PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning

• URL: http://arxiv.org/abs/2507.05764v1
• Date: Tue, 08 Jul 2025 08:07:36 GMT
• Title: PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
• Authors: Tristan Kirscher, Sylvain Faisan, Xavier Coubez, Loris Barrier, Philippe Meyer,
• Abstract summary: Direct application of segmentation models trained on adult data often yields suboptimal performance.<n>We introduce PSAT (Pediatric Approaches via Adult Augmentations and Transfer learning), a systematic study that investigates the impact of these axes on performance.<n>Our experiments reveal that a training plan based on an adult fingerprint dataset is misaligned with pediatric anatomy-resulting in significant performance degradation.
• Score: 0.18641315013048293
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pediatric medical imaging presents unique challenges due to significant anatomical and developmental differences compared to adults. Direct application of segmentation models trained on adult data often yields suboptimal performance, particularly for small or rapidly evolving structures. To address these challenges, several strategies leveraging the nnU-Net framework have been proposed, differing along four key axes: (i) the fingerprint dataset (adult, pediatric, or a combination thereof) from which the Training Plan -including the network architecture-is derived; (ii) the Learning Set (adult, pediatric, or mixed), (iii) Data Augmentation parameters, and (iv) the Transfer learning method (finetuning versus continual learning). In this work, we introduce PSAT (Pediatric Segmentation Approaches via Adult Augmentations and Transfer learning), a systematic study that investigates the impact of these axes on segmentation performance. We benchmark the derived strategies on two pediatric CT datasets and compare them with state-of-theart methods, including a commercial radiotherapy solution. PSAT highlights key pitfalls and provides actionable insights for improving pediatric segmentation. Our experiments reveal that a training plan based on an adult fingerprint dataset is misaligned with pediatric anatomy-resulting in significant performance degradation, especially when segmenting fine structures-and that continual learning strategies mitigate institutional shifts, thus enhancing generalization across diverse pediatric datasets. The code is available at https://github.com/ICANS-Strasbourg/PSAT.

Related papers

• Lifelong Whole Slide Image Analysis: Online Vision-Language Adaptation and Past-to-Present Gradient Distillation [1.1497371646067622]
  Whole Slide Images (WSIs) play a crucial role in accurate cancer diagnosis and prognosis.<n>Given that WSIs are gigapixels in size, they present difficulties in terms of storage, processing, and model training.<n>We introduce ADaFGrad, a method designed to enhance lifelong learning for whole-slide image (WSI) analysis.
  arXiv  Detail & Related papers  (2025-05-04T04:46:08Z)
• Knowledge-Guided Prompt Learning for Lifespan Brain MR Image Segmentation [53.70131202548981]
  We present a two-step segmentation framework employing Knowledge-Guided Prompt Learning (KGPL) for brain MRI. Specifically, we first pre-train segmentation models on large-scale datasets with sub-optimal labels. The introduction of knowledge-wise prompts captures semantic relationships between anatomical variability and biological processes.
  arXiv  Detail & Related papers  (2024-07-31T04:32:43Z)
• Unlocking Robust Segmentation Across All Age Groups via Continual Learning [6.733504608145498]
  We evaluate the performance of CT organ segmentation algorithms trained on adult data when applied to pediatric CT volumes. We propose and evaluate strategies, including data augmentation and continual learning approaches, to achieve good segmentation accuracy across all age groups.
  arXiv  Detail & Related papers  (2024-04-19T21:21:36Z)
• Retinal Vessel Segmentation via a Multi-resolution Contextual Network and Adversarial Learning [4.776465250559035]
  We propose a Multi-resolution Contextual Network (MRC-Net) to learn contextual dependencies between semantically different features. We have evaluated our method on three benchmark datasets, including DRIVE, STARE, and CHASE.
  arXiv  Detail & Related papers  (2023-04-25T14:27:34Z)
• Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions [66.40971096248946]
  In this paper, we collect a series of MedISeg tricks for different model implementation phases. We experimentally explore the effectiveness of these tricks on consistent baselines. We also open-sourced a strong MedISeg repository, where each component has the advantage of plug-and-play.
  arXiv  Detail & Related papers  (2022-09-21T12:30:05Z)
• Dissecting Self-Supervised Learning Methods for Surgical Computer Vision [51.370873913181605]
  Self-Supervised Learning (SSL) methods have begun to gain traction in the general computer vision community. The effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection.
  arXiv  Detail & Related papers  (2022-07-01T14:17:11Z)
• Cross-Modality Deep Feature Learning for Brain Tumor Segmentation [158.8192041981564]
  This paper proposes a novel cross-modality deep feature learning framework to segment brain tumors from the multi-modality MRI data. The core idea is to mine rich patterns across the multi-modality data to make up for the insufficient data scale. Comprehensive experiments are conducted on the BraTS benchmarks, which show that the proposed cross-modality deep feature learning framework can effectively improve the brain tumor segmentation performance.
  arXiv  Detail & Related papers  (2022-01-07T07:46:01Z)
• Towards Cross-modality Medical Image Segmentation with Online Mutual Knowledge Distillation [71.89867233426597]
  In this paper, we aim to exploit the prior knowledge learned from one modality to improve the segmentation performance on another modality. We propose a novel Mutual Knowledge Distillation scheme to thoroughly exploit the modality-shared knowledge. Experimental results on the public multi-class cardiac segmentation data, i.e., MMWHS 2017, show that our method achieves large improvements on CT segmentation.
  arXiv  Detail & Related papers  (2020-10-04T10:25:13Z)
• DONet: Dual Objective Networks for Skin Lesion Segmentation [77.9806410198298]
  We propose a simple yet effective framework, named Dual Objective Networks (DONet), to improve the skin lesion segmentation. Our DONet adopts two symmetric decoders to produce different predictions for approaching different objectives. To address the challenge of large variety of lesion scales and shapes in dermoscopic images, we additionally propose a recurrent context encoding module (RCEM)
  arXiv  Detail & Related papers  (2020-08-19T06:02:46Z)
• A survey of statistical learning techniques as applied to inexpensive pediatric Obstructive Sleep Apnea data [3.1373682691616787]
  obstructive sleep apnea affects an estimated 1-5% of elementary-school aged children. Swift diagnosis and treatment are critical to a child's growth and development, but the variability of symptoms and the complexity of the available data make this a challenge. We apply correlation networks, the Mapper algorithm from topological data analysis, and singular value decomposition in a process of exploratory data analysis.
  arXiv  Detail & Related papers  (2020-02-17T18:15:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.