RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans
Abstract Renal carcinoma is a frequently seen cancer globally, with laparoscopic partial nephrectomy (LPN) being the primary form of treatment. Accurately identifying renal structures such as kidneys, tumors, veins, and arteries on CT scans is crucial for optimal surgical preparation and treatment....
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01751-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861493401124864 |
|---|---|
| author | Rashid Khan Chao Chen Asim Zaman Jiayi Wu Haixing Mai Liyilei Su Yan Kang Bingding Huang |
| author_facet | Rashid Khan Chao Chen Asim Zaman Jiayi Wu Haixing Mai Liyilei Su Yan Kang Bingding Huang |
| author_sort | Rashid Khan |
| collection | DOAJ |
| description | Abstract Renal carcinoma is a frequently seen cancer globally, with laparoscopic partial nephrectomy (LPN) being the primary form of treatment. Accurately identifying renal structures such as kidneys, tumors, veins, and arteries on CT scans is crucial for optimal surgical preparation and treatment. However, the automatic segmentation of these structures remains challenging due to the kidney's complex anatomy and the variability of imaging data. This study presents RenalSegNet, a novel deep-learning framework for automatically segmenting renal structure in contrast-enhanced CT images. RenalSegNet has an innovative encoder-decoder architecture, including the FlexEncoder Block for efficient multivariate feature extraction and the MedSegPath mechanism for advanced feature distribution and fusion. Evaluated on the KiPA dataset, RenalSegNet achieved remarkable performance, with an average dice score of 86.25%, IOU of 76.75%, Recall of 86.69%, Precision of 86.48%, HD of 15.78 mm, and AVD of 0.79 mm. Ablation studies confirm the critical roles of the MedSegPath and MedFuse components in achieving these results. RenalSegNet's robust performance highlights its potential for clinical applications and offers significant advances in renal cancer treatment by contributing to accurate preoperative planning and postoperative evaluation. Future improvements to model accuracy and applicability will involve integrating advanced techniques, such as unsupervised transformer-based approaches. |
| format | Article |
| id | doaj-art-b078e995f9b84239b117e3f7c1f31b63 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-b078e995f9b84239b117e3f7c1f31b632025-02-09T13:00:57ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111212010.1007/s40747-024-01751-2RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scansRashid Khan0Chao Chen1Asim Zaman2Jiayi Wu3Haixing Mai4Liyilei Su5Yan Kang6Bingding Huang7College of Big Data and Internet, Shenzhen Technology UniversityCollege of Big Data and Internet, Shenzhen Technology UniversityCollege of Health Science and Environmental Engineering, Shenzhen Technology UniversityCollege of Big Data and Internet, Shenzhen Technology UniversityDepartment of Urology, Third Medical Center, Chinese PLA General HospitalCollege of Big Data and Internet, Shenzhen Technology UniversityCollege of Applied Sciences, Shenzhen UniversityCollege of Big Data and Internet, Shenzhen Technology UniversityAbstract Renal carcinoma is a frequently seen cancer globally, with laparoscopic partial nephrectomy (LPN) being the primary form of treatment. Accurately identifying renal structures such as kidneys, tumors, veins, and arteries on CT scans is crucial for optimal surgical preparation and treatment. However, the automatic segmentation of these structures remains challenging due to the kidney's complex anatomy and the variability of imaging data. This study presents RenalSegNet, a novel deep-learning framework for automatically segmenting renal structure in contrast-enhanced CT images. RenalSegNet has an innovative encoder-decoder architecture, including the FlexEncoder Block for efficient multivariate feature extraction and the MedSegPath mechanism for advanced feature distribution and fusion. Evaluated on the KiPA dataset, RenalSegNet achieved remarkable performance, with an average dice score of 86.25%, IOU of 76.75%, Recall of 86.69%, Precision of 86.48%, HD of 15.78 mm, and AVD of 0.79 mm. Ablation studies confirm the critical roles of the MedSegPath and MedFuse components in achieving these results. RenalSegNet's robust performance highlights its potential for clinical applications and offers significant advances in renal cancer treatment by contributing to accurate preoperative planning and postoperative evaluation. Future improvements to model accuracy and applicability will involve integrating advanced techniques, such as unsupervised transformer-based approaches.https://doi.org/10.1007/s40747-024-01751-2RenalSegNetKidney cancerContrast-enhanced CT scansMedSegPathDeep learning |
| spellingShingle | Rashid Khan Chao Chen Asim Zaman Jiayi Wu Haixing Mai Liyilei Su Yan Kang Bingding Huang RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans Complex & Intelligent Systems RenalSegNet Kidney cancer Contrast-enhanced CT scans MedSegPath Deep learning |
| title | RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans |
| title_full | RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans |
| title_fullStr | RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans |
| title_full_unstemmed | RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans |
| title_short | RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans |
| title_sort | renalsegnet automated segmentation of renal tumor veins and arteries in contrast enhanced ct scans |
| topic | RenalSegNet Kidney cancer Contrast-enhanced CT scans MedSegPath Deep learning |
| url | https://doi.org/10.1007/s40747-024-01751-2 |
| work_keys_str_mv | AT rashidkhan renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT chaochen renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT asimzaman renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT jiayiwu renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT haixingmai renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT liyileisu renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT yankang renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans AT bingdinghuang renalsegnetautomatedsegmentationofrenaltumorveinsandarteriesincontrastenhancedctscans |