A self‐adaptive case‐based reasoning system for dose planning in prostate cancer radiotherapy

Petrović, Sanja; Sundar, Santhanam

doi:10.1118/1.3660517

Cited by 23 publications

(12 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The heterogeneous sources of information that elicit physical contexts as well as cultural contexts, an intelligent environment can build and use a contextual picture of the situation to perceive the environmental change [5]. Whereas, 'context reasoning' terms are used when high degree of meaningful information is extracted from the context data and provide a fact for an action to be taken [30]. This context awareness is middleware that supplies necessary feedback to the interface to adapt a situation for better services.…”

Section: Discussionmentioning

confidence: 99%

Is ‘Context-Aware Reasoning = Case-Based Reasoning’?

Khan

Alegre

Kramer

et al. 2017

Modeling and Using Context

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Is ‘Context-Aware Reasoning = Case-Based Reasoning’?

Khan

Alegre

Kramer

et al. 2017

Modeling and Using Context

View full text Add to dashboard Cite

“…Such an approach to rule-based adaptation was employed in the CBR system for RTP for prostate cancer by Mishra et al [2], in which experts' personal opinions were modelled by rules.…”

Section: Adaptation In Case-based Reasoningmentioning

confidence: 99%

“…Dempster-Shafer theory was applied in the retrieval phase to fuse plans from multiple retrieved similar cases to strengthen agreements and decrease conflicts in situations where oncologists might have different opinions of the same case [19]. Mishra et al [2] developed a CBR system for dose planning in prostate cancer to determine the extent to which dose limits set for an OAR can be exceeded to better fight cancer cells.…”

Section: Case-based Reasoning In Cancer Treatmentmentioning

confidence: 99%

“…Many knowledge-based methods for radiotherapy planning have been developed to decide upon parameters for treatment plans, including the radiation dose plan, beam configuration, beam weight and wedge configuration [2][3][4][5]7]. Such methods aim at utilising knowledge available in the domain and used by the domain end-user to simulate the natural solving process as much as possible.…”

Section: Approaches To Radiotherapy Planningmentioning

confidence: 99%

“…When determining suitable values of planning parameters such as the number of beams, beam angles, number of wedges and their configuration and dose in different phases of treatment, various methodologies can be used. The literature on RTP offers a variety of methods that can be classified into optimisation and knowledge-based methods [2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Knowledge-light adaptation approaches in case-based reasoning for radiotherapy treatment planning

Petrović

Khussainova

Jagannathan

2016

Artificial Intelligence in Medicine

Self Cite

View full text Add to dashboard Cite

Objective: Radiotherapy treatment planning aims at delivering a sufficient radiation dose to cancerous tumour cells while sparing healthy organs in the tumour-surrounding area. It is a time-consuming trial-and-error process that requires the expertise of a group of medical experts including oncologists and medical physicists and can take from 2-3 hours to a few days. Our objective is to improve the performance of our previously built case-based reasoning (CBR) system for brain tumour radiotherapy treatment planning. In this system, a treatment plan for a new patient is retrieved from a case base containing patient cases treated in the past and their treatment plans. However, this system does not perform any adaptation, which is needed to account for any difference between the new and retrieved cases. Generally, the adaptation phase is considered to be intrinsically knowledge-intensive and domain-dependent. Therefore, an adaptation often requires a large amount of domain-specific knowledge, which can be difficult to acquire and often is not readily available. In this study, we investigate approaches to adaptation that do not require much domain knowledge, referred to as knowledge-light adaptation.Methodology: We developed two adaptation approaches: adaptation based on machine-learning tools and adaptationguided retrieval. They were used to adapt the beam number and beam angles suggested in the retrieved case. Two machine-learning tools, neural networks and naive Bayes classifier, were used in the adaptation to learn how the difference in attribute values between the retrieved and new cases affects the output of these two cases. The adaptation-guided retrieval takes into consideration not only the similarity between the new and retrieved cases, but also how to adapt the retrieved case.Results: The research was carried out in collaboration with medical physicists at the Nottingham University Hospitals NHS Trust, City Hospital Campus, UK. All experiments were performed using real-world brain cancer patient cases treated with three-dimensional (3D)-conformal radiotherapy. Neural networks-based adaptation improved the success rate of the CBR system with no adaptation by 12%. However, naive Bayes classifier did not improve the current retrieval results as it did not consider the interplay among attributes. The adaptation-guided retrieval of the case for beam number improved the success rate of the CBR system by 29%. However, it did not demonstrate good performance for the beam angle adaptation. Its success rate was 29% versus 39% when no adaptation was performed.Conclusions:The obtained empirical results demonstrate that the proposed adaptation methods improve the performance of the existing CBR system in recommending the number of beams to use. However, we also conclude that to be effective, the proposed adaptation of beam angles requires a large number of relevant cases in the case base.

show abstract