Identifying clinically applicable machine learning algorithms for glioma segmentation: recent advances and discoveries

Abstract

Background While there are innumerable Machine learning (ML) research algorithms used for segmentation of gliomas, there is yet to be a US FDA cleared product. The aim of this study is to explore the systemic limitations of research algorithms that have prevented translation from concept to product by a review of the current research literature. Methods We performed a systematic literature review on four databases. Of 11,727 articles, 58 articles met the inclusion criteria and were used for data extraction and screening using TRIPOD. Results We found that while many articles were published on ML based glioma segmentation and report high accuracy results, there were substantial limitations in the methods and results portions of the papers that result in difficulty reproducing the methods and translation into clinical practice. Conclusion In addition, we identified that more than a third of the articles used the same publicly available BRaTS and TCIA datasets and are responsible for the majority of patient data on which ML algorithms were trained, which leads to limited generalizability and potential for overfitting and bias.

Clinical implementation of artificial intelligence in neuroradiology with development of a novel workflow-efficient picture archiving and communication system-based automated brain tumor segmentation and radiomic feature extraction

“…Multiple works demonstrated high accuracy with use of ML for tumor segmentation, identification of images with brain tumors from other pathologies, glioma grade and molecular subtype prediction, differentiation of gliomas from lymphoma or brain metastases. These results suggest that clinical implementation of these algorithms is imminent and will be seen in the clinical practice in the next few years (Subramanian et al, 2021;Afridi et al, 2022;Avery et al, 2022;Bahar et al, 2022;Cassinelli Petersen et al, 2022;Jekel et al, 2022;Tillmanns et al, 2022). The next frontier in neuro-oncology imaging is identification of clinical applications of ML algorithms in clinical practice and determining the aspects of clinical care that can be improved with predictions that can be generated by these algorithms.…”

A Fully Automated Post-Surgical Brain Tumor Segmentation Model for Radiation Treatment Planning and Longitudinal Tracking

“…While there have been several efforts to segment brain lesions from MRIs, such as through the Brain Tumor Segmentation Challenge (BraTS), those efforts have focused on pre-surgical brain MRIs, and have yet to make a substantial translation into clinically useful tools [6][7][8][9]. There have been minimal efforts to develop segmentation algorithms to assist RT planning after surgery.…”

Radiomics as an emerging tool in the management of brain metastases

“… 36–38 Deep convolutional neural network models have been widely used for tumor segmentation. 39 U-Net architecture and its variants are among the most commonly used models for tumor segmentation. 40 In fact, conventional machine learning (ML) and DL U-Net models proposed for glioma segmentation have been systematically reviewed.…”

“… 40 In fact, conventional machine learning (ML) and DL U-Net models proposed for glioma segmentation have been systematically reviewed. 39 They reported that deep learning models such as U-Net have the potential for deployment in a clinical setting.…”