Gross failure rates and failure modes for a commercial AI-based auto-segmentation algorithm in head and neck cancer patients.

PURPOSE: Artificial intelligence (AI) based commercial software can be used to automatically delineate organs at risk (OAR), with potential for efficiency savings in the radiotherapy treatment planning pathway, and reduction of inter- and intra-observer variability. There has been little research investigating gross failure rates and failure modes of such systems. METHOD: 50 head and neck (H&N) patient data sets with "gold standard" contours were compared to AI-generated contours to produce expected mean and standard deviation values for the Dice Similarity Coefficient (DSC), for four common H&N OARs (brainstem, mandible, left and right parotid). An AI-based commercial system was applied to 500 H&N patients. AI-generated contours were compared to manual contours, outlined by an expert human, and a gross failure was set at three standard deviations below the expected mean DSC. Failures were inspected to assess reason for failure of the AI-based system with failures relating to suboptimal manual contouring censored. True failures were classified into 4 sub-types (setup position, anatomy, image artefacts and unknown). RESULTS: There were 24 true failures of the AI-based commercial software, a gross failure rate of 1.2%. Fifteen failures were due to patient anatomy, four were due to dental image artefacts, three were due to patient position and two were unknown. True failure rates by OAR were 0.4% (brainstem), 2.2% (mandible), 1.4% (left parotid) and 0.8% (right parotid). CONCLUSION: True failures of the AI-based system were predominantly associated with a non-standard element within the CT scan. It is likely that these non-standard elements were the reason for the gross failure, and suggests that patient datasets used to train the AI model did not contain sufficient heterogeneity of data. Regardless of the reasons for failure, the true failure rate for the AI-based system in the H&N region for the OARs investigated was low (∼1%).

Evaluating the Effectiveness of Deep Learning Contouring across Multiple Radiotherapy Centres.

Background and purpose: Deep learning contouring (DLC) has the potential to decrease contouring time and variability of organ contours. This work evaluates the effectiveness of DLC for prostate and head and neck across four radiotherapy centres using a commercial system. Materials and methods: Computed tomography scans of 123 prostate and 310 head and neck patients were evaluated. Besides one head and neck model, generic DLC models were used. Contouring time using centres' existing clinical methods and contour editing time after DLC were compared. Timing was evaluated using paired and non-paired studies. Commercial software or in-house scripts assessed dice similarity coefficient (DSC) and distance to agreement (DTA). One centre assessed head and neck inter-observer variability. Results: The mean contouring time saved for prostate structures using DLC compared to the existing clinical method was 5.9 ± 3.5 min. The best agreement was shown for the femoral heads (median DSC 0.92 ± 0.03, median DTA 1.5 ± 0.3 mm) and the worst for the rectum (median DSC 0.68 ± 0.04, median DTA 4.6 ± 0.6 mm). The mean contouring time saved for head and neck structures using DLC was 16.2 ± 8.6 min. For one centre there was no DLC time-saving compared to an atlas-based method. DLC contours reduced inter-observer variability compared to manual contours for the brainstem, left parotid gland and left submandibular gland. Conclusions: Generic prostate and head and neck DLC models can provide time-savings which can be assessed with paired or non-paired studies to integrate with clinical workload. Reducing inter-observer variability potential has been shown.

Volumetric modulated arc therapy in prostate cancer patients with metallic hip prostheses in a UK centre.

AIM: This study aimed to investigate whether IMRT using VMAT is a viable and safe solution in dose escalated RT in these patients. BACKGROUND: An increasing number of prostate cancer patients are elderly and have hip prostheses. These implants pose challenges in radiotherapy treatment planning. Although intensity modulated radiotherapy (IMRT) is commonly used, there is a lack of clinical studies documenting its efficacy and toxicities in this subgroup of patients. MATERIALS AND METHODS: The data from 23 patients with hip prostheses and non-metastatic prostate cancer treated with VMAT (volumetric modulated arc therapy) between 2009 and 2011, were retrospectively analyzed. Baseline characteristics, treatment details and outcome data were collected on all patients. The median follow up was 40.9 months. MRI-CT image fusion was performed and the treatment plans were created using RapidArc™ (RA) techniques utilizing 1 or 2 arcs and 10 MV photon beams. RESULTS: 96% of patients were treated with a dose of 72 Gy/32 fractions over 44 days. 21/23 plans met the PTV targets. The mean homogeneity index was 1.07. 20/23 plans met all OAR constraints (rectum, bladder). Two plans deviated from rectal constraints, four from bladder constraints; all were classed as minor deviations. One patient experienced late grade 3 genitourinary toxicity. Three other patients experienced late grade 2 or lower gastrointestinal toxicity. One patient had biochemical failure and one had a non-prostate cancer related death. CONCLUSIONS: VMAT provides an elegant solution to deliver dose escalated RT in patients with unilateral and bilateral hip replacements with minimal acute and late toxicities.