A scoping review of transfer learning research on medical image analysis using ImageNet

By Mohammad Amin Morid, Alireza Borjali, Guilherme Del Fiol. Comput. Biol. Medicine, 2020

465 citations recorded by the source corpus.

OBJECTIVE Employing transfer learning (TL) with convolutional neural networks (CNNs), well-trained on non-medical ImageNet dataset, has shown promising results for medical image analysis in recent years. We aimed to conduct a scoping review to identify these studies and summarize their characteristics in terms of the problem description, input, methodology, and outcome. MATERIALS AND METHODS To identify relevant studies, MEDLINE, IEEE, and ACM digital library were searched for studies published between June 1st, 2012 and January 2nd, 2020. Two investigators independently reviewed articles to determine eligibility and to extract data according to a study protocol defined a priori. RESULTS After screening of 8421 articles, 102 met the inclusion criteria. Of 22 anatomical areas, eye (18%), breast (14%), and brain (12%) were the most commonly studied. Data augmentation was performed in 72% of fine-tuning TL studies versus 15% of the feature-extracting TL studies. Inception models were the most commonly used in breast related studies (50%), while VGGNet was the common in eye (44%), skin (50%) and tooth (57%) studies. AlexNet for brain (42%) and DenseNet for lung studies (38%) were the most frequently used models. Inception models were the most frequently used for studies that analyzed ultrasound (55%), endoscopy (57%), and skeletal system X-rays (57%). VGGNet was the most common for fundus (42%) and optical coherence tomography images (50%). AlexNet was the most frequent model for brain MRIs (36%) and breast X-Rays (50%). 35% of the studies compared their model with other well-trained CNN models and 33% of them provided visualization for interpretation. DISCUSSION This study identified the most prevalent tracks of implementation in the literature for data preparation, methodology selection and output evaluation for various medical image analysis tasks. Also, we identified several critical research gaps existing in the TL studies on medical image analysis. The findings of this scoping review can be used in future TL studies to guide the selection of appropriate research approaches, as well as identify research gaps and opportunities for innovation.

Subfields: Artificial Intelligence, Neurology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/909a289d79614b7e556a07fbc309f468582cffb5

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 Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Transfer learning for medical image classification: a literature review (2022, background): “Morid et al. [48] stated that deep CNN models may be more effective for the following image modalities: X-ray, endoscopic and ultrasound images, while shallow CNN models may be optimal for processing these image modalities: OCT and photography for skin lesions and fundus.”
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019, background): “We refer the reader to Morid et al. (2021); Raghu et al. (2019); Cheplygina et al. (2019) for a more general overview of transfer learning in medical imaging, and focus on the use of TL in AL scenarios in the following.”
A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications (2023, background): “• Benefits of transfer learning for DL Notably, TL offers many advantages for DL models in training new models [23, 127].”
Domain Adaptation for Medical Image Analysis: A Survey (2021, unknown): “Morid et al. [24] review transfer learning methods based on pre-training on ImageNet [6] that can beneﬁt from knowledge from large-scale labeled natural images.”