Search NASA⌕ Search

Engineering topics

Flickinger, John

Publications and source records attributed to Flickinger, John.

Laika BOSS (Binary Object Scanning System)

Laika BOSS (Binary Object Scanning System), often written as "Laikaboss", is an object scanner and intrusion detection system that strives to be scalable, flexible, and verbose. Its goal is to take arbitrary file input and extract all relevant subfiles and metadata for use in helping analysts determine the function and maliciousness of a file at a glance. This is an extension to the original code developed by Lockheed Martin.

Walkup, Gregory↗

Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective

Radiation oncology has always been deeply rooted in modeling, from the early days of isoeffect curves to the contemporary Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) initiative. In recent years, medical modeling for both prognostic and therapeutic purposes has exploded thanks to increasing availability of electronic data and genomics. One promising direction that medical modeling is moving toward is adopting the same machine learning methods used by companies such as Google and Facebook to combat disease. Broadly defined, machine learning is a branch of computer science that deals with making predictions from complex data through statistical models. These methods serve to uncover patterns in data and are actively used in areas such as speech recognition, handwriting recognition, face recognition, “spam” filtering (junk email), and targeted advertising. Although multiple radiation oncology research groups have shown the value of applied machine learning (ML), clinical adoption has been slow due to the high barrier to understanding these complex models by clinicians. Here, we present a review of the use of ML to predict radiation therapy outcomes from the clinician's point of view with the hope that it lowers the “barrier to entry” for those without formal training in ML. We begin by describing 7 principles that one should consider when evaluating (or creating) an ML model in radiation oncology. We next introduce 3 popular ML methods—logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN)—and critique 3 seminal papers in the context of these principles. Although current studies are in exploratory stages, the overall methodology has progressively matured, and the field is ready for larger-scale further investigation.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Nodal Stage of Surgically Resected Non-Small Cell Lung Cancer and Its Effect on Recurrence Patterns and Overall Survival

Purpose: Current National Comprehensive Cancer Network guidelines recommend postoperative radiation therapy (PORT) for patients with resected non-small cell lung cancer (NSCLC) with N2 involvement. We investigated the relationship between nodal stage and local-regional recurrence (LR), distant recurrence (DR) and overall survival (OS) for patients having an R0 resection. Methods and Materials: A multi-institutional database of consecutive patients undergoing R0 resection for stage I-IIIA NSCLC from 1995 to 2008 was used. Patients receiving any radiation therapy before relapse were excluded. A total of 1241, 202, and 125 patients were identified with N0, N1, and N2 involvement, respectively; 161 patients received chemotherapy. Cumulative incidence rates were calculated for LR and DR as first sites of failure, and Kaplan-Meier estimates were made for OS. Competing risk analysis and proportional hazards models were used to examine LR, DR, and OS. Independent variables included age, sex, surgical procedure, extent of lymph node sampling, histology, lymphatic or vascular invasion, tumor size, tumor grade, chemotherapy, nodal stage, and visceral pleural invasion. Results: The median follow-up time was 28.7 months. Patients with N1 or N2 nodal stage had rates of LR similar to those of patients with N0 disease, but were at significantly increased risk for both DR (N1, hazard ratio [HR] = 1.84, 95% confidence interval [CI]: 1.30-2.59; P=.001; N2, HR = 2.32, 95% CI: 1.55-3.48; P<.001) and death (N1, HR = 1.46, 95% CI: 1.18-1.81; P<.001; N2, HR = 2.33, 95% CI: 1.78-3.04; P<.001). LR was associated with squamous histology, visceral pleural involvement, tumor size, age, wedge resection, and segmentectomy. The most frequent site of LR was the mediastinum. Conclusions: Our investigation demonstrated that nodal stage is directly associated with DR and OS but not with LR. Thus, even some patients with, N0-N1 disease are at relatively high risk of local recurrence. Prospective identification of risk factors for local recurrence may aid in selecting an appropriate population for further study of postoperative radiation therapy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Surgical Management of Early-Stage Non-small Cell Lung Carcinoma and the Present and Future Roles of Adjuvant Therapy: A Review for the Radiation Oncologist

We review the evidence for optimal surgical management and adjuvant therapy for patients with stages I and II non-small cell lung cancer (NSCLC) along with factors associated with increased risks of recurrence. Based on the current evidence, we recommend optimal use of mediastinal lymph node dissection, adjuvant chemotherapy, and post-operative radiation therapy, and make suggestions for areas to explore in future prospective randomized clinical trials.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

International Spine Radiosurgery Consortium Consensus Guidelines for Target Volume Definition in Spinal Stereotactic Radiosurgery

Purpose: Spinal stereotactic radiosurgery (SRS) is increasingly used to manage spinal metastases. However, target volume definition varies considerably and no consensus target volume guidelines exist. This study proposes consensus target volume definitions using common scenarios in metastatic spine radiosurgery. Methods and Materials: Seven radiation oncologists and 3 neurological surgeons with spinal radiosurgery expertise independently contoured target and critical normal structures for 10 cases representing common scenarios in metastatic spine radiosurgery. Each set of volumes was imported into the Computational Environment for Radiotherapy Research. Quantitative analysis was performed using an expectation maximization algorithm for Simultaneous Truth and Performance Level Estimation (STAPLE) with kappa statistics calculating agreement between physicians. Optimized confidence level consensus contours were identified using histogram agreement analysis and characterized to create target volume definition guidelines. Results: Mean STAPLE agreement sensitivity and specificity was 0.76 (range, 0.67-0.84) and 0.97 (range, 0.94-0.99), respectively, for gross tumor volume (GTV) and 0.79 (range, 0.66-0.91) and 0.96 (range, 0.92-0.98), respectively, for clinical target volume (CTV). Mean kappa agreement was 0.65 (range, 0.54-0.79) for GTV and 0.64 (range, 0.54-0.82) for CTV (P<.01 for GTV and CTV in all cases). STAPLE histogram agreement analysis identified optimal consensus contours (80% confidence limit). Consensus recommendations include that the CTV should include abnormal marrow signal suspicious for microscopic invasion and an adjacent normal bony expansion to account for subclinical tumor spread in the marrow space. No epidural CTV expansion is recommended without epidural disease, and circumferential CTVs encircling the cord should be used only when the vertebral body, bilateral pedicles/lamina, and spinous process are all involved or there is extensive metastatic disease along the circumference of the epidural space. Conclusions: This report provides consensus guidelines for target volume definition for spinal metastases receiving upfront SRS in common clinical situations.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Radiation Dose-Volume Effects of Optic Nerves and Chiasm

Publications relating radiation toxicity of the optic nerves and chiasm to quantitative dose and dose-volume measures were reviewed. Few studies have adequate data for dose-volume outcome modeling. The risk of toxicity increased markedly at doses >60 Gy at {approx}1.8 Gy/fraction and at >12 Gy for single-fraction radiosurgery. The evidence is strong that radiation tolerance is increased with a reduction in the dose per fraction. Models of threshold tolerance were examined.

62 RADIOLOGY AND NUCLEAR MEDICINE↗