Applications and limitations of machine learning in radiation oncology
Machine learning approaches to problem-solving are growing rapidly within healthcare, and radiation oncology is no exception. With the burgeoning interest in machine learning comes the significant risk of misaligned expectations as to what it can and cannot accomplish. This paper evaluates the role...
| Үндсэн зохиолчид: | , , , |
|---|---|
| Формат: | Journal article |
| Хэвлэсэн: |
British Institute of Radiology
2019
|
| _version_ | 1826290498356117504 |
|---|---|
| author | Jarrett, D Stride, E Vallis, K Gooding, M |
| author_facet | Jarrett, D Stride, E Vallis, K Gooding, M |
| author_sort | Jarrett, D |
| collection | OXFORD |
| description | Machine learning approaches to problem-solving are growing rapidly within healthcare, and radiation oncology is no exception. With the burgeoning interest in machine learning comes the significant risk of misaligned expectations as to what it can and cannot accomplish. This paper evaluates the role of machine learning and the problems it solves within the context of current clinical challenges in radiation oncology. The role of learning algorithms within the workflow for external beam radiation therapy are surveyed, considering simulation imaging, multimodal fusion, image segmentation, treatment planning, quality assurance, and treatment delivery and adaptation. For each aspect, the clinical challenges faced, the learning algorithms proposed, and the successes and limitations of various approaches are analyzed. It is observed that machine learning has largely thrived on reproducibly mimicking conventional human-driven solutions with more efficiency and consistency. On the other hand, since algorithms are generally trained using expert opinion as ground truth, machine learning is of limited utility where problems or ground truths are not well-defined, or if suitable measures of correctness are not available. As a result, machines may excel at replicating, automating and standardizing human behaviour on manual chores, meanwhile the conceptual clinical challenges relating to definition, evaluation, and judgement remain in the realm of human intelligence and insight. |
| first_indexed | 2024-03-07T02:45:06Z |
| format | Journal article |
| id | oxford-uuid:abc977ef-6ccd-4cc1-adca-ccbaa1cbadb6 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T02:45:06Z |
| publishDate | 2019 |
| publisher | British Institute of Radiology |
| record_format | dspace |
| spelling | oxford-uuid:abc977ef-6ccd-4cc1-adca-ccbaa1cbadb62022-03-27T03:24:15ZApplications and limitations of machine learning in radiation oncologyJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:abc977ef-6ccd-4cc1-adca-ccbaa1cbadb6Symplectic Elements at OxfordBritish Institute of Radiology2019Jarrett, DStride, EVallis, KGooding, MMachine learning approaches to problem-solving are growing rapidly within healthcare, and radiation oncology is no exception. With the burgeoning interest in machine learning comes the significant risk of misaligned expectations as to what it can and cannot accomplish. This paper evaluates the role of machine learning and the problems it solves within the context of current clinical challenges in radiation oncology. The role of learning algorithms within the workflow for external beam radiation therapy are surveyed, considering simulation imaging, multimodal fusion, image segmentation, treatment planning, quality assurance, and treatment delivery and adaptation. For each aspect, the clinical challenges faced, the learning algorithms proposed, and the successes and limitations of various approaches are analyzed. It is observed that machine learning has largely thrived on reproducibly mimicking conventional human-driven solutions with more efficiency and consistency. On the other hand, since algorithms are generally trained using expert opinion as ground truth, machine learning is of limited utility where problems or ground truths are not well-defined, or if suitable measures of correctness are not available. As a result, machines may excel at replicating, automating and standardizing human behaviour on manual chores, meanwhile the conceptual clinical challenges relating to definition, evaluation, and judgement remain in the realm of human intelligence and insight. |
| spellingShingle | Jarrett, D Stride, E Vallis, K Gooding, M Applications and limitations of machine learning in radiation oncology |
| title | Applications and limitations of machine learning in radiation oncology |
| title_full | Applications and limitations of machine learning in radiation oncology |
| title_fullStr | Applications and limitations of machine learning in radiation oncology |
| title_full_unstemmed | Applications and limitations of machine learning in radiation oncology |
| title_short | Applications and limitations of machine learning in radiation oncology |
| title_sort | applications and limitations of machine learning in radiation oncology |
| work_keys_str_mv | AT jarrettd applicationsandlimitationsofmachinelearninginradiationoncology AT stridee applicationsandlimitationsofmachinelearninginradiationoncology AT vallisk applicationsandlimitationsofmachinelearninginradiationoncology AT goodingm applicationsandlimitationsofmachinelearninginradiationoncology |