Deep learning has the potential to automate many clinically useful tasks in medical imaging. However translation of deep learning into clinical practice has been hindered by issues such as lack of the transparency and interpretability in these "black box" algorithms compared to traditional statistical methods. Specifically, many clinical deep learning models lack rigorous and robust techniques for conveying certainty (or lack thereof) in their predictions -- ultimately limiting their appeal for extensive use in medical decision-making. Furthermore, numerous demonstrations of algorithmic bias have increased hesitancy towards deployment of deep learning for clinical applications. To this end, we explore how conformal predictions can complement existing deep learning approaches by providing an intuitive way of expressing uncertainty while facilitating greater transparency to clinical users. In this paper, we conduct field interviews with radiologists to assess possible use-cases for conformal predictors. Using insights gathered from these interviews, we devise two clinical use-cases and empirically evaluate several methods of conformal predictions on a dermatology photography dataset for skin lesion classification. We show how to modify conformal predictions to be more adaptive to subgroup differences in patient skin tones through equalized coverage. Finally, we compare conformal prediction against measures of epistemic uncertainty.
翻译:深层学习有可能使医学成像方面的许多临床有用任务自动化。然而,将深层学习转化为临床实践却受到一些问题的阻碍,例如这些“黑盒”算法与传统统计方法相比缺乏透明度和可解释性等问题的阻碍。具体地说,许多临床深层学习模型缺乏在预测中传达确定性(或缺乏确定性)的严格和有力的技术 -- -- 最终限制了它们在医疗决策中广泛应用的吸引力。此外,许多算法偏向的示范增加了在临床应用中应用深层学习的偏执性。为此,我们探索如何通过提供直观的方式表达不确定性,同时促进临床用户更大的透明度,使符合的预测能够补充现有的深层学习方法。在本文件中,我们与放射科专家进行实地访谈,以评估可能用于符合预测的病例。我们利用这些访谈获得的洞察,设计了两个临床使用案例和实证性评估了皮肤病变分类的皮肤病理学摄影数据集的几种符合性预测方法。我们展示了如何修改符合的预测,以便更适应病人皮肤分层差异,同时通过均衡的覆盖措施。最后,我们对比了各种预测。