Background: As available medical image datasets increase in size, it becomes infeasible for clinicians to review content manually for knowledge extraction. The objective of this study was to create an automated clustering resulting in human-interpretable pattern discovery. Methods: Images from the public HAM10000 dataset, including 7 common pigmented skin lesion diagnoses, were tiled into 29420 tiles and clustered via k-means using neural network-extracted image features. The final number of clusters per diagnosis was chosen by either the elbow method or a compactness metric balancing intra-lesion variance and cluster numbers. The amount of resulting non-informative clusters, defined as those containing less than six image tiles, was compared between the two methods. Results: Applying k-means, the optimal elbow cutoff resulted in a mean of 24.7 (95%-CI: 16.4-33) clusters for every included diagnosis, including 14.9% (95% CI: 0.8-29.0) non-informative clusters. The optimal cutoff, as estimated by the compactness metric, resulted in significantly fewer clusters (13.4; 95%-CI 11.8-15.1; p=0.03) and less non-informative ones (7.5%; 95% CI: 0-19.5; p=0.017). The majority of clusters (93.6%) from the compactness metric could be manually mapped to previously described dermatoscopic diagnostic patterns. Conclusions: Automatically constraining unsupervised clustering can produce an automated extraction of diagnostically relevant and human-interpretable clusters of visual patterns from a large image dataset.

翻译：背景：随着可用医学影像数据集规模增大，临床医生通过人工审查提取知识变得不可行。本研究旨在创建一种自动聚类方法，实现可解释性模式的发现。方法：从公共HAM10000数据集中选取包含7种常见色素性皮肤病变诊断的影像，将其切割为29420个图像块，利用神经网络提取图像特征后通过k-means进行聚类。各诊断终聚类数通过肘部法则或平衡病变内方差与聚类数的紧凑度指标确定。比较两种方法产生的非信息性聚类（定义为包含少于6个图像块的聚类）数量。结果：应用k-means时，最优肘部截断点对每项纳入诊断产生平均24.7个聚类（95%置信区间：16.4-33），其中包含14.9%非信息性聚类（95%置信区间：0.8-29.0）。通过紧凑度指标估计的最优截断点产生的聚类数显著减少（13.4；95%置信区间11.8-15.1；p=0.03），非信息性聚类比例也更低（7.5%；95%置信区间0-19.5；p=0.017）。紧凑度指标产生的93.6%聚类可手动映射至既往描述的皮肤镜诊断模式。结论：对无监督聚类进行自动约束，可从大规模影像数据集中自动提取具有诊断相关性和人工可解释性的视觉模式聚类。