Explainable machine learning framework for cataracts recognition using visual features
Abstract Cataract is the leading ocular disease of blindness and visual impairment globally. Deep neural networks (DNNs) have achieved promising cataracts recognition performance based on anterior segment optical coherence tomography (AS-OCT) images; however, they have poor explanations, limiting th...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Visual Computing for Industry, Biomedicine, and Art |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42492-024-00183-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595068302655488 |
|---|---|
| author | Xiao Wu Lingxi Hu Zunjie Xiao Xiaoqing Zhang Risa Higashita Jiang Liu |
| author_facet | Xiao Wu Lingxi Hu Zunjie Xiao Xiaoqing Zhang Risa Higashita Jiang Liu |
| author_sort | Xiao Wu |
| collection | DOAJ |
| description | Abstract Cataract is the leading ocular disease of blindness and visual impairment globally. Deep neural networks (DNNs) have achieved promising cataracts recognition performance based on anterior segment optical coherence tomography (AS-OCT) images; however, they have poor explanations, limiting their clinical applications. In contrast, visual features extracted from original AS-OCT images and their transform forms (e.g., AS-OCT-based histograms) have good explanations but have not been fully exploited. Motivated by these observations, an explainable machine learning framework to recognize cataracts severity levels automatically using AS-OCT images was proposed, consisting of three stages: visual feature extraction, feature importance explanation and selection, and recognition. First, the intensity histogram and intensity-based statistical methods are applied to extract visual features from original AS-OCT images and AS-OCT-based histograms. Subsequently, the SHapley Additive exPlanations and Pearson correlation coefficient methods are applied to analyze the feature importance and select significant visual features. Finally, an ensemble multi-class ridge regression method is applied to recognize the cataracts severity levels based on the selected visual features. Experiments on a clinical AS-OCT-NC dataset demonstrate that the proposed framework not only achieves competitive performance through comparisons with DNNs, but also has a good explanation ability, meeting the requirements of clinical diagnostic practice. |
| format | Article |
| id | doaj-art-b7e58b3223e24095a909a90cfa2f0c26 |
| institution | Kabale University |
| issn | 2524-4442 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Visual Computing for Industry, Biomedicine, and Art |
| spelling | doaj-art-b7e58b3223e24095a909a90cfa2f0c262025-01-19T12:08:45ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422025-01-018111810.1186/s42492-024-00183-6Explainable machine learning framework for cataracts recognition using visual featuresXiao Wu0Lingxi Hu1Zunjie Xiao2Xiaoqing Zhang3Risa Higashita4Jiang Liu5Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and TechnologyResearch Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and TechnologyResearch Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and TechnologyResearch Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and TechnologyResearch Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and TechnologyResearch Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and TechnologyAbstract Cataract is the leading ocular disease of blindness and visual impairment globally. Deep neural networks (DNNs) have achieved promising cataracts recognition performance based on anterior segment optical coherence tomography (AS-OCT) images; however, they have poor explanations, limiting their clinical applications. In contrast, visual features extracted from original AS-OCT images and their transform forms (e.g., AS-OCT-based histograms) have good explanations but have not been fully exploited. Motivated by these observations, an explainable machine learning framework to recognize cataracts severity levels automatically using AS-OCT images was proposed, consisting of three stages: visual feature extraction, feature importance explanation and selection, and recognition. First, the intensity histogram and intensity-based statistical methods are applied to extract visual features from original AS-OCT images and AS-OCT-based histograms. Subsequently, the SHapley Additive exPlanations and Pearson correlation coefficient methods are applied to analyze the feature importance and select significant visual features. Finally, an ensemble multi-class ridge regression method is applied to recognize the cataracts severity levels based on the selected visual features. Experiments on a clinical AS-OCT-NC dataset demonstrate that the proposed framework not only achieves competitive performance through comparisons with DNNs, but also has a good explanation ability, meeting the requirements of clinical diagnostic practice.https://doi.org/10.1186/s42492-024-00183-6Nuclear cataractAnterior segment optical coherence tomographyMachine learningExplainableVisual feature |
| spellingShingle | Xiao Wu Lingxi Hu Zunjie Xiao Xiaoqing Zhang Risa Higashita Jiang Liu Explainable machine learning framework for cataracts recognition using visual features Visual Computing for Industry, Biomedicine, and Art Nuclear cataract Anterior segment optical coherence tomography Machine learning Explainable Visual feature |
| title | Explainable machine learning framework for cataracts recognition using visual features |
| title_full | Explainable machine learning framework for cataracts recognition using visual features |
| title_fullStr | Explainable machine learning framework for cataracts recognition using visual features |
| title_full_unstemmed | Explainable machine learning framework for cataracts recognition using visual features |
| title_short | Explainable machine learning framework for cataracts recognition using visual features |
| title_sort | explainable machine learning framework for cataracts recognition using visual features |
| topic | Nuclear cataract Anterior segment optical coherence tomography Machine learning Explainable Visual feature |
| url | https://doi.org/10.1186/s42492-024-00183-6 |
| work_keys_str_mv | AT xiaowu explainablemachinelearningframeworkforcataractsrecognitionusingvisualfeatures AT lingxihu explainablemachinelearningframeworkforcataractsrecognitionusingvisualfeatures AT zunjiexiao explainablemachinelearningframeworkforcataractsrecognitionusingvisualfeatures AT xiaoqingzhang explainablemachinelearningframeworkforcataractsrecognitionusingvisualfeatures AT risahigashita explainablemachinelearningframeworkforcataractsrecognitionusingvisualfeatures AT jiangliu explainablemachinelearningframeworkforcataractsrecognitionusingvisualfeatures |