fusion partner or the type or number of prior therapies, including chemotherapy, ICIs and multikinase inhibitors with anti-RET activity. The median DoR was 20.3 months (95% CI 16.6-NR) with a median follow-up of 7.5 months (range 1.9-21.1 months); as evidenced by the wide confidence interval, this DoR estimate is not statistically stable due to a low number of events (12 of 70 confirmed responders). The intracranial ORR was 90% (n=9/10: 2 confirmed CRs, 7 confirmed PRs) for patients with measurable brain metastases at baseline. The ORR in evaluable treatment naive RET fusion-positive NSCLC patients was 88% (95% CI 72-97%, n=29/33, 10 PRs pending confirmation). In the safety data set of all 247 patients, 5 treatment-related AEs occurred in >=15% of patients: dry mouth, AST increased, diarrhea, ALT increased, and hypertension. Most AEs were grade 1-2. Only 3 of 247 (1.2%) NSCLC patients discontinued LOXO-292 for treatment-related AEs. Updated data will be presented at the meeting.
Conclusion(s): LOXO-292 had marked antitumor activity in RET fusion-positive NSCLC patients and was well tolerated. These data will form the basis of an FDA NDA submission later this year. Keywords: RET fusion, selective RET inhibitor, NSCLC
Copyright

OBJECTIVE:The use of a neoadjuvant chemoradiation followed by surgery in patients with stage IIIA NSCLC is controversial and the benefit of surgery is limited. There are currently no clinically validated biomarkers to select patients for such an approach. In this study we evaluate computed tomography (CT) derived intratumoral and peritumoral texture and nodule shape features in their ability to predict major pathological response (MPR). MPR being defined as ≤10% of residual viable tumor, assessed at the time of surgery. MATERIAL AND METHODS/METHODS:Ninety patients with stage III NSCLC treated with chemoradiation prior to surgical resection were selected. The patients were divided randomly into two equal sets, one for training and one for independent testing. The radiomic texture and shape features were extracted from within the nodule (intra) and from the parenchymal regions immediately surrounding the nodule (peritumoral). A univariate regression analysis was performed on the image and clinicopathologic variables and then included into a multivariable logistic regression (MLR) for binary outcome prediction of MPR. The radiomic signature risk-score was generated by using a multivariate Cox regression model and association of the signature with OS and DFS was also evaluated. RESULTS:Thirteen stable and predictive intratumoral and peritumoral radiomic texture features were found to be predictive of MPR. The MLR classifier yielded an AUC of 0.90 ± 0.025 within the training set and a corresponding AUC = 0.86 in prediction of MPR within the test set. The radiomic signature was also significantly associated with OS (HR = 11.18, 95% CI = 3.17, 44.1; p-value = 0.008) and DFS (HR = 2.78, 95% CI = 1.11, 4.12; p-value = 0.0042) in the testing set. CONCLUSION/CONCLUSIONS:Texture features extracted within and around the lung tumor on CT images appears to be associated with the likelihood of MPR, OS and DFS to chemoradiation.

In the past decade, advances in precision oncology have resulted in an increased demand for predictive assays that enable the selection and stratification of patients for treatment. The enormous divergence of signalling and transcriptional networks mediating the crosstalk between cancer, stromal and immune cells complicates the development of functionally relevant biomarkers based on a single gene or protein. However, the result of these complex processes can be uniquely captured in the morphometric features of stained tissue specimens. The possibility of digitizing whole-slide images of tissue has led to the advent of artificial intelligence (AI) and machine learning tools in digital pathology, which enable mining of subvisual morphometric phenotypes and might, ultimately, improve patient management. In this Perspective, we critically evaluate various AI-based computational approaches for digital pathology, focusing on deep neural networks and 'hand-crafted' feature-based methodologies. We aim to provide a broad framework for incorporating AI and machine learning tools into clinical oncology, with an emphasis on biomarker development. We discuss some of the challenges relating to the use of AI, including the need for well-curated validation datasets, regulatory approval and fair reimbursement strategies. Finally, we present potential future opportunities for precision oncology.

Aim: To determine real-world time on treatment (rwToT) with first-line pembrolizumab monotherapy for metastatic non-small-cell lung cancer (NSCLC) with programmed death ligand-1 (PD-L1) tumor proportion score (TPS) ≥50%. Methods: The Kaplan-Meier rwToT was estimated from electronic health record data for adults who initiated first-line pembrolizumab monotherapy for stage IV, PD-L1 TPS ≥50% NSCLC, with negative/unknown EGFR/ALK aberrations, and ≥6 months' follow-up until database cutoff. Results: A total of 386 patients with ECOG 0-1 had a median rwToT of 6.9 months (95% CI: 5.6-8.3) and 12-month on-treatment rate of 36.4% (31.2-41.6) versus 40.3% (32.5-47.9) and 37.6% (31.9-43.4) in KEYNOTE-024 (KN024) and KN042 (stage IV/TPS ≥50% subpopulation), respectively. The 24-month restricted-mean rwTOT (extrapolated) was 10.5 months (9.4-11.7), versus 11.0 (9.5-12.5) and 10.4 (9.3-11.5) in KN024 and KN042, respectively. Conclusion: First-line pembrolizumab monotherapy rwToT in metastatic PD-L1 TPS ≥50% NSCLC for trial-matched patients is similar to treatment duration in KN024 and KN042.