Despite the intense attention and investment into clinical machine learning (CML) research, relatively few applications convert to clinical practice. While research is important in advancing the state-of-the-art, translation is equally important in b
ringing these technologies into a position to ultimately impact patient care and live up to extensive expectations surrounding AI in healthcare. To better characterize a holistic perspective among researchers and practitioners, we survey several participants with experience in developing CML for clinical deployment about their learned experiences. We collate these insights and identify several main categories of barriers and pitfalls in order to better design and develop clinical machine learning applications.
Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting. Seve
n clinical institutions from across the world joined this FL effort to train a model for breast density classification based on Breast Imaging, Reporting & Data System (BI-RADS). We show that despite substantial differences among the datasets from all sites (mammography system, class distribution, and data set size) and without centralizing data, we can successfully train AI models in federation. The results show that models trained using FL perform 6.3% on average better than their counterparts trained on an institutes local data alone. Furthermore, we show a 45.8% relative improvement in the models generalizability when evaluated on the other participating sites testing data.
Deep learning has quickly become the weapon of choice for brain lesion segmentation. However, few existing algorithms pre-configure any biological context of their chosen segmentation tissues, and instead rely on the neural networks optimizer to deve
lop such associations de novo. We present a novel method for applying deep neural networks to the problem of glioma tissue segmentation that takes into account the structured nature of gliomas - edematous tissue surrounding mutually-exclusive regions of enhancing and non-enhancing tumor. We trained multiple deep neural networks with a 3D U-Net architecture in a tree structure to create segmentations for edema, non-enhancing tumor, and enhancing tumor regions. Specifically, training was configured such that the whole tumor region including edema was predicted first, and its output segmentation was fed as input into separate models to predict enhancing and non-enhancing tumor. Our method was trained and evaluated on the publicly available BraTS dataset, achieving Dice scores of 0.882, 0.732, and 0.730 for whole tumor, enhancing tumor and tumor core respectively.
