Assessment of manual adjustment performed in clinical practice following deep learning contouring for head and neck organs at risk in radiotherapy

Abstract

Background and purpose: Auto-contouring performance has been widely studied in development and commissioning studies in radiotherapy, and its impact on clinical workflow assessed in that context. This study aimed to evaluate the manual adjustment of auto-contouring in routine clinical practice and to identify improvements regarding the auto-contouring model and clinical user interaction, to improve the efficiency of auto-contouring. Materials and methods: A total of 103 clinical head and neck cancer cases, contoured using a commercial deeplearning contouring system and subsequently checked and edited for clinical use were retrospectively taken from clinical data over a twelve-month period (April 2019-April 2020). The amount of adjustment performed was calculated, and all cases were registered to a common reference frame for assessment purposes. The median, 10th and 90th percentile of adjustment were calculated and displayed using 3D renderings of structures to visually assess systematic and random adjustment. Results were also compared to inter-observer variation reported previously. Assessment was performed for both the whole structures and for regional sub-structures, and according to the radiation therapy technologist (RTT) who edited the contour. Results: The median amount of adjustment was low for all structures (<2 mm), although large local adjustment was observed for some structures. The median was systematically greater or equal to zero, indicating that the auto-contouring tends to under-segment the desired contour. Conclusion: Auto-contouring performance assessment in routine clinical practice has identified systematic improvements required technically, but also highlighted the need for continued RTT training to ensure adherence to guidelines.

Real-world analysis of manual editing of deep learning contouring in the thorax region

“…For the heart and esophagus, the Lung DL-model was used. The thyroid was taken from a head-and-neck DL-model [15] . The esophagus and thyroid were included when periclavicular or parasternal lymph node regions were involved.…”

“…The quality of automatic contouring has been widely studied on the geometrical level by comparing automatic delineations and user-adjustments, but typically using whole-organ measures and performed mostly on a limited patient cohort. A more extended analysis was previously published for head & neck cancer patients by Brouwer et al [15] . This current study aimed to evaluate the extent of manual adjustments following auto-contouring of organs-at-risk (OARs) in the thorax region in clinical practice for a large patient group.…”

RootPainter3D: Interactive‐machine‐learning enables rapid and accurate contouring for radiotherapy

“…Similarly to [5], we observed that many time consuming contour adjustments were minor changes along the boundary which are in many cases unlikely to have a large impact on dose. We agree with [5] that there is a need for methods that guide delineators in determining which corrections are meaningful for dose-planning. The combination of electronic health records, stored dose matrices and CT scans from record and verify systems has great potential to increase our understanding of radiation dose effects for normal tissues [59].…”

Barriers and facilitators to clinical implementation of radiotherapy treatment planning automation: A survey study of medical dosimetrists

“…14,15 Prospective studies have shown that in carefully controlled situations, automated treatment planning (ATP) generates plans of comparable or better clinical quality, at significant time savings. [16][17][18] A variety of commercially available automation tools exist, including but not limited to atlas-based 19 and deep-learningbased 13 auto-contouring (AC), knowledge-based planning (KBP), 20 rule-based automated planning, 21 and automated field-in-field planning. 22 However, little is known about the scale of clinical implementation of ATP techniques in the United States.…”