Ignite Creation Date:
2024-10-25 @ 8:01 PM
Last Modification Date:
2024-10-26 @ 3:40 PM
Study NCT ID:
NCT06602674
Status:
ACTIVE_NOT_RECRUITING
Last Update Posted:
None
First Post:
2024-09-11
Brief Title:
PETCT-Based Image Analysis and Machine Learning of Hypermetabolic Pulmonary Lesions
Sponsor:
None
Organization:
None
Study Overview
Official Title:
PETCT Imaging-Based Distinction of Pulmonary Lymphoma and Other Hypermetabolic Lesions Via Imaging Manifestations and Machine Learning Techniques a Multicenter Retrospective Study
Status:
ACTIVE_NOT_RECRUITING
Status Verified Date:
2024-09
Last Known Status:
None
Delayed Posting:
No
If Stopped, Why?:
Not Stopped
Has Expanded Access:
No
If Expanded Access, NCT#:
N/A
Has Expanded Access, NCT# Status:
N/A
Acronym:
None
Brief Summary:
First we analyse the types imaging findings and relevant treatment responses based on PETCT to complete a more comprehensive view of pulmonary lymphomas
Then some models based on radiomics features will be developed to verify the possibility of differentiating pulmonary lymphomas via machine learning and develop a multi-class classification model
The final objective of this study is to develop a set of deep learning models for preliminary lung lesion segmentation and multi-class classification The models will classify FDG-avid lung lesions into four groups each defined by their pathological origin primary therapy and relevant clinical department
Then some models based on radiomics features will be developed to verify the possibility of differentiating pulmonary lymphomas via machine learning and develop a multi-class classification model
The final objective of this study is to develop a set of deep learning models for preliminary lung lesion segmentation and multi-class classification The models will classify FDG-avid lung lesions into four groups each defined by their pathological origin primary therapy and relevant clinical department
Detailed Description:
1 The local image feature extraction software LIFEx v 740 France was employed for the image review and measurement of relevant data Three observers independently interpreted the images In cases of disagreement the opinion of a senior doctor with over a decade of experience was given precedence The imaging findings were recorded based on the baseline examinations Lesion counts locations and descriptive labels were systematically logged in accordance with the norms set out in imaging report The statistical software SPSS v260 was used in data sorting and calculation Chi-square test was employed to compare SPL and PPL based on categorical variables like CT findings while T-test was used to assess continuous variables like glycemia and SUV Given the predominance of categorical variables chi-square or Fisher39s exact test for samples lt40 or gt20 cells with lt5 expected counts was utilised to assess treatment response and imaging performance Spearman39s correlation coefficient was employed to analyse the relationship between categorical and SUV-based continuous variables
2 In this study the metabolic tumor volume at a relative threshold of 40 MTV40 was selected as the volume of interest VOI for image analysis For feature extraction we employed the Python v3117-based radiomics feature extraction toolkit PyRadiomics v310 along with the medical image processing library SimpleITK v231 the numerical computation and data manipulation library Numpy v1262 and the wavelet transform library PyWavelet v150 Feature selection was conducted using RStudio v2023120369 based on the R programming language v420 To ensure computational efficiency and avoid overfitting the number of features retained was limited to 10 or less of the number of lesions in the training set Model analysis and validation were primarily performed using RStudio as well
3 The deep learning study divides the task of identifying and classifying hypermetabolic lung lesions into two stages segmentation and classification In the segmentation stage we first utilized the open-source 2D model Lungmask to automatically crop the lung region from whole-body PETCT images ensuring that subsequent processing is focused on the lung area Next we developed a 3D UNet model with residual modules specifically designed for segmenting hypermetabolic lung lesions This model takes the cropped PETCT images as input efficiently extracting lesion information from the three-dimensional images and accurately segmenting the hypermetabolic lung lesion areasThe model was then applied to both internal test sets and external validation sets for inference resulting in the extraction of lesion-containing ROIs
2 In this study the metabolic tumor volume at a relative threshold of 40 MTV40 was selected as the volume of interest VOI for image analysis For feature extraction we employed the Python v3117-based radiomics feature extraction toolkit PyRadiomics v310 along with the medical image processing library SimpleITK v231 the numerical computation and data manipulation library Numpy v1262 and the wavelet transform library PyWavelet v150 Feature selection was conducted using RStudio v2023120369 based on the R programming language v420 To ensure computational efficiency and avoid overfitting the number of features retained was limited to 10 or less of the number of lesions in the training set Model analysis and validation were primarily performed using RStudio as well
3 The deep learning study divides the task of identifying and classifying hypermetabolic lung lesions into two stages segmentation and classification In the segmentation stage we first utilized the open-source 2D model Lungmask to automatically crop the lung region from whole-body PETCT images ensuring that subsequent processing is focused on the lung area Next we developed a 3D UNet model with residual modules specifically designed for segmenting hypermetabolic lung lesions This model takes the cropped PETCT images as input efficiently extracting lesion information from the three-dimensional images and accurately segmenting the hypermetabolic lung lesion areasThe model was then applied to both internal test sets and external validation sets for inference resulting in the extraction of lesion-containing ROIs
Study Oversight
Has Oversight DMC:
None
Is a FDA Regulated Drug?:
None
Is a FDA Regulated Device?:
None
Is an Unapproved Device?:
None
Is a PPSD?:
None
Is a US Export?:
None
Is an FDA AA801 Violation?:
None