Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review
The objective of this systematic review was to analyze the current state of the art of imaging-derived biomarkers predictive of genetic alterations and immunotherapy targets in lung cancer. We included original research studies reporting the development and validation of imaging feature-based models...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/10/6/359 |
| _version_ | 1827715882618454016 |
|---|---|
| author | Gaia Ninatti Margarita Kirienko Emanuele Neri Martina Sollini Arturo Chiti |
| author_facet | Gaia Ninatti Margarita Kirienko Emanuele Neri Martina Sollini Arturo Chiti |
| author_sort | Gaia Ninatti |
| collection | DOAJ |
| description | The objective of this systematic review was to analyze the current state of the art of imaging-derived biomarkers predictive of genetic alterations and immunotherapy targets in lung cancer. We included original research studies reporting the development and validation of imaging feature-based models. The overall quality, the standard of reporting and the advancements towards clinical practice were assessed. Eighteen out of the 24 selected articles were classified as “high-quality” studies according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). The 18 “high-quality papers” adhered to Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) with a mean of 62.9%. The majority of “high-quality” studies (16/18) were classified as phase II. The most commonly used imaging predictors were radiomic features, followed by visual qualitative computed tomography (CT) features, convolutional neural network-based approaches and positron emission tomography (PET) parameters, all used alone or combined with clinicopathologic features. The majority (14/18) were focused on the prediction of epidermal growth factor receptor (EGFR) mutation. Thirty-five imaging-based models were built to predict the EGFR status. The model’s performances ranged from weak (<i>n</i> = 5) to acceptable (<i>n</i> = 11), to excellent (<i>n</i> = 18) and outstanding (<i>n</i> = 1) in the validation set. Positive outcomes were also reported for the prediction of ALK rearrangement, ALK/ROS1/RET fusions and programmed cell death ligand 1 (PD-L1) expression. Despite the promising results in terms of predictive performance, image-based models, suffering from methodological bias, require further validation before replacing traditional molecular pathology testing. |
| first_indexed | 2024-03-10T19:29:03Z |
| format | Article |
| id | doaj.art-c726410a056c43b881970a46a9fcacd8 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T19:29:03Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-c726410a056c43b881970a46a9fcacd82023-11-20T02:20:07ZengMDPI AGDiagnostics2075-44182020-05-0110635910.3390/diagnostics10060359Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic ReviewGaia Ninatti0Margarita Kirienko1Emanuele Neri2Martina Sollini3Arturo Chiti4Humanitas University, Pieve Emanuele, 20090 Milan, ItalyFondazione IRCCS Istituto Nazionale dei Tumori, 20133 Milan, ItalyDepartment of Translational Research, Diagnostic Radiology 3, University of Pisa, 56126 Pisa, ItalyHumanitas University, Pieve Emanuele, 20090 Milan, ItalyHumanitas University, Pieve Emanuele, 20090 Milan, ItalyThe objective of this systematic review was to analyze the current state of the art of imaging-derived biomarkers predictive of genetic alterations and immunotherapy targets in lung cancer. We included original research studies reporting the development and validation of imaging feature-based models. The overall quality, the standard of reporting and the advancements towards clinical practice were assessed. Eighteen out of the 24 selected articles were classified as “high-quality” studies according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). The 18 “high-quality papers” adhered to Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) with a mean of 62.9%. The majority of “high-quality” studies (16/18) were classified as phase II. The most commonly used imaging predictors were radiomic features, followed by visual qualitative computed tomography (CT) features, convolutional neural network-based approaches and positron emission tomography (PET) parameters, all used alone or combined with clinicopathologic features. The majority (14/18) were focused on the prediction of epidermal growth factor receptor (EGFR) mutation. Thirty-five imaging-based models were built to predict the EGFR status. The model’s performances ranged from weak (<i>n</i> = 5) to acceptable (<i>n</i> = 11), to excellent (<i>n</i> = 18) and outstanding (<i>n</i> = 1) in the validation set. Positive outcomes were also reported for the prediction of ALK rearrangement, ALK/ROS1/RET fusions and programmed cell death ligand 1 (PD-L1) expression. Despite the promising results in terms of predictive performance, image-based models, suffering from methodological bias, require further validation before replacing traditional molecular pathology testing.https://www.mdpi.com/2075-4418/10/6/359radiogenomicsCTPET/CTlung cancerEGFRALK |
| spellingShingle | Gaia Ninatti Margarita Kirienko Emanuele Neri Martina Sollini Arturo Chiti Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review Diagnostics radiogenomics CT PET/CT lung cancer EGFR ALK |
| title | Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review |
| title_full | Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review |
| title_fullStr | Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review |
| title_full_unstemmed | Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review |
| title_short | Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review |
| title_sort | imaging based prediction of molecular therapy targets in nsclc by radiogenomics and ai approaches a systematic review |
| topic | radiogenomics CT PET/CT lung cancer EGFR ALK |
| url | https://www.mdpi.com/2075-4418/10/6/359 |
| work_keys_str_mv | AT gaianinatti imagingbasedpredictionofmoleculartherapytargetsinnsclcbyradiogenomicsandaiapproachesasystematicreview AT margaritakirienko imagingbasedpredictionofmoleculartherapytargetsinnsclcbyradiogenomicsandaiapproachesasystematicreview AT emanueleneri imagingbasedpredictionofmoleculartherapytargetsinnsclcbyradiogenomicsandaiapproachesasystematicreview AT martinasollini imagingbasedpredictionofmoleculartherapytargetsinnsclcbyradiogenomicsandaiapproachesasystematicreview AT arturochiti imagingbasedpredictionofmoleculartherapytargetsinnsclcbyradiogenomicsandaiapproachesasystematicreview |