Radiation Oncologists’ Perceptions of Adopting an Artificial Intelligence–Assisted Contouring Technology: Model Development and Questionnaire Study

Zhai, Huiwen; Yang, Xin; Xue, Jiaolong; Lavender, Christopher; Ye, Tiantian; Li, Jibin; Xu, Lanyang; Lin, Li; Cao, Weiwei; Sun, Yu

doi:10.2196/27122

Cited by 32 publications

(42 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our questionnaire, few agreed that AI is more accurate than physicians (15% agreement), but these objectors seemed to be more confident in AI's efficiency with 52% agreeing that "clinical AI is more efficient than physicians" (Figure 3). Four studies used structural equation modeling to identify determinants of adoption intention for clinical AI among healthcare providers and medical students (38, [65][66][67]. Perceived usefulness, the experience of using mHealth, subjective norms, and social influence had a positive effect on adoption intention, while perceived risk had the opposite effect.…”

Section: Attitude and Acceptability Of Clinical Artificial Intelligencementioning

confidence: 99%

Acceptance of clinical artificial intelligence among physicians and medical students: A systematic review with cross-sectional survey

Chen

Zhang²,

Cai³

et al. 2022

Front. Med.

View full text Add to dashboard Cite

BackgroundArtificial intelligence (AI) needs to be accepted and understood by physicians and medical students, but few have systematically assessed their attitudes. We investigated clinical AI acceptance among physicians and medical students around the world to provide implementation guidance.Materials and methodsWe conducted a two-stage study, involving a foundational systematic review of physician and medical student acceptance of clinical AI. This enabled us to design a suitable web-based questionnaire which was then distributed among practitioners and trainees around the world.ResultsSixty studies were included in this systematic review, and 758 respondents from 39 countries completed the online questionnaire. Five (62.50%) of eight studies reported 65% or higher awareness regarding the application of clinical AI. Although, only 10–30% had actually used AI and 26 (74.28%) of 35 studies suggested there was a lack of AI knowledge. Our questionnaire uncovered 38% awareness rate and 20% utility rate of clinical AI, although 53% lacked basic knowledge of clinical AI. Forty-five studies mentioned attitudes toward clinical AI, and over 60% from 38 (84.44%) studies were positive about AI, although they were also concerned about the potential for unpredictable, incorrect results. Seventy-seven percent were optimistic about the prospect of clinical AI. The support rate for the statement that AI could replace physicians ranged from 6 to 78% across 40 studies which mentioned this topic. Five studies recommended that efforts should be made to increase collaboration. Our questionnaire showed 68% disagreed that AI would become a surrogate physician, but believed it should assist in clinical decision-making. Participants with different identities, experience and from different countries hold similar but subtly different attitudes.ConclusionMost physicians and medical students appear aware of the increasing application of clinical AI, but lack practical experience and related knowledge. Overall, participants have positive but reserved attitudes about AI. In spite of the mixed opinions around clinical AI becoming a surrogate physician, there was a consensus that collaborations between the two should be strengthened. Further education should be conducted to alleviate anxieties associated with change and adopting new technologies.

show abstract

Section: Attitude and Acceptability Of Clinical Artificial Intelligencementioning

confidence: 99%

Acceptance of clinical artificial intelligence among physicians and medical students: A systematic review with cross-sectional survey

Chen

Zhang²,

Cai³

et al. 2022

Front. Med.

View full text Add to dashboard Cite

show abstract

“…Currently, it functions best as an adjunct to manual delineation. While it can assist in reducing manual contouring time, 34 the process of organ and tumor sketching remains onerous for doctors. In addition to the hurdles of precise automatic segmentation, dataset collection and acquisition is also problematic as fully supervised learning and model efficiency is dependent on high‐quality datasets.…”

Section: Discussionmentioning

confidence: 99%

Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism

et al. 2021

Self Cite

View full text Add to dashboard Cite

Purpose To create a network which fully utilizes multi‐sequence MRI and compares favorably with manual human contouring. Methods We retrospectively collected 89 MRI studies of the pelvic cavity from patients with prostate cancer and cervical cancer. The dataset contained 89 samples from 87 patients with a total of 84 valid samples. MRI was performed with T1‐weighted (T1), T2‐weighted (T2), and Enhanced Dixon T1‐weighted (T1DIXONC) sequences. There were two cohorts. The training cohort contained 55 samples and the testing cohort contained 29 samples. The MRI images in the training cohort contained contouring data from radiotherapist α. The MRI images in the testing cohort contained contouring data from radiotherapist α and contouring data from another radiotherapist: radiotherapist β. The training cohort was used to optimize the convolution neural networks, which included the attention mechanism through the proposed activation module and the blended module into multiple MRI sequences, to perform autodelineation. The testing cohort was used to assess the networks’ autodelineation performance. The contoured organs at risk (OAR) were the anal canal, bladder, rectum, femoral head (L), and femoral head (R). Results We compared our proposed network with UNet and FuseUNet using our dataset. When T1 was the main sequence, we input three sequences to segment five organs and evaluated the results using four metrics: the DSC (Dice similarity coefficient), the JSC (Jaccard similarity coefficient), the ASD (average mean distance), and the 95% HD (robust Hausdorff distance). The proposed network achieved improved results compared with the baselines among all metrics. The DSC were 0.834±0.029, 0.818±0.037, and 0.808±0.050 for our proposed network, FuseUNet, and UNet, respectively. The 95% HD were 7.256±2.748 mm, 8.404±3.297 mm, and 8.951±4.798 mm for our proposed network, FuseUNet, and UNet, respectively. Our proposed network also had superior performance on the JSC and ASD coefficients. Conclusion Our proposed activation module and blended module significantly improved the performance of FuseUNet for multi‐sequence MRI segmentation. Our proposed network integrated multiple MRI sequences efficiently and autosegmented OAR rapidly and accurately. We also discovered that three‐sequence fusion (T1‐T1DIXONC‐T2) was superior to two‐sequence fusion (T1‐T2 and T1‐T1DIXONC, respectively). We infer that the more MRI sequences fused, the better the automatic segmentation results.

show abstract

“…For example, Nikolov et al [20] demonstrated a novel 3D U-Net architecture that could achieve expert-level performance while delineating 21 distinct head-and-neck target commonly segmented in clinical practice. While AI-assisted contouring can effectively empower clinicians beyond their current practices [35], there is a high cost associated to false positives and negatives in this domain. In addition, to support effective AI-approaches, large datasets are required and the limited availability of those large datasets impacts the scalability of applying AI to contouring.…”

Section: Background and Related Work 21 Contour Delineation In Radiot...mentioning

confidence: 99%

“…Contour delineation is a critical step in RT workflow where practicing oncologists identify and outline malignant tumors and/or healthy organs from a stack of medical images. Inaccurate contouring could lead to systematic errors throughout the entire treatment course, leading to either miss the malignant tumors, or over-treat the healthy tissues [35]. From the patient's side, poor contouring could cause increased risks of toxicity, tumor recurrence and death.…”

Section: Introductionmentioning

confidence: 99%

Exploring Needs and Design Opportunities for Virtual Reality-based Contour Delineations of Medical Structures

Chen

Yarmand

Singh

et al. 2022

Companion of the 2022 ACM SIGCHI Symposium on Engineering Interactive Computing Systems

View full text Add to dashboard Cite

Contour delineation, a critical phase in radiotherapy planning, refers to the process of identifying and segmenting malignant tumors and/or healthy organs from medical images. Today's contouring software requires oncologists to inspect and contour target of interests by analyzing a stack of planar medical images, which is lengthy, tedious and sometimes error prone. Such design is also in contrast to the stereoscopic nature of medical images. Therefore, it is intuitive to consider bringing contouring into immersive Virtual Reality (VR) space. We present an exploratory study that uses iterative design to understand needs and opportunities to bring contour delineation into an immersive 3D space, such as the one enabled by today's head-mounted VR displays. We report on the interactions with three medical professionals and three engineering & design experts, and demonstrate the potential for VR-based 3D contouring while studying the benefits of using 3D immersive spaces to augment the process of contour in 2D. Through needsfinding interviews and co-design workshops, we evaluated our initial iterations and proof-of-concept prototypes. We believe that our preliminary findings will benefit researchers and practitioners who are attempting to bring today's contour delineation processes into an immersive 3D space.

show abstract

Radiation Oncologists’ Perceptions of Adopting an Artificial Intelligence–Assisted Contouring Technology: Model Development and Questionnaire Study

Cited by 32 publications

References 49 publications

Acceptance of clinical artificial intelligence among physicians and medical students: A systematic review with cross-sectional survey

Acceptance of clinical artificial intelligence among physicians and medical students: A systematic review with cross-sectional survey

Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism

Exploring Needs and Design Opportunities for Virtual Reality-based Contour Delineations of Medical Structures

Contact Info

Product

Resources

About