Framework for Radiation Oncology Department-wide Evaluation and Implementation of Commercial Artificial Intelligence Autocontouring.

PURPOSE: Artificial intelligence (AI)-based autocontouring in radiation oncology has potential benefits such as standardization and time savings. However, commercial AI solutions require careful evaluation before clinical integration. We developed a multidimensional evaluation method to test pretrained AI-based automated contouring solutions across a network of clinics. METHODS AND MATERIALS: Curated data included 121 patient planning computed tomography (CT) scans with a total of 859 clinically approved contours used for treatment from 4 clinics. Regions of interest (ROIs) were generated with 3 commercial AI-based automated contouring software solutions (AI1, AI2, AI3) spanning the following disease sites: brain, head and neck (H&N), thorax, abdomen, and pelvis. Quantitative agreement between AI-generated and clinical contours was measured by Dice similarity coefficient (DSC) and Hausdorff distance (HD). Qualitative assessment was performed by multiple experts scoring blinded AI-contours using a Likert scale. Workflow and usability surveying was also conducted. RESULTS: AI1, AI2, and AI3 contours had high quantitative agreement in 27.8%, 32.8%, and 34.1% of cases (DSC >0.9), performing well in pelvis (median DSC = 0.86/0.88/0.91) and thorax (median DSC = 0.91/0.89/0.91). All 3 solutions had low quantitative agreement in 7.4%, 8.8%, and 6.1% of cases (DSC <0.5), performing worse in brain (median DSC = 0.65/0.78/0.75) and H&N (median DSC = 0.76/0.80/0.81). Qualitatively, AI1 and AI2 contours were acceptable (rated 1-2) with at most minor edits in 70.7% and 74.6% of ROIs (2906 ratings), higher for abdomen (AI1: 79.2%) and thorax (AI2: 90.2%), and lower for H&N (29.0/35.6%). An end-user survey showed strong user preference for full automation and mixed preferences for accuracy versus total number of structures generated. CONCLUSIONS: Our evaluation method provided a comprehensive analysis of both quantitative and qualitative measures of commercially available pretrained AI autocontouring algorithms. The evaluation framework served as a roadmap for clinical integration that aligned with user workflow preference.

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration.

Multiomics data including imaging radiomics and various types of molecular biomarkers have been increasingly investigated for better diagnosis and therapy in the era of precision oncology. Artificial intelligence (AI) including machine learning (ML) and deep learning (DL) techniques combined with the exponential growth of multiomics data may have great potential to revolutionize cancer subtyping, risk stratification, prognostication, prediction and clinical decision-making. In this article, we first present different categories of multiomics data and their roles in diagnosis and therapy. Second, AI-based data fusion methods and modeling methods as well as different validation schemes are illustrated. Third, the applications and examples of multiomics research in oncology are demonstrated. Finally, the challenges regarding the heterogeneity data set, availability of omics data, and validation of the research are discussed. The transition of multiomics research to real clinics still requires consistent efforts in standardizing omics data collection and analysis, building computational infrastructure for data sharing and storing, developing advanced methods to improve data fusion and interpretability, and ultimately, conducting large-scale prospective clinical trials to fill the gap between study findings and clinical benefits.

Improved safety and quality in intravascular brachytherapy: A multi-institutional study using failure modes and effects analysis.

PURPOSE: Highlight safety considerations in intravascular brachytherapy (IVBT) programs, provide relevant quality assurance (QA) and safety measures, and establish their effectiveness. METHODS AND MATERIALS: Radiation oncologists, medical physicists, and cardiologists from three institutions performed a failure modes and effects analysis (FMEA) on the radiation delivery portion of IVBT. We identified 40 failure modes and rated the severity, occurrence, and detectability before and after consideration of safety practices. Risk priority numbers (RPN) and relative risk rankings were determined, and a sample QA safety checklist was developed. RESULTS: We developed a process map based on multi-institutional consensus. Highest-RPN failure modes were due to incorrect source train length, incorrect vessel diameter, and missing prior radiation history. Based on these, we proposed QA and safety measures: ten of which were not previously recommended. These measures improved occurrence and detectability: reducing the average RPN from 116 to 58 and median from 84 to 40. Importantly, the average RPN of the top 10% of failure modes reduced from 311 to 172. With QA considered, the highest risk failure modes were from contamination and incorrect source train length. CONCLUSIONS: We identified several high-risk failure modes in IVBT procedures and practical safety and QA measures to address them.

Independent association of metabolic tumor response on FDG-PET with pulmonary toxicity following risk-adaptive chemoradiation for unresectable non-small cell lung cancer: Inherent radiosensitivity or immune response?

BACKGROUND: In the context of a phase II trial of risk-adaptive chemoradiation, we evaluated whether tumor metabolic response could serve as a correlate of treatment sensitivity and toxicity. METHODS: Forty-five patients with AJCCv7 stage IIB-IIIB NSCLC enrolled on the FLARE-RT phase II trial (NCT02773238). [18F]fluorodeoxyglucose (FDG) PET-CT images were acquired prior to treatment and after 24 Gy during week 3. Patients with unfavorable on-treatment tumor response received concomitant boosts to 74 Gy total over 30 fractions rather than standard 60 Gy. Metabolic tumor volume and mean standardized uptake value (SUVmean) were calculated semi-automatically. Risk factors of pulmonary toxicity included concurrent chemotherapy regimen, adjuvant anti-PDL1 immunotherapy, and lung dosimetry. Incidence of CTCAE v4 grade 2+ pneumonitis was analyzed using the Fine-Gray method with competing risks of metastasis or death. Peripheral germline DNA microarray sequencing measured predefined candidate genes from distinct pathways: 96 DNA repair, 53 immunology, 38 oncology, 27 lung biology. RESULTS: Twenty-four patients received proton therapy, 23 received ICI, 26 received carboplatin-paclitaxel, and 17 pneumonitis events were observed. Pneumonitis risk was significantly higher for patients with COPD (HR 3.78 [1.48, 9.60], p = 0.005), those treated with immunotherapy (HR 2.82 [1.03, 7.71], p = 0.043) but not with carboplatin-paclitaxel (HR 1.98 [0.71, 5.54], p = 0.19). Pneumonitis rates were similar among selected patients receiving 74 Gy radiation vs 60 Gy (p = 0.33), proton therapy vs photon (p = 0.60), or with higher lung dosimetric V20 (p = 0.30). Patients in the upper quartile decrease in SUVmean (>39.7%) were at greater risk for pneumonitis (HR 4.00 [1.54, 10.44], p = 0.005) and remained significant in multivariable analysis (HR 3.34 [1.23, 9.10], p = 0.018). Germline DNA gene alterations in immunology pathways were most frequently associated with pneumonitis. CONCLUSION: Tumor metabolic response as measured by mean SUV is associated with increased pneumonitis risk in a clinical trial cohort of NSCLC patients independent of treatment factors. This may be partially attributed to patient-specific differences in immunogenicity.

An efficient magnetic resonance image data quality screening dashboard.

PURPOSE: Complex data processing and curation for artificial intelligence applications rely on high-quality data sets for training and analysis. Manually reviewing images and their associated annotations is a very laborious task and existing quality control tools for data review are generally limited to raw images only. The purpose of this work was to develop an imaging informatics dashboard for the easy and fast review of processed magnetic resonance (MR) imaging data sets; we demonstrated its ability in a large-scale data review. METHODS: We developed a custom R Shiny dashboard that displays key static snapshots of each imaging study and its annotations. A graphical interface allows the structured entry of review data and download of tabulated review results. We evaluated the dashboard using two large data sets: 1380 processed MR imaging studies from our institution and 285 studies from the 2018 MICCAI Brain Tumor Segmentation Challenge (BraTS). RESULTS: Studies were reviewed at an average rate of 100/h using the dashboard, 10 times faster than using existing data viewers. For data from our institution, 1181 of the 1380 (86%) studies were of acceptable quality. The most commonly identified failure modes were tumor segmentation (9.6% of cases) and image registration (4.6% of cases). Tumor segmentation without visible errors on the dashboard had much better agreement with reference tumor volume measurements (root-mean-square error 12.2 cm3 ) than did segmentations with minor errors (20.5 cm3 ) or failed segmentations (27.4 cm3 ). In the BraTS data, 242 of 285 (85%) studies were acceptable quality after processing. Among the 43 cases that failed review, 14 had unacceptable raw image quality. CONCLUSION: Our dashboard provides a fast, effective tool for reviewing complex processed MR imaging data sets. It is freely available for download at https://github.com/EGates1/MRDQED.

Spatial Distance Correlates With Genetic Distance in Diffuse Glioma.

Background: Treatment effectiveness and overall prognosis for glioma patients depend heavily on the genetic and epigenetic factors in each individual tumor. However, intra-tumoral genetic heterogeneity is known to exist and needs to be managed. Currently, evidence for genetic changes varying spatially within the tumor is qualitative, and quantitative data is lacking. We hypothesized that a greater genetic diversity or "genetic distance" would be observed for distinct tumor samples taken with larger physical distances between them. Methods: Stereotactic biopsies were obtained from untreated primary glioma patients as part of a clinical trial between 2011 and 2016, with at least one biopsy pair collected in each case. The physical (Euclidean) distance between biopsy sites was determined using coordinates from imaging studies. The tissue samples underwent whole exome DNA sequencing and epigenetic methylation profiling and genomic distances were defined in three separate ways derived from differences in number of genes, copy number variations (CNV), and methylation profiles. Results: Of the 31 patients recruited to the trial, 23 were included in DNA methylation analysis, for a total of 71 tissue samples (14 female, 9 male patients, age range 21-80). Samples from an 8 patient subset of the 23 evaluated patients were further included in whole exome and copy number variation analysis. Physical and genomic distances were found to be independently and positively correlated for each of the three genomic distance measures. The correlation coefficients were 0.63, 0.65, and 0.35, respectively for (a) gene level mutations, (b) copy number variation, and (c) methylation status. We also derived quantitative linear relationships between physical and genomic distances. Conclusion: Primary brain tumors are genetically heterogeneous, and the physical distance within a given glioma correlates to genomic distance using multiple orthogonal genomic assessments. These data should be helpful in the clinical diagnostic and therapeutic management of glioma, for example by: managing sampling error, and estimating genetic heterogeneity using simple imaging inputs.

Guiding the first biopsy in glioma patients using estimated Ki-67 maps derived from MRI: conventional versus advanced imaging.

BACKGROUND: Undersampling of gliomas at first biopsy is a major clinical problem, as accurate grading determines all subsequent treatment. We submit a technological solution to reduce the problem of undersampling by estimating a marker of tumor proliferation (Ki-67) using MR imaging data as inputs, against a stereotactic histopathology gold standard. METHODS: MR imaging was performed with anatomic, diffusion, permeability, and perfusion sequences, in untreated glioma patients in a prospective clinical trial. Stereotactic biopsies were harvested from each patient immediately prior to surgical resection. For each biopsy, an imaging description (23 parameters) was developed, and the Ki-67 index was recorded. Machine learning models were built to estimate Ki-67 from imaging inputs, and cross validation was undertaken to determine the error in estimates. The best model was used to generate graphical maps of Ki-67 estimates across the whole brain. RESULTS: Fifty-two image-guided biopsies were collected from 23 evaluable patients. The random forest algorithm best modeled Ki-67 with 4 imaging inputs (T2-weighted, fractional anisotropy, cerebral blood flow, Ktrans). It predicted the Ki-67 expression levels with a root mean square (RMS) error of 3.5% (R2 = 0.75). A less accurate predictive result (RMS error 5.4%, R2 = 0.50) was found using conventional imaging only. CONCLUSION: Ki-67 can be predicted to clinically useful accuracies using clinical imaging data. Advanced imaging (diffusion, perfusion, and permeability) improves predictive accuracy over conventional imaging alone. Ki-67 predictions, displayed as graphical maps, could be used to guide biopsy, resection, and/or radiation in the care of glioma patients.