ArticleArtificial intelligence in medicine2021
Transfer learning in medical image segmentation: New insights from analysis of the dynamics of model parameters and learned representations.
Article in Artificial intelligence in medicine, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 49 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
49 citing papers in PubMed.
- Deep Learning in Dental Imaging: Advances, Challenges, and Future.Oral radiology · 2026Review
- Efficient transformer integration in nnU-Net for liver tumor segmentation: an external validation study.BMC medical imaging · 2026Article
- A minimal-net CNN model for an IoT-based brain tumor detection and monitoring system.Scientific reports · 2026Article
- BrainFusionNet: a deep learning and XAI model to understand local, global, and sequential features of MRI images for improved brain tumour detection.Brain informatics · 2026Article
- Detailed Delineation of the Fetal Brain in Diffusion MRI via Multi-Task Learning.IEEE transactions on medical imaging · 2026Article
- Automated Semisupervised Measurement of Optic Nerve Sheath Diameter From CT Following Traumatic Brain Injury.International journal of biomedical imaging · 2026Article
- Breaking barriers: noninvasive AI model for BRAFInternational journal of computer assisted radiology and surgery · 2025Article
- The usefulness of automated high frequency ultrasound image analysis in atopic dermatitis staging.Scientific reports · 2025Article
- Feasibility and time gain of implementing artificial intelligence-based delineation tools in daily magnetic resonance image-guided adaptive prostate cancer radiotherapy.Physics and imaging in radiation oncology · 2025Article
- Mitigating catastrophic forgetting in Multiple sclerosis lesion segmentation using elastic weight consolidation.NeuroImage. Clinical · 2025Article
- Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation.Medical physics · 2024Article
- A deep learning based method for left ventricular strain measurements: repeatability and accuracy compared to experienced echocardiographers.BMC medical imaging · 2024Article
- An approach to building foundation models for brain image analysis.Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention · 2024Article
- Article
- Radiology and multi-scale data integration for precision oncology.NPJ precision oncology · 2024Review
- Automating Linear and Angular Measurements for the Hip and Knee After Computed Tomography: Validation of a Three-Stage Deep Learning and Computer Vision-Based Pipeline for Pathoanatomic Assessment.Arthroplasty today · 2024Article
- Self and Mixed Supervision to Improve Training Labels for Multi-Class Medical Image Segmentation.ArXiv · 2024Article
- Enhancing deep learning classification performance of tongue lesions in imbalanced data: mosaic-based soft labeling with curriculum learning.BMC oral health · 2024Article
- Uncertainty-based Active Learning by Bayesian U-Net for Multi-label Cone-beam CT Segmentation.Journal of endodontics · 2024Article
- Augmented reality navigation systems in endoscopy.Frontiers in gastroenterology (Lausanne, Switzerland) · 2024Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
We present a critical assessment of the role of transfer learning in training fully convolutional networks (FCNs) for medical image segmentation. We first show that although transfer learning reduces the training time on the target task, improvements in segmentation accuracy are highly task/data-dependent. Large improvements are observed only when the segmentation task is more challenging and the target training data is smaller. We shed light on these observations by investigating the impact of transfer learning on the evolution of model parameters and learned representations. We observe that convolutional filters change little during training and still look random at convergence. We further show that quite accurate FCNs can be built by freezing the encoder section of the network at random values and only training the decoder section. At least for medical image segmentation, this finding challenges the common belief that the encoder section needs to learn data/task-specific representations. We examine the evolution of FCN representations to gain a deeper insight into the effects of transfer learning on the training dynamics. Our analysis shows that although FCNs trained via transfer learning learn different representations than FCNs trained with random initialization, the variability among FCNs trained via transfer learning can be as high as that among FCNs trained with random initialization. Moreover, feature reuse is not restricted to the early encoder layers; rather, it can be more significant in deeper layers. These findings offer new insights and suggest alternative ways of training FCNs for medical image segmentation.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.