1
|
Shi Z, Geng K, Zhao X, Mahmoudi F, Haas CJ, Leader JK, Duman E, Pu J. XRayWizard: Reconstructing 3-D lung surfaces from a single 2-D chest x-ray image via Vision Transformer. Med Phys 2024; 51:2806-2816. [PMID: 37819009 DOI: 10.1002/mp.16781] [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: 07/19/2023] [Revised: 09/26/2023] [Accepted: 09/27/2023] [Indexed: 10/13/2023] Open
Abstract
BACKGROUND Chest x-ray is widely utilized for the evaluation of pulmonary conditions due to its technical simplicity, cost-effectiveness, and portability. However, as a two-dimensional (2-D) imaging modality, chest x-ray images depict limited anatomical details and are challenging to interpret. PURPOSE To validate the feasibility of reconstructing three-dimensional (3-D) lungs from a single 2-D chest x-ray image via Vision Transformer (ViT). METHODS We created a cohort of 2525 paired chest x-ray images (scout images) and computed tomography (CT) acquired on different subjects and we randomly partitioned them as follows: (1) 1800 - training set, (2) 200 - validation set, and (3) 525 - testing set. The 3-D lung volumes segmented from the chest CT scans were used as the ground truth for supervised learning. We developed a novel model termed XRayWizard that employed ViT blocks to encode the 2-D chest x-ray image. The aim is to capture global information and establish long-range relationships, thereby improving the performance of 3-D reconstruction. Additionally, a pooling layer at the end of each transformer block was introduced to extract feature information. To produce smoother and more realistic 3-D models, a set of patch discriminators was incorporated. We also devised a novel method to incorporate subject demographics as an auxiliary input to further improve the accuracy of 3-D lung reconstruction. Dice coefficient and mean volume error were used as performance metrics as the agreement between the computerized results and the ground truth. RESULTS In the absence of subject demographics, the mean Dice coefficient for the generated 3-D lung volumes achieved a value of 0.738 ± 0.091. When subject demographics were included as an auxiliary input, the mean Dice coefficient significantly improved to 0.769 ± 0.089 (p < 0.001), and the volume prediction error was reduced from 23.5 ± 2.7%. to 15.7 ± 2.9%. CONCLUSION Our experiment demonstrated the feasibility of reconstructing 3-D lung volumes from 2-D chest x-ray images, and the inclusion of subject demographics as additional inputs can significantly improve the accuracy of 3-D lung volume reconstruction.
Collapse
Affiliation(s)
- Zhiyi Shi
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Kaiwen Geng
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Xiaoyan Zhao
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Farhad Mahmoudi
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Christopher J Haas
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Joseph K Leader
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Emrah Duman
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Jiantao Pu
- Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
- Department of Bioengineering, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| |
Collapse
|
2
|
Khosravi B, Rouzrokh P, Faghani S, Moassefi M, Vahdati S, Mahmoudi E, Chalian H, Erickson BJ. Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review. Diagnostics (Basel) 2022; 12:2512. [PMID: 36292201 PMCID: PMC9600598 DOI: 10.3390/diagnostics12102512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2022] [Revised: 10/14/2022] [Accepted: 10/15/2022] [Indexed: 01/17/2023] Open
Abstract
Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.
Collapse
Affiliation(s)
- Bardia Khosravi
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
- Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN 55905, USA
| | - Pouria Rouzrokh
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
- Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN 55905, USA
| | - Shahriar Faghani
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Mana Moassefi
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Sanaz Vahdati
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Elham Mahmoudi
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Hamid Chalian
- Department of Radiology, Cardiothoracic Imaging, University of Washington, Seattle, WA 98195, USA
| | - Bradley J. Erickson
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| |
Collapse
|
3
|
Çallı E, Murphy K, Scholten ET, Schalekamp S, van Ginneken B. Explainable emphysema detection on chest radiographs with deep learning. PLoS One 2022; 17:e0267539. [PMID: 35900979 PMCID: PMC9333227 DOI: 10.1371/journal.pone.0267539] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2021] [Accepted: 04/12/2022] [Indexed: 12/02/2022] Open
Abstract
We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.
Collapse
Affiliation(s)
- Erdi Çallı
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
- * E-mail:
| | - Keelin Murphy
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| | - Ernst T. Scholten
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| | - Steven Schalekamp
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| | - Bram van Ginneken
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| |
Collapse
|
4
|
Kim Y, Hyon Y, Jung SS, Lee S, Yoo G, Chung C, Ha T. Respiratory sound classification for crackles, wheezes, and rhonchi in the clinical field using deep learning. Sci Rep 2021; 11:17186. [PMID: 34433880 PMCID: PMC8387488 DOI: 10.1038/s41598-021-96724-7] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2021] [Accepted: 08/12/2021] [Indexed: 11/09/2022] Open
Abstract
Auscultation has been essential part of the physical examination; this is non-invasive, real-time, and very informative. Detection of abnormal respiratory sounds with a stethoscope is important in diagnosing respiratory diseases and providing first aid. However, accurate interpretation of respiratory sounds requires clinician's considerable expertise, so trainees such as interns and residents sometimes misidentify respiratory sounds. To overcome such limitations, we tried to develop an automated classification of breath sounds. We utilized deep learning convolutional neural network (CNN) to categorize 1918 respiratory sounds (normal, crackles, wheezes, rhonchi) recorded in the clinical setting. We developed the predictive model for respiratory sound classification combining pretrained image feature extractor of series, respiratory sound, and CNN classifier. It detected abnormal sounds with an accuracy of 86.5% and the area under the ROC curve (AUC) of 0.93. It further classified abnormal lung sounds into crackles, wheezes, or rhonchi with an overall accuracy of 85.7% and a mean AUC of 0.92. On the other hand, as a result of respiratory sound classification by different groups showed varying degree in terms of accuracy; the overall accuracies were 60.3% for medical students, 53.4% for interns, 68.8% for residents, and 80.1% for fellows. Our deep learning-based classification would be able to complement the inaccuracies of clinicians' auscultation, and it may aid in the rapid diagnosis and appropriate treatment of respiratory diseases.
Collapse
Affiliation(s)
- Yoonjoo Kim
- Division of Pulmonology and Critical Care Medicine, Department of Internal Medicine, College of Medicine, Chungnam National University, Daejeon, 34134, Republic of Korea
| | - YunKyong Hyon
- Division of Medical Mathematics, National Institute for Mathematical Sciences, Daejeon, 34047, Republic of Korea
| | - Sung Soo Jung
- Division of Pulmonology and Critical Care Medicine, Department of Internal Medicine, College of Medicine, Chungnam National University, Daejeon, 34134, Republic of Korea
| | - Sunju Lee
- Division of Medical Mathematics, National Institute for Mathematical Sciences, Daejeon, 34047, Republic of Korea
| | - Geon Yoo
- Clinical Research Division, National Institute of Food and Drug Safety Evaluation, Cheongju-si, Chungcheongbuk-do, Republic of Korea
| | - Chaeuk Chung
- Division of Pulmonology and Critical Care Medicine, Department of Internal Medicine, College of Medicine, Chungnam National University, Daejeon, 34134, Republic of Korea. .,Infection Control Convergence Research Center, Chungnam National University School of Medicine, Daejeon, 35015, Republic of Korea.
| | - Taeyoung Ha
- Division of Medical Mathematics, National Institute for Mathematical Sciences, Daejeon, 34047, Republic of Korea.
| |
Collapse
|