Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models
Imaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COV...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/9/12/283 |
| _version_ | 1797380456525594624 |
|---|---|
| author | Rossana Buongiorno Giulio Del Corso Danila Germanese Leonardo Colligiani Lorenzo Python Chiara Romei Sara Colantonio |
| author_facet | Rossana Buongiorno Giulio Del Corso Danila Germanese Leonardo Colligiani Lorenzo Python Chiara Romei Sara Colantonio |
| author_sort | Rossana Buongiorno |
| collection | DOAJ |
| description | Imaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COVID-19, which are crucial to be detected and quantified in order to obtain an accurate disease stratification and prognosis. However, visual assessment and quantification represent a time-consuming task for radiologists. In this regard, tools for semi-automatic segmentation, such as those based on Convolutional Neural Networks, can facilitate the detection of pathological lesions by delineating their contour. In this work, we compared four state-of-the-art Convolutional Neural Networks based on the encoder–decoder paradigm for the binary segmentation of COVID-19 infections after training and testing them on 90 HRCT volumetric scans of patients diagnosed with COVID-19 collected from the database of the Pisa University Hospital. More precisely, we started from a basic model, the well-known UNet, then we added an attention mechanism to obtain an Attention-UNet, and finally we employed a recurrence paradigm to create a Recurrent–Residual UNet (R2-UNet). In the latter case, we also added attention gates to the decoding path of an R2-UNet, thus designing an R2-Attention UNet so as to make the feature representation and accumulation more effective. We compared them to gain understanding of both the cognitive mechanism that can lead a neural model to the best performance for this task and the good compromise between the amount of data, time, and computational resources required. We set up a five-fold cross-validation and assessed the strengths and limitations of these models by evaluating the performances in terms of Dice score, Precision, and Recall defined both on 2D images and on the entire 3D volume. From the results of the analysis, it can be concluded that Attention-UNet outperforms the other models by achieving the best performance of 81.93%, in terms of 2D Dice score, on the test set. Additionally, we conducted statistical analysis to assess the performance differences among the models. Our findings suggest that integrating the recurrence mechanism within the UNet architecture leads to a decline in the model’s effectiveness for our particular application. |
| first_indexed | 2024-03-08T20:37:31Z |
| format | Article |
| id | doaj.art-1b5e260b8e344463b9ad4117f64bb5d5 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-08T20:37:31Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-1b5e260b8e344463b9ad4117f64bb5d52023-12-22T14:18:14ZengMDPI AGJournal of Imaging2313-433X2023-12-0191228310.3390/jimaging9120283Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet ModelsRossana Buongiorno0Giulio Del Corso1Danila Germanese2Leonardo Colligiani3Lorenzo Python4Chiara Romei5Sara Colantonio6Institute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, ItalyInstitute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, ItalyInstitute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, ItalyDepartment of Translational Research, Academic Radiology, University of Pisa, 56124 Pisa, PI, Italy2nd Radiology Unit, Pisa University Hospital, 56124 Pisa, PI, Italy2nd Radiology Unit, Pisa University Hospital, 56124 Pisa, PI, ItalyInstitute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, ItalyImaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COVID-19, which are crucial to be detected and quantified in order to obtain an accurate disease stratification and prognosis. However, visual assessment and quantification represent a time-consuming task for radiologists. In this regard, tools for semi-automatic segmentation, such as those based on Convolutional Neural Networks, can facilitate the detection of pathological lesions by delineating their contour. In this work, we compared four state-of-the-art Convolutional Neural Networks based on the encoder–decoder paradigm for the binary segmentation of COVID-19 infections after training and testing them on 90 HRCT volumetric scans of patients diagnosed with COVID-19 collected from the database of the Pisa University Hospital. More precisely, we started from a basic model, the well-known UNet, then we added an attention mechanism to obtain an Attention-UNet, and finally we employed a recurrence paradigm to create a Recurrent–Residual UNet (R2-UNet). In the latter case, we also added attention gates to the decoding path of an R2-UNet, thus designing an R2-Attention UNet so as to make the feature representation and accumulation more effective. We compared them to gain understanding of both the cognitive mechanism that can lead a neural model to the best performance for this task and the good compromise between the amount of data, time, and computational resources required. We set up a five-fold cross-validation and assessed the strengths and limitations of these models by evaluating the performances in terms of Dice score, Precision, and Recall defined both on 2D images and on the entire 3D volume. From the results of the analysis, it can be concluded that Attention-UNet outperforms the other models by achieving the best performance of 81.93%, in terms of 2D Dice score, on the test set. Additionally, we conducted statistical analysis to assess the performance differences among the models. Our findings suggest that integrating the recurrence mechanism within the UNet architecture leads to a decline in the model’s effectiveness for our particular application.https://www.mdpi.com/2313-433X/9/12/283COVID-19segmentationdeep learningconvolutional neural networksUNetattention mechanism |
| spellingShingle | Rossana Buongiorno Giulio Del Corso Danila Germanese Leonardo Colligiani Lorenzo Python Chiara Romei Sara Colantonio Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models Journal of Imaging COVID-19 segmentation deep learning convolutional neural networks UNet attention mechanism |
| title | Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models |
| title_full | Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models |
| title_fullStr | Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models |
| title_full_unstemmed | Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models |
| title_short | Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models |
| title_sort | enhancing covid 19 ct image segmentation a comparative study of attention and recurrence in unet models |
| topic | COVID-19 segmentation deep learning convolutional neural networks UNet attention mechanism |
| url | https://www.mdpi.com/2313-433X/9/12/283 |
| work_keys_str_mv | AT rossanabuongiorno enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels AT giuliodelcorso enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels AT danilagermanese enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels AT leonardocolligiani enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels AT lorenzopython enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels AT chiararomei enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels AT saracolantonio enhancingcovid19ctimagesegmentationacomparativestudyofattentionandrecurrenceinunetmodels |