Name: Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Uploaded: 2023-10-13T15:00:00
Description: Watch this Scientific Journal Video about Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer at JoVE.com

This publication was supported by the fifth national traditional Chinese medicine clinical excellent talents research program organized by the National Administration of Traditional Chinese Medicine. The official network link is&#160;http://www.natcm.gov.cn/renjiaosi/zhengcewenjian/2021-11-04/23082.html.

For the present study, ethical clearance was obtained from The Ethics Committee of Dongzhimen Hospital, affiliated with Beijing University of Chinese Medicine (DZMEC-KY-2019.90). In this specific case, a methodical description of the research approach is provided, outlining a case involving a 65-year-old female patient with multiple pulmonary nodules. This patient provided informed consent for her diagnosis through digital modeling and authorized the use of her data for scientific research purposes. The model reconstruct...

Enhancing Pulmonary Nodule Diagnosis Using Whole-Lung 3D Reconstruction

<ol>
	<li>Mazzone, P. J., Lam, L. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Evaluating+the+patient+with+a+pulmonary+nodule:+A+review.">Evaluating the patient with a pulmonary nodule: A review.</a> JAMA. 327 (3), 264-273 (2022).</li><li>MacMahon, H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Guidelines+for+management+of+incidental+pulmonary+nodules+detected+on+ct+images:+from+the+fleischner+society.">Guidelines for management of incidental pulmonary nodules detected on ct images: from the fleischner society.</a> Radiology. 284 (1), 228-243 (2017).</li><li>Yankelevitz, D. F., Yip, R., Henschke, C. I. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Impact+of+duration+of+diagnostic+workup+on+prognosis+for+early+lung+cancer.">Impact of duration of diagnostic workup on prognosis for early lung cancer.</a> Journal of Thoracic Oncology. 18 (4), 527-537 (2023).</li><li>Zhao, W., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=PUNDIT:+Pulmonary+nodule+detection+with+image+category+transformation.">PUNDIT: Pulmonary nodule detection with image category transformation.</a> Medical Physics. 50, 2914-2927 (2023).</li><li>Ather, S., Kadir, T., Gleeson, F. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Artificial+intelligence+and+radiomics+in+pulmonary+nodule+management:+current+status+and+future+applications.">Artificial intelligence and radiomics in pulmonary nodule management: current status and future applications.</a> Clinical Radiology. 75 (1), 13-19 (2020).</li><li>Gruden, J. F., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Incremental+benefit+of+maximum-intensity-projection+images+on+observer+detection+of+small+pulmonary+nodules+revealed+by+multidetector+CT.">Incremental benefit of maximum-intensity-projection images on observer detection of small pulmonary nodules revealed by multidetector CT.</a> American Journal of Roentgenology. 179 (1), 149-157 (2002).</li><li>Guleryuz Kizil, P., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Diagnostic+importance+of+maximum+intensity+projection+technique+in+the+identification+of+small+pulmonary+nodules+with+computed+tomography.">Diagnostic importance of maximum intensity projection technique in the identification of small pulmonary nodules with computed tomography.</a> Tuberk Toraks. 68 (1), 35-42 (2020).</li><li>Valencia, R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Value+of+axial+and+coronal+maximum+intensity+projection+(MIP)+images+in+the+detection+of+pulmonary+nodules+by+multislice+spiral+CT:+comparison+with+axial+1-mm+and+5-mm+slices.">Value of axial and coronal maximum intensity projection (MIP) images in the detection of pulmonary nodules by multislice spiral CT: comparison with axial 1-mm and 5-mm slices.</a> European Radiology. 16, 325-332 (2006).</li><li>Jabeen, N., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Diagnostic+accuracy+of+maximum+intensity+projection+in+diagnosis+of+malignant+pulmonary+nodules.">Diagnostic accuracy of maximum intensity projection in diagnosis of malignant pulmonary nodules.</a> Cureus. 11 (11), e6120 (2019).</li><li>Naeem, M., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Comparison+of+maximum+intensity+projection+and+volume+rendering+in+detecting+pulmonary+nodules+on+multidetector+computed+tomography.">Comparison of maximum intensity projection and volume rendering in detecting pulmonary nodules on multidetector computed tomography.</a> Cureus. 13 (3), e14025 (2021).</li><li>Bianconi, F., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Comparative+evaluation+of+conventional+and+deep+learning+methods+for+semi-automated+segmentation+of+pulmonary+nodules+on+CT.">Comparative evaluation of conventional and deep learning methods for semi-automated segmentation of pulmonary nodules on CT.</a> Quantitative Imaging in Medicine and Surgery. 11 (7), 3286-3305 (2021).</li><li>Christe, A., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Computer-aided+diagnosis+of+pulmonary+fibrosis+using+deep+learning+and+CT+images.">Computer-aided diagnosis of pulmonary fibrosis using deep learning and CT images.</a> Investigative Radiology. 54 (10), 627-632 (2019).</li><li>Kim, Y., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Applications+of+artificial+intelligence+in+the+thorax:+a+narrative+review+focusing+on+thoracic+radiology.">Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology.</a> Journal of Thoracic Disease. 13 (12), 6943-6962 (2021).</li><li>Schreuder, A., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Artificial+intelligence+for+detection+and+characterization+of+pulmonary+nodules+in+lung+cancer+CT+screening:+ready+for+practice.">Artificial intelligence for detection and characterization of pulmonary nodules in lung cancer CT screening: ready for practice.</a> Translational Lung Cancer Research. 10 (5), 2378-2388 (2021).</li><li>Zheng, S., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Automatic+pulmonary+nodule+detection+in+CT+scans+using+convolutional+neural+networks+based+on+maximum+intensity+projection.">Automatic pulmonary nodule detection in CT scans using convolutional neural networks based on maximum intensity projection.</a> IEEE Transactions on Medical Imaging. 39 (3), 797-805 (2019).</li><li>Yabuuchi, H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Clinical+application+of+radiation+dose+reduction+for+head+and+neck+CT.">Clinical application of radiation dose reduction for head and neck CT.</a> European Journal of Radiology. 107, 209-215 (2018).</li><li>Rana, B., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Regions-of-interest+based+automated+diagnosis+of+Parkinson's+disease+using+T1-weighted+MRI.">Regions-of-interest based automated diagnosis of Parkinson's disease using T1-weighted MRI.</a> Expert Systems with Applications. 42 (9), 4506-4516 (2015).</li></ol>

This research introduces a unique approach for creating a complete three-dimensional (3D) reconstruction of the entire lung, employing advanced medical image processing techniques to delineate the lung&#39;s 3D shape amidst the context of a full chest scan. This technique offers a more precise and thorough depiction of the spatial arrangement and radiological characteristics of early multiple nodules across the entire lung. This study makes a valuable contribution to enhancing the accuracy and efficacy of diagnostic and ...

Early multiple pulmonary nodules, which are small, round growths on the lung, can be benign or malignant1,2,3. Although solitary pulmonary nodules are easier to diagnose and treat, patients with early multiple pulmonary nodules face significant diagnostic and treatment challenges. To develop effective treatment plans, it is essential to accurately identify the spatial distribution, size, location, and relationship with surrounding lung tissue of these nodules throughout the whole lung4,5. Traditional diagnostic methods have limitations in accurately identifying early multiple pulmonary nodules.
Recent advancements in medical image processing technology and machine learning algorithms have the potential to improve the accuracy and efficiency of early pulmonary nodule detection and diagnosis. Various approaches have been proposed, such as pattern recognition methods based on machine vision and visualization methods based on maximum intensity projection (MIP)6,7,8,9,10. However, these methods suffer from limitations such as false positives, false negatives11,12,13,14,15, and lack of macroscopic and holistic descriptions of the distribution and spatial features of early multiple pulmonary nodules.
To address these limitations, this study proposes a whole-lung 3D reconstruction method that utilizes medical image processing technology to extract the 3D contour of the lung against the background of the whole chest scan. The method then performs 3D reconstruction of the lung, pulmonary artery, and early multiple pulmonary nodules in 3D space. This approach allows for a more comprehensive and accurate representation of the spatial distribution and radiological features of early multiple nodules throughout the whole lung.
The proposed method involves several key steps. Firstly, the medical images are imported into the 3D image processing software, and the lung region is extracted using a threshold-based segmentation technique. Subsequently, the extracted lung region is separated from the surrounding chest wall and the bony structures of the thoracic vertebrae. The early multiple pulmonary nodules and their relationship with surrounding blood vessels are then reconstructed in 3D space using maximum intensity projection (MIP) algorithms. Finally, the reconstructed 3D model of the lung, pulmonary artery, and nodules is displayed for further analysis.
This method has several advantages over existing methods. Unlike traditional methods that rely on 2D images, this method utilizes 3D volume to provide a more accurate and comprehensive representation of early multiple pulmonary nodules. The method also overcomes the limitations of false positives and false negatives associated with pattern recognition methods and MIP visualization methods. Furthermore, this method provides a macroscopic and holistic description of the distribution and spatial features of early multiple pulmonary nodules, which is essential for developing effective treatment plans.
The proposed method has several potential applications in the diagnosis and treatment of early multiple pulmonary nodules. The accurate identification of the spatial distribution and radiological features of early multiple nodules can aid in the early diagnosis and treatment of lung cancer. Furthermore, the method can be used to monitor the progression of the disease and evaluate the effectiveness of treatment plans.
Pattern recognition methods6,7,8 based on machine vision have shown promise in identifying pulmonary nodules, but suffer from limitations such as false positives and false negatives. MIP visualization methods, on the other hand, provide a more accurate representation of individual nodules, but lack a macroscopic and holistic description of the distribution and spatial features of early multiple nodules. The proposed whole-lung 3D reconstruction method overcomes these limitations and provides a more accurate and comprehensive representation of early multiple pulmonary nodules.
Isovoxel transformation16,17refers to the process of converting 3D images with different voxel sizes into 3D images with uniform voxel sizes. In the field of medical image processing, 3D volumes are often composed of voxels with varying sizes, which can lead to computational and visualization issues. The purpose of isovoxel transformation is to address these issues by resampling and interpolating the voxels in the original 3D volume, resulting in a new 3D image with consistent voxel sizes. This technique finds applications in various medical contexts, including image registration, segmentation, and visualization. Thus, this study proposed a whole-lung 3D reconstruction method that utilizes medical image processing technology to extract the 3D contour of the lung against the background of the whole chest scan. The method provides a more accurate and comprehensive representation of the spatial distribution and radiological features of early multiple nodules throughout the whole lung. This study contributes to the development of more accurate and effective diagnostic and treatment strategies for patients with early multiple pulmonary nodules.

<table border="1" fo:keep-together.within-page="1" fo:keep-with-next.within-page="always">
	<tbody>
		<tr>
			<td>MATLAB</td>
			<td>MathWorks&#160;</td>
			<td>2022B</td>
			<td>Computing and visualization&#160;</td>
		</tr>
		<tr>
			<td>Tools for Modeling</td>
			<td>Intelligent Entropy</td>
			<td>PulmonaryNodule V1.0</td>
			<td>Beijing Intelligent Entropy Science &#38; Technology Co Ltd. 
			Modeling for CT/MRI fusion</td>
		</tr>
	</tbody>
</table>

three-dimensional reconstruction for the whole lung with early multiple pulmonary nodules

For patients with early multiple pulmonary nodules, it is essential, from a diagnostic perspective, to determine the spatial distribution, size, location, and relationship with surrounding lung tissue of these nodules throughout the entire lung. This is crucial for identifying the primary lesion and developing more scientifically grounded treatment plans for doctors. However, pattern recognition methods based on machine vision are susceptible to false positives and false negatives and, therefore, cannot fully meet clinical demands in this regard. Visualization methods based on maximum intensity projection (MIP) can better illustrate local and individual pulmonary nodules but lack a macroscopic and holistic description of the distribution and spatial features of multiple pulmonary nodules.
Therefore, this study proposes a whole-lung 3D reconstruction method. It extracts the 3D contour of the lung using medical image processing technology against the background of the entire lung and performs 3D reconstruction of the lung, pulmonary artery, and multiple pulmonary nodules in 3D space. This method can comprehensively depict the spatial distribution and radiological features of multiple nodules throughout the entire lung, providing a simple and convenient means of evaluating the diagnosis and prognosis of multiple pulmonary nodules.

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer 

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

This research develops a 3D modeling approach to comprehensively visualize multiple pulmonary nodules throughout the whole lung, aiming to improve the diagnosis and the treatment of early-stage lung cancer patients. The key questions are how to accurately reconstruct nodule distribution and interplay with lung tissue. Recent advance in deep learning and computer vision enable more accurate AI-assisted detection and segmentation of lung nodules.However, limitation persist regarding whole lung modeling and the spatial relationships between multiple nodules. This research offers progress through a 3D reconstruction technique for the entire lung. Integrating AI-driven medical imaging and visualization with specialist clinical diagnosis and treatment is critical.Technologies like deep learning for segmentation volumetric modeling, virtual augmented reality for 3D visualization and multimodal data fusion are advancing whole lung modeling and multinodule assessment to enhance clinical decision-making. This research establish a effective 3D modeling approach for visualizing the distribution and the spatial relationships of multiple pulmonary nodules across the whole lung volume. Key innovations include lung contour extraction, nodule reconstruction in 3D space, and interactive whole lung visualization.This enables more accurate diagnosis and treatment planning for early-lung cancer patients. Developing a accurate 3D modeling approach for visualizing whole lung nodule patterns provide a new capability for comprehending disease progression. This can enable earlier diagnosis, personalize the treatment plans and improve the outcomes for lung cancer patients.The findings lay the groundwork for expanding whole lung modeling using multimodal data and advancing clinical translation.

In the data preprocessing stage, DICOM data sorting should be the first step (Figure 1) to ensure the correct scan sequence for each layer during 3D reconstruction. Next, isotropic transformation is performed to ensure the correct aspect ratio of the 3D volume (Figure 2). Afterward, spatial filtering is applied to the original 3D volume (Figure 3) to eliminate interference signals from the patient couch of the CT equipment (<strong ...

Watch this Scientific Journal Video about Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer at JoVE.com

This study introduces a three-dimensional (3D) reconstruction method for the entire lung in patients with early multiple pulmonary nodules. It offers a comprehensive visualization of nodule distribution and their interplay with lung tissue, simplifying the assessment of diagnosis and prognosis for these patients.

For patients with early multiple pulmonary nodules, it is essential, from a diagnostic perspective, to determine the spatial distribution, size, location, ...

three-dimensional-reconstruction-for-whole-lung-with-early-multiple

Research

JoVE Journal

Medicine

Whole-Lung 3D Reconstruction Using Medical Image Processing Technology

To begin, copy the patient's digital imaging and communications in medicine, or DICOM data, to a defined working directory. Using the file browser, examine each file directory to identify the image sequence with the highest number of scanning layers for analysis. Employ the DICOM function within MATLAB by providing DICOM files as input to extract essential parameters, such as slice thickness and pixel spacing, directly in the MATLAB environment.Then retrieve the location data for each image and access the information via info. SliceLocation in MATLAB workspace. Next, use the slice location function to save the location data into a variable and generate a plot for it.Click the data tips button in the GUI's upper right corner to add data points and enhance the plot. Then use the volume resort function to organize all images and extract the images ranging from the first to the maximum location. Safeguard the volume data from the valid images along with their sorted index.Using the size function in MATLAB examine the three dimensional scale of a 3D volume. To view the 3D volume using the slice view command function, record the sequence scan range obtaining the lungs from 60 to 340. Then use the command to obtain a 3D volume containing all the data of the entire lung.Employ the MATLAB command function DICOM info to obtain the slice thickness of the image sequence. Use the command to calculate the number of Z axes for the isovoxel transformation. Then use the MATLAB command function imresize3 to perform isovoxel transformation on V one, employ the 3D slice view function to view the isovoxel transformed 3D volume.To remove the noise interference, use the data tips button to add continuous data points within the interactive interface. Next, right click on the data tips and select export cursor data to workspace to export the reference boundary for spatial filtering to the MATLAB workspace. Invoke the noise clean function to apply spatial filtering to V two using the input parameter CI from the workspace.Use this slice view command function to visualize the resulting volume. Select a template slice such as the two 32nd image for the image segmentation design and assign it to a variable. Then open the MATLAB image segmenter GUI by executing the image segmenter one command.Select the auto cluster tool from the toolbar at the top and click the left mouse button to execute the command. Next, click the show binary button in the upper right corner to display the image in black and white binary. To make the lung region white, select the invert mask button from the top toolbar and click the left mouse button for the execution of the command.To eliminate the white color outside the lung area, select the clear borders button to the top toolbar and click the left mouse button. Initiate the 3D lung volume function within the MATLAB workspace. Next, select maximize in the dropdown menu in the top right corner of the fourth view.Select MIP projection, and then choose the jet color map from the built-in color maps option below. Once more, invoke the slice view function, but this time input the entire lung's 3D volume. Within the resulting GUI, use the bottom scroll bar to navigate to the region where the dominant lung nodules are situated spanning scans 48 to 70.Use the 3D lung horizon function to conduct a 3D reconstruction of the region of interest, encompassing sections 48 to 70 from the whole lungs 3D volume.