EFCM: Efficient Fine-tuning on Compressed Models for deployment of large models in medical image analysis

• URL: http://arxiv.org/abs/2409.11817v1
• Date: Wed, 18 Sep 2024 09:08:16 GMT
• Title: EFCM: Efficient Fine-tuning on Compressed Models for deployment of large models in medical image analysis
• Authors: Shaojie Li, Zhaoshuo Diao,
• Abstract summary: This study presents an Efficient Fine-tuning on Compressed Models (EFCM) framework with two stages: unsupervised feature distillation and fine-tuning. Experiments are conducted on 11 downstream datasets related to three large medical models: RETFound for retina, MRM for chest X-ray, and BROW for histopathology.
• Score: 17.876140405367764
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent development of deep learning large models in medicine shows remarkable performance in medical image analysis and diagnosis, but their large number of parameters causes memory and inference latency challenges. Knowledge distillation offers a solution, but the slide-level gradients cannot be backpropagated for student model updates due to high-resolution pathological images and slide-level labels. This study presents an Efficient Fine-tuning on Compressed Models (EFCM) framework with two stages: unsupervised feature distillation and fine-tuning. In the distillation stage, Feature Projection Distillation (FPD) is proposed with a TransScan module for adaptive receptive field adjustment to enhance the knowledge absorption capability of the student model. In the slide-level fine-tuning stage, three strategies (Reuse CLAM, Retrain CLAM, and End2end Train CLAM (ETC)) are compared. Experiments are conducted on 11 downstream datasets related to three large medical models: RETFound for retina, MRM for chest X-ray, and BROW for histopathology. The experimental results demonstrate that the EFCM framework significantly improves accuracy and efficiency in handling slide-level pathological image problems, effectively addressing the challenges of deploying large medical models. Specifically, it achieves a 4.33% increase in ACC and a 5.2% increase in AUC compared to the large model BROW on the TCGA-NSCLC and TCGA-BRCA datasets. The analysis of model inference efficiency highlights the high efficiency of the distillation fine-tuning method.

Related papers

• Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models [48.87160158792048]
  We introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way. Experiments on a public high-resolution OCT dataset show that our synthetic data have realistic high-resolution and global features, surpassing the capabilities of existing methods.
  arXiv  Detail & Related papers  (2024-05-26T10:58:22Z)
• Transformer-Based Self-Supervised Learning for Histopathological Classification of Ischemic Stroke Clot Origin [0.0]
  Identifying the thromboembolism source in ischemic stroke is crucial for treatment and secondary prevention. This study describes a self-supervised deep learning approach in digital pathology of emboli for classifying ischemic stroke clot origin.
  arXiv  Detail & Related papers  (2024-05-01T23:40:12Z)
• Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement [34.11633495477596]
  We propose an algorithm for source-free unsupervised domain adaptive medical image enhancement (SAME) A structure-preserving enhancement network is first constructed to learn a robust source model from synthesized training data. A pseudo-label picker is developed to boost the knowledge distillation of enhancement tasks.
  arXiv  Detail & Related papers  (2023-12-03T10:01:59Z)
• Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning [5.438725298163702]
  Contrastive Self-Supervised Learning (SSL) offers a potential solution to labeled data scarcity. We propose uncovering the optimal augmentations for applying contrastive learning in 1D phonocardiogram (PCG) classification. We demonstrate that depending on its training distribution, the effectiveness of a fully-supervised model can degrade up to 32%, while SSL models only lose up to 10% or even improve in some cases.
  arXiv  Detail & Related papers  (2023-12-01T11:06:00Z)
• EMIT-Diff: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model [4.057796755073023]
  We develop controllable diffusion models for medical image synthesis, called EMIT-Diff. We leverage recent diffusion probabilistic models to generate realistic and diverse synthetic medical image data. In our approach, we ensure that the synthesized samples adhere to medically relevant constraints.
  arXiv  Detail & Related papers  (2023-10-19T16:18:02Z)
• The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease detection [51.697248252191265]
  This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation. We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare. Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
  arXiv  Detail & Related papers  (2023-09-13T10:40:41Z)
• Knowledge Distillation for Adaptive MRI Prostate Segmentation Based on Limit-Trained Multi-Teacher Models [4.711401719735324]
  Knowledge Distillation (KD) has been proposed as a compression method and an acceleration technology. KD is an efficient learning strategy that can transfer knowledge from a burdensome model to a lightweight model. We develop a KD-based deep model for prostate MRI segmentation in this work by combining features-based distillation with Kullback-Leibler divergence, Lovasz, and Dice losses.
  arXiv  Detail & Related papers  (2023-03-16T17:15:08Z)
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation [65.62538699160085]
  We propose a Directed Acyclic Graph Factorization Machine (KD-DAGFM) to learn the high-order feature interactions from existing complex interaction models for CTR prediction via Knowledge Distillation. KD-DAGFM achieves the best performance with less than 21.5% FLOPs of the state-of-the-art method on both online and offline experiments.
  arXiv  Detail & Related papers  (2022-11-21T03:09:42Z)
• SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images [62.60956024215873]
  Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. This study specifically proposes a novel method, termed SSD-KD, that unifies diverse knowledge into a generic KD framework for skin diseases classification.
  arXiv  Detail & Related papers  (2022-03-22T06:54:29Z)
• A multi-stage machine learning model on diagnosis of esophageal manometry [50.591267188664666]
  The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage. This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
  arXiv  Detail & Related papers  (2021-06-25T20:09:23Z)
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN [52.851990439671475]
  We propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation.
  arXiv  Detail & Related papers  (2020-08-05T02:33:04Z)

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.