Training and Validation of Deep Learning-Based Auto-Segmentation Models for Lung Stereotactic Ablative Radiotherapy Using Retrospective Radiotherapy Planning Contours.

PURPOSE: Deep learning-based auto-segmented contour (DC) models require high quality data for their development, and previous studies have typically used prospectively produced contours, which can be resource intensive and time consuming to obtain. The aim of this study was to investigate the feasibility of using retrospective peer-reviewed radiotherapy planning contours in the training and evaluation of DC models for lung stereotactic ablative radiotherapy (SABR). METHODS: Using commercial deep learning-based auto-segmentation software, DC models for lung SABR organs at risk (OAR) and gross tumor volume (GTV) were trained using a deep convolutional neural network and a median of 105 contours per structure model obtained from 160 publicly available CT scans and 50 peer-reviewed SABR planning 4D-CT scans from center A. DCs were generated for 50 additional planning CT scans from center A and 50 from center B, and compared with the clinical contours (CC) using the Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD). RESULTS: Comparing DCs to CCs, the mean DSC and 95% HD were 0.93 and 2.85mm for aorta, 0.81 and 3.32mm for esophagus, 0.95 and 5.09mm for heart, 0.98 and 2.99mm for bilateral lung, 0.52 and 7.08mm for bilateral brachial plexus, 0.82 and 4.23mm for proximal bronchial tree, 0.90 and 1.62mm for spinal cord, 0.91 and 2.27mm for trachea, and 0.71 and 5.23mm for GTV. DC to CC comparisons of center A and center B were similar for all OAR structures. CONCLUSIONS: The DCs developed with retrospective peer-reviewed treatment contours approximated CCs for the majority of OARs, including on an external dataset. DCs for structures with more variability tended to be less accurate and likely require using a larger number of training cases or novel training approaches to improve performance. Developing DC models from existing radiotherapy planning contours appears feasible and warrants further clinical workflow testing.

Implementation of deep learning-based auto-segmentation for radiotherapy planning structures: a workflow study at two cancer centers.

PURPOSE: We recently described the validation of deep learning-based auto-segmented contour (DC) models for organs at risk (OAR) and clinical target volumes (CTV). In this study, we evaluate the performance of implemented DC models in the clinical radiotherapy (RT) planning workflow and report on user experience. METHODS AND MATERIALS: DC models were implemented at two cancer centers and used to generate OAR and CTVs for all patients undergoing RT for a central nervous system (CNS), head and neck (H&N), or prostate cancer. Radiation Therapists/Dosimetrists and Radiation Oncologists completed post-contouring surveys rating the degree of edits required for DCs (1 = minimal, 5 = significant) and overall DC satisfaction (1 = poor, 5 = high). Unedited DCs were compared to the edited treatment approved contours using Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD). RESULTS: Between September 19, 2019 and March 6, 2020, DCs were generated on approximately 551 eligible cases. 203 surveys were collected on 27 CNS, 54 H&N, and 93 prostate RT plans, resulting in an overall survey compliance rate of 32%. The majority of OAR DCs required minimal edits subjectively (mean editing score ≤ 2) and objectively (mean DSC and 95% HD was ≥ 0.90 and ≤ 2.0 mm). Mean OAR satisfaction score was 4.1 for CNS, 4.4 for H&N, and 4.6 for prostate structures. Overall CTV satisfaction score (n = 25), which encompassed the prostate, seminal vesicles, and neck lymph node volumes, was 4.1. CONCLUSIONS: Previously validated OAR DC models for CNS, H&N, and prostate RT planning required minimal subjective and objective edits and resulted in a positive user experience, although low survey compliance was a concern. CTV DC model evaluation was even more limited, but high user satisfaction suggests that they may have served as appropriate starting points for patient specific edits.

Radiation Oncology Resident and Program Director Perceptions of the Job Market and Impact on Well-being.

Background Radiation oncology graduates occasionally experience difficulties obtaining employment. The purpose of this study was to explore the perceptions of radiation oncology residents (RORs) and program directors (PDs) about the job market and the potential impact on their well-being. Methods RORs and PDs from 13 Canadian training programs were invited to participate. Semi-structured interviews were conducted from March 2014 to January 2015. Knowledge/perception of the job market, impact on personal/professional life, as well as opinions regarding possible contributing factors/solutions to the job market were assessed. A conventional content analysis of each transcript was performed with the clustering of conceptually similar expressions into themes. Demographic information was summarized with descriptive statistics. Results Twenty RORs and four PDs participated. All the participants described delayed retirement and over-training as contributors to the job shortage. The majority of trainees interviewed were concerned about the job market (60%) and reported that it impacted their personal (60%) and professional (55%) relationships. PDs described the job market as negatively impacting their job satisfaction. Resident morale was ranked as poor by both groups. Conclusions Job market shortages can negatively impact the personal and professional well-being of trainees and PDs. Attention to manpower planning is important to maintaining a high-quality workforce. The cyclical undersupply and oversupply of residents occur in several countries, which makes our findings potentially relevant to residency training programs internationally.

Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning.

BACKGROUND: Deep learning-based auto-segmented contours (DC) aim to alleviate labour intensive contouring of organs at risk (OAR) and clinical target volumes (CTV). Most previous DC validation studies have a limited number of expert observers for comparison and/or use a validation dataset related to the training dataset. We determine if DC models are comparable to Radiation Oncologist (RO) inter-observer variability on an independent dataset. METHODS: Expert contours (EC) were created by multiple ROs for central nervous system (CNS), head and neck (H&N), and prostate radiotherapy (RT) OARs and CTVs. DCs were generated using deep learning-based auto-segmentation software trained by a single RO on publicly available data. Contours were compared using Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD). RESULTS: Sixty planning CT scans had 2-4 ECs, for a total of 60 CNS, 53 H&N, and 50 prostate RT contour sets. The mean DC and EC contouring times were 0.4 vs 7.7 min for CNS, 0.6 vs 26.6 min for H&N, and 0.4 vs 21.3 min for prostate RT contours. There were minimal differences in DSC and 95% HD involving DCs for OAR comparisons, but more noticeable differences for CTV comparisons. CONCLUSIONS: The accuracy of DCs trained by a single RO is comparable to expert inter-observer variability for the RT planning contours in this study. Use of deep learning-based auto-segmentation in clinical practice will likely lead to significant benefits to RT planning workflow and resources.

Magnetic Resonance Imaging Volumetry of Primary Nasopharyngeal Cancer in Patients Treated with Induction Gemcitabine and Cisplatin Followed by Concurrent Cisplatin and Volumetric Modulated Arc Therapy.

Introduction The addition of induction chemotherapy (IC) to the standard concurrent chemoradiotherapy (CCRT) is under consideration in locally advanced nasopharyngeal carcinoma (LANPC). To-date, no studies have reported primary gross tumour volume (GTVp) changes using gemcitabine and cisplatin as the IC phase in LANPC. We investigated the timing and magnitude of GTVp response throughout sequential gemcitabine and cisplatin IC and CCRT for LANPC. Toxicity and tumour control probability (TCP) analyses are also presented Methods Ten patients with LANPC underwent sequential IC and CCRT between 2011 and 2015. All patients had magnetic resonance imaging (MRI) at three time points: before IC (MRI0), after IC (MRI1), and three months after CCRT (MRI3). Five of the 10 patients had an additional MRI four to five weeks into CCRT (MRI2). GTVp contours were delineated retrospectively using contrast-enhanced MRIs, and each GTVp underwent secondary review by a neuroradiologist. Acute toxicities were graded retrospectively via chart review based on the National Cancer Institute Common Terminology for Adverse Events version 4.0 (NCI CTCAE v4.0). Results Mean GTVp reduction between MRI0 - MRI1 was from 68 cc to 47 cc and from 47 cc to 9 cc between MRI1 - MRI3. In patients with MRI2, the mean GTVp reduction between MRI1 - MRI2 was from 57 cc to 32 cc. Tumour control probability estimates increased by 0.11 after IC. Patients tolerated the treatment well with one Grade IV toxicity event. Conclusion The observed GTVp response and improved tumor control probability support further investigation into the use of IC in LANPC.

Practical Considerations in Breast Papillary Lesions: A Review of the Literature.

CONTEXT: -Diagnosis of papillary breast lesions, especially in core biopsies, is challenging for most pathologists, and these lesions pose problems for patient management. Distinction between benign, premalignant, and malignant components of papillary lesions is challenging, and the diagnosis of invasion is problematic in lesions that have circumscribed margins. Obtaining a balance between overtreatment and undertreatment of these lesions is also challenging. OBJECTIVES: -To provide a classification and a description of the histologic and immunohistochemical features and the differential diagnosis of papillary breast lesions, to provide an update on the molecular pathology of papillary breast lesions, and to discuss the recommendations for further investigation and management of papillary breast lesions. This review provides a concise description of the histologic and immunohistochemical features of the different papillary lesions of the breast. DATA SOURCES: -The standard pathology text books on breast pathology and literature on papillary breast lesions were reviewed with the assistance of the PubMed database ( http://www.ncbi.nlm.nih.gov/pubmed ). CONCLUSIONS: -Knowledge of the clinical presentation, histology, immunoprofile, and behavior of papillary breast lesions will assist pathologists with the diagnosis and optimal management of patients with papillary breast lesions.