AI Article Synopsis
- Machine learning-based clinical decision support systems (CDSS) face challenges with transparency and reliability, as explainability often reduces predictive accuracy.
- A novel method called Rad4XCNN enhances the predictive power of CNN features while maintaining interpretability through Radiomics, moving beyond traditional saliency maps.
- In breast cancer classification tasks, Rad4XCNN demonstrates superior accuracy compared to other feature types and allows for global insights, effectively addressing the explainability-accuracy trade-off in AI models.
Article Abstract
Background And Objective: In recent years, machine learning-based clinical decision support systems (CDSS) have played a key role in the analysis of several medical conditions. Despite their promising capabilities, the lack of transparency in AI models poses significant challenges, particularly in medical contexts where reliability is a mandatory aspect. However, it appears that explainability is inversely proportional to accuracy. For this reason, achieving transparency without compromising predictive accuracy remains a key challenge.
Methods: This paper presents a novel method, namely Rad4XCNN, to enhance the predictive power of CNN-derived features with the inherent interpretability of radiomic features. Rad4XCNN diverges from conventional methods based on saliency maps, by associating intelligible meaning to CNN-derived features by means of Radiomics, offering new perspectives on explanation methods beyond visualization maps.
Results: Using a breast cancer classification task as a case study, we evaluated Rad4XCNN on ultrasound imaging datasets, including an online dataset and two in-house datasets for internal and external validation. Some key results are: (i) CNN-derived features guarantee more robust accuracy when compared against ViT-derived and radiomic features; (ii) conventional visualization map methods for explanation present several pitfalls; (iii) Rad4XCNN does not sacrifice model accuracy for their explainability; (iv) Rad4XCNN provides a global explanation enabling the physician to extract global insights and findings.
Conclusions: Our method can mitigate some concerns related to the explainability-accuracy trade-off. This study highlighted the importance of proposing new methods for model explanation without affecting their accuracy.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.cmpb.2024.108576 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Rad4XCNN: A new agnostic method for post-hoc global explanation of CNN-derived features by means of Radiomics.
Comput Methods Programs Biomed
January 2025
Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, 90127, Italy. Electronic address:
Article Synopsis
- Machine learning-based clinical decision support systems (CDSS) face challenges with transparency and reliability, as explainability often reduces predictive accuracy.
- A novel method called Rad4XCNN enhances the predictive power of CNN features while maintaining interpretability through Radiomics, moving beyond traditional saliency maps.
- In breast cancer classification tasks, Rad4XCNN demonstrates superior accuracy compared to other feature types and allows for global insights, effectively addressing the explainability-accuracy trade-off in AI models.
Improving prognostic accuracy in lung transplantation using unique features of isolated human lung radiographs.
NPJ Digit Med
October 2024
Latner Thoracic Research Laboratories, Toronto General Hospital Research Institute, University Health Network, Toronto, ON, Canada.
Ex vivo lung perfusion (EVLP) enables advanced assessment of human lungs for transplant suitability. We developed a convolutional neural network (CNN)-based approach to analyze the largest cohort of isolated lung radiographs to date. CNNs were trained to process 1300 longitudinal radiographs from n = 650 clinical EVLP cases.
View Article and Find Full Text PDFPrediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging.
Eur Stroke J
September 2023
Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK.
Background: In ischaemic stroke patients undergoing reperfusion therapy, the amount of salvageable tissue, that is, extent of the ischaemic penumbra, predicts the clinical outcomes. CT perfusion (CTP) enables quantification of penumbral tissues to guide decision making, and current programmes have automated its analysis. More advanced machine learning techniques utilising the CTP maps may improve prediction beyond the ischaemic volume measures.
View Article and Find Full Text PDFDeciphering multiple sclerosis disability with deep learning attention maps on clinical MRI.
Neuroimage Clin
June 2023
Multiple Sclerosis Centre of Catalonia (Cemcat), Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain. Electronic address:
The application of convolutional neural networks (CNNs) to MRI data has emerged as a promising approach to achieving unprecedented levels of accuracy when predicting the course of neurological conditions, including multiple sclerosis, by means of extracting image features not detectable through conventional methods. Additionally, the study of CNN-derived attention maps, which indicate the most relevant anatomical features for CNN-based decisions, has the potential to uncover key disease mechanisms leading to disability accumulation. From a cohort of patients prospectively followed up after a first demyelinating attack, we selected those with T1-weighted and T2-FLAIR brain MRI sequences available for image analysis and a clinical assessment performed within the following six months (N = 319).
View Article and Find Full Text PDFHeart rate estimation network from facial videos using spatiotemporal feature image.
Comput Biol Med
December 2022
Department of ECE, National Institute of Technology, Raipur 492010, India.
Remote health monitoring has become quite inevitable after SARS-CoV-2 pandemic and continues to be accepted as a measure of healthcare in future too. However, contact-less measurement of vital sign, like Heart Rate(HR) is quite difficult to measure because, the amplitude of physiological signal is very weak and can be easily degraded due to noise. The various sources of noise are head movements, variation in illumination or acquisition devices.
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!