1
|
Ramamurthy K, Thayumanaswamy I, Radhakrishnan M, Won D, Lingaswamy S. Integration of Localized, Contextual, and Hierarchical Features in Deep Learning for Improved Skin Lesion Classification. Diagnostics (Basel) 2024; 14:1338. [PMID: 39001229 PMCID: PMC11241006 DOI: 10.3390/diagnostics14131338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2024] [Revised: 06/11/2024] [Accepted: 06/12/2024] [Indexed: 07/16/2024] Open
Abstract
Skin lesion classification is vital for the early detection and diagnosis of skin diseases, facilitating timely intervention and treatment. However, existing classification methods face challenges in managing complex information and long-range dependencies in dermoscopic images. Therefore, this research aims to enhance the feature representation by incorporating local, global, and hierarchical features to improve the performance of skin lesion classification. We introduce a novel dual-track deep learning (DL) model in this research for skin lesion classification. The first track utilizes a modified Densenet-169 architecture that incorporates a Coordinate Attention Module (CoAM). The second track employs a customized convolutional neural network (CNN) comprising a Feature Pyramid Network (FPN) and Global Context Network (GCN) to capture multiscale features and global contextual information. The local features from the first track and the global features from second track are used for precise localization and modeling of the long-range dependencies. By leveraging these architectural advancements within the DenseNet framework, the proposed neural network achieved better performance compared to previous approaches. The network was trained and validated using the HAM10000 dataset, achieving a classification accuracy of 93.2%.
Collapse
Affiliation(s)
- Karthik Ramamurthy
- Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai 600127, India
| | - Illakiya Thayumanaswamy
- Department of Computational Intelligence, School of Computing, SRM Institute of Science and Technology, Kattankulathur 603203, India
| | - Menaka Radhakrishnan
- Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai 600127, India
| | - Daehan Won
- System Sciences and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Sindhia Lingaswamy
- Department of Computer Applications, National Institute of Technology, Tiruchirappalli 620015, India
| |
Collapse
|
2
|
Lambert B, Forbes F, Doyle S, Dehaene H, Dojat M. Trustworthy clinical AI solutions: A unified review of uncertainty quantification in Deep Learning models for medical image analysis. Artif Intell Med 2024; 150:102830. [PMID: 38553168 DOI: 10.1016/j.artmed.2024.102830] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Revised: 02/28/2024] [Accepted: 03/01/2024] [Indexed: 04/02/2024]
Abstract
The full acceptance of Deep Learning (DL) models in the clinical field is rather low with respect to the quantity of high-performing solutions reported in the literature. End users are particularly reluctant to rely on the opaque predictions of DL models. Uncertainty quantification methods have been proposed in the literature as a potential solution, to reduce the black-box effect of DL models and increase the interpretability and the acceptability of the result by the final user. In this review, we propose an overview of the existing methods to quantify uncertainty associated with DL predictions. We focus on applications to medical image analysis, which present specific challenges due to the high dimensionality of images and their variable quality, as well as constraints associated with real-world clinical routine. Moreover, we discuss the concept of structural uncertainty, a corpus of methods to facilitate the alignment of segmentation uncertainty estimates with clinical attention. We then discuss the evaluation protocols to validate the relevance of uncertainty estimates. Finally, we highlight the open challenges for uncertainty quantification in the medical field.
Collapse
Affiliation(s)
- Benjamin Lambert
- Univ. Grenoble Alpes, Inserm, U1216, Grenoble Institut des Neurosciences, Grenoble, 38000, France; Pixyl Research and Development Laboratory, Grenoble, 38000, France
| | - Florence Forbes
- Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, 38000, France
| | - Senan Doyle
- Pixyl Research and Development Laboratory, Grenoble, 38000, France
| | - Harmonie Dehaene
- Pixyl Research and Development Laboratory, Grenoble, 38000, France
| | - Michel Dojat
- Univ. Grenoble Alpes, Inserm, U1216, Grenoble Institut des Neurosciences, Grenoble, 38000, France.
| |
Collapse
|
3
|
Ma X, Shan J, Ning F, Li W, Li H. EFFNet: A skin cancer classification model based on feature fusion and random forests. PLoS One 2023; 18:e0293266. [PMID: 37871038 PMCID: PMC10593232 DOI: 10.1371/journal.pone.0293266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Accepted: 10/03/2023] [Indexed: 10/25/2023] Open
Abstract
Computer-aided diagnosis techniques based on deep learning in skin cancer classification have disadvantages such as unbalanced datasets, redundant information in the extracted features and ignored interactions of partial features among different convolutional layers. In order to overcome these disadvantages, we propose a skin cancer classification model named EFFNet, which is based on feature fusion and random forests. Firstly, the model preprocesses the HAM10000 dataset to make each category of training set images balanced by image enhancement technology. Then, the pre-training weights of the EfficientNetV2 model on the ImageNet dataset are fine-tuned on the HAM10000 skin cancer dataset. After that, an improved hierarchical bilinear pooling is introduced to capture the interactions of some features between the layers and enhance the expressive ability of features. Finally, the fused features are passed into the random forests for classification prediction. The experimental results show that the accuracy, recall, precision and F1-score of the model reach 94.96%, 93.74%, 93.16% and 93.24% respectively. Compared with other models, the accuracy rate is improved to some extent and the highest accuracy rate can be increased by about 10%.
Collapse
Affiliation(s)
- Xiaopu Ma
- School of Computer Science and Technology, Nanyang Normal University, Nanyang, Henan, China
| | - Jiangdan Shan
- School of Life Sciences and Agricultural Engineering, Nanyang Normal University, Nanyang, Henan, China
| | - Fei Ning
- School of Life Sciences and Agricultural Engineering, Nanyang Normal University, Nanyang, Henan, China
| | - Wentao Li
- School of Computer Science and Technology, Nanyang Normal University, Nanyang, Henan, China
| | - He Li
- School of Computer Science and Technology, Nanyang Normal University, Nanyang, Henan, China
| |
Collapse
|
4
|
Seoni S, Jahmunah V, Salvi M, Barua PD, Molinari F, Acharya UR. Application of uncertainty quantification to artificial intelligence in healthcare: A review of last decade (2013-2023). Comput Biol Med 2023; 165:107441. [PMID: 37683529 DOI: 10.1016/j.compbiomed.2023.107441] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Revised: 08/27/2023] [Accepted: 08/29/2023] [Indexed: 09/10/2023]
Abstract
Uncertainty estimation in healthcare involves quantifying and understanding the inherent uncertainty or variability associated with medical predictions, diagnoses, and treatment outcomes. In this era of Artificial Intelligence (AI) models, uncertainty estimation becomes vital to ensure safe decision-making in the medical field. Therefore, this review focuses on the application of uncertainty techniques to machine and deep learning models in healthcare. A systematic literature review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Our analysis revealed that Bayesian methods were the predominant technique for uncertainty quantification in machine learning models, with Fuzzy systems being the second most used approach. Regarding deep learning models, Bayesian methods emerged as the most prevalent approach, finding application in nearly all aspects of medical imaging. Most of the studies reported in this paper focused on medical images, highlighting the prevalent application of uncertainty quantification techniques using deep learning models compared to machine learning models. Interestingly, we observed a scarcity of studies applying uncertainty quantification to physiological signals. Thus, future research on uncertainty quantification should prioritize investigating the application of these techniques to physiological signals. Overall, our review highlights the significance of integrating uncertainty techniques in healthcare applications of machine learning and deep learning models. This can provide valuable insights and practical solutions to manage uncertainty in real-world medical data, ultimately improving the accuracy and reliability of medical diagnoses and treatment recommendations.
Collapse
Affiliation(s)
- Silvia Seoni
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | | | - Massimo Salvi
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Prabal Datta Barua
- School of Business (Information System), University of Southern Queensland, Toowoomba, QLD, 4350, Australia; Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, 2007, Australia
| | - Filippo Molinari
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy.
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia
| |
Collapse
|
5
|
Lemay A, Hoebel K, Bridge CP, Befano B, De Sanjosé S, Egemen D, Rodriguez AC, Schiffman M, Campbell JP, Kalpathy-Cramer J. Improving the repeatability of deep learning models with Monte Carlo dropout. NPJ Digit Med 2022; 5:174. [PMID: 36400939 PMCID: PMC9674698 DOI: 10.1038/s41746-022-00709-3] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2022] [Accepted: 10/10/2022] [Indexed: 11/19/2022] Open
Abstract
The integration of artificial intelligence into clinical workflows requires reliable and robust models. Repeatability is a key attribute of model robustness. Ideal repeatable models output predictions without variation during independent tests carried out under similar conditions. However, slight variations, though not ideal, may be unavoidable and acceptable in practice. During model development and evaluation, much attention is given to classification performance while model repeatability is rarely assessed, leading to the development of models that are unusable in clinical practice. In this work, we evaluate the repeatability of four model types (binary classification, multi-class classification, ordinal classification, and regression) on images that were acquired from the same patient during the same visit. We study the each model's performance on four medical image classification tasks from public and private datasets: knee osteoarthritis, cervical cancer screening, breast density estimation, and retinopathy of prematurity. Repeatability is measured and compared on ResNet and DenseNet architectures. Moreover, we assess the impact of sampling Monte Carlo dropout predictions at test time on classification performance and repeatability. Leveraging Monte Carlo predictions significantly increases repeatability, in particular at the class boundaries, for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 16% points and of the class disagreement rate by 7% points. The classification accuracy improves in most settings along with the repeatability. Our results suggest that beyond about 20 Monte Carlo iterations, there is no further gain in repeatability. In addition to the higher test-retest agreement, Monte Carlo predictions are better calibrated which leads to output probabilities reflecting more accurately the true likelihood of being correctly classified.
Collapse
Affiliation(s)
- Andreanne Lemay
- Martinos Center for Biomedical Imaging, Boston, MA, USA
- NeuroPoly, Polytechnique Montreal, Montreal, QC, Canada
| | - Katharina Hoebel
- Martinos Center for Biomedical Imaging, Boston, MA, USA
- Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Christopher P Bridge
- Martinos Center for Biomedical Imaging, Boston, MA, USA
- MGH & BWH Center for Clinical Data Science, Boston, MA, USA
| | - Brian Befano
- Department of Epidemiology, University of Washington School of Public Health, Seattle, WA, USA
| | - Silvia De Sanjosé
- Division of Cancer Epidemiology & Genetics, National Cancer Institute, Rockville, MD, USA
| | - Didem Egemen
- Division of Cancer Epidemiology & Genetics, National Cancer Institute, Rockville, MD, USA
| | - Ana Cecilia Rodriguez
- Division of Cancer Epidemiology & Genetics, National Cancer Institute, Rockville, MD, USA
| | - Mark Schiffman
- Division of Cancer Epidemiology & Genetics, National Cancer Institute, Rockville, MD, USA
| | | | | |
Collapse
|