Retrospective Clinical Evaluation of a Decision-Support Software for Adaptive Radiotherapy of Head and Neck Cancer Patients

Gros, Sébastien; Santhanam, Anand P.; Block, Alec M.; Emami, Bahman; Lee, Brian H.; Joyce, Cara

doi:10.3389/fonc.2022.777793

Cited by 6 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To our knowledge, there are other public and commercial software for ART 24 , 25 , but ARCliDS is the first interactive software dedicated to KBR-ART that will be available through a web portal. In this work, we have shown its applicability to adaptive RT and SBRT.…”

Section: Discussionmentioning

confidence: 99%

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Niraula

Sun

Jin

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient’s pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN’s RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

show abstract

Section: Discussionmentioning

confidence: 99%

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Niraula

Sun

Jin

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Others have used changes in longitudinal cone‐beam CT (CBCT) imaging characteristics, either measured quantitatively 40 or reported manually 41 to identify replanning candidates. Longitudinal dose accumulation strategies have also been used to more directly assess the dosimetric impact of anatomic changes by either computing original treatment plans on updated anatomy or deformably mapping planned dose maps to an updated scan 42–44 . AWARE could complement existing dose accumulation strategies by incorporating offline MRI information (which provides superior soft tissue discrimination in the head and neck compared with CBCT) and leveraging expert feedback on propagated structures to improve the accuracy of accumulated DVH statistics.…”

Section: Discussionmentioning

confidence: 99%

“…Longitudinal dose accumulation strategies have also been used to more directly assess the dosimetric impact of anatomic changes by either computing original treatment plans on updated anatomy or deformably mapping planned dose maps to an updated scan. [42][43][44] AWARE could complement existing dose accumulation strategies by incorporating offline MRI information (which provides superior soft tissue discrimination in the head and neck compared with CBCT) and leveraging expert feedback on propagated structures to improve the accuracy of accumulated DVH statistics. Importantly, AWARE was developed to run prospectively and work within clinical workflows to enable tracking at-scale and with minimal clinical overhead.…”

Section: Discussionmentioning

confidence: 99%

Automated tracking of morphologic changes in weekly magnetic resonance imaging during head and neck radiotherapy

Aliotta

Zhang

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background and Purpose Anatomic changes during head and neck radiotherapy can impact dose delivery, necessitate adaptive replanning, and indicate patient‐specific response to treatment. We have developed an automated system to track these changes through longitudinal MRI scans to aid identification and clinical intervention. The purpose of this article is to describe this tracking system and present results from an initial cohort of patients. Materials and Methods The Automated Watchdog in Adaptive Radiotherapy Environment (AWARE) was developed to process longitudinal MRI data for radiotherapy patients. AWARE automatically identifies and collects weekly scans, propagates radiotherapy planning structures, computes structure changes over time, and reports important trends to the clinical team. AWARE also incorporates manual structure review and revision from clinical experts and dynamically updates tracking statistics when necessary. AWARE was applied to patients receiving weekly T2‐weighted MRI scans during head and neck radiotherapy. Changes in nodal gross tumor volume (GTV) and parotid gland delineations were tracked over time to assess changes during treatment and identify early indicators of treatment response. Results N = 91 patients were tracked and analyzed in this study. Nodal GTVs and parotids both shrunk considerably throughout treatment (−9.7 ± 7.7% and −3.7 ± 3.3% per week, respectively). Ipsilateral parotids shrunk significantly faster than contralateral (−4.3 ± 3.1% vs. −2.9 ± 3.3% per week, p = 0.005) and increased in distance from GTVs over time (+2.7 ± 7.2% per week, p < 1 × 10−5). Automatic structure propagations agreed well with manual revisions (Dice = 0.88 ± 0.09 for parotids and 0.80 ± 0.15 for GTVs), but for GTVs the agreement degraded 4–5 weeks after the start of treatment. Changes in GTV volume observed by AWARE as early as one week into treatment were predictive of large changes later in the course (AUC = 0.79). Conclusion AWARE automatically identified longitudinal changes in GTV and parotid volumes during radiotherapy. Results suggest that this system may be useful for identifying rapidly responding patients as early as one week into treatment.

show abstract

“…To our knowledge, there are software for ART 27,28 but ARCliDS is the first interactive software dedicated to KBR-ART that will be available through a web portal. In this work, we have shown its applicability to adaptive RT and SBRT.…”

Section: Discussionmentioning

confidence: 99%

ARCliDS: A Clinical Decision Support System for AI-assisted Decision-Making in Response-Adaptive Radiotherapy

Niraula

Sun

Jin

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). Methods: ARCliDS is composed of two main components: Artificial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient's pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Network (GNN) is applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid unphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Network to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. Results: Double GNN architecture was able to correct the unphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 ± 0.03 Gy/frac (mean ± sem) for adaptive RT in NSCLC patients and 2.96±0.42 Gy/frac for adaptive SBRT HCC compared to the single GNN's RMSDs of 0.97 ± 0.12 Gy/frac and 4.75 ± 0.16 Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. Conclusion: ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

show abstract

Retrospective Clinical Evaluation of a Decision-Support Software for Adaptive Radiotherapy of Head and Neck Cancer Patients

Cited by 6 publications

References 47 publications

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Automated tracking of morphologic changes in weekly magnetic resonance imaging during head and neck radiotherapy

ARCliDS: A Clinical Decision Support System for AI-assisted Decision-Making in Response-Adaptive Radiotherapy

Contact Info

Product

Resources

About