Automatic brain lesion segmentation on standard MRIs of the human head: a scoping review protocol

Abstract

IntroductionAutomatic brain lesion segmentation from medical images has great potential to support clinical decision making. Although numerous methods have been proposed, significant challenges must be addressed before they will become established in clinical and research practice. We aim to elucidate the state of the art, to provide a synopsis of competing approaches and identify contrasts between them.Methods and analysisWe present the background and study design of a scoping review for automatic brain lesion segmentation methods for conventional MRI according to the framework proposed by Arksey and O’Malley. We aim to identify common image processing steps as well as mathematical and computational theories implemented in these methods. We will aggregate the evidence on the efficacy and identify limitations of the approaches. Methods to be investigated work with standard MRI sequences from human patients examined for brain lesions, and are validated with quantitative measures against a trusted reference. PubMed, IEEE Xplore and Scopus will be searched using search phrases that will ensure an inclusive and unbiased overview. For matching records, titles and abstracts will be screened to ensure eligibility. Studies will be excluded if a full paper is not available or is not written in English, if non-standard MR sequences are used, if there is no quantitative validation, or if the method is not automatic. In the data charting phase, we will extract information about authors, publication details and study cohort. We expect to find information about preprocessing, segmentation and validation procedures. We will develop an analytical framework to collate, summarise and synthesise the data.Ethics and disseminationEthical approval for this study is not required since the information will be extracted from published studies. We will submit the review report to a peer-reviewed scientific journal and explore other venues for presenting the work.

Accuracy and practical aspects of semi- and fully automatic segmentation methods for resected brain areas

“…To date, slice-by-slice manual lesion tracing by expert raters remains the gold standard [ 5 , 11 , 12 ]. This approach is considered most precise [ 3 ], but also tedious and time-consuming [ 13 ] and requires significant experience [ 14 ].…”

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

“…We acknowledge self-critically that, due to the extensive nature of the task, the time taken, and the lessons learnt during the work, some epistemic drift occurred, taking our focus away from the first two RQs and towards the question of clinical applicability that appears to be underserved by the current literature. Thanks to our early decision to hold ourselves to account by writing a detailed protocol, 22 this drift stayed within reasonable boundaries and is well-documented, as we accounted for protocol modifications in the present work.…”

“…This study has been conducted according to a previously published protocol 22 and based on scoping review methods proposed by Arksey and O'Malley 17 and further developed by Levac et al and Colquhoun et al 18 19 We also incorporate relevant parts of the Preferred Reporting Items for Systematic Reviews andMeta-Analyses (PRISMA) 20 and PRISMA extension for Scoping Reviews 21 protocol for this type of review. Here, we provide a summary of the protocol as well as an account of changes made, along with their respective rationale.…”

“…The following RQs were posed in the protocol 22 While getting familiar with the abstracts of the sample, we questioned the relevance of RQs 1 and 2. We recognised the need for consultation at this early stage of the project as opposed to consultation on the findings as originally proposed by Arksey and O'Malley.…”