Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients

Summary: Promptly identification of multidrug-resistant tuberculosis (MDR-TB) patients at high risk of treatment failure is essential for improving cure rates. This study aimed to develop a habitat radiomics based transformer fusion model to assess treatment effectiveness of MDR-TB. Independent pati...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinna Lv, Yichuan Wang, Chenyu Ding, Lixin Qin, Xiaoyue Xu, Ye Li, Dailun Hou
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004225010041
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722129909547008
author Xinna Lv
Yichuan Wang
Chenyu Ding
Lixin Qin
Xiaoyue Xu
Ye Li
Dailun Hou
author_facet Xinna Lv
Yichuan Wang
Chenyu Ding
Lixin Qin
Xiaoyue Xu
Ye Li
Dailun Hou
author_sort Xinna Lv
collection DOAJ
description Summary: Promptly identification of multidrug-resistant tuberculosis (MDR-TB) patients at high risk of treatment failure is essential for improving cure rates. This study aimed to develop a habitat radiomics based transformer fusion model to assess treatment effectiveness of MDR-TB. Independent patient cohorts from two hospitals were included. Radiomics features were extracted from the habitat and peripheral regions of cavities to construct predictive models. Then, a transformer-based fusion model integrating features from all regions was established. The areas under the receiver operating characteristic curves (AUCs) were used to evaluate the performance. The transformer fusion model combining two subregions and peripheral area achieved remarkable performance, with AUC values of 1.000, 0.959, and 0.879 in the training, validation, and test cohort, respectively. The finding highlights the efficacy of our model in predicting treatment effectiveness of MDR-TB patients and its potential to guide individualized therapy.
format Article
id doaj-art-756fd857c55041eab3c5ee2d6f9309ae
institution DOAJ
issn 2589-0042
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series iScience
spelling doaj-art-756fd857c55041eab3c5ee2d6f9309ae2025-08-20T03:11:26ZengElsevieriScience2589-00422025-06-0128611274310.1016/j.isci.2025.112743Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patientsXinna Lv0Yichuan Wang1Chenyu Ding2Lixin Qin3Xiaoyue Xu4Ye Li5Dailun Hou6Department of Radiology, Beijing Chest Hospital, Capital Medical University, Beijing, ChinaDepartment of Radiology, Beijing Tuberculosis and Thoracic Tumor Research Institute, Beijing, ChinaDepartment of Radiology, Wuhan Pulmonary Hospital, Wuhan, ChinaDepartment of Radiology, Wuhan Pulmonary Hospital, Wuhan, ChinaDepartment of Radiology, Beijing Chest Hospital, Capital Medical University, Beijing, ChinaDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Shandong Provincial Hospital, Jinan, China; Corresponding authorDepartment of Radiology, Beijing Chest Hospital, Capital Medical University, Beijing, China; Corresponding authorSummary: Promptly identification of multidrug-resistant tuberculosis (MDR-TB) patients at high risk of treatment failure is essential for improving cure rates. This study aimed to develop a habitat radiomics based transformer fusion model to assess treatment effectiveness of MDR-TB. Independent patient cohorts from two hospitals were included. Radiomics features were extracted from the habitat and peripheral regions of cavities to construct predictive models. Then, a transformer-based fusion model integrating features from all regions was established. The areas under the receiver operating characteristic curves (AUCs) were used to evaluate the performance. The transformer fusion model combining two subregions and peripheral area achieved remarkable performance, with AUC values of 1.000, 0.959, and 0.879 in the training, validation, and test cohort, respectively. The finding highlights the efficacy of our model in predicting treatment effectiveness of MDR-TB patients and its potential to guide individualized therapy.http://www.sciencedirect.com/science/article/pii/S2589004225010041DiseaseArtificial intelligence applications
spellingShingle Xinna Lv
Yichuan Wang
Chenyu Ding
Lixin Qin
Xiaoyue Xu
Ye Li
Dailun Hou
Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients
iScience
Disease
Artificial intelligence applications
title Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients
title_full Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients
title_fullStr Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients
title_full_unstemmed Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients
title_short Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients
title_sort habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary mdr tb patients
topic Disease
Artificial intelligence applications
url http://www.sciencedirect.com/science/article/pii/S2589004225010041
work_keys_str_mv AT xinnalv habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients
AT yichuanwang habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients
AT chenyuding habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients
AT lixinqin habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients
AT xiaoyuexu habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients
AT yeli habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients
AT dailunhou habitatradiomicsandtransformerfusionmodeltoevaluatetreatmenteffectivenessofcavitarymdrtbpatients