AI Article Synopsis
- The study aims to create a new multi-task learning model using attention encoders for better classification of non-small cell lung cancer (NSCLC) subtypes and stages, outperforming existing deep-learning methods.
- Data from six public datasets were analyzed, totaling 4548 CT slices from 758 NSCLC patients, with models integrating attention mechanisms to improve classification accuracy.
- The MobileNet-based model improved performance significantly, with high AUC scores (0.963 for subtypes and 0.966 for staging), demonstrating a clear advantage over models without attention mechanisms and single-task configurations.
Article Abstract
Objectives: The objective of this study is to develop a novel multi-task learning approach with attention encoders for classifying histologic subtypes and clinical stages of non-small cell lung cancer (NSCLC), with superior performance compared to currently popular deep-learning models.
Material And Methods: Data were collected from six publicly available datasets in The Cancer Imaging Archive (TCIA). Following the inclusion and exclusion criteria, a total of 4548 CT slices from 758 cases were allocated. We evaluated multiple multi-task learning models that integrate attention mechanisms to resolve challenges in NSCLC subtype classification and clinical staging. These models utilized convolution-based modules in their shared layers for feature extraction, while the task layers were dedicated to histological subtype classification and staging. Each branch sequentially processed features through convolution-based and attention-based modules prior to classification.
Results: Our study evaluated 758 NSCLC patients (mean age, 66.2 years ± 10.3; 473 men), spanning ADC and SCC cases. In the classification of histological subtypes and clinical staging of NSCLC, the MobileNet-based multi-task learning model enhanced with attention mechanisms (MN-MTL-A) demonstrated superior performance, achieving Area Under the Curve (AUC) scores of 0.963 (95 % CI: 0.943, 0.981) and 0.966 (95 % CI: 0.945, 0.982) for each task, respectively. The model significantly surpassed its counterparts lacking attention mechanisms and those configured for single-task learning, as evidenced by P-values of 0.01 or less for both tasks, according to DeLong's test.
Conclusions: The integration of attention encoder blocks into our multi-task learning network significantly enhanced the accuracy of NSCLC histological subtyping and clinical staging. Given the reduced reliance on precise radiologist annotation, our proposed model shows promising potential for clinical application.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ijmedinf.2024.105694 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Automated Distal Radius and Ulna Skeletal Maturity Grading from Hand Radiographs with an Attention Multi-Task Learning Method.
Tomography
November 2024
Department of Orthopaedics and Traumatology, The University of Hong Kong, Hong Kong 999077.
Assessment of skeletal maturity is a common clinical practice to investigate adolescent growth and endocrine disorders. The distal radius and ulna (DRU) maturity classification is a practical and easy-to-use scheme that was designed for adolescent idiopathic scoliosis clinical management and presents high sensitivity in predicting the growth peak and cessation among adolescents. However, time-consuming and error-prone manual assessment limits DRU in clinical application.
View Article and Find Full Text PDFMulti-Task Deep Neural Networks for Irregularly Sampled Multivariate Clinical Time Series.
Proc (IEEE Int Conf Healthc Inform)
June 2024
College of Medicine, University of Florida, Gainesville, FL, USA.
Multivariate clinical time series data, such as those contained in Electronic Health Records (EHR), often exhibit high levels of irregularity, notably, many missing values and varying time intervals. Existing methods usually construct deep neural network architectures that combine recurrent neural networks and time decay mechanisms to model variable correlations, impute missing values, and capture the impact of varying time intervals. The complete data matrices thus obtained from the imputation task are used for downstream risk prediction tasks.
View Article and Find Full Text PDFDrug toxicity prediction model based on enhanced graph neural network.
Comput Biol Med
December 2024
Faculty of Computer and AI, Cairo University, Egypt. Electronic address:
Prediction of drug toxicity remains a significant challenge and an essential process in drug discovery. Traditional machine learning algorithms struggle to capture the full scope of molecular structure features, limiting their effectiveness in toxicity prediction. Graph Neural Network offers a promising solution by effectively extracting drug features from their molecular graphs.
View Article and Find Full Text PDFConcordance-based Predictive Uncertainty (CPU)-Index: Proof-of-concept with application towards improved specificity of lung cancers on low dose screening CT.
Artif Intell Med
December 2024
Department of Electrical and Computer Engineering, Duke University, Durham, NC, United States of America; Medical Physics Graduate Program, Duke University, Durham, NC, United States of America; Department of Radiology, Duke University, Durham, NC, United States of America; Department of Biomedical Engineering, Duke University, Durham, NC, United States of America; Department of Radiation Oncology, Duke University, Durham, NC, United States of America; Department of Pathology, Duke University, Durham, NC, United States of America. Electronic address:
In this paper, we introduce a novel concordance-based predictive uncertainty (CPU)-Index, which integrates insights from subgroup analysis and personalized AI time-to-event models. Through its application in refining lung cancer screening (LCS) predictions generated by an individualized AI time-to-event model trained with fused data of low dose CT (LDCT) radiomics with patient demographics, we demonstrate its effectiveness, resulting in improved risk assessment compared to the Lung CT Screening Reporting & Data System (Lung-RADS). Subgroup-based Lung-RADS faces challenges in representing individual variations and relies on a limited set of predefined characteristics, resulting in variable predictions.
View Article and Find Full Text PDFAccurate intra-operative Remaining Surgery Duration (RSD) predictions allow for anaesthetists to more accurately decide when to administer anaesthetic agents and drugs, as well as to notify hospital staff to send in the next patient. Therefore, RSD plays an important role in improved patient care and minimising surgical theatre costs via efficient scheduling. In endoscopic pituitary surgery, it is uniquely challenging due to variable workflow sequences with a selection of optional steps contributing to high variability in surgery duration.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!