Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features
Objectives: To differentiate invasive lepidic predominant adenocarcinoma (iLPA) from adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) of lung utilizing visual semantic and computer-aided detection (CAD)-based texture features on subjects initially diagnosed as AIS or MIA with CT-...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Medical Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3271/12/4/57 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850035655584776192 |
|---|---|
| author | Sean F. Johnson Seyed Mohammad Hossein Tabatabaei Grace Hyun J. Kim Bianca E. Villegas Matthew Brown Scott Genshaft Robert D. Suh Igor Barjaktarevic William Dean Wallace Fereidoun Abtin |
| author_facet | Sean F. Johnson Seyed Mohammad Hossein Tabatabaei Grace Hyun J. Kim Bianca E. Villegas Matthew Brown Scott Genshaft Robert D. Suh Igor Barjaktarevic William Dean Wallace Fereidoun Abtin |
| author_sort | Sean F. Johnson |
| collection | DOAJ |
| description | Objectives: To differentiate invasive lepidic predominant adenocarcinoma (iLPA) from adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) of lung utilizing visual semantic and computer-aided detection (CAD)-based texture features on subjects initially diagnosed as AIS or MIA with CT-guided biopsy. Materials and Methods: From 2011 to 2017, all patients with CT-guided biopsy results of AIS or MIA who subsequently underwent resection were identified. CT scan before the biopsy was used to assess visual semantic and CAD texture features, totaling 23 semantic and 95 CAD-based quantitative texture variables. The least absolute shrinkage and selection operator (LASSO) method or forward selection was used to select the most predictive feature and combination of semantic and texture features for detection of invasive lung adenocarcinoma. Results: Among the 33 core needle-biopsied patients with AIS/MIA pathology, 24 (72.7%) had invasive LPA and 9 (27.3%) had AIS/MIA on resection. On CT, visual semantic features included 21 (63.6%) part-solid, 5 (15.2%) pure ground glass, and 7 (21.2%) solid nodules. LASSO selected seven variables for the model, but all were not statistically significant. “Volume” was found to be statistically significant when assessing the correlation between independent variables using the backward selection technique. The LASSO selected “tumor_Perc95”, “nodule surround”, “small cyst-like spaces”, and “volume” when assessing the correlation between independent variables. Conclusions: Lung biopsy results showing noninvasive LPA underestimate invasiveness. Although statistically non-significant, some semantic features showed potential for predicting invasiveness, with septal stretching absent in all noninvasive cases, and solid consistency present in a significant portion of invasive cases. |
| format | Article |
| id | doaj-art-aa1b27bbb46f4463925399c03520b691 |
| institution | DOAJ |
| issn | 2076-3271 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medical Sciences |
| spelling | doaj-art-aa1b27bbb46f4463925399c03520b6912025-08-20T02:57:26ZengMDPI AGMedical Sciences2076-32712024-10-011245710.3390/medsci12040057Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic FeaturesSean F. Johnson0Seyed Mohammad Hossein Tabatabaei1Grace Hyun J. Kim2Bianca E. Villegas3Matthew Brown4Scott Genshaft5Robert D. Suh6Igor Barjaktarevic7William Dean Wallace8Fereidoun Abtin9Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Pulmonary and Critical Care Medicine, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USADepartment of Pathology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90089, USADepartment of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90024, USAObjectives: To differentiate invasive lepidic predominant adenocarcinoma (iLPA) from adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) of lung utilizing visual semantic and computer-aided detection (CAD)-based texture features on subjects initially diagnosed as AIS or MIA with CT-guided biopsy. Materials and Methods: From 2011 to 2017, all patients with CT-guided biopsy results of AIS or MIA who subsequently underwent resection were identified. CT scan before the biopsy was used to assess visual semantic and CAD texture features, totaling 23 semantic and 95 CAD-based quantitative texture variables. The least absolute shrinkage and selection operator (LASSO) method or forward selection was used to select the most predictive feature and combination of semantic and texture features for detection of invasive lung adenocarcinoma. Results: Among the 33 core needle-biopsied patients with AIS/MIA pathology, 24 (72.7%) had invasive LPA and 9 (27.3%) had AIS/MIA on resection. On CT, visual semantic features included 21 (63.6%) part-solid, 5 (15.2%) pure ground glass, and 7 (21.2%) solid nodules. LASSO selected seven variables for the model, but all were not statistically significant. “Volume” was found to be statistically significant when assessing the correlation between independent variables using the backward selection technique. The LASSO selected “tumor_Perc95”, “nodule surround”, “small cyst-like spaces”, and “volume” when assessing the correlation between independent variables. Conclusions: Lung biopsy results showing noninvasive LPA underestimate invasiveness. Although statistically non-significant, some semantic features showed potential for predicting invasiveness, with septal stretching absent in all noninvasive cases, and solid consistency present in a significant portion of invasive cases.https://www.mdpi.com/2076-3271/12/4/57lung biopsyinvasiveness predictionlepidic predominant adenocarcinomasemantic featuresradiomic features |
| spellingShingle | Sean F. Johnson Seyed Mohammad Hossein Tabatabaei Grace Hyun J. Kim Bianca E. Villegas Matthew Brown Scott Genshaft Robert D. Suh Igor Barjaktarevic William Dean Wallace Fereidoun Abtin Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features Medical Sciences lung biopsy invasiveness prediction lepidic predominant adenocarcinoma semantic features radiomic features |
| title | Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features |
| title_full | Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features |
| title_fullStr | Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features |
| title_full_unstemmed | Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features |
| title_short | Predicting Invasiveness in Lepidic Pattern Adenocarcinoma of Lung: Analysis of Visual Semantic and Radiomic Features |
| title_sort | predicting invasiveness in lepidic pattern adenocarcinoma of lung analysis of visual semantic and radiomic features |
| topic | lung biopsy invasiveness prediction lepidic predominant adenocarcinoma semantic features radiomic features |
| url | https://www.mdpi.com/2076-3271/12/4/57 |
| work_keys_str_mv | AT seanfjohnson predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT seyedmohammadhosseintabatabaei predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT gracehyunjkim predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT biancaevillegas predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT matthewbrown predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT scottgenshaft predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT robertdsuh predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT igorbarjaktarevic predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT williamdeanwallace predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures AT fereidounabtin predictinginvasivenessinlepidicpatternadenocarcinomaoflunganalysisofvisualsemanticandradiomicfeatures |