Wide-Scale Clinical Implementation of Knowledge-Based Planning: An Investigation of Workforce Efficiency, Need for Post-automation Refinement, and Data-Driven Model Maintenance

Kaderka, Robert; Hild, Sebastian; Bry, Victoria; Cornell, M.; Ray, Xenia; Murphy, James D.; Atwood, Todd; Moore, Kevin L.

doi:10.1016/j.ijrobp.2021.06.028

Cited by 19 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence is demonstrating its importance with automatic contouring tools and autoplanning systems. 15 , 16 , 17 , 18 New technologies will appear in the short term 19 that will change the way of working, as happened with the appearance of 3-dimensional RT.…”

Section: Discussionmentioning

confidence: 99%

Clinical Validation of Siemens’ Syngo.via Automatic Contouring System

Pera

Álvaro

Christian

et al. 2023

Advances in Radiation Oncology

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Clinical Validation of Siemens’ Syngo.via Automatic Contouring System

Pera

Álvaro

Christian

et al. 2023

Advances in Radiation Oncology

View full text Add to dashboard Cite

“…Several clinics that utilize KBP demonstrated that KBP plans were non-inferior to manual planning and that planning time could be decreased. [13][14][15][16] To create high-quality plans using a KBP model, a database of "good" plans is required to train the model. Quality filtering is suggested to improve trained models.…”

Section: Introductionmentioning

confidence: 99%

“…These predictions can then be used to automatically generate optimization objectives, decreasing the amount of trial and error needed in manual treatment planning. Several clinics that utilize KBP demonstrated that KBP plans were non‐inferior to manual planning and that planning time could be decreased 13–16 …”

Section: Introductionmentioning

confidence: 99%

Effects of model size and composition on quality of head‐and‐neck knowledge‐based plans

Kaderka,

Dogan,

Jin

et al. 2023

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

PurposeKnowledge‐based planning (KBP) aims to automate and standardize treatment planning. New KBP users are faced with many questions: How much does model size matter, and are multiple models needed to accommodate specific physician preferences? In this study, six head‐and‐neck KBP models were trained to address these questions.MethodsThe six models differed in training size and plan composition: The KBPFull (n = 203 plans), KBP101 (n = 101), KBP50 (n = 50), and KBP25 (n = 25) were trained with plans from two head‐and‐neck physicians. KBPA and KBPB each contained n = 101 plans from only one physician, respectively. An independent set of 39 patients treated to 6000–7000 cGy by a third physician was re‐planned with all KBP models for validation. Standard head‐and‐neck dosimetric parameters were used to compare resulting plans. KBPFull plans were compared to the clinical plans to evaluate overall model quality. Additionally, clinical and KBPFull plans were presented to another physician for blind review. Dosimetric comparison of KBPFull against KBP101, KBP50, and KBP25 investigated the effect of model size. Finally, KBPA versus KBPB tested whether training KBP models on plans from one physician only influences the resulting output. Dosimetric differences were tested for significance using a paired t‐test (p < 0.05).ResultsCompared to manual plans, KBPFull significantly increased PTV Low D95% and left parotid mean dose but decreased dose cochlea, constrictors, and larynx. The physician preferred the KBPFull plan over the manual plan in 20/39 cases. Dosimetric differences between KBPFull, KBP101, KBP50, and KBP25 plans did not exceed 187 cGy on aggregate, except for the cochlea. Further, average differences between KBPA and KBPB were below 110 cGy.ConclusionsOverall, all models were shown to produce high‐quality plans. Differences between model outputs were small compared to the prescription. This indicates only small improvements when increasing model size and minimal influence of the physician when choosing treatment plans for training head‐and‐neck KBP models.

show abstract

“…In particular, successful commercial implementation of DVH-based KBP, RapidPlan 7 (Varian Medical Systems, Palo Alto, CA, USA) has been widely implemented in radiation oncology clinics, and its clinical successes have been well documented. [8][9][10][11] As fully automated clinical workflows powered by KBP methods are increasingly used, [12][13][14][15] it is of paramount importance to ensure a high-quality treatment plan is generated for every patient, even when the patient has uncommon anatomical features. It has been shown that the effectiveness of the KBP workflow relies on accurate dose predictions, and inaccurate predictions potentially result in inferior treatment plans.…”

Section: Introductionmentioning

confidence: 99%

“…The TPS can generate the final plan based on the KBP constraints. In particular, successful commercial implementation of DVH‐based KBP, RapidPlan 7 (Varian Medical Systems, Palo Alto, CA, USA) has been widely implemented in radiation oncology clinics, and its clinical successes have been well documented 8–11 …”

Section: Introductionmentioning

confidence: 99%

Technical note: Determining the applicability of a clinical knowledge‐based learning model via prospective outlier detection

et al. 2022

View full text Add to dashboard Cite

Background: Knowledge-based planning (KBP) is increasingly implemented clinically because of its demonstrated ability to improve treatment planning efficiency and reduce plan quality variations. However, cases with large dosevolume histogram (DVH) prediction uncertainties may still need manual adjustments by the planner to achieve high plan quality. Purpose: The purpose of this study is to develop a data-driven method to detect patients with high prediction uncertainties so that intentional effort is directed to these patients. Methods: We apply an anomaly detection method known as the local outlier factor (LOF) to a dataset consisting of the training set and each of the prospective patients considered, to evaluate their likelihood of being an anomaly when compared with the training cases. Features used in the LOF analysis include anatomical features and the model-generated DVH principal component scores. To test the efficacy of the proposed model, 142 prostate patients were retrieved from the clinical database and split into a training dataset of 100 patients and a test dataset of 42 patients. The outlier identification performance was quantified by the difference between the DVH prediction root-mean-squared errors (RMSE) of the identified outlier cases and that of the remaining inlier cases. Results: With a predefined LOF threshold of 1.4, the inlier cases achieved average RMSEs of 5.0 and 6.7 for bladder and rectum, while the outlier cases have substantially higher RMSEs of 6.7 and 13.0 in comparison. Conclusions:We propose a method that can determine the prospective patient's outlier status. This method can be integrated into existing automated treatment planning workflows to reduce the risk of generating suboptimal treatment plans while providing an upfront alert to the treatment planner.

show abstract

Wide-Scale Clinical Implementation of Knowledge-Based Planning: An Investigation of Workforce Efficiency, Need for Post-automation Refinement, and Data-Driven Model Maintenance

Cited by 19 publications

References 26 publications

Clinical Validation of Siemens’ Syngo.via Automatic Contouring System

Clinical Validation of Siemens’ Syngo.via Automatic Contouring System

Effects of model size and composition on quality of head‐and‐neck knowledge‐based plans

Technical note: Determining the applicability of a clinical knowledge‐based learning model via prospective outlier detection

Contact Info

Product

Resources

About