Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review

Abstract

Objectives: To summarize the available literature on using machine learning (ML) for the detection and segmentation of benign tumors of the central nervous system (CNS) and to assess the adherence of published ML/diagnostic accuracy studies to best practice. Methods: The MEDLINE database was searched for the use of ML in patients with any benign tumor of the CNS, and the records were screened according to PRISMA guidelines. Results: Eleven retrospective studies focusing on meningioma (n = 4), vestibular schwannoma (n = 4), pituitary adenoma (n = 2) and spinal schwannoma (n = 1) were included. The majority of studies attempted segmentation. Links to repositories containing code were provided in two manuscripts, and no manuscripts shared imaging data. Only one study used an external test set, which raises the question as to whether some of the good performances that have been reported were caused by overfitting and may not generalize to data from other institutions. Conclusion: Using ML for detecting and segmenting benign brain tumors is still in its infancy. Stronger adherence to ML best practices could facilitate easier comparisons between studies and contribute to the development of models that are more likely to one day be used in clinical practice.

Comparative Efficacy of AZD9496 and Fulvestrant on the Growth of Pituitary Adenoma via Blocking JAK2/STAT5B Pathway

“…Based on the biological behavior, pituitary adenoma can be classified into benign adenoma, invasive adenoma and carcinoma [2]. Although most pituitary adenoma are not cancerous, they can lead the pituitary to produce abnormal hormones, resulting in health problems [3][4][5]. Usually, it causes endocrine metabolic disorders and is harmful to the corresponding target organs.…”

Impact of Denoising on Deep-Learning-Based Automatic Segmentation Framework for Breast Cancer Radiotherapy Planning

“…As such, atlas-based and deep-learning algorithms based on convolutional neural network auto-segmentation have been developed to alleviate the labor-intensive delineation of OARs [ 1 , 2 , 3 , 4 , 5 , 6 , 7 ]. Machine learning approaches, especially deep learning with multi-layered neural networks, have been actively applied to treatment planning in radiotherapy [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ]. Many studies have investigated the deep-learning-based auto-segmentation of OARs for various disease sites [ 1 , 2 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ].…”