Development of RLK-Unet: a clinically favorable deep learning algorithm for brain metastasis detection and treatment response assessment

Seungyeon Son; Bio Joo; Mina Park; Sang Hyun Suh; Hee Sang Oh; Jun Won Kim; Seoyoung Lee; Sung Jun Ahn; Jong-Min Lee

doi:10.3389/fonc.2023.1273013

Development of RLK-Unet: a clinically favorable deep learning algorithm for brain metastasis detection and treatment response assessment

Front Oncol. 2024 Jan 15:13:1273013. doi: 10.3389/fonc.2023.1273013. eCollection 2023.

Authors

Seungyeon Son¹, Bio Joo², Mina Park², Sang Hyun Suh², Hee Sang Oh², Jun Won Kim³, Seoyoung Lee⁴, Sung Jun Ahn^#², Jong-Min Lee^#⁵

Affiliations

¹ Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea.
² Department of Radiology, Gangnam Severance Hospital, Yonsei University, College of Medicine, Seoul, Republic of Korea.
³ Department of Radiation Oncology, Gangnam Severance Hospital, Yonsei University, College of Medicine, Seoul, Republic of Korea.
⁴ Division of Medical Oncology, Department of Internal Medicine, Gangnam Severance Hospital, College of Medicine, Yonsei University, Seoul, Republic of Korea.
⁵ Department of Biomedical Engineering, Hanyang University, Seoul, Republic of Korea.

^# Contributed equally.

Abstract

Purpose/objectives: Previous deep learning (DL) algorithms for brain metastasis (BM) detection and segmentation have not been commonly used in clinics because they produce false-positive findings, require multiple sequences, and do not reflect physiological properties such as necrosis. The aim of this study was to develop a more clinically favorable DL algorithm (RLK-Unet) using a single sequence reflecting necrosis and apply it to automated treatment response assessment.

Methods and materials: A total of 128 patients with 1339 BMs, who underwent BM magnetic resonance imaging using the contrast-enhanced 3D T1 weighted (T1WI) turbo spin-echo black blood sequence, were included in the development of the DL algorithm. Fifty-eight patients with 629 BMs were assessed for treatment response. The detection sensitivity, precision, Dice similarity coefficient (DSC), and agreement of treatment response assessments between neuroradiologists and RLK-Unet were assessed.

Results: RLK-Unet demonstrated a sensitivity of 86.9% and a precision of 79.6% for BMs and had a DSC of 0.663. Segmentation performance was better in the subgroup with larger BMs (DSC, 0.843). The agreement in the response assessment for BMs between the radiologists and RLK-Unet was excellent (intraclass correlation, 0.84).

Conclusion: RLK-Unet yielded accurate detection and segmentation of BM and could assist clinicians in treatment response assessment.

Keywords: brain metastasis; deep learning algorithm; detection; segmentation; treatment response.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This research was supported by the Neurological Disorder Research Program of the National Research Foundation (NRF) funded by the Korea government (MSIT) (No. 2020M3E5D9080788) to J-ML and by a National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1F1A1056512) and a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: HI20C2125) to SA.