Dataset Information

Predicting EGFR mutational status from pathology images using a real-world dataset.

ABSTRACT: Treatment of non-small cell lung cancer is increasingly biomarker driven with multiple genomic alterations, including those in the epidermal growth factor receptor (EGFR) gene, that benefit from targeted therapies. We developed a set of algorithms to assess EGFR status and morphology using a real-world advanced lung adenocarcinoma cohort of 2099 patients with hematoxylin and eosin (H&E) images exhibiting high morphological diversity and low tumor content relative to public datasets. The best performing EGFR algorithm was attention-based and achieved an area under the curve (AUC) of 0.870, a negative predictive value (NPV) of 0.954 and a positive predictive value (PPV) of 0.410 in a validation cohort reflecting the 15% prevalence of EGFR mutations in lung adenocarcinoma. The attention model outperformed a heuristic-based model focused exclusively on tumor regions, and we show that although the attention model also extracts signal primarily from tumor morphology, it extracts additional signal from non-tumor tissue regions. Further analysis of high-attention regions by pathologists showed associations of predicted EGFR negativity with solid growth patterns and higher peritumoral immune presence. This algorithm highlights the potential of deep learning tools to provide instantaneous rule-out screening for biomarker alterations and may help prioritize the use of scarce tissue for biomarker testing.

SUBMITTER: Pao JJ

PROVIDER: S-EPMC10020556 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting EGFR mutational status from pathology images using a real-world dataset.

Pao James J JJ Biggs Mikayla M Duncan Daniel D Lin Douglas I DI Davis Richard R Huang Richard S P RSP Ferguson Donna D Janovitz Tyler T Hiemenz Matthew C MC Eddy Nathanial R NR Lehnert Erik E Cabili Moran N MN Frampton Garrett M GM Hegde Priti S PS Albacker Lee A LA

Scientific reports 20230316 1

Treatment of non-small cell lung cancer is increasingly biomarker driven with multiple genomic alterations, including those in the epidermal growth factor receptor (EGFR) gene, that benefit from targeted therapies. We developed a set of algorithms to assess EGFR status and morphology using a real-world advanced lung adenocarcinoma cohort of 2099 patients with hematoxylin and eosin (H&E) images exhibiting high morphological diversity and low tumor content relative to public datasets. The best per ...[more]

PMID: 36927889

Similar Datasets

Project description:BackgroundHippocampal sclerosis (HS) is the most common pathological type of temporal lobe epilepsy (TLE) and one of the important surgical markers. Currently, HS is mainly diagnosed manually by radiologists based on visual inspection of MRI, which greatly relies on MRI quality and physician experience. In clinical practice, non-thin MRI scans are often used due to the time and efficiency needed for the acquisition. However, these scans can be difficult for junior physicians to interpret accurately. Thus, the rapid and accurate diagnosis of HS using real-world MRI images in clinical settings is a challenging task.ObjectiveOur aim was to explore the feasibility of using computer vision methods to diagnose HS on real-world clinical MRI images and to provide a reference for future clinical applications of artificial intelligence methods to aid in detecting HS.MethodsWe proposed a deep learning algorithm called "HS-Net" to discriminate HS using real-world clinical MRI images. First, we delineated and segmented a region of interest (ROI) around the hippocampus. Then, we utilized the fractional differential (FD) method to enhance the textures of the ROIs. Finally, we used a small-sample image classification method based on transfer learning to fine-tune the feature extraction part of a pretrained model and added two fully connected layers and an output layer. In the study, 96 TLE patients with HS confirmed by postoperative pathology and 89 healthy controls were retrospectively enrolled. All subjects were cross-validated, and models were evaluated for performance, robustness, and clinical utility.ResultsThe HS-Net model achieved an area under the curve (AUC) of 0.894, an accuracy of 82.88%, an F1-score of 84.08% in the test cohort based on real, routine, clinical T2-weighted fluid attenuated inversion recovery (FLAIR) sequence MRI images. Additionally, the AUC, accuracy and F1 scores of our model all increased by around 3 percentage points when the inputs were augmented with the ROIs of the textures enhanced using the FD method.ConclusionsOur computational model has the potential to be used for the diagnosis of HS in real clinical MRI images, which could assist physicians, particularly junior physicians, in improving the accuracy of discrimination.

Project description:BackgroundTesting for epidermal growth factor receptor (EGFR) mutations is an essential recommendation in guidelines for metastatic non-squamous non-small-cell lung cancer, and is considered mandatory in European countries. However, in practice, challenges are often faced when carrying out routine biomarker testing, including access to testing, inadequate tissue samples and long turnaround times (TATs).Materials and methodsTo evaluate the real-world EGFR testing practices of European pathology laboratories, an online survey was set up and validated by the Pulmonary Pathology Working Group of the European Society of Pathology and distributed to 64 expert testing laboratories. The retrospective survey focussed on laboratory organisation and daily EGFR testing practice of pathologists and molecular biologists between 2018 and 2021.ResultsTATs varied greatly both between and within countries. These discrepancies may be partly due to reflex testing practices, as 20.8% of laboratories carried out EGFR testing only at the request of the clinician. Many laboratories across Europe still favour single-test sequencing as a primary method of EGFR mutation identification; 32.7% indicated that they only used targeted techniques and 45.1% used single-gene testing followed by next-generation sequencing (NGS), depending on the case. Reported testing rates were consistent over time with no significant decrease in the number of EGFR tests carried out in 2020, despite the increased pressure faced by testing facilities during the COVID-19 pandemic. ISO 15189 accreditation was reported by 42.0% of molecular biology laboratories for single-test sequencing, and by 42.3% for NGS. 92.5% of laboratories indicated they regularly participate in an external quality assessment scheme.ConclusionsThese results highlight the strong heterogeneity of EGFR testing that still occurs within thoracic pathology and molecular biology laboratories across Europe. Even among expert testing facilities there is variability in testing capabilities, TAT, reflex testing practice and laboratory accreditation, stressing the need to harmonise reimbursement technologies and decision-making algorithms in Europe.

Project description:BackgroundMedications targeting the glucagon-like peptide-1 (GLP-1) pathway are an important therapeutic class currently used for the treatment of Type 2 diabetes (T2D). However, there is not enough known about which subgroups of patients would receive the most benefit from these medications.ObjectiveThe goal of this study was to develop a predictive model for patient responsiveness to medications, here collectively called GLP-1 M, that include GLP-1 receptor agonists and dipeptidyl peptidase-4 (DPP4) inhibitors (that normally degrade endogenously-produced GLP-1). Such a model could guide clinicians to consider certain patient characteristics when prescribing second line medications for T2D.MethodsWe analyzed de-identified electronic health records of 7856 subjects with T2D treated with GLP-1 M drugs at Vanderbilt University Medical Center from 2003-2019. Using common clinical features (including commonly ordered lab tests, demographic information, other T2D medications, and diabetes-associated complications), we compared four different models: logistic regression, LightGBM, artificial neural network (ANN), and support vector classifier (SVC).ResultsOur analysis revealed that the traditional logistic regression model outperforms the other machine learning models, with an area under the Receiver Operating Characteristic curve (auROC) of 0.77.Our model showed that higher pre-treatment HbA1C is a dominant feature for predicting better response to GLP-1 M, while features such as use of thiazolidinediones or sulfonylureas is correlated with poorer response to GLP-1 M, as assessed by lowering of hemoglobin A1C (HbA1C), a standard marker of glycated hemoglobin used for assessing glycemic control in individuals with diabetes. Among female subjects under 40 taking GLP-1 M, the simultaneous use of non-steroidal anti-inflammatory drugs (NSAIDs) was associated with a greater reduction in HbA1C (0.82 ± 1.72% vs 0.28 ± 1.70%, p = 0.008).ConclusionThese findings indicate a thorough analysis of real-world electronic health records could reveal new information to improve treatment decisions for the treatment of T2D. The predictive model developed in this study highlights the importance of considering individual patient characteristics and medication interactions when prescribing GLP-1 M drugs.

Dataset Information

Predicting EGFR mutational status from pathology images using a real-world dataset.

Publications

Predicting EGFR mutational status from pathology images using a real-world dataset.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets