Residual-based Language Models are Free Boosters for Biomedical Imaging
- URL: http://arxiv.org/abs/2403.17343v3
- Date: Thu, 28 Mar 2024 21:28:00 GMT
- Title: Residual-based Language Models are Free Boosters for Biomedical Imaging
- Authors: Zhixin Lai, Jing Wu, Suiyao Chen, Yucheng Zhou, Naira Hovakimyan,
- Abstract summary: In this study, we uncover the unexpected efficacy of residual-based large language models (LLMs) as part of encoders for biomedical imaging tasks.
We found that these LLMs could boost performance across a spectrum of biomedical imaging applications, including both 2D and 3D visual classification tasks.
As a byproduct, we found that the proposed framework achieved superior performance, setting new state-of-the-art results on extensive, standardized datasets in MedMNIST-2D and 3D.
- Score: 15.154015369984572
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this study, we uncover the unexpected efficacy of residual-based large language models (LLMs) as part of encoders for biomedical imaging tasks, a domain traditionally devoid of language or textual data. The approach diverges from established methodologies by utilizing a frozen transformer block, extracted from pre-trained LLMs, as an innovative encoder layer for the direct processing of visual tokens. This strategy represents a significant departure from the standard multi-modal vision-language frameworks, which typically hinge on language-driven prompts and inputs. We found that these LLMs could boost performance across a spectrum of biomedical imaging applications, including both 2D and 3D visual classification tasks, serving as plug-and-play boosters. More interestingly, as a byproduct, we found that the proposed framework achieved superior performance, setting new state-of-the-art results on extensive, standardized datasets in MedMNIST-2D and 3D. Through this work, we aim to open new avenues for employing LLMs in biomedical imaging and enriching the understanding of their potential in this specialized domain.
Related papers
- LIMIS: Towards Language-based Interactive Medical Image Segmentation [58.553786162527686]
LIMIS is the first purely language-based interactive medical image segmentation model.
We adapt Grounded SAM to the medical domain and design a language-based model interaction strategy.
We evaluate LIMIS on three publicly available medical datasets in terms of performance and usability.
arXiv Detail & Related papers (2024-10-22T12:13:47Z) - Knowledge-grounded Adaptation Strategy for Vision-language Models: Building Unique Case-set for Screening Mammograms for Residents Training [5.819704618007536]
A visual-language model (VLM) pre-trained on natural images and text pairs poses a significant barrier when applied to medical contexts.
We propose a framework designed to adeptly tailor VLMs to the medical domain, employing selective sampling and hard-negative mining techniques.
arXiv Detail & Related papers (2024-05-30T04:04:36Z) - VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity Recognition [3.4923338594757674]
Large language models (LLMs) can be used to train a model capable of extracting various types of entities.
In this paper, we utilize the open-sourced LLM LLaMA2 as the backbone model, and design specific instructions to distinguish between different types of entities and datasets.
Our model VANER, trained with a small partition of parameters, significantly outperforms previous LLMs-based models and, for the first time, as a model based on LLM, surpasses the majority of conventional state-of-the-art BioNER systems.
arXiv Detail & Related papers (2024-04-27T09:00:39Z) - Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references.
Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
arXiv Detail & Related papers (2024-03-05T13:45:46Z) - Incorporating Visual Experts to Resolve the Information Loss in
Multimodal Large Language Models [121.83413400686139]
This paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism.
We introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline.
arXiv Detail & Related papers (2024-01-06T02:02:34Z) - Effectively Fine-tune to Improve Large Multimodal Models for Radiology
Report Generation [8.788649244412591]
Large Language Models (LLM) have demonstrated impressive capabilities recently.
We propose a simple yet effective two-stage fine-tuning protocol to align visual features to LLM's text embedding space as soft visual prompts.
Our framework with OpenLLaMA-7B achieved state-of-the-art level performance without domain-specific pretraining.
arXiv Detail & Related papers (2023-12-03T20:42:38Z) - Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models [0.8878802873945023]
This study introduces the first systematic study on transferring Vision-Language Models to 2D medical images.
Although VLSMs show competitive performance compared to image-only models for segmentation, not all VLSMs utilize the additional information from language prompts.
arXiv Detail & Related papers (2023-08-15T11:28:21Z) - Disruptive Autoencoders: Leveraging Low-level features for 3D Medical
Image Pre-training [51.16994853817024]
This work focuses on designing an effective pre-training framework for 3D radiology images.
We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations.
The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
arXiv Detail & Related papers (2023-07-31T17:59:42Z) - UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for
Biomedical Entity Recognition [4.865221751784403]
This work contributes a data-centric paradigm for enriching the language representations of biomedical transformer-encoder LMs by extracting text sequences from the UMLS.
Preliminary results from experiments in the extension of pre-trained LMs as well as training from scratch show that this framework improves downstream performance on multiple biomedical and clinical Named Entity Recognition (NER) tasks.
arXiv Detail & Related papers (2023-07-20T18:08:34Z) - Align, Reason and Learn: Enhancing Medical Vision-and-Language
Pre-training with Knowledge [68.90835997085557]
We propose a systematic and effective approach to enhance structured medical knowledge from three perspectives.
First, we align the representations of the vision encoder and the language encoder through knowledge.
Second, we inject knowledge into the multi-modal fusion model to enable the model to perform reasoning using knowledge as the supplementation of the input image and text.
Third, we guide the model to put emphasis on the most critical information in images and texts by designing knowledge-induced pretext tasks.
arXiv Detail & Related papers (2022-09-15T08:00:01Z) - Multi-Modal Masked Autoencoders for Medical Vision-and-Language
Pre-Training [62.215025958347105]
We propose a self-supervised learning paradigm with multi-modal masked autoencoders.
We learn cross-modal domain knowledge by reconstructing missing pixels and tokens from randomly masked images and texts.
arXiv Detail & Related papers (2022-09-15T07:26:43Z)
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.