Pub Date : 2024-07-20DOI: 10.1016/j.compmedimag.2024.102419
David Oluigbo, Tejas Sudharshan Mathai, Bikash Santra, Pritam Mukherjee, Jianfei Liu, Abhishek Jha, Mayank Patel, Karel Pacak, Ronald M Summers
Pheochromocytomas and Paragangliomas (PPGLs) are rare adrenal and extra-adrenal tumors that have metastatic potential. Management of patients with PPGLs mainly depends on the makeup of their genetic cluster: SDHx, VHL/EPAS1, kinase, and sporadic. CT is the preferred modality for precise localization of PPGLs, such that their metastatic progression can be assessed. However, the variable size, morphology, and appearance of these tumors in different anatomical regions can pose challenges for radiologists. Since radiologists must routinely track changes across patient visits, manual annotation of PPGLs is quite time-consuming and cumbersome to do across all axial slices in a CT volume. As such, PPGLs are only weakly annotated on axial slices by radiologists in the form of RECIST measurements. To ameliorate the manual effort spent by radiologists, we propose a method for the automated detection of PPGLs in CT via a proxy segmentation task. Weak 3D annotations (derived from 2D bounding boxes) were used to train both 2D and 3D nnUNet models to detect PPGLs via segmentation. We evaluated our approaches on an in-house dataset comprised of chest-abdomen-pelvis CTs of 255 patients with confirmed PPGLs. On a test set of 53 CT volumes, our 3D nnUNet model achieved a detection precision of 70% and sensitivity of 64.1%, and outperformed the 2D model that obtained a precision of 52.7% and sensitivity of 27.5% (p< 0.05). SDHx and sporadic genetic clusters achieved the highest precisions of 73.1% and 72.7% respectively. Our state-of-the art findings highlight the promising nature of the challenging task of automated PPGL detection.
{"title":"Weakly supervised detection of pheochromocytomas and paragangliomas in CT using noisy data.","authors":"David Oluigbo, Tejas Sudharshan Mathai, Bikash Santra, Pritam Mukherjee, Jianfei Liu, Abhishek Jha, Mayank Patel, Karel Pacak, Ronald M Summers","doi":"10.1016/j.compmedimag.2024.102419","DOIUrl":"10.1016/j.compmedimag.2024.102419","url":null,"abstract":"<p><p>Pheochromocytomas and Paragangliomas (PPGLs) are rare adrenal and extra-adrenal tumors that have metastatic potential. Management of patients with PPGLs mainly depends on the makeup of their genetic cluster: SDHx, VHL/EPAS1, kinase, and sporadic. CT is the preferred modality for precise localization of PPGLs, such that their metastatic progression can be assessed. However, the variable size, morphology, and appearance of these tumors in different anatomical regions can pose challenges for radiologists. Since radiologists must routinely track changes across patient visits, manual annotation of PPGLs is quite time-consuming and cumbersome to do across all axial slices in a CT volume. As such, PPGLs are only weakly annotated on axial slices by radiologists in the form of RECIST measurements. To ameliorate the manual effort spent by radiologists, we propose a method for the automated detection of PPGLs in CT via a proxy segmentation task. Weak 3D annotations (derived from 2D bounding boxes) were used to train both 2D and 3D nnUNet models to detect PPGLs via segmentation. We evaluated our approaches on an in-house dataset comprised of chest-abdomen-pelvis CTs of 255 patients with confirmed PPGLs. On a test set of 53 CT volumes, our 3D nnUNet model achieved a detection precision of 70% and sensitivity of 64.1%, and outperformed the 2D model that obtained a precision of 52.7% and sensitivity of 27.5% (p< 0.05). SDHx and sporadic genetic clusters achieved the highest precisions of 73.1% and 72.7% respectively. Our state-of-the art findings highlight the promising nature of the challenging task of automated PPGL detection.</p>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141762309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-09DOI: 10.1016/j.compmedimag.2024.102416
Despite that deep learning has achieved state-of-the-art performance for automatic medical image segmentation, it often requires a large amount of pixel-level manual annotations for training. Obtaining these high-quality annotations is time-consuming and requires specialized knowledge, which hinders the widespread application that relies on such annotations to train a model with good segmentation performance. Using scribble annotations can substantially reduce the annotation cost, but often leads to poor segmentation performance due to insufficient supervision. In this work, we propose a novel framework named as ScribSD+ that is based on multi-scale knowledge distillation and class-wise contrastive regularization for learning from scribble annotations. For a student network supervised by scribbles and the teacher based on Exponential Moving Average (EMA), we first introduce multi-scale prediction-level Knowledge Distillation (KD) that leverages soft predictions of the teacher network to supervise the student at multiple scales, and then propose class-wise contrastive regularization which encourages feature similarity within the same class and dissimilarity across different classes, thereby effectively improving the segmentation performance of the student network. Experimental results on the ACDC dataset for heart structure segmentation and a fetal MRI dataset for placenta and fetal brain segmentation demonstrate that our method significantly improves the student’s performance and outperforms five state-of-the-art scribble-supervised learning methods. Consequently, the method has a potential for reducing the annotation cost in developing deep learning models for clinical diagnosis.
{"title":"ScribSD+: Scribble-supervised medical image segmentation based on simultaneous multi-scale knowledge distillation and class-wise contrastive regularization","authors":"","doi":"10.1016/j.compmedimag.2024.102416","DOIUrl":"10.1016/j.compmedimag.2024.102416","url":null,"abstract":"<div><p>Despite that deep learning has achieved state-of-the-art performance for automatic medical image segmentation, it often requires a large amount of pixel-level manual annotations for training. Obtaining these high-quality annotations is time-consuming and requires specialized knowledge, which hinders the widespread application that relies on such annotations to train a model with good segmentation performance. Using scribble annotations can substantially reduce the annotation cost, but often leads to poor segmentation performance due to insufficient supervision. In this work, we propose a novel framework named as ScribSD+ that is based on multi-scale knowledge distillation and class-wise contrastive regularization for learning from scribble annotations. For a student network supervised by scribbles and the teacher based on Exponential Moving Average (EMA), we first introduce multi-scale prediction-level Knowledge Distillation (KD) that leverages soft predictions of the teacher network to supervise the student at multiple scales, and then propose class-wise contrastive regularization which encourages feature similarity within the same class and dissimilarity across different classes, thereby effectively improving the segmentation performance of the student network. Experimental results on the ACDC dataset for heart structure segmentation and a fetal MRI dataset for placenta and fetal brain segmentation demonstrate that our method significantly improves the student’s performance and outperforms five state-of-the-art scribble-supervised learning methods. Consequently, the method has a potential for reducing the annotation cost in developing deep learning models for clinical diagnosis.</p></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141629743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1016/j.compmedimag.2024.102415
Purpose
To evaluate lymphovascular invasion (LVI) in breast cancer by comparing the diagnostic performance of preoperative multimodal magnetic resonance imaging (MRI)-based radiomics and deep-learning (DL) models.
Methods
This retrospective study included 262 patients with breast cancer—183 in the training cohort (144 LVI-negative and 39 LVI-positive cases) and 79 in the validation cohort (59 LVI-negative and 20 LVI-positive cases). Radiomics features were extracted from the intra- and peritumoral breast regions using multimodal MRI to generate gross tumor volume (GTV)_radiomics and gross tumor volume plus peritumoral volume (GPTV)_radiomics. Subsequently, DL models (GTV_DL and GPTV_DL) were constructed based on the GTV and GPTV to determine the LVI status. Finally, the most effective radiomics and DL models were integrated with imaging findings to establish a hybrid model, which was converted into a nomogram to quantify the LVI risk.
Results
The diagnostic efficiency of GPTV_DL was superior to that of GTV_DL (areas under the curve [AUCs], 0.771 and 0.720, respectively). Similarly, GPTV_radiomics outperformed GTV_radiomics (AUC, 0.685 and 0.636, respectively). Univariate and multivariate logistic regression analyses revealed an association between imaging findings, such as MRI-axillary lymph nodes and peritumoral edema (AUC, 0.665). The hybrid model achieved the highest accuracy by combining GPTV_DL, GPTV_radiomics, and imaging findings (AUC, 0.872).
Conclusion
The diagnostic efficiency of the GPTV-derived radiomics and DL models surpassed that of the GTV-derived models. Furthermore, the hybrid model, which incorporated GPTV_DL, GPTV_radiomics, and imaging findings, demonstrated the effective determination of LVI status prior to surgery in patients with breast cancer.
{"title":"A comprehensive approach for evaluating lymphovascular invasion in invasive breast cancer: Leveraging multimodal MRI findings, radiomics, and deep learning analysis of intra- and peritumoral regions","authors":"","doi":"10.1016/j.compmedimag.2024.102415","DOIUrl":"10.1016/j.compmedimag.2024.102415","url":null,"abstract":"<div><h3>Purpose</h3><p>To evaluate lymphovascular invasion (LVI) in breast cancer by comparing the diagnostic performance of preoperative multimodal magnetic resonance imaging (MRI)-based radiomics and deep-learning (DL) models.</p></div><div><h3>Methods</h3><p>This retrospective study included 262 patients with breast cancer—183 in the training cohort (144 LVI-negative and 39 LVI-positive cases) and 79 in the validation cohort (59 LVI-negative and 20 LVI-positive cases). Radiomics features were extracted from the intra- and peritumoral breast regions using multimodal MRI to generate gross tumor volume (GTV)_radiomics and gross tumor volume plus peritumoral volume (GPTV)_radiomics. Subsequently, DL models (GTV_DL and GPTV_DL) were constructed based on the GTV and GPTV to determine the LVI status. Finally, the most effective radiomics and DL models were integrated with imaging findings to establish a hybrid model, which was converted into a nomogram to quantify the LVI risk.</p></div><div><h3>Results</h3><p>The diagnostic efficiency of GPTV_DL was superior to that of GTV_DL (areas under the curve [AUCs], 0.771 and 0.720, respectively). Similarly, GPTV_radiomics outperformed GTV_radiomics (AUC, 0.685 and 0.636, respectively). Univariate and multivariate logistic regression analyses revealed an association between imaging findings, such as MRI-axillary lymph nodes and peritumoral edema (AUC, 0.665). The hybrid model achieved the highest accuracy by combining GPTV_DL, GPTV_radiomics, and imaging findings (AUC, 0.872).</p></div><div><h3>Conclusion</h3><p>The diagnostic efficiency of the GPTV-derived radiomics and DL models surpassed that of the GTV-derived models. Furthermore, the hybrid model, which incorporated GPTV_DL, GPTV_radiomics, and imaging findings, demonstrated the effective determination of LVI status prior to surgery in patients with breast cancer.</p></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141692455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.1016/j.compmedimag.2024.102414
Chenchu Xu , Xue Wu , Boyan Wang , Jie Chen , Zhifan Gao , Xiujian Liu , Heye Zhang
The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder–decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality’s conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.
{"title":"Accurate segmentation of liver tumor from multi-modality non-contrast images using a dual-stream multi-level fusion framework","authors":"Chenchu Xu , Xue Wu , Boyan Wang , Jie Chen , Zhifan Gao , Xiujian Liu , Heye Zhang","doi":"10.1016/j.compmedimag.2024.102414","DOIUrl":"10.1016/j.compmedimag.2024.102414","url":null,"abstract":"<div><p>The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder–decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality’s conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.</p></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141564962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1016/j.compmedimag.2024.102417
D. M. S. Arsa, Talha Ilyas, Seok-Hwan Park, Leon O. Chua, Hyongsuk Kim
{"title":"Efficient multi-stage feedback attention for diverse lesion in cancer image segmentation","authors":"D. M. S. Arsa, Talha Ilyas, Seok-Hwan Park, Leon O. Chua, Hyongsuk Kim","doi":"10.1016/j.compmedimag.2024.102417","DOIUrl":"https://doi.org/10.1016/j.compmedimag.2024.102417","url":null,"abstract":"","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141716333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1016/j.compmedimag.2024.102420
Yifan Li, Chao Li, Yiran Wei, Stephen J. Price, C. Schönlieb, Xi Chen
{"title":"Multi-objective Bayesian optimization with enhanced features for adaptively improved glioblastoma partitioning and survival prediction","authors":"Yifan Li, Chao Li, Yiran Wei, Stephen J. Price, C. Schönlieb, Xi Chen","doi":"10.1016/j.compmedimag.2024.102420","DOIUrl":"https://doi.org/10.1016/j.compmedimag.2024.102420","url":null,"abstract":"","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141838546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"2D/3D deformable registration for endoscopic camera images using self-supervised offline learning of intraoperative pneumothorax deformation","authors":"Tomoki Oya, Yuka Kadomatsu, T.F. Chen-Yoshikawa, Megumi Nakao","doi":"10.1016/j.compmedimag.2024.102418","DOIUrl":"https://doi.org/10.1016/j.compmedimag.2024.102418","url":null,"abstract":"","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141851662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-25DOI: 10.1016/j.compmedimag.2024.102413
Caryn Geady , Farnoosh Abbas-Aghababazadeh , Andres Kohan , Scott Schuetze , David Shultz , Benjamin Haibe-Kains
Despite sharing the same histologic classification, individual tumors in multi metastatic patients may present with different characteristics and varying sensitivities to anticancer therapies. In this study, we investigate the utility of radiomic biomarkers for prediction of lesion-specific treatment resistance in multi metastatic leiomyosarcoma patients. Using a dataset of n=202 lung metastases (LM) from n=80 patients with 1648 pre-treatment computed tomography (CT) radiomics features and LM progression determined from follow-up CT, we developed a radiomic model to predict the progression of each lesion. Repeat experiments assessed the relative predictive performance across LM volume groups. Lesion-specific radiomic models indicate up to a 4.5-fold increase in predictive capacity compared with a no-skill classifier, with an area under the precision-recall curve of 0.70 for the most precise model (FDR = 0.05). Precision varied by administered drug and LM volume. The effect of LM volume was controlled by removing radiomic features at a volume-correlation coefficient threshold of 0.20. Predicting lesion-specific responses using radiomic features represents a novel strategy by which to assess treatment response that acknowledges biological diversity within metastatic subclones, which could facilitate management strategies involving selective ablation of resistant clones in the setting of systemic therapy.
{"title":"Radiomic-based prediction of lesion-specific systemic treatment response in metastatic disease","authors":"Caryn Geady , Farnoosh Abbas-Aghababazadeh , Andres Kohan , Scott Schuetze , David Shultz , Benjamin Haibe-Kains","doi":"10.1016/j.compmedimag.2024.102413","DOIUrl":"10.1016/j.compmedimag.2024.102413","url":null,"abstract":"<div><p>Despite sharing the same histologic classification, individual tumors in multi metastatic patients may present with different characteristics and varying sensitivities to anticancer therapies. In this study, we investigate the utility of radiomic biomarkers for prediction of lesion-specific treatment resistance in multi metastatic leiomyosarcoma patients. Using a dataset of n=202 lung metastases (LM) from n=80 patients with 1648 pre-treatment computed tomography (CT) radiomics features and LM progression determined from follow-up CT, we developed a radiomic model to predict the progression of each lesion. Repeat experiments assessed the relative predictive performance across LM volume groups. Lesion-specific radiomic models indicate up to a 4.5-fold increase in predictive capacity compared with a no-skill classifier, with an area under the precision-recall curve of 0.70 for the most precise model (FDR = 0.05). Precision varied by administered drug and LM volume. The effect of LM volume was controlled by removing radiomic features at a volume-correlation coefficient threshold of 0.20. Predicting lesion-specific responses using radiomic features represents a novel strategy by which to assess treatment response that acknowledges biological diversity within metastatic subclones, which could facilitate management strategies involving selective ablation of resistant clones in the setting of systemic therapy.</p></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141472247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-19DOI: 10.1016/j.compmedimag.2024.102412
Bolun Zeng , Huixiang Wang , Leo Joskowicz , Xiaojun Chen
Pelvic fracture is a complex and severe injury. Accurate diagnosis and treatment planning require the segmentation of the pelvic structure and the fractured fragments from preoperative CT scans. However, this segmentation is a challenging task, as the fragments from a pelvic fracture typically exhibit considerable variability and irregularity in the morphologies, locations, and quantities. In this study, we propose a novel dual-stream learning framework for the automatic segmentation and category labeling of pelvic fractures. Our method uniquely identifies pelvic fracture fragments in various quantities and locations using a dual-branch architecture that leverages distance learning from bone fragments. Moreover, we develop a multi-size feature fusion module that adaptively aggregates features from diverse receptive fields tailored to targets of different sizes and shapes, thus boosting segmentation performance. Extensive experiments on three pelvic fracture datasets from different medical centers demonstrated the accuracy and generalizability of the proposed method. It achieves a mean Dice coefficient and mean Sensitivity of 0.9350.068 and 0.9290.058 in the dataset FracCLINIC, and 0.9550.072 and 0.9120.125 in the dataset FracSegData, which are superior than other comparing methods. Our method optimizes the process of pelvic fracture segmentation, potentially serving as an effective tool for preoperative planning in the clinical management of pelvic fractures.
{"title":"Fragment distance-guided dual-stream learning for automatic pelvic fracture segmentation","authors":"Bolun Zeng , Huixiang Wang , Leo Joskowicz , Xiaojun Chen","doi":"10.1016/j.compmedimag.2024.102412","DOIUrl":"10.1016/j.compmedimag.2024.102412","url":null,"abstract":"<div><p>Pelvic fracture is a complex and severe injury. Accurate diagnosis and treatment planning require the segmentation of the pelvic structure and the fractured fragments from preoperative CT scans. However, this segmentation is a challenging task, as the fragments from a pelvic fracture typically exhibit considerable variability and irregularity in the morphologies, locations, and quantities. In this study, we propose a novel dual-stream learning framework for the automatic segmentation and category labeling of pelvic fractures. Our method uniquely identifies pelvic fracture fragments in various quantities and locations using a dual-branch architecture that leverages distance learning from bone fragments. Moreover, we develop a multi-size feature fusion module that adaptively aggregates features from diverse receptive fields tailored to targets of different sizes and shapes, thus boosting segmentation performance. Extensive experiments on three pelvic fracture datasets from different medical centers demonstrated the accuracy and generalizability of the proposed method. It achieves a mean Dice coefficient and mean Sensitivity of 0.935<span><math><mo>±</mo></math></span>0.068 and 0.929<span><math><mo>±</mo></math></span>0.058 in the dataset FracCLINIC, and 0.955<span><math><mo>±</mo></math></span>0.072 and 0.912<span><math><mo>±</mo></math></span>0.125 in the dataset FracSegData, which are superior than other comparing methods. Our method optimizes the process of pelvic fracture segmentation, potentially serving as an effective tool for preoperative planning in the clinical management of pelvic fractures.</p></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":null,"pages":null},"PeriodicalIF":5.4,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141472246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}