Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature
In this review, we compiled convolutional neural network (CNN) methods which have the potential to automate the manual, costly and error-prone processing of medical images. We attempted to provide a thorough survey of improved architectures, popular frameworks, activation functions, ensemble techniq...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/6/1/33 |
| _version_ | 1797240202926751744 |
|---|---|
| author | Foziya Ahmed Mohammed Kula Kekeba Tune Beakal Gizachew Assefa Marti Jett Seid Muhie |
| author_facet | Foziya Ahmed Mohammed Kula Kekeba Tune Beakal Gizachew Assefa Marti Jett Seid Muhie |
| author_sort | Foziya Ahmed Mohammed |
| collection | DOAJ |
| description | In this review, we compiled convolutional neural network (CNN) methods which have the potential to automate the manual, costly and error-prone processing of medical images. We attempted to provide a thorough survey of improved architectures, popular frameworks, activation functions, ensemble techniques, hyperparameter optimizations, performance metrics, relevant datasets and data preprocessing strategies that can be used to design robust CNN models. We also used machine learning algorithms for the statistical modeling of the current literature to uncover latent topics, method gaps, prevalent themes and potential future advancements. The statistical modeling results indicate a temporal shift in favor of improved CNN designs, such as a shift from the use of a CNN architecture to a CNN-transformer hybrid. The insights from statistical modeling point that the surge of CNN practitioners into the medical imaging field, partly driven by the COVID-19 challenge, catalyzed the use of CNN methods for detecting and diagnosing pathological conditions. This phenomenon likely contributed to the sharp increase in the number of publications on the use of CNNs for medical imaging, both during and after the pandemic. Overall, the existing literature has certain gaps in scope with respect to the design and optimization of CNN architectures and methods specifically for medical imaging. Additionally, there is a lack of post hoc explainability of CNN models and slow progress in adopting CNNs for low-resource medical imaging. This review ends with a list of open research questions that have been identified through statistical modeling and recommendations that can potentially help set up more robust, improved and reproducible CNN experiments for medical imaging. |
| first_indexed | 2024-04-24T18:03:41Z |
| format | Article |
| id | doaj.art-2a732a765d5e40f19eb48ab3a0139191 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-04-24T18:03:41Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-2a732a765d5e40f19eb48ab3a01391912024-03-27T13:52:07ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902024-03-016169973510.3390/make6010033Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the LiteratureFoziya Ahmed Mohammed0Kula Kekeba Tune1Beakal Gizachew Assefa2Marti Jett3Seid Muhie4Department of Software Engineering, College of Electrical and Mechanical Engineering, Addis Ababa Science and Technology University, Addis Ababa 16417, EthiopiaDepartment of Software Engineering, College of Electrical and Mechanical Engineering, Addis Ababa Science and Technology University, Addis Ababa 16417, EthiopiaSchool of Information Technology and Engineering, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa P.O. Box 1000, EthiopiaHead Quarter, Walter Reed Army Institute of Research, Silver Spring, MD 20910, USAMedical Readiness Systems Biology, Walter Reed Army Institute of Research, Silver Spring, MD 20910, USAIn this review, we compiled convolutional neural network (CNN) methods which have the potential to automate the manual, costly and error-prone processing of medical images. We attempted to provide a thorough survey of improved architectures, popular frameworks, activation functions, ensemble techniques, hyperparameter optimizations, performance metrics, relevant datasets and data preprocessing strategies that can be used to design robust CNN models. We also used machine learning algorithms for the statistical modeling of the current literature to uncover latent topics, method gaps, prevalent themes and potential future advancements. The statistical modeling results indicate a temporal shift in favor of improved CNN designs, such as a shift from the use of a CNN architecture to a CNN-transformer hybrid. The insights from statistical modeling point that the surge of CNN practitioners into the medical imaging field, partly driven by the COVID-19 challenge, catalyzed the use of CNN methods for detecting and diagnosing pathological conditions. This phenomenon likely contributed to the sharp increase in the number of publications on the use of CNNs for medical imaging, both during and after the pandemic. Overall, the existing literature has certain gaps in scope with respect to the design and optimization of CNN architectures and methods specifically for medical imaging. Additionally, there is a lack of post hoc explainability of CNN models and slow progress in adopting CNNs for low-resource medical imaging. This review ends with a list of open research questions that have been identified through statistical modeling and recommendations that can potentially help set up more robust, improved and reproducible CNN experiments for medical imaging.https://www.mdpi.com/2504-4990/6/1/33medical imagingconvolutional neural network modelsclassificationhyperparameter tuningframeworkspreprocessing |
| spellingShingle | Foziya Ahmed Mohammed Kula Kekeba Tune Beakal Gizachew Assefa Marti Jett Seid Muhie Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature Machine Learning and Knowledge Extraction medical imaging convolutional neural network models classification hyperparameter tuning frameworks preprocessing |
| title | Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature |
| title_full | Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature |
| title_fullStr | Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature |
| title_full_unstemmed | Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature |
| title_short | Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature |
| title_sort | medical image classifications using convolutional neural networks a survey of current methods and statistical modeling of the literature |
| topic | medical imaging convolutional neural network models classification hyperparameter tuning frameworks preprocessing |
| url | https://www.mdpi.com/2504-4990/6/1/33 |
| work_keys_str_mv | AT foziyaahmedmohammed medicalimageclassificationsusingconvolutionalneuralnetworksasurveyofcurrentmethodsandstatisticalmodelingoftheliterature AT kulakekebatune medicalimageclassificationsusingconvolutionalneuralnetworksasurveyofcurrentmethodsandstatisticalmodelingoftheliterature AT beakalgizachewassefa medicalimageclassificationsusingconvolutionalneuralnetworksasurveyofcurrentmethodsandstatisticalmodelingoftheliterature AT martijett medicalimageclassificationsusingconvolutionalneuralnetworksasurveyofcurrentmethodsandstatisticalmodelingoftheliterature AT seidmuhie medicalimageclassificationsusingconvolutionalneuralnetworksasurveyofcurrentmethodsandstatisticalmodelingoftheliterature |