Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis

By Veronika Cheplygina, Marleen de Bruijne, Josien P. W. Pluim. Medical Image Anal., 2018

897 citations recorded by the source corpus.

&NA; Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi‐supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not‐so‐supervised_a_survey_of_semi‐supervised_multi‐instance_and_transfer_learning_in_medical_image_analysis_/7479416.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/11663c4130486e1ea088906b19b72925f7d80213

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

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep learning with noisy labels: exploring techniques and remedies in medical image analysis (2019, background): “Semi-supervised learning, multipleinstance learning, and transfer learning in medical image analysis have been reviewed in [29].”
Domain Adaptation for Medical Image Analysis: A Survey (2021, neutral): “Recently, domain adaptation has attracted increasing interests and attention of researchers, and become an important research topic in machine learning based medical image analysis [22], [32]–[34].”
Multimodal data fusion for cancer biomarker discovery with deep learning (2023, background): “…include basic data transformations as well as generation of synthetic data, but other strategies such as semi-supervised learning 136–139 , active learning 140,141 , transfer learning 139,142–144 and automated annotation 145,146 have shown to be promising avenues to overcome labelled-data scarcity.”
Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images (2020, background): “Moreover, the transfer learning technique is another good choice for dealing with limited data [35], [36].”
Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation (2019, background): “The lack of the labeled data motivates the study of methods that can be trained with limited supervision, such as semisupervised learning [4]–[6], weakly supervised learning [7]–[9], and unsupervised domain adaptation [10]–[12].”
Spatial components of molecular tissue biology (2022, neutral): “These include established approaches in image-based deep learning that can deal with the absence of sufficiently informative labels, such as unsupervised, self-supervised and multi-task learning 61 .”
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation (2019, background): “(2018); Cheplygina et al. (2019) that broadly cover deep learning for general medical image analysis, from Hesamian et al.”
Towards Learning a Universal Non-Semantic Representation of Speech (2020, methodology): “This strategy has been used successfully in many application domains [13, 14].”
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019, background): “In a semi-supervised learning (SSL) scenario we may have some labelled data, but this is often very limited.”
Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, background): “Compared with related surveys[27, 25], we mainly focus on deep semi-supervised medical image segmentation.”
Predicting cancer outcomes with radiomics and artificial intelligence in radiology (2021, background): “…a category of features measuring the abnormal shape of the tumour-associated vasculature, has shown promise in the prediction of response to chemotherapy in patients with breast cancer 78,79 or malignant gliomas 50 and response to targeted agents in patients with breast cancer brain metastases 80 .”
An Incremental Self-Labeling Strategy for Semi-Supervised Deep Learning Based on Generative Adversarial Networks (2020, methodology): “…loss (cid:96) usp , the total loss on the discriminator side takes the following form : For our generator, we choose to use a feature matching [2] constraint, as denoted in Equation (7): In this part, we will detail our incremental self-labeling strategy for promoting the performance of…”
A Review of Domain Adaptation without Target Labels (2019, methodology): “Secondly, there is an empirical comparison of domain adaptation methods for genomic sequence analysis [27] and thirdly, a survey paper on, amongst others, transfer learning in biomedical imaging [28].”