1
|
Gong J, Fu F, Ma X, Wang T, Ma X, You C, Zhang Y, Peng W, Chen H, Gu Y. Hybrid deep multi-task learning radiomics approach for predicting EGFR mutation status of non-small cell lung cancer in CT images. Phys Med Biol 2023; 68:245021. [PMID: 37972417 DOI: 10.1088/1361-6560/ad0d43] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2023] [Accepted: 11/15/2023] [Indexed: 11/19/2023]
Abstract
Objective.Epidermal growth factor receptor (EGFR) mutation genotyping plays a pivotal role in targeted therapy for non-small cell lung cancer (NSCLC). We aimed to develop a computed tomography (CT) image-based hybrid deep radiomics model to predict EGFR mutation status in NSCLC and investigate the correlations between deep image and quantitative radiomics features.Approach.First, we retrospectively enrolled 818 patients from our centre and 131 patients from The Cancer Imaging Archive database to establish a training cohort (N= 654), an independent internal validation cohort (N= 164) and an external validation cohort (N= 131). Second, to predict EGFR mutation status, we developed three CT image-based models, namely, a multi-task deep neural network (DNN), a radiomics model and a feature fusion model. Third, we proposed a hybrid loss function to train the DNN model. Finally, to evaluate the model performance, we computed the areas under the receiver operating characteristic curves (AUCs) and decision curve analysis curves of the models.Main results.For the two validation cohorts, the feature fusion model achieved AUC values of 0.86 ± 0.03 and 0.80 ± 0.05, which were significantly higher than those of the single-task DNN and radiomics models (allP< 0.05). There was no significant difference between the feature fusion and the multi-task DNN models (P> 0.8). The binary prediction scores showed excellent prognostic value in predicting disease-free survival (P= 0.02) and overall survival (P< 0.005) for validation cohort 2.Significance.The results demonstrate that (1) the feature fusion and multi-task DNN models achieve significantly higher performance than that of the conventional radiomics and single-task DNN models, (2) the feature fusion model can decode the imaging phenotypes representing NSCLC heterogeneity related to both EGFR mutation and patient NSCLC prognosis, and (3) high correlations exist between some deep image and radiomics features.
Collapse
Affiliation(s)
- Jing Gong
- Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 20003, People's Republic of China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Fangqiu Fu
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
- Department of Thoracic Surgery and State key Laboratory of Genetic Engineering, Fudan University Shanghai Cancer Center, Shanghai, 200032, People's Republic of China
| | - Xiaowen Ma
- Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 20003, People's Republic of China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Ting Wang
- Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 20003, People's Republic of China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Xiangyi Ma
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
- Department of Thoracic Surgery and State key Laboratory of Genetic Engineering, Fudan University Shanghai Cancer Center, Shanghai, 200032, People's Republic of China
| | - Chao You
- Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 20003, People's Republic of China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Yang Zhang
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
- Department of Thoracic Surgery and State key Laboratory of Genetic Engineering, Fudan University Shanghai Cancer Center, Shanghai, 200032, People's Republic of China
| | - Weijun Peng
- Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 20003, People's Republic of China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Haiquan Chen
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
- Department of Thoracic Surgery and State key Laboratory of Genetic Engineering, Fudan University Shanghai Cancer Center, Shanghai, 200032, People's Republic of China
| | - Yajia Gu
- Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 20003, People's Republic of China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| |
Collapse
|
2
|
Xu Y, Zhou C, He X, Song R, Liu Y, Zhang H, Wang Y, Fan Q, Chen W, Wu J, Wang J, Guo D. Deep learning-assisted LI-RADS grading and distinguishing hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT: a two-center study. Eur Radiol 2023; 33:8879-8888. [PMID: 37392233 DOI: 10.1007/s00330-023-09857-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 05/05/2023] [Accepted: 05/14/2023] [Indexed: 07/03/2023]
Abstract
OBJECTIVES To develop a deep learning (DL) method that can determine the Liver Imaging Reporting and Data System (LI-RADS) grading of high-risk liver lesions and distinguish hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT. METHODS This retrospective study included 1049 patients with 1082 lesions from two independent hospitals that were pathologically confirmed as HCC or non-HCC. All patients underwent a four-phase CT imaging protocol. All lesions were graded (LR 4/5/M) by radiologists and divided into an internal (n = 886) and external cohort (n = 196) based on the examination date. In the internal cohort, Swin-Transformer based on different CT protocols were trained and tested for their ability to LI-RADS grading and distinguish HCC from non-HCC, and then validated in the external cohort. We further developed a combined model with the optimal protocol and clinical information for distinguishing HCC from non-HCC. RESULTS In the test and external validation cohorts, the three-phase protocol without pre-contrast showed κ values of 0.6094 and 0.4845 for LI-RADS grading, and its accuracy was 0.8371 and 0.8061, while the accuracy of the radiologist was 0.8596 and 0.8622, respectively. The AUCs in distinguishing HCC from non-HCC were 0.865 and 0.715 in the test and external validation cohorts, while those of the combined model were 0.887 and 0.808. CONCLUSION The Swin-Transformer based on three-phase CT protocol without pre-contrast could feasibly simplify LI-RADS grading and distinguish HCC from non-HCC. Furthermore, the DL model have the potential in accurately distinguishing HCC from non-HCC using imaging and highly characteristic clinical data as inputs. CLINICAL RELEVANCE STATEMENT The application of deep learning model for multiphase CT has proven to improve the clinical applicability of the Liver Imaging Reporting and Data System and provide support to optimize the management of patients with liver diseases. KEY POINTS • Deep learning (DL) simplifies LI-RADS grading and helps distinguish hepatocellular carcinoma (HCC) from non-HCC. • The Swin-Transformer based on the three-phase CT protocol without pre-contrast outperformed other CT protocols. • The Swin-Transformer provide help in distinguishing HCC from non-HCC by using CT and characteristic clinical information as inputs.
Collapse
Affiliation(s)
- Yang Xu
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China
| | - Chaoyang Zhou
- Department of Radiology, The First Affiliated Hospital of Army Military Medical University, Chongqing, 400038, People's Republic of China
| | - Xiaojuan He
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China
| | - Rao Song
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China
| | - Yangyang Liu
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China
| | - Haiping Zhang
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China
| | - Yudong Wang
- Institute of Research, Ocean International Center, InferVision, Chaoyang District, Beijing, 100025, China
| | - Qianrui Fan
- Institute of Research, Ocean International Center, InferVision, Chaoyang District, Beijing, 100025, China
| | - Weidao Chen
- Institute of Research, Ocean International Center, InferVision, Chaoyang District, Beijing, 100025, China
| | - Jiangfen Wu
- Institute of Research, Ocean International Center, InferVision, Chaoyang District, Beijing, 100025, China
| | - Jian Wang
- Department of Radiology, The First Affiliated Hospital of Army Military Medical University, Chongqing, 400038, People's Republic of China.
| | - Dajing Guo
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China.
| |
Collapse
|
3
|
Ali H, Mohsen F, Shah Z. Improving diagnosis and prognosis of lung cancer using vision transformers: a scoping review. BMC Med Imaging 2023; 23:129. [PMID: 37715137 PMCID: PMC10503208 DOI: 10.1186/s12880-023-01098-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2023] [Accepted: 09/05/2023] [Indexed: 09/17/2023] Open
Abstract
BACKGROUND Vision transformer-based methods are advancing the field of medical artificial intelligence and cancer imaging, including lung cancer applications. Recently, many researchers have developed vision transformer-based AI methods for lung cancer diagnosis and prognosis. OBJECTIVE This scoping review aims to identify the recent developments on vision transformer-based AI methods for lung cancer imaging applications. It provides key insights into how vision transformers complemented the performance of AI and deep learning methods for lung cancer. Furthermore, the review also identifies the datasets that contributed to advancing the field. METHODS In this review, we searched Pubmed, Scopus, IEEEXplore, and Google Scholar online databases. The search terms included intervention terms (vision transformers) and the task (i.e., lung cancer, adenocarcinoma, etc.). Two reviewers independently screened the title and abstract to select relevant studies and performed the data extraction. A third reviewer was consulted to validate the inclusion and exclusion. Finally, the narrative approach was used to synthesize the data. RESULTS Of the 314 retrieved studies, this review included 34 studies published from 2020 to 2022. The most commonly addressed task in these studies was the classification of lung cancer types, such as lung squamous cell carcinoma versus lung adenocarcinoma, and identifying benign versus malignant pulmonary nodules. Other applications included survival prediction of lung cancer patients and segmentation of lungs. The studies lacked clear strategies for clinical transformation. SWIN transformer was a popular choice of the researchers; however, many other architectures were also reported where vision transformer was combined with convolutional neural networks or UNet model. Researchers have used the publicly available lung cancer datasets of the lung imaging database consortium and the cancer genome atlas. One study used a cluster of 48 GPUs, while other studies used one, two, or four GPUs. CONCLUSION It can be concluded that vision transformer-based models are increasingly in popularity for developing AI methods for lung cancer applications. However, their computational complexity and clinical relevance are important factors to be considered for future research work. This review provides valuable insights for researchers in the field of AI and healthcare to advance the state-of-the-art in lung cancer diagnosis and prognosis. We provide an interactive dashboard on lung-cancer.onrender.com/ .
Collapse
Affiliation(s)
- Hazrat Ali
- College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar.
| | - Farida Mohsen
- College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar
| | - Zubair Shah
- College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar.
| |
Collapse
|
4
|
Mu J, Kuang K, Ao M, Li W, Dai H, Ouyang Z, Li J, Huang J, Guo S, Yang J, Yang L. Deep learning predicts malignancy and metastasis of solid pulmonary nodules from CT scans. Front Med (Lausanne) 2023; 10:1145846. [PMID: 37275359 PMCID: PMC10235703 DOI: 10.3389/fmed.2023.1145846] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Accepted: 04/10/2023] [Indexed: 06/07/2023] Open
Abstract
In the clinic, it is difficult to distinguish the malignancy and aggressiveness of solid pulmonary nodules (PNs). Incorrect assessments may lead to delayed diagnosis and an increased risk of complications. We developed and validated a deep learning-based model for the prediction of malignancy as well as local or distant metastasis in solid PNs based on CT images of primary lesions during initial diagnosis. In this study, we reviewed the data from multiple patients with solid PNs at our institution from 1 January 2019 to 30 April 2022. The patients were divided into three groups: benign, Ia-stage lung cancer, and T1-stage lung cancer with metastasis. Each cohort was further split into training and testing groups. The deep learning system predicted the malignancy and metastasis status of solid PNs based on CT images, and then we compared the malignancy prediction results among four different levels of clinicians. Experiments confirmed that human-computer collaboration can further enhance diagnostic accuracy. We made a held-out testing set of 134 cases, with 689 cases in total. Our convolutional neural network model reached an area under the ROC (AUC) of 80.37% for malignancy prediction and an AUC of 86.44% for metastasis prediction. In observer studies involving four clinicians, the proposed deep learning method outperformed a junior respiratory clinician and a 5-year respiratory clinician by considerable margins; it was on par with a senior respiratory clinician and was only slightly inferior to a senior radiologist. Our human-computer collaboration experiment showed that by simply adding binary human diagnosis into model prediction probabilities, model AUC scores improved to 81.80-88.70% when combined with three out of four clinicians. In summary, the deep learning method can accurately diagnose the malignancy of solid PNs, improve its performance when collaborating with human experts, predict local or distant metastasis in patients with T1-stage lung cancer, and facilitate the application of precision medicine.
Collapse
Affiliation(s)
- Junhao Mu
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Kaiming Kuang
- Dianei Technology, Shanghai, China
- University of California, San Diego, San Diego, CA, United States
| | - Min Ao
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Weiyi Li
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Haiyun Dai
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Zubin Ouyang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jingyu Li
- Dianei Technology, Shanghai, China
- School of Computer Science, Wuhan University, Wuhan, China
| | - Jing Huang
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Shuliang Guo
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jiancheng Yang
- Dianei Technology, Shanghai, China
- Shanghai Jiao Tong University, Shanghai, China
- École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
| | - Li Yang
- Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| |
Collapse
|
5
|
de Vries BM, Zwezerijnen GJC, Burchell GL, van Velden FHP, Menke-van der Houven van Oordt CW, Boellaard R. Explainable artificial intelligence (XAI) in radiology and nuclear medicine: a literature review. Front Med (Lausanne) 2023; 10:1180773. [PMID: 37250654 PMCID: PMC10213317 DOI: 10.3389/fmed.2023.1180773] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2023] [Accepted: 04/17/2023] [Indexed: 05/31/2023] Open
Abstract
Rational Deep learning (DL) has demonstrated a remarkable performance in diagnostic imaging for various diseases and modalities and therefore has a high potential to be used as a clinical tool. However, current practice shows low deployment of these algorithms in clinical practice, because DL algorithms lack transparency and trust due to their underlying black-box mechanism. For successful employment, explainable artificial intelligence (XAI) could be introduced to close the gap between the medical professionals and the DL algorithms. In this literature review, XAI methods available for magnetic resonance (MR), computed tomography (CT), and positron emission tomography (PET) imaging are discussed and future suggestions are made. Methods PubMed, Embase.com and Clarivate Analytics/Web of Science Core Collection were screened. Articles were considered eligible for inclusion if XAI was used (and well described) to describe the behavior of a DL model used in MR, CT and PET imaging. Results A total of 75 articles were included of which 54 and 17 articles described post and ad hoc XAI methods, respectively, and 4 articles described both XAI methods. Major variations in performance is seen between the methods. Overall, post hoc XAI lacks the ability to provide class-discriminative and target-specific explanation. Ad hoc XAI seems to tackle this because of its intrinsic ability to explain. However, quality control of the XAI methods is rarely applied and therefore systematic comparison between the methods is difficult. Conclusion There is currently no clear consensus on how XAI should be deployed in order to close the gap between medical professionals and DL algorithms for clinical implementation. We advocate for systematic technical and clinical quality assessment of XAI methods. Also, to ensure end-to-end unbiased and safe integration of XAI in clinical workflow, (anatomical) data minimization and quality control methods should be included.
Collapse
Affiliation(s)
- Bart M. de Vries
- Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, Netherlands
| | - Gerben J. C. Zwezerijnen
- Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, Netherlands
| | | | | | | | - Ronald Boellaard
- Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, Netherlands
| |
Collapse
|
6
|
Chen W, Wu J, Wei R, Wu S, Xia C, Wang D, Liu D, Zheng L, Zou T, Li R, Qi X, Zhang X. Improving the diagnosis of acute ischemic stroke on non-contrast CT using deep learning: a multicenter study. Insights Imaging 2022; 13:184. [PMID: 36471022 PMCID: PMC9723089 DOI: 10.1186/s13244-022-01331-3] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2022] [Accepted: 11/11/2022] [Indexed: 12/12/2022] Open
Abstract
OBJECTIVE This study aimed to develop a deep learning (DL) model to improve the diagnostic performance of EIC and ASPECTS in acute ischemic stroke (AIS). METHODS Acute ischemic stroke patients were retrospectively enrolled from 5 hospitals. We proposed a deep learning model to simultaneously segment the infarct and estimate ASPECTS automatically using baseline CT. The model performance of segmentation and ASPECTS scoring was evaluated using dice similarity coefficient (DSC) and ROC, respectively. Four raters participated in the multi-reader and multicenter (MRMC) experiment to fulfill the region-based ASPECTS reading under the assistance of the model or not. At last, sensitivity, specificity, interpretation time and interrater agreement were used to evaluate the raters' reading performance. RESULTS In total, 1391 patients were enrolled for model development and 85 patients for external validation with onset to CT scanning time of 176.4 ± 93.6 min and NIHSS of 5 (IQR 2-10). The model achieved a DSC of 0.600 and 0.762 and an AUC of 0.876 (CI 0.846-0.907) and 0.729 (CI 0.679-0.779), in the internal and external validation set, respectively. The assistance of the DL model improved the raters' average sensitivities and specificities from 0.254 (CI 0.22-0.26) and 0.896 (CI 0.884-0.907), to 0.333 (CI 0.301-0.345) and 0.915 (CI 0.904-0.926), respectively. The average interpretation time of the raters was reduced from 219.0 to 175.7 s (p = 0.035). Meanwhile, the interrater agreement increased from 0.741 to 0.980. CONCLUSIONS With the assistance of our proposed DL model, radiologists got better performance in the detection of AIS lesions on NCCT.
Collapse
Affiliation(s)
- Weidao Chen
- grid.13402.340000 0004 1759 700XInterdisciplinary Institute of Neuroscience and Technology, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, 310027 Zhejiang China ,Infervision Institute of Research, Beijing, 100025 China
| | - Jiangfen Wu
- grid.11135.370000 0001 2256 9319Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China ,Infervision Institute of Research, Beijing, 100025 China
| | - Ren Wei
- Infervision Institute of Research, Beijing, 100025 China
| | - Shuang Wu
- Infervision Institute of Research, Beijing, 100025 China
| | - Chen Xia
- Infervision Institute of Research, Beijing, 100025 China
| | - Dawei Wang
- Infervision Institute of Research, Beijing, 100025 China
| | - Daliang Liu
- grid.415912.a0000 0004 4903 149XLiaocheng People’s Hospital, Liaocheng, 252000 Shandong China
| | - Longmei Zheng
- Medical Imaging Center, Ankang Central Hospital, Ankang, 725000 Shanxi China
| | - Tianyu Zou
- grid.478119.20000 0004 1757 8159Weihai Municipal Hospital, Weihai, 264200 Shandong China
| | - Ruijiang Li
- grid.168010.e0000000419368956Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA 94304 USA
| | - Xianrong Qi
- grid.11135.370000 0001 2256 9319School of Pharmaceutical Sciences, Peking University, Beijing, 100191 China ,grid.11135.370000 0001 2256 9319Beijing Key Laboratory of Molecular Pharmaceutics and New Drug Delivery System, School of Pharmaceutical Sciences, Peking University, Beijing, 100191 China
| | - Xiaotong Zhang
- grid.13402.340000 0004 1759 700XInterdisciplinary Institute of Neuroscience and Technology, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, 310027 Zhejiang China ,grid.13402.340000 0004 1759 700XCollege of Electrical Engineering, Zhejiang University, Hangzhou, 310000 Zhejiang China ,grid.13402.340000 0004 1759 700XMOE Frontier Science Center for Brain Science & Brain-machine Integration, Zhejiang University, Hangzhou, 310000 Zhejiang China
| |
Collapse
|
7
|
Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation. J Clin Med 2022; 11:jcm11154625. [PMID: 35956236 PMCID: PMC9369996 DOI: 10.3390/jcm11154625] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Revised: 08/03/2022] [Accepted: 08/05/2022] [Indexed: 11/16/2022] Open
Abstract
Background: Deep learning (DL) could predict isocitrate dehydrogenase (IDH) mutation status from MRIs. Yet, previous work focused on CNNs with refined tumor segmentation. To bridge the gap, this study aimed to evaluate the feasibility of developing a Transformer-based network to predict the IDH mutation status free of refined tumor segmentation. Methods: A total of 493 glioma patients were recruited from two independent institutions for model development (TCIA; N = 259) and external test (AHXZ; N = 234). IDH mutation status was predicted directly from T2 images with a Swin Transformer and conventional ResNet. Furthermore, to investigate the necessity of refined tumor segmentation, seven strategies for the model input image were explored: (i) whole tumor slice; (ii-iii) tumor mask and/or not edema; (iv-vii) tumor bounding box of 0.8, 1.0, 1.2, 1.5 times. Performance comparison was made among the networks of different architectures along with different image input strategies, using area under the curve (AUC) and accuracy (ACC). Finally, to further boost the performance, a hybrid model was built by incorporating the images with clinical features. Results: With the seven proposed input strategies, seven Swin Transformer models and seven ResNet models were built, respectively. Based on the seven Swin Transformer models, an averaged AUC of 0.965 (internal test) and 0.842 (external test) were achieved, outperforming 0.922 and 0.805 resulting from the seven ResNet models, respectively. When a bounding box of 1.0 times was used, Swin Transformer (AUC = 0.868, ACC = 80.7%), achieved the best results against the one that used tumor segmentation (Tumor + Edema, AUC = 0.862, ACC = 78.5%). The hybrid model that integrated age and location features into images yielded improved performance (AUC = 0.878, Accuracy = 82.0%) over the model that used images only. Conclusions: Swin Transformer outperforms the CNN-based ResNet in IDH prediction. Using bounding box input images benefits the DL networks in IDH prediction and makes the IDH prediction free of refined glioma segmentation feasible.
Collapse
|