Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data
<i>Background and Objective</i>: Kidney ultrasound (US) imaging is a significant imaging modality for evaluating kidney health and is essential for diagnosis, treatment, surgical intervention planning, and follow-up assessments. Kidney US image segmentation consists of extracting useful...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/13/10/1548 |
| _version_ | 1797574531077898240 |
|---|---|
| author | Tao Peng Yidong Gu Shanq-Jang Ruan Qingrong Jackie Wu Jing Cai |
| author_facet | Tao Peng Yidong Gu Shanq-Jang Ruan Qingrong Jackie Wu Jing Cai |
| author_sort | Tao Peng |
| collection | DOAJ |
| description | <i>Background and Objective</i>: Kidney ultrasound (US) imaging is a significant imaging modality for evaluating kidney health and is essential for diagnosis, treatment, surgical intervention planning, and follow-up assessments. Kidney US image segmentation consists of extracting useful objects or regions from the total image, which helps determine tissue organization and improve diagnosis. Thus, obtaining accurate kidney segmentation data is an important first step for precisely diagnosing kidney diseases. However, manual delineation of the kidney in US images is complex and tedious in clinical practice. To overcome these challenges, we developed a novel automatic method for US kidney segmentation. <i>Methods</i>: Our method comprises two cascaded steps for US kidney segmentation. The first step utilizes a coarse segmentation procedure based on a deep fusion learning network to roughly segment each input US kidney image. The second step utilizes a refinement procedure to fine-tune the result of the first step by combining an automatic searching polygon tracking method with a machine learning network. In the machine learning network, a suitable and explainable mathematical formula for kidney contours is denoted by basic parameters. <i>Results</i>: Our method is assessed using 1380 trans-abdominal US kidney images obtained from 115 patients. Based on comprehensive comparisons of different noise levels, our method achieves accurate and robust results for kidney segmentation. We use ablation experiments to assess the significance of each component of the method. Compared with state-of-the-art methods, the evaluation metrics of our method are significantly higher. The Dice similarity coefficient (DSC) of our method is 94.6 ± 3.4%, which is higher than those of recent deep learning and hybrid algorithms (89.4 ± 7.1% and 93.7 ± 3.8%, respectively). <i>Conclusions</i>: We develop a coarse-to-refined architecture for the accurate segmentation of US kidney images. It is important to precisely extract kidney contour features because segmentation errors can cause under-dosing of the target or over-dosing of neighboring normal tissues during US-guided brachytherapy. Hence, our method can be used to increase the rigor of kidney US segmentation. |
| first_indexed | 2024-03-10T21:23:47Z |
| format | Article |
| id | doaj.art-b55df17125b64dde844999b252f729e2 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-10T21:23:47Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-b55df17125b64dde844999b252f729e22023-11-19T15:50:48ZengMDPI AGBiomolecules2218-273X2023-10-011310154810.3390/biom13101548Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound DataTao Peng0Yidong Gu1Shanq-Jang Ruan2Qingrong Jackie Wu3Jing Cai4School of Future Science and Engineering, Soochow University, Suzhou 215006, ChinaDepartment of Medical Ultrasound, Suzhou Municipal Hospital, Suzhou 215000, ChinaDepartment of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USADepartment of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China<i>Background and Objective</i>: Kidney ultrasound (US) imaging is a significant imaging modality for evaluating kidney health and is essential for diagnosis, treatment, surgical intervention planning, and follow-up assessments. Kidney US image segmentation consists of extracting useful objects or regions from the total image, which helps determine tissue organization and improve diagnosis. Thus, obtaining accurate kidney segmentation data is an important first step for precisely diagnosing kidney diseases. However, manual delineation of the kidney in US images is complex and tedious in clinical practice. To overcome these challenges, we developed a novel automatic method for US kidney segmentation. <i>Methods</i>: Our method comprises two cascaded steps for US kidney segmentation. The first step utilizes a coarse segmentation procedure based on a deep fusion learning network to roughly segment each input US kidney image. The second step utilizes a refinement procedure to fine-tune the result of the first step by combining an automatic searching polygon tracking method with a machine learning network. In the machine learning network, a suitable and explainable mathematical formula for kidney contours is denoted by basic parameters. <i>Results</i>: Our method is assessed using 1380 trans-abdominal US kidney images obtained from 115 patients. Based on comprehensive comparisons of different noise levels, our method achieves accurate and robust results for kidney segmentation. We use ablation experiments to assess the significance of each component of the method. Compared with state-of-the-art methods, the evaluation metrics of our method are significantly higher. The Dice similarity coefficient (DSC) of our method is 94.6 ± 3.4%, which is higher than those of recent deep learning and hybrid algorithms (89.4 ± 7.1% and 93.7 ± 3.8%, respectively). <i>Conclusions</i>: We develop a coarse-to-refined architecture for the accurate segmentation of US kidney images. It is important to precisely extract kidney contour features because segmentation errors can cause under-dosing of the target or over-dosing of neighboring normal tissues during US-guided brachytherapy. Hence, our method can be used to increase the rigor of kidney US segmentation.https://www.mdpi.com/2218-273X/13/10/1548ultrasound kidney segmentationdeep fusion learning networkautomatic searching polygon trackingmathematical mapping model |
| spellingShingle | Tao Peng Yidong Gu Shanq-Jang Ruan Qingrong Jackie Wu Jing Cai Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data Biomolecules ultrasound kidney segmentation deep fusion learning network automatic searching polygon tracking mathematical mapping model |
| title | Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data |
| title_full | Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data |
| title_fullStr | Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data |
| title_full_unstemmed | Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data |
| title_short | Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data |
| title_sort | novel solution for using neural networks for kidney boundary extraction in 2d ultrasound data |
| topic | ultrasound kidney segmentation deep fusion learning network automatic searching polygon tracking mathematical mapping model |
| url | https://www.mdpi.com/2218-273X/13/10/1548 |
| work_keys_str_mv | AT taopeng novelsolutionforusingneuralnetworksforkidneyboundaryextractionin2dultrasounddata AT yidonggu novelsolutionforusingneuralnetworksforkidneyboundaryextractionin2dultrasounddata AT shanqjangruan novelsolutionforusingneuralnetworksforkidneyboundaryextractionin2dultrasounddata AT qingrongjackiewu novelsolutionforusingneuralnetworksforkidneyboundaryextractionin2dultrasounddata AT jingcai novelsolutionforusingneuralnetworksforkidneyboundaryextractionin2dultrasounddata |