Rad4XCNN: a new agnostic method for post-hoc global explanation of CNN-derived features by means of radiomics
- URL: http://arxiv.org/abs/2405.02334v1
- Date: Fri, 26 Apr 2024 15:02:39 GMT
- Title: Rad4XCNN: a new agnostic method for post-hoc global explanation of CNN-derived features by means of radiomics
- Authors: Francesco Prinzi, Carmelo Militello, Calogero Zarcaro, Tommaso Vincenzo Bartolotta, Salvatore Gaglio, Salvatore Vitabile,
- Abstract summary: This paper presents a novel method, namely Rad4XCNN, to enhance the predictive power of CNN-derived features with the interpretability inherent in radiomic features.
We evaluated Rad4XCNN on ultrasound imaging datasets, including an online dataset and two in-house datasets for internal and external validation.
- Score: 0.26200292205757436
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In the last years, artificial intelligence (AI) in clinical decision support systems (CDSS) played a key role in harnessing machine learning and deep learning architectures. Despite their promising capabilities, the lack of transparency and explainability of AI models poses significant challenges, particularly in medical contexts where reliability is a mandatory aspect. Achieving transparency without compromising predictive accuracy remains a key challenge. This paper presents a novel method, namely Rad4XCNN, to enhance the predictive power of CNN-derived features with the interpretability inherent in radiomic features. Rad4XCNN diverges from conventional methods based on saliency map, by associating intelligible meaning to CNN-derived features by means of Radiomics, offering new perspectives on explanation methods beyond visualization maps. 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 global explanation insights enabling the physician to analyze the model outputs and findings. In addition, we highlight the importance of integrating interpretability into AI models for enhanced trust and adoption in clinical practice, emphasizing how our method can mitigate some concerns related to explainable AI methods.
Related papers
- Explainable Transformer Prototypes for Medical Diagnoses [7.680878119988482]
Self-attention feature of transformers contributes towards identifying crucial regions during the classification process.
Our research endeavors to innovate a unique attention block that underscores the correlation between'regions' rather than 'pixels'
A combined quantitative and qualitative methodological approach was used to demonstrate the effectiveness of the proposed method on a large-scale NIH chest X-ray dataset.
arXiv Detail & Related papers (2024-03-11T17:46:21Z) - Enhancing Radiology Diagnosis through Convolutional Neural Networks for
Computer Vision in Healthcare [0.0]
CNNs in radiology diagnostics are examined, with a focus on interpretability, effectiveness, and ethical issues.
CNNs perform admirably in terms of particularity, sensitivity, as well as accuracy.
arXiv Detail & Related papers (2023-11-19T05:35:32Z) - Robust and Interpretable Medical Image Classifiers via Concept
Bottleneck Models [49.95603725998561]
We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts.
Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
arXiv Detail & Related papers (2023-10-04T21:57:09Z) - Transferability of coVariance Neural Networks and Application to
Interpretable Brain Age Prediction using Anatomical Features [119.45320143101381]
Graph convolutional networks (GCN) leverage topology-driven graph convolutional operations to combine information across the graph for inference tasks.
We have studied GCNs with covariance matrices as graphs in the form of coVariance neural networks (VNNs)
VNNs inherit the scale-free data processing architecture from GCNs and here, we show that VNNs exhibit transferability of performance over datasets whose covariance matrices converge to a limit object.
arXiv Detail & Related papers (2023-05-02T22:15:54Z) - Improving Interpretability of Deep Neural Networks in Medical Diagnosis
by Investigating the Individual Units [24.761080054980713]
We demonstrate the efficiency of recent attribution techniques to explain the diagnostic decision by visualizing the significant factors in the input image.
Our analysis of unmasking machine intelligence represents the necessity of explainability in the medical diagnostic decision.
arXiv Detail & Related papers (2021-07-19T11:49:31Z) - In-Line Image Transformations for Imbalanced, Multiclass Computer Vision
Classification of Lung Chest X-Rays [91.3755431537592]
This study aims to leverage a body of literature in order to apply image transformations that would serve to balance the lack of COVID-19 LCXR data.
Deep learning techniques such as convolutional neural networks (CNNs) are able to select features that distinguish between healthy and disease states.
This study utilizes a simple CNN architecture for high-performance multiclass LCXR classification at 94 percent accuracy.
arXiv Detail & Related papers (2021-04-06T02:01:43Z) - Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for
Thoracic Disease Identification [83.6017225363714]
deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance.
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
arXiv Detail & Related papers (2021-02-26T02:29:30Z) - Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
We propose a deep co-attention network for multi-view subspace learning.
It aims to extract both the common information and the complementary information in an adversarial setting.
In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
arXiv Detail & Related papers (2021-02-15T18:46:44Z) - An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks.
We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem.
We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
arXiv Detail & Related papers (2020-12-06T18:55:07Z) - Deep Transparent Prediction through Latent Representation Analysis [0.0]
The paper presents a novel deep learning approach, which extracts latent information from trained Deep Neural Networks (DNNs) and derives concise representations that are analyzed in an effective, unified way for prediction purposes.
Transparency combined with high prediction accuracy are the targeted goals of the proposed approach.
arXiv Detail & Related papers (2020-09-13T19:21:40Z) - Learning Interpretable Microscopic Features of Tumor by Multi-task
Adversarial CNNs To Improve Generalization [1.7371375427784381]
Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model.
Here we show that our architecture, by learning end-to-end an uncertainty-based weighting combination of multi-task and adversarial losses, is encouraged to focus on pathology features.
Our results on breast lymph node tissue show significantly improved generalization in the detection of tumorous tissue, with best average AUC 0.89 (0.01) against the baseline AUC 0.86 (0.005)
arXiv Detail & Related papers (2020-08-04T12:10:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.