图像质量对临床医生与深度学习模型诊断性能的影响:横断面比较阅读研究
医生在高质量图像上二分类和多分类诊断性能最佳,但在多分类中CNN模型在高质量图像上显著优于医生。
要点
- 高质量图像使医生二分类诊断敏感度77.3%、特异度63.1%、准确率70.2%。
- 多分类中高质量图像下医生特异度91.9%、准确率51.5%。
- 低质量和增强质量图像上医生二分类优于CNN,但高质量图像多分类CNN显著更优。
核心结论
- 图像质量显著影响医生和深度学习模型的诊断性能,对远程医疗报告和分诊有重要意义。
主要发现
- 医生二分类诊断在高质量图像上表现最佳:敏感度77.3%(95%CI 69.1-85.5)、特异度63.1%(95%CI 53.7-72.5)、准确率70.2%(95%CI 61.3-79.1)。
- 医生多分类诊断在高质量图像上总体最佳:特异度91.9%(95%CI 83.2-95.0)、准确率51.5%(95%CI 48.4-54.7)。
- 二分类中,医生在低质量和增强质量图像上的中位正确诊断数优于CNN模型,但在高质量图像上两者表现相当。
- 多分类中,CNN模型在高质量图像上显著优于医生(p < 0.01)。
临床怎么用
- 远程皮肤科诊疗和分诊中应重视图像质量,高质量图像有助于提升医生诊断准确性。
- 对于多分类诊断任务,高质量图像下CNN模型可能提供优于医生的辅助诊断价值。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Skin cancer is a prevalent and clinically significant condition, with early and accurate diagnosis being crucial for improved patient outcomes. Dermoscopy and artificial intelligence (AI) hold promise in enhancing diagnostic accuracy. However, the impact of image quality, particularly high dynamic range (HDR) conversion in smartphone images, on diagnostic performance remains poorly understood. OBJECTIVE: This study aimed to investigate the effect of varying image qualities, including HDR-enhanced dermoscopic images, on the diagnostic capabilities of clinicians and a convolutional neural network (CNN) model. METHODS: Eighteen dermatology clinicians assessed 303 images of 101 skin lesions that were categorized into three image quality groups: low quality (LQ), high quality (HQ) and enhanced quality (EQ) produced using HDR-style conversion. Clinicians participated in a two part reader study that required their diagnosis, management and confidence level for each image assessed. RESULTS: In the binary classification of lesions, clinicians had the greatest diagnostic performance with HQ images, with sensitivity (77.3%; CI 69.1-85.5), specificity (63.1%; CI 53.7-72.5) and accuracy (70.2%; CI 61.3-79.1). For the multiclass classification, the overall performance was also best with HQ images, attaining the greatest specificity (91.9%; CI 83.2-95.0) and accuracy (51.5%; CI 48.4-54.7). Clinicians had a superior performance (median correct diagnoses) to the CNN model for the binary classification of LQ and EQ images, but their performance was comparable on the HQ images. However, in the multiclass classification, the CNN model significantly outperformed the clinicians on HQ images (p < 0.01). CONCLUSION: This study highlights the importance of image quality on the diagnostic performance of clinicians and deep learning models. This has significant implications for telehealth reporting and triage.
引用
- Oloruntoba AI, Asghari-Jafarabadi M, Sashindranath M, et al. Assessment of image quality on the diagnostic performance of clinicians and deep learning models: Cross-sectional comparative reader study. J Eur Acad Dermatol Venereol. 2024. PMID: 39655640. doi:10.1111/jdv.20462
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。