Vali-Betts Elham, Krause Kevin J, Dubrovsky Alanna, Olson Kristin, Graff John Paul, Mitra Anupam, Datta-Mitra Ananya, Beck Kenneth, Tsirigos Aristotelis, Loomis Cynthia, Neto Antonio Galvao, Adler Esther, Rashidi Hooman H
Department of Pathology and Laboratory Medicine, University of California Davis School of Medicine, Sacramento, CA, USA.
Department of Psychiatry, Oregon Health and Science University, Portland, OR, USA.
J Pathol Inform. 2021 Jan 23;12:5. doi: 10.4103/jpi.jpi_69_20. eCollection 2021.
Histology, the microscopic study of normal tissues, is a crucial element of most medical curricula. Learning tools focused on histology are very important to learners who seek diagnostic competency within this important diagnostic arena. Recent developments in machine learning (ML) suggest that certain ML tools may be able to benefit this histology learning platform. Here, we aim to explore how one such tool based on a convolutional neural network, can be used to build a generalizable multi-classification model capable of classifying microscopic images of human tissue samples with the ultimate goal of providing a differential diagnosis (a list of look-alikes) for each entity.
We obtained three institutional training datasets and one generalizability test dataset, each containing images of histologic tissues in 38 categories. Models were trained on data from single institutions, low quantity combinations of multiple institutions, and high quantity combinations of multiple institutions. Models were tested against withheld validation data, external institutional data, and generalizability test images obtained from Google image search. Performance was measured with macro and micro accuracy, sensitivity, specificity, and f1-score.
In this study, we were able to show that such a model's generalizability is dependent on both the training data source variety and the total number of training images used. Models which were trained on 760 images from only a single institution performed well on withheld internal data but poorly on external data (lower generalizability). Increasing data source diversity improved generalizability, even when decreasing data quantity: models trained on 684 images, but from three sources improved generalization accuracy between 4.05% and 18.59%. Maintaining this diversity and increasing the quantity of training images to 2280 further improved generalization accuracy between 16.51% and 32.79%.
This pilot study highlights the significance of data diversity within such studies. As expected, optimal models are those that incorporate both diversity and quantity into their platforms.s.
组织学，即对正常组织的微观研究，是大多数医学课程的关键要素。对于在这个重要诊断领域寻求诊断能力的学习者来说，专注于组织学的学习工具非常重要。机器学习（ML）的最新进展表明，某些ML工具可能有助于这个组织学学习平台。在这里，我们旨在探索一种基于卷积神经网络的此类工具如何用于构建一个可推广的多分类模型，该模型能够对人体组织样本的微观图像进行分类，最终目标是为每个实体提供鉴别诊断（相似物列表）。
我们获得了三个机构训练数据集和一个泛化测试数据集，每个数据集包含38个类别的组织学组织图像。模型在来自单个机构的数据、多个机构的少量组合数据以及多个机构的大量组合数据上进行训练。模型针对保留的验证数据、外部机构数据以及从谷歌图像搜索获得的泛化测试图像进行测试。性能通过宏观和微观准确率、灵敏度、特异性和F1分数来衡量。
在本研究中，我们能够表明这种模型的泛化性取决于训练数据源的多样性和所使用的训练图像总数。仅在单个机构的760张图像上训练的模型在保留的内部数据上表现良好，但在外部数据上表现不佳（泛化性较低）。增加数据源的多样性提高了泛化性，即使减少数据量也是如此：在684张图像上训练但来自三个来源的模型将泛化准确率提高了4.05%至18.59%。保持这种多样性并将训练图像数量增加到2280进一步将泛化准确率提高了16.51%至32.79%。
这项初步研究突出了此类研究中数据多样性的重要性。正如预期的那样，最佳模型是那些在其平台中纳入了多样性和数量的模型。
