EXACT-Net: Framework for EHR-Guided Lung Tumor Auto-Segmentation for Non-Small Cell Lung Cancer Radiotherapy.
Simple Summary: In recent years, large language models have shown great potential to enhance traditional medical image processing by incorporating multimodality information into decision-making. Conventional artificial intelligence systems solely rely on images to make predictions or decisions. Howe...
| Publicado en: | Cancers Vol. 16; no. 23; pp. 4097 - 4111 |
|---|---|
| Autores principales: | , , , , , , , , |
| Formato: | diagnostic images equations & formulas research tables/charts Journal Article |
| Publicado: |
MDPI
Dec2024
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=181661096&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 181661096 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Dec2024 vid: 16 iid: 23 pid: 97109 pub: MDPI artinfo: ui: 181661096 181661096 181661096 10.3390/cancers16234097 181661096 ppf: 4097 ppct: 14 formats: tig: atl: EXACT-Net: Framework for EHR-Guided Lung Tumor Auto-Segmentation for Non-Small Cell Lung Cancer Radiotherapy. aug: au: Hooshangnejad, Hamed Huang, Gaofeng Kelly, Katelyn Feng, Xue Luo, Yi Zhang, Rui Xu, Ziyue Chen, Quan Ding, Kai affil: Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA sug: subj: Electronic Health Records Carcinoma, Non-Small-Cell Lung Radiotherapy Carcinoma, Non-Small-Cell Lung Diagnosis Human Funding Source Convolutional Neural Networks Natural Language Processing Decision Making Survival Rate Cancer Patients Tomography, X-Ray Computed Descriptive Statistics ab: Simple Summary: In recent years, large language models have shown great potential to enhance traditional medical image processing by incorporating multimodality information into decision-making. Conventional artificial intelligence systems solely rely on images to make predictions or decisions. However, information from medical reports can provide invaluable information for the system to curate its decision. Here we are presenting a multimodality language-vision model and framework for accurate segmentation of medical images. Background/Objectives: Lung cancer is a devastating disease with the highest mortality rate among cancer types. Over 60% of non-small cell lung cancer (NSCLC) patients, accounting for 87% of lung cancer diagnoses, require radiation therapy. Rapid treatment initiation significantly increases the patient's survival rate and reduces the mortality rate. Accurate tumor segmentation is a critical step in diagnosing and treating NSCLC. Manual segmentation is time- and labor-consuming and causes delays in treatment initiation. Although many lung nodule detection methods, including deep learning-based models, have been proposed. Most of these methods still have a long-standing problem of high false positives (FPs). Methods: Here, we developed an electronic health record (EHR)-guided lung tumor auto-segmentation called EXACT-Net (EHR-enhanced eXACtitude in Tumor segmentation), where the extracted information from EHRs using a pre-trained large language model (LLM) was used to remove the FPs and keep the TP nodules only. Results: The auto-segmentation model was trained on NSCLC patients' computed tomography (CT), and the pre-trained LLM was used with the zero-shot learning approach. Our approach resulted in a 250% boost in successful nodule detection using the data from ten NSCLC patients treated in our institution. Conclusions: We demonstrated that combining vision-language information in EXACT-Net multi-modal AI framework greatly enhances the performance of vision only models, paving the road to multimodal AI framework for medical image processing. pubtype: Academic Journal doctype: diagnostic images equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|