Deep learning workflow in radiology: a primer

Abstract

Interest for deep learning in radiology has increased tremendously in the past decade due to the high achievable performance for various computer vision tasks such as detection, segmentation, classification, monitoring, and prediction. This article provides step-by-step practical guidance for conducting a project that involves deep learning in radiology, from defining specifications, to deployment and scaling. Specifically, the objectives of this article are to provide an overview of clinical use cases of deep learning, describe the composition of multi-disciplinary team, and summarize current approaches to patient, data, model, and hardware selection. Key ideas will be illustrated by examples from a prototypical project on imaging of colorectal liver metastasis. This article illustrates the workflow for liver lesion detection, segmentation, classification, monitoring, and prediction of tumor recurrence and patient survival. Challenges are discussed, including ethical considerations, cohorting, data collection, anonymization, and availability of expert annotations. The practical guidance may be adapted to any project that requires automated medical image analysis.

Integrative radiogenomics for virtual biopsy and treatment monitoring in ovarian cancer

“…These steps and their limitations have been discussed in the existing literature [26,28,[30][31][32][33][34]. More recently, radiomic analyses have also included deep learning methods, which have the advantage of being able to learn the most useful quantitative representations of the data by themselves, therefore bypassing the need for handcrafted features [35][36][37].…”

CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection

“…As in many areas, the most preferred deep learning model in medicine is Convolutional Neural Networks (CNN)-based deep learning models [20] . When the patients learn early diagnosis, they can have the time for better medical care and better-personalized therapies [21] . CNNs, is a synthetic neural network, is one of machine learning algorithms.…”

A bird’s-eye view of deep learning in bioimage analysis

“…The impact of deep learning has been reviewed more specifically in a wide range of medical imaging areas, including abdominal imaging [103] , atherosclerosis imaging [104] , structural and functional brain imaging [105] , [106] , in-vivo cancer imaging [107] , dermatological imaging [108] , endoscopy [109] , mammography [110] , musculoskeletal imaging [111] , nuclear imaging [112] , ophthalmology [113] , pulmonary imaging [114] , thoracic imaging [115] , as well as in radiotherapy [116] , interventional radiology [117] , and radiology in general [118] , [119] , [120] . The massive body of papers on deep learning in virtually all areas of medical imaging has inspired many to write primers [121] , [122] , [123] , guides [124] , [125] , [126] , white papers or roadmaps [127] , [128] , [129] , and other commentaries [130] , [131] , [132] . There is now growing evidence that deep learning methods can perform on par with, if not better than, radiologists in specific tasks [133] , though the latter will continue to play a critical role in integrating such methods in clinical workflows [127] .…”