Shao-Lun Lu1,2, Fu-Ren Xiao3, Jason Chia-Hsien Cheng1,4,2, Wen-Chi Yang1,4, Yueh-Hung Cheng5, Yu-Cheng Chang5, Jhih-Yuan Lin5, Chih-Hung Liang5, Jen-Tang Lu5, Ya-Fang Chen6, Feng-Ming Hsu1,4. 1. Department of Oncology, National Taiwan University Hospital, Taipei, Taiwan. 2. Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan. 3. Department of Surgery, National Taiwan University Hospital, Taipei, Taiwan. 4. Graduate Institute of Oncology, National Taiwan University College of Medicine, Taipei, Taiwan. 5. Vysioneer Inc, Cambridge, MA, United States. 6. Department of Medical Imaging, National Taiwan University Hospital, Taipei, Taiwan.
Abstract
BACKGROUND: Stereotactic radiosurgery (SRS), a validated treatment for brain tumors, requires accurate tumor contouring. This manual segmentation process is time-consuming and prone to substantial inter-practitioner variability. Artificial intelligence (AI) with deep neural networks have increasingly been proposed for use in lesion detection and segmentation but have seldom been validated in a clinical setting. METHODS: We conducted a randomized, cross-modal, multi-reader, multi-specialty, multi-case study to evaluate the impact of AI assistance on brain tumor SRS. A state-of-the-art auto-contouring algorithm built on multi-modality imaging and ensemble neural networks was integrated into the clinical workflow. Nine medical professionals contoured the same case series in two reader modes (assisted or un-assisted) with a memory washout period of 6 weeks between each section. The case series consisted of ten algorithm-unseen cases, including five cases of brain metastases, three of meningiomas and two of acoustic neuromas. Among the nine readers, three experienced experts determined the ground truths of tumor contours. RESULTS: With the AI assistance, the inter-reader agreement significantly increased (Dice similarity coefficient [DSC] from 0.86 to 0.90, P<0.001). Algorithm-assisted physicians demonstrated a higher sensitivity for lesion detection than un-assisted physicians (91.3% versus 82.6%, P=0.030). AI assistance improved contouring accuracy, with an average increase in DSC of 0.028, especially for physicians with less SRS experience (average DSC from 0.847 to 0.865, P=0.002). In addition, AI assistance improved efficiency with a median of 30.8%-time savings. Less-experienced clinicians gained prominent improvement on contouring accuracy but less benefit in reduction of working hours. By contrast, SRS specialists had a relatively minor advantage in DSC, but greater timesaving with the aid of AI. CONCLUSIONS: Deep learning neural networks can be optimally utilized to improve accuracy and efficiency for the clinical workflow in brain tumor SRS.
BACKGROUND: Stereotactic radiosurgery (SRS), a validated treatment for brain tumors, requires accurate tumor contouring. This manual segmentation process is time-consuming and prone to substantial inter-practitioner variability. Artificial intelligence (AI) with deep neural networks have increasingly been proposed for use in lesion detection and segmentation but have seldom been validated in a clinical setting. METHODS: We conducted a randomized, cross-modal, multi-reader, multi-specialty, multi-case study to evaluate the impact of AI assistance on brain tumor SRS. A state-of-the-art auto-contouring algorithm built on multi-modality imaging and ensemble neural networks was integrated into the clinical workflow. Nine medical professionals contoured the same case series in two reader modes (assisted or un-assisted) with a memory washout period of 6 weeks between each section. The case series consisted of ten algorithm-unseen cases, including five cases of brain metastases, three of meningiomas and two of acoustic neuromas. Among the nine readers, three experienced experts determined the ground truths of tumor contours. RESULTS: With the AI assistance, the inter-reader agreement significantly increased (Dice similarity coefficient [DSC] from 0.86 to 0.90, P<0.001). Algorithm-assisted physicians demonstrated a higher sensitivity for lesion detection than un-assisted physicians (91.3% versus 82.6%, P=0.030). AI assistance improved contouring accuracy, with an average increase in DSC of 0.028, especially for physicians with less SRS experience (average DSC from 0.847 to 0.865, P=0.002). In addition, AI assistance improved efficiency with a median of 30.8%-time savings. Less-experienced clinicians gained prominent improvement on contouring accuracy but less benefit in reduction of working hours. By contrast, SRS specialists had a relatively minor advantage in DSC, but greater timesaving with the aid of AI. CONCLUSIONS: Deep learning neural networks can be optimally utilized to improve accuracy and efficiency for the clinical workflow in brain tumor SRS.
Authors: Che Wei Chang; Mesakh Christian; Dun Hao Chang; Feipei Lai; Tom J Liu; Yo Shen Chen; Wei Jen Chen Journal: PLoS One Date: 2022-02-17 Impact factor: 3.240