A survey on deep learning in medical image analysis
By Geert J. S. Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, J. A. van der Laak, B. van Ginneken, Clara I. Sánchez. 2017
13,846 citations recorded by the source corpus.
Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per application area: neuro, retinal, pulmonary, digital pathology, breast, cardiac, abdominal, musculoskeletal. We end with a summary of the current state-of-the-art, a critical discussion of open challenges and directions for future research.
Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Percy Liang
- Dacheng Tao
- Mohit Bansal
- Quoc V. Le
- Jianfeng Gao
- Sergey Levine
- Ruslan Salakhutdinov
In Biomedical Engineering
- Dinggang Shen
- Arvid Lundervold
- Mingxia Liu
- Yi Yang
- Daniel Rueckert
- Xiahai Zhuang
- Christos Davatzikos
- Jun Ma
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Yi Yang
- Xiaogang Wang
- Trevor Darrell
- Andrea Vedaldi
- Jitendra Malik
In Radiology, Nuclear Medicine and Imaging
- Arvid Lundervold
- Mingxia Liu
- B. van Ginneken
- Ronald M. Summers
- Xiaosong Wang
- Daniel Rueckert
- Huan Fu
- Dinggang Shen
Citations in the corpus
- Rotation Equivariant CNNs for Digital Pathology (2018, methodology): “ized at 2 dierent centers using a 40 objective (resultant pixel resolution of 0.243 microns). In the Camelyon16 challenge, model performance is evaluated using the FROC curve for tumor localization. (2) The PCam dataset contains 327,680 patches extracted from Camelyon16 at a size of 96 96 pixels @ 1”
- SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (2022, background): “Interactive image segmentation approaches have been widely applied to annotate large-scale image datasets, which drive the success of deep models in various applications, including video understanding [5,49], self-driving [7], and medical imaging [32, 41].”
- Iterative Interaction Training for Segmentation Editing Networks (2018, neutral): “With the introduction of machine learning and especially convolutional neural networks (CNNs) the performance of automatic segmentation approaches improved greatly [7].”
- Split learning for health: Distributed deep learning without sharing raw patient data (2018, background): “Deep learning methods in general have found a pervasive suite of applications in biology, clinical medicine, genomics and public health as surveyed in [24, 23, 25, 29, 30, 31].”
- Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans (2020, background): “In recent years, DL techniques have been proved to be effective in the diagnosis of diseases with X-ray and CT images [25].”
- Style transfer-based image synthesis as an efficient regularization technique in deep learning (2019, background): “Recently, GANs started gaining attention in the field of medical image processing to solve tasks such as de-noising [29], segmentation [30], detection [31] and classification [32].”
- Albumentations: fast and flexible image augmentations (2018, background): “One typical use case for keypoint annotations is image registration, a common task in biomedical image analysis [29,63].”
- An overview of deep learning in medical imaging focusing on MRI (2018, background): “9 For a broad overview of deep learning applied to medical imaging, see [41].”
- Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Deep learning has been used to classify lesions and nodules; localize organs, regions, landmarks and lesions; segment organs, organ substructures and lesions; retrieve images based on content; generate and enhance images; and combine images with clinical reports [40,41].”
- Incremental Learning Through Deep Adaptation (2017, background): “While deep neural networks continue to show remarkable performance gains in various areas such as image classification [1], semantic segmentation [2], object detection [3], speech recognition [4] medical image analysis [5] - and many more - it is still the case that typically, a separate model needs”
- Attention-based Deep Multiple Instance Learning (2018, neutral): “Current supervised approaches utilize pixel-level annotations (Litjens et al., 2017).”
- Generative Adversarial Network in Medical Imaging: A Review (2018, background): “It is estimated that there were over 400 papers published in 2016 and 2017 in major medical imaging related conference venues and journals (Litjens et al., 2017).”
- Research on a Surface Defect Detection Algorithm Based on MobileNet-SSD (2018, neutral): “In recent years, deep learning has been successfully applied to image classification, speech recognition and natural language processing [20–22].”
- Temporal Convolutional Memory Networks for Remaining Useful Life Estimation of Industrial Machinery (2018, background): “Recently, convolutional neural networks (CNN) and long short-term memory (LSTM) networks have emerged as efficient methods in many pattern recognition application domains such as computer vision [6], [7], surveillance [8], [9], and medicine [10].”