1
|
Qiu J, Mitra J, Ghose S, Dumas C, Yang J, Sarachan B, Judson MA. A Multichannel CT and Radiomics-Guided CNN-ViT (RadCT-CNNViT) Ensemble Network for Diagnosis of Pulmonary Sarcoidosis. Diagnostics (Basel) 2024; 14:1049. [PMID: 38786347 PMCID: PMC11120014 DOI: 10.3390/diagnostics14101049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2024] [Revised: 05/10/2024] [Accepted: 05/15/2024] [Indexed: 05/25/2024] Open
Abstract
Pulmonary sarcoidosis is a multisystem granulomatous interstitial lung disease (ILD) with a variable presentation and prognosis. The early accurate detection of pulmonary sarcoidosis may prevent progression to pulmonary fibrosis, a serious and potentially life-threatening form of the disease. However, the lack of a gold-standard diagnostic test and specific radiographic findings poses challenges in diagnosing pulmonary sarcoidosis. Chest computed tomography (CT) imaging is commonly used but requires expert, chest-trained radiologists to differentiate pulmonary sarcoidosis from lung malignancies, infections, and other ILDs. In this work, we develop a multichannel, CT and radiomics-guided ensemble network (RadCT-CNNViT) with visual explainability for pulmonary sarcoidosis vs. lung cancer (LCa) classification using chest CT images. We leverage CT and hand-crafted radiomics features as input channels, and a 3D convolutional neural network (CNN) and vision transformer (ViT) ensemble network for feature extraction and fusion before a classification head. The 3D CNN sub-network captures the localized spatial information of lesions, while the ViT sub-network captures long-range, global dependencies between features. Through multichannel input and feature fusion, our model achieves the highest performance with accuracy, sensitivity, specificity, precision, F1-score, and combined AUC of 0.93 ± 0.04, 0.94 ± 0.04, 0.93 ± 0.08, 0.95 ± 0.05, 0.94 ± 0.04, and 0.97, respectively, in a five-fold cross-validation study with pulmonary sarcoidosis (n = 126) and LCa (n = 93) cases. A detailed ablation study showing the impact of CNN + ViT compared to CNN or ViT alone, and CT + radiomics input, compared to CT or radiomics alone, is also presented in this work. Overall, the AI model developed in this work offers promising potential for triaging the pulmonary sarcoidosis patients for timely diagnosis and treatment from chest CT.
Collapse
Affiliation(s)
- Jianwei Qiu
- GE HealthCare, Niskayuna, NY 12309, USA; (J.Q.); (S.G.); (B.S.)
| | - Jhimli Mitra
- GE HealthCare, Niskayuna, NY 12309, USA; (J.Q.); (S.G.); (B.S.)
| | - Soumya Ghose
- GE HealthCare, Niskayuna, NY 12309, USA; (J.Q.); (S.G.); (B.S.)
| | - Camille Dumas
- Department of Medical Imaging, Albany Medical College, Albany, NY 12208, USA; (C.D.); (J.Y.)
| | - Jun Yang
- Department of Medical Imaging, Albany Medical College, Albany, NY 12208, USA; (C.D.); (J.Y.)
| | - Brion Sarachan
- GE HealthCare, Niskayuna, NY 12309, USA; (J.Q.); (S.G.); (B.S.)
| | - Marc A. Judson
- Department of Medicine, Albany Medical College, Albany, NY 12208, USA;
| |
Collapse
|
2
|
Zyla J, Marczyk M, Prazuch W, Sitkiewicz M, Durawa A, Jelitto M, Dziadziuszko K, Jelonek K, Kurczyk A, Szurowska E, Rzyman W, Widłak P, Polanska J. Combining Low-Dose Computer-Tomography-Based Radiomics and Serum Metabolomics for Diagnosis of Malignant Nodules in Participants of Lung Cancer Screening Studies. Biomolecules 2023; 14:44. [PMID: 38254644 PMCID: PMC10813699 DOI: 10.3390/biom14010044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 12/23/2023] [Accepted: 12/25/2023] [Indexed: 01/24/2024] Open
Abstract
Radiomics is an emerging approach to support the diagnosis of pulmonary nodules detected via low-dose computed tomography lung cancer screening. Serum metabolome is a promising source of auxiliary biomarkers that could help enhance the precision of lung cancer diagnosis in CT-based screening. Thus, we aimed to verify whether the combination of these two techniques, which provides local/morphological and systemic/molecular features of disease at the same time, increases the performance of lung cancer classification models. The collected cohort consists of 1086 patients with radiomic and 246 patients with serum metabolomic evaluations. Different machine learning techniques, i.e., random forest and logistic regression were applied for each omics. Next, model predictions were combined with various integration methods to create a final model. The best single omics models were characterized by an AUC of 83% in radiomics and 60% in serum metabolomics. The model integration only slightly increased the performance of the combined model (AUC equal to 85%), which was not statistically significant. We concluded that radiomics itself has a good ability to discriminate lung cancer from benign lesions. However, additional research is needed to test whether its combination with other molecular assessments would further improve the diagnosis of screening-detected lung nodules.
Collapse
Affiliation(s)
- Joanna Zyla
- Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland; (J.Z.); (W.P.); (J.P.)
| | - Michal Marczyk
- Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland; (J.Z.); (W.P.); (J.P.)
- Yale Cancer Center, Yale School of Medicine, New Haven, CT 06510, USA
| | - Wojciech Prazuch
- Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland; (J.Z.); (W.P.); (J.P.)
| | - Magdalena Sitkiewicz
- Department of Thoracic Surgery, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.S.); (A.D.); (W.R.)
| | - Agata Durawa
- Department of Thoracic Surgery, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.S.); (A.D.); (W.R.)
| | - Malgorzata Jelitto
- 2nd Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.J.); (K.D.); (E.S.); (P.W.)
| | - Katarzyna Dziadziuszko
- 2nd Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.J.); (K.D.); (E.S.); (P.W.)
| | - Karol Jelonek
- Center for Translational Research and Molecular Biology of Cancer, Maria Sklodowska-Curie National Research Institute of Oncology, Gliwice Branch, 44-100 Gliwice, Poland;
| | - Agata Kurczyk
- Department of Biostatistics and Bioinformatics, Maria Sklodowska-Curie National Research Institute of Oncology, Gliwice Branch, 44-100 Gliwice, Poland;
| | - Edyta Szurowska
- 2nd Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.J.); (K.D.); (E.S.); (P.W.)
| | - Witold Rzyman
- Department of Thoracic Surgery, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.S.); (A.D.); (W.R.)
| | - Piotr Widłak
- 2nd Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.J.); (K.D.); (E.S.); (P.W.)
| | - Joanna Polanska
- Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland; (J.Z.); (W.P.); (J.P.)
| |
Collapse
|
3
|
Judson MA, Qiu J, Dumas CL, Yang J, Sarachan B, Mitra J. An Artificial Intelligence Platform for the Radiologic Diagnosis of Pulmonary Sarcoidosis: An Initial Pilot Study of Chest Computed Tomography Analysis to Distinguish Pulmonary Sarcoidosis from a Negative Lung Cancer Screening Scan. Lung 2023; 201:611-616. [PMID: 37962584 DOI: 10.1007/s00408-023-00655-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2023] [Accepted: 10/31/2023] [Indexed: 11/15/2023]
Abstract
PURPOSE To determine the reliability of an artificial intelligence, deep learning (AI/DL)-based method of chest computer tomography (CT) scan analysis to distinguish pulmonary sarcoidosis from negative lung cancer screening chest CT scans (Lung Imaging Reporting and Data System score 1, Lung-RADS score 1). METHODS Chest CT scans of pulmonary sarcoidosis were evaluated by a clinician experienced with sarcoidosis and a chest radiologist for clinical and radiologic evidence of sarcoidosis and exclusion of alternative or concomitant pulmonary diseases. The AI/DL based method used an ensemble network architecture combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The method was applied to 126 pulmonary sarcoidosis and 96 Lung-RADS score 1 CT scans. The analytic approach of training and validation of the AI/DL method used a fivefold cross-validation technique, where 4/5th of the available data set was used to train a diagnostic model and tested on the remaining 1/5th of the data set, and repeated 4 more times with non-overlapping validation/test data. The probability values were used to generate Receiver Operating Characteristic (ROC) curves to assess the model's discriminatory power. RESULTS The sensitivity, specificity, positive and negative predictive value of the AI/DL method for the 5 folds of the training/validation sets and the entire set of CT scans were all over 94% to distinguish pulmonary sarcoidosis from LUNG-RADS score 1 chest CT scans. The area under the curve for the corresponding ROC curves were all over 97%. CONCLUSION This AL/DL model shows promise to distinguish sarcoidosis from alternative pulmonary conditions using minimal radiologic data.
Collapse
Affiliation(s)
- Marc A Judson
- Division of Pulmonary and Critical Care Medicine, Department of Medicine, Albany Medical College, MC-91; 16 New Scotland, Albany, NY, 12208, USA.
| | | | - Camille L Dumas
- Cardiovascular Division, Department of Radiology, Albany Medical College, Albany, NY, USA
| | - Jun Yang
- Albany Medical College, Albany, NY, USA
| | | | | |
Collapse
|
4
|
Bidzińska J, Szurowska E. See Lung Cancer with an AI. Cancers (Basel) 2023; 15:cancers15041321. [PMID: 36831662 PMCID: PMC9954317 DOI: 10.3390/cancers15041321] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2023] [Revised: 02/13/2023] [Accepted: 02/17/2023] [Indexed: 02/22/2023] Open
Abstract
A lot has happened in the field of lung cancer screening in recent months. The ongoing discussion and documentation published by the scientific community and policymakers are of great importance to the entire European community and perhaps beyond. Lung cancer is the main worldwide killer. Low-dose computed tomography-based screening, together with smoking cessation, is the only tool to fight lung cancer, as it has already been proven in the United States of America but also European randomized controlled trials. Screening requires a lot of well-organized specialized work, but it can be supported by artificial intelligence (AI). Here we discuss whether and how to use AI for patients, radiologists, pulmonologists, thoracic surgeons, and all hospital staff supporting screening process benefits.
Collapse
|
5
|
Zerunian M, Laghi A, Caruso D. Radiomics in Oncology III. Diagnostics (Basel) 2023; 13:diagnostics13010149. [PMID: 36611441 PMCID: PMC9818531 DOI: 10.3390/diagnostics13010149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2022] [Accepted: 12/22/2022] [Indexed: 01/04/2023] Open
Abstract
In recent years, radiomics has been among the most impactful topics in the research field of quantitative imaging [...].
Collapse
|
6
|
Sheikhpour M, Mirbahari SN, Sadr M, Maleki M, Arabi M, Abolfathi H. A Comprehensive Study on the Correlation of Treatment, Diagnosis and Epidemiology of Tuberculosis and Lung Cancer. TANAFFOS 2023; 22:7-18. [PMID: 37920308 PMCID: PMC10618578] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Accepted: 12/24/2022] [Indexed: 11/04/2023]
Abstract
The correlation between tuberculosis (TB) and lung cancer (LC) in diagnosis, epidemiology, and treatment is still unclear. Based on different cohort and retrospective studies, this correlation could be justified by immune weakness because of exposure to TB which may increase the risk of LC. In this study, we tried to exhibit a prominent connection between TB and LC. The diagnosis and treatment of patients with concomitant TB and LC differ from patients with only one of the diseases. In this review, it was well clarified that the most practical diagnostic method for LC is chest tomography, biopsy, and histopathology, and for pulmonary TB sputum microscopic examination, Autofluorescence bronchoscopy (AFB), culture, and PCR. Also, immunological methods can be a good alternative for differential diagnosis. Most epidemiological studies were about concomitant TB and LC in TB-endemic areas, especially in the Middle East. The most suggested methods for definite treatment of LC are chemotherapy, radiotherapy, and surgery while for TB, a long course of anti-TB therapy can be used. Moreover, immunotherapy is considered a good treatment for lung cancer if the interferon-gamma release assay (IGRA) is negative.
Collapse
Affiliation(s)
- Mojgan Sheikhpour
- Department of Mycobacteriology and Pulmonary Research, Pasteur Institute of Iran, Tehran, Iran
| | - Seyedeh Nasim Mirbahari
- Reproductive Biomedicine Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, Iran
| | - Makan Sadr
- Virology Research Center, National Research Institute of Tuberculosis and Lung Diseases (NRITLD), Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mobina Maleki
- Department of Mycobacteriology and Pulmonary Research, Pasteur Institute of Iran, Tehran, Iran
| | - Mohadeseh Arabi
- Department of Mycobacteriology and Pulmonary Research, Pasteur Institute of Iran, Tehran, Iran
| | - Hanie Abolfathi
- Department of Mycobacteriology and Pulmonary Research, Pasteur Institute of Iran, Tehran, Iran
| |
Collapse
|
7
|
Peng B, Wang K, Xu R, Guo C, Lu T, Li Y, Wang Y, Wang C, Chang X, Shen Z, Shi J, Xu C, Zhang L. Preoperative computed tomography-based tumoral radiomic features prediction for overall survival in resectable non-small cell lung cancer. Front Oncol 2023; 13:1131816. [PMID: 37207163 PMCID: PMC10189057 DOI: 10.3389/fonc.2023.1131816] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2022] [Accepted: 04/24/2023] [Indexed: 05/21/2023] Open
Abstract
Objectives The purpose of this study was to evaluate whether preoperative radiomics features could meliorate risk stratification for the overall survival (OS) of non-small cell lung cancer (NSCLC) patients. Methods After rigorous screening, the 208 NSCLC patients without any pre-operative adjuvant therapy were eventually enrolled. We segmented the 3D volume of interest (VOI) based on malignant lesion of computed tomography (CT) imaging and extracted 1542 radiomics features. Interclass correlation coefficients (ICC) and LASSO Cox regression analysis were utilized to perform feature selection and radiomics model building. In the model evaluation phase, we carried out stratified analysis, receiver operating characteristic (ROC) curve, concordance index (C-index), and decision curve analysis (DCA). In addition, integrating the clinicopathological trait and radiomics score, we developed a nomogram to predict the OS at 1 year, 2 years, and 3 years, respectively. Results Six radiomics features, including gradient_glcm_InverseVariance, logarithm_firstorder_Median, logarithm_firstorder_RobustMeanAbsoluteDeviation, square_gldm_LargeDependenceEmphasis, wavelet_HLL_firstorder_Kurtosis, and wavelet_LLL_firstorder_Maximum, were selected to construct the radiomics signature, whose areas under the curve (AUCs) for 3-year prediction reached 0.857 in the training set (n=146) and 0.871 in the testing set (n=62). The results of multivariate analysis revealed that the radiomics score, radiological sign, and N stage were independent prognostic factors in NSCLC. Moreover, compared with clinical factors and the separate radiomics model, the established nomogram exhibited a better performance in predicting 3-year OS. Conclusions Our radiomics model may provide a promising non-invasive approach for preoperative risk stratification and personalized postoperative surveillance for resectable NSCLC patients.
Collapse
Affiliation(s)
- Bo Peng
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Kaiyu Wang
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Ran Xu
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Congying Guo
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Tong Lu
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Yongchao Li
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Yiqiao Wang
- Department of Radiology, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Chenghao Wang
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Xiaoyan Chang
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Zhiping Shen
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Jiaxin Shi
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Chengyu Xu
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Linyou Zhang
- Department of Thoracic Surgery, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
- *Correspondence: Linyou Zhang,
| |
Collapse
|