• Home
  • Search
  • Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
  • Open Access IconOpen Access
  • Cite Icon3327
  • https://doi.org/10.1109/tmi.2016.2535302Copy DOI Icon

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.

Similar Papers
  • Conference Article
  • Citations56

Medical Image Analysis using Deep Convolutional Neural Networks: CNN Architectures and Transfer Learning

  • Feb 01, 2020
  • Pronnoy Dutta +3
  • Research Article
  • Citations6

Optimizing machine learning performance for medical imaging analyses in low-resource environments: The prospects of CNN-based Feature Extractors

  • Jan 17, 2025
  • F1000Research
  • Itunuoluwa Isewon +2
  • Research Article

The Use of Pretrained Convolutional Neural Networks in Recognizing Phytoplankton Species. Cases from a marine, a brakishwater and a freshwater site.

  • May 28, 2025
  • ARPHA Conference Abstracts
  • Mauro Bastianini +11
  • Research Article
  • Citations16

Patient-specific fine-tuning of convolutional neural networks for follow-up lesion quantification

  • Nov 01, 2020
  • Journal of Medical Imaging
  • Mariëlle J A Jansen +6
  • Research Article
  • Citations6

Knowledge Transferred Fine-Tuning: Convolutional Neural Network Is Born Again With Anti-Aliasing Even in Data-Limited Situations

  • Jan 01, 2022
  • IEEE Access
  • Satoshi Suzuki +5
  • Book Chapter
  • Citations16

Painting Classification Using a Pre-trained Convolutional Neural Network

  • Jan 01, 2017
  • Sugata Banerji +1
  • Conference Article
  • Citations31

Enhance deep learning performance in face recognition

  • Jun 01, 2017
  • Ze Lu +2
  • Research Article
  • Citations571

Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images.

  • Apr 16, 2018
  • PeerJ
  • Sivaramakrishnan Rajaraman +7
  • Research Article
  • Citations8

Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images

  • Oct 24, 2024
  • Remote Sensing
  • Baohua Yuan +2
  • Research Article
  • Citations7

Enhanced Multi-Class Brain Tumor Classification in MRI Using Pre-Trained CNNs and Transformer Architectures

  • Aug 22, 2025
  • Technologies
  • Marco Antonio Gómez-Guzmán +8
  • Book Chapter
  • Citations9

Three Aspects on Using Convolutional Neural Networks for Computer-Aided Detection in Medical Imaging

  • Jan 01, 2017
  • Hoo-Chang Shin +8
  • Research Article
  • Citations6

Transfer Learning Strategies for Fine-Tuning Pretrained Convolutional Neural Networks in Medical Imaging

  • Dec 31, 2023
  • Research Journal of Computer Systems and Engineering
  • Muhamad Angriawan
  • Research Article
  • Citations70

Unsupervised Domain Adaptation to Classify Medical Images Using Zero-Bias Convolutional Auto-Encoders and Context-Based Feature Augmentation.

  • Feb 03, 2020
  • IEEE Transactions on Medical Imaging
  • Euijoon Ahn +4
  • PDF
  • Research Article
  • Citations4

Sonar image recognition based on fine-tuned convolutional neural network

  • Jan 01, 2019
  • MATEC Web of Conferences
  • Zhaotong Zhu +1
  • Conference Article
  • Citations24

Comparison of Handcrafted Features and Deep Learning in Classification of Medical X-ray Images

  • Mar 01, 2018
  • Mohammad Reza Zare +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.