Related papers: Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment

Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment

URL: http://arxiv.org/abs/2602.00910v1
Date: Sat, 31 Jan 2026 21:42:36 GMT
Title: Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment
Authors: Cuong Manh Nguyen, Truong-Son Hy,
Abstract summary: This review provides a comprehensive synthesis of efficient and lightweight deep learning architectures specifically tailored for the medical domain.<n>We categorize the landscape of modern efficient models into three primary streams: Convolutional Neural Networks (CNNs), Lightweight Transformers, and emerging Linear Complexity Models.<n>By identifying current limitations and discussing the transition toward on-device intelligence, this review serves as a roadmap for researchers and practitioners aiming to bridge the gap between high-performance AI and resource-constrained clinical environments.
Score: 7.556909298052158
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Deep learning has revolutionized medical image analysis, playing a vital role in modern clinical applications. However, the deployment of large-scale models in real-world clinical settings remains challenging due to high computational costs, latency constraints, and patient data privacy concerns associated with cloud-based processing. To address these bottlenecks, this review provides a comprehensive synthesis of efficient and lightweight deep learning architectures specifically tailored for the medical domain. We categorize the landscape of modern efficient models into three primary streams: Convolutional Neural Networks (CNNs), Lightweight Transformers, and emerging Linear Complexity Models. Furthermore, we examine key model compression strategies (including pruning, quantization, knowledge distillation, and low-rank factorization) and evaluate their efficacy in maintaining diagnostic performance while reducing hardware requirements. By identifying current limitations and discussing the transition toward on-device intelligence, this review serves as a roadmap for researchers and practitioners aiming to bridge the gap between high-performance AI and resource-constrained clinical environments.

Related papers

Resource-efficient medical image classification for edge devices [0.43748379918040853]
This research investigates a resource-efficient approach to medical image classification by employing model quantization techniques.<n> Quantization reduces the precision of model parameters and activations, significantly lowering computational overhead and memory requirements.<n> Experimental results demonstrate that quantized models achieve substantial reductions in model size and inference latency, enabling real-time processing on edge hardware.
arXiv Detail & Related papers (2025-12-19T12:32:57Z)
A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
arXiv Detail & Related papers (2025-12-15T10:22:43Z)
Robust Multi-Disease Retinal Classification via Xception-Based Transfer Learning and W-Net Vessel Segmentation [0.0]
This paper presents a comprehensive study on deep learning architectures for the automated diagnosis of ocular conditions.<n>We implement a pipeline that combines deep feature extraction with interpretable image processing modules.<n>By grounding the model's predictions in clinically relevant morphological features, we aim to bridge the gap between algorithmic output and expert medical validation.
arXiv Detail & Related papers (2025-12-11T13:03:03Z)
Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets [1.2648105980808475]
This study investigates a systematic evaluation of state-of-the-art deep learning segmentation models.<n>Our findings reveal that model performance is highly sensitive to data splits, with minor differences driven more by statistical noise than by true algorithmic superiority.
arXiv Detail & Related papers (2025-09-07T01:54:20Z)
DermINO: Hybrid Pretraining for a Versatile Dermatology Foundation Model [92.66916452260553]
DermNIO is a versatile foundation model for dermatology.<n>It incorporates a novel hybrid pretraining framework that augments the self-supervised learning paradigm.<n>It consistently outperforms state-of-the-art models across a wide range of tasks.
arXiv Detail & Related papers (2025-08-17T00:41:39Z)
Clinical NLP with Attention-Based Deep Learning for Multi-Disease Prediction [44.0876796031468]
This paper addresses the challenges posed by the unstructured nature and high-dimensional semantic complexity of electronic health record texts.<n>A deep learning method based on attention mechanisms is proposed to achieve unified modeling for information extraction and multi-label disease prediction.
arXiv Detail & Related papers (2025-07-02T07:45:22Z)
L-SFAN: Lightweight Spatially-focused Attention Network for Pain Behavior Detection [44.016805074560295]
Chronic Low Back Pain (CLBP) afflicts millions globally, significantly impacting individuals' well-being and imposing economic burdens on healthcare systems. While artificial intelligence (AI) and deep learning offer promising avenues for analyzing pain-related behaviors to improve rehabilitation strategies, current models, including convolutional neural networks (CNNs), have limitations. We introduce hbox EmoL-SFAN, a lightweight CNN architecture incorporating 2D filters designed to capture the spatial-temporal interplay of data from motion capture and surface electromyography sensors.
arXiv Detail & Related papers (2024-06-07T12:01:37Z)
Investigation of Energy-efficient AI Model Architectures and Compression Techniques for "Green" Fetal Brain Segmentation [42.52549987351643]
Fetal brain segmentation in medical imaging is challenging due to the small size of the fetal brain and the limited image quality of fast 2D sequences. Deep neural networks are a promising method to overcome this challenge. Our study aims to explore model architectures and compression techniques that promote energy efficiency.
arXiv Detail & Related papers (2024-04-03T15:11:53Z)
Demystifying Deep Learning Models for Retinal OCT Disease Classification using Explainable AI [0.6117371161379209]
The adoption of various deep learning techniques is quite common as well as effective, and its statement is equally true when it comes to implementing it into the retina Optical Coherence Tomography sector. These techniques have the black box characteristics that prevent the medical professionals to completely trust the results generated from them. This paper proposes a self-developed CNN model which is comparatively smaller and simpler along with the use of Lime that introduces Explainable AI to the study.
arXiv Detail & Related papers (2021-11-06T13:54:07Z)
FocusLiteNN: High Efficiency Focus Quality Assessment for Digital Pathology [42.531674974834544]
We propose a CNN-based model that maintains fast computations similar to the knowledge-driven methods without excessive hardware requirements. We create a training dataset using FocusPath which encompasses diverse tissue slides across nine different stain colors. In our attempt to reduce the CNN complexity, we find with surprise that even trimming down the CNN to the minimal level, it still achieves a highly competitive performance.
arXiv Detail & Related papers (2020-07-11T20:52:01Z)

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