论文标题
可解释的图像质量评估
Explainable Image Quality Assessments in Teledermatological Photography
论文作者
论文摘要
图像质量是远程咨询的有效性和效率的关键因素。但是，多达50％的由患者发送的图像存在质量问题，从而增加了诊断和治疗的时间。为了改善当前的远程咨询流量，需要一种自动化，易于部署，可解释的方法来评估图像质量。我们介绍了ImageQX，这是一个用于图像质量评估的卷积神经网络，其学习机制可确定最常见的图像质量解释：不良框架，不良照明，模糊，低分辨率和距离问题。 ImageQX接受了26,635张照片的培训，并在9,874张照片上进行了验证，每张照片都有图像质量标签和不良图像质量解释的注释，最多可提供12位董事会认证的皮肤科医生。摄影图像是在2017年至2019年之间使用移动皮肤病跟踪应用程序在全球范围内访问的。我们的方法可实现图像质量评估和图像质量差的解释的专家级别的性能。对于图像质量评估，ImageQX获得了0.73 +-0.01的宏F1分数，将其置于成对评估者Inter-Reter F1得分的标准偏差为0.77 +-0.07。对于差的图像质量解释，我们的方法获得了0.37 +-0.01和0.70 +-0.01之间的F1得分，类似于评分者间成对的F1得分，介于0.24 +-0.15和0.83 +-0.06之间。此外，ImageQX的尺寸仅为15 MB，可在移动设备上很容易部署。通过与皮肤科医生相似的图像质量检测性能，将ImageQX纳入远程表面学流程可以使更好，更快的流程进行远程咨询。
Image quality is a crucial factor in the effectiveness and efficiency of teledermatological consultations. However, up to 50% of images sent by patients have quality issues, thus increasing the time to diagnosis and treatment. An automated, easily deployable, explainable method for assessing image quality is necessary to improve the current teledermatological consultation flow. We introduce ImageQX, a convolutional neural network for image quality assessment with a learning mechanism for identifying the most common poor image quality explanations: bad framing, bad lighting, blur, low resolution, and distance issues. ImageQX was trained on 26,635 photographs and validated on 9,874 photographs, each annotated with image quality labels and poor image quality explanations by up to 12 board-certified dermatologists. The photographic images were taken between 2017 and 2019 using a mobile skin disease tracking application accessible worldwide. Our method achieves expert-level performance for both image quality assessment and poor image quality explanation. For image quality assessment, ImageQX obtains a macro F1-score of 0.73 +- 0.01, which places it within standard deviation of the pairwise inter-rater F1-score of 0.77 +- 0.07. For poor image quality explanations, our method obtains F1-scores of between 0.37 +- 0.01 and 0.70 +- 0.01, similar to the inter-rater pairwise F1-score of between 0.24 +- 0.15 and 0.83 +- 0.06. Moreover, with a size of only 15 MB, ImageQX is easily deployable on mobile devices. With an image quality detection performance similar to that of dermatologists, incorporating ImageQX into the teledermatology flow can enable a better, faster flow for remote consultations.
