Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors
Objectives: Accurate kidney and tumor segmentation of computed tomography (CT) scans is vital for diagnosis and treatment, but manual methods are time-consuming and inconsistent, highlighting the value of AI automation. This study develops a fully automated AI model using vision transformers (ViTs)...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/11/1/3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587441617240064 |
|---|---|
| author | Nalan Karunanayake Lin Lu Hao Yang Pengfei Geng Oguz Akin Helena Furberg Lawrence H. Schwartz Binsheng Zhao |
| author_facet | Nalan Karunanayake Lin Lu Hao Yang Pengfei Geng Oguz Akin Helena Furberg Lawrence H. Schwartz Binsheng Zhao |
| author_sort | Nalan Karunanayake |
| collection | DOAJ |
| description | Objectives: Accurate kidney and tumor segmentation of computed tomography (CT) scans is vital for diagnosis and treatment, but manual methods are time-consuming and inconsistent, highlighting the value of AI automation. This study develops a fully automated AI model using vision transformers (ViTs) and convolutional neural networks (CNNs) to detect and segment kidneys and kidney tumors in Contrast-Enhanced (CECT) scans, with a focus on improving sensitivity for small, indistinct tumors. Methods: The segmentation framework employs a ViT-based model for the kidney organ, followed by a 3D UNet model with enhanced connections and attention mechanisms for tumor detection and segmentation. Two CECT datasets were used: a public dataset (KiTS23: 489 scans) and a private institutional dataset (Private: 592 scans). The AI model was trained on 389 public scans, with validation performed on the remaining 100 scans and external validation performed on all 592 private scans. Tumors were categorized by TNM staging as small (≤4 cm) (KiTS23: 54%, Private: 41%), medium (>4 cm to ≤7 cm) (KiTS23: 24%, Private: 35%), and large (>7 cm) (KiTS23: 22%, Private: 24%) for detailed evaluation. Results: Kidney and kidney tumor segmentations were evaluated against manual annotations as the reference standard. The model achieved a Dice score of 0.97 ± 0.02 for kidney organ segmentation. For tumor detection and segmentation on the KiTS23 dataset, the sensitivities and average false-positive rates per patient were as follows: 0.90 and 0.23 for small tumors, 1.0 and 0.08 for medium tumors, and 0.96 and 0.04 for large tumors. The corresponding Dice scores were 0.84 ± 0.11, 0.89 ± 0.07, and 0.91 ± 0.06, respectively. External validation on the private data confirmed the model’s effectiveness, achieving the following sensitivities and average false-positive rates per patient: 0.89 and 0.15 for small tumors, 0.99 and 0.03 for medium tumors, and 1.0 and 0.01 for large tumors. The corresponding Dice scores were 0.84 ± 0.08, 0.89 ± 0.08, and 0.92 ± 0.06. Conclusions: The proposed model demonstrates consistent and robust performance in segmenting kidneys and kidney tumors of various sizes, with effective generalization to unseen data. This underscores the model’s significant potential for clinical integration, offering enhanced diagnostic precision and reliability in radiological assessments. |
| format | Article |
| id | doaj-art-97531b648dc9459ea34f11abbacea32e |
| institution | Kabale University |
| issn | 2379-1381 2379-139X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj-art-97531b648dc9459ea34f11abbacea32e2025-01-24T13:50:51ZengMDPI AGTomography2379-13812379-139X2025-01-01111310.3390/tomography11010003Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and TumorsNalan Karunanayake0Lin Lu1Hao Yang2Pengfei Geng3Oguz Akin4Helena Furberg5Lawrence H. Schwartz6Binsheng Zhao7Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY 10017, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USAObjectives: Accurate kidney and tumor segmentation of computed tomography (CT) scans is vital for diagnosis and treatment, but manual methods are time-consuming and inconsistent, highlighting the value of AI automation. This study develops a fully automated AI model using vision transformers (ViTs) and convolutional neural networks (CNNs) to detect and segment kidneys and kidney tumors in Contrast-Enhanced (CECT) scans, with a focus on improving sensitivity for small, indistinct tumors. Methods: The segmentation framework employs a ViT-based model for the kidney organ, followed by a 3D UNet model with enhanced connections and attention mechanisms for tumor detection and segmentation. Two CECT datasets were used: a public dataset (KiTS23: 489 scans) and a private institutional dataset (Private: 592 scans). The AI model was trained on 389 public scans, with validation performed on the remaining 100 scans and external validation performed on all 592 private scans. Tumors were categorized by TNM staging as small (≤4 cm) (KiTS23: 54%, Private: 41%), medium (>4 cm to ≤7 cm) (KiTS23: 24%, Private: 35%), and large (>7 cm) (KiTS23: 22%, Private: 24%) for detailed evaluation. Results: Kidney and kidney tumor segmentations were evaluated against manual annotations as the reference standard. The model achieved a Dice score of 0.97 ± 0.02 for kidney organ segmentation. For tumor detection and segmentation on the KiTS23 dataset, the sensitivities and average false-positive rates per patient were as follows: 0.90 and 0.23 for small tumors, 1.0 and 0.08 for medium tumors, and 0.96 and 0.04 for large tumors. The corresponding Dice scores were 0.84 ± 0.11, 0.89 ± 0.07, and 0.91 ± 0.06, respectively. External validation on the private data confirmed the model’s effectiveness, achieving the following sensitivities and average false-positive rates per patient: 0.89 and 0.15 for small tumors, 0.99 and 0.03 for medium tumors, and 1.0 and 0.01 for large tumors. The corresponding Dice scores were 0.84 ± 0.08, 0.89 ± 0.08, and 0.92 ± 0.06. Conclusions: The proposed model demonstrates consistent and robust performance in segmenting kidneys and kidney tumors of various sizes, with effective generalization to unseen data. This underscores the model’s significant potential for clinical integration, offering enhanced diagnostic precision and reliability in radiological assessments.https://www.mdpi.com/2379-139X/11/1/3kidney cancertumor detection and segmentationdeep learningCECTvision transformersconvolutional neural networks |
| spellingShingle | Nalan Karunanayake Lin Lu Hao Yang Pengfei Geng Oguz Akin Helena Furberg Lawrence H. Schwartz Binsheng Zhao Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors Tomography kidney cancer tumor detection and segmentation deep learning CECT vision transformers convolutional neural networks |
| title | Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors |
| title_full | Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors |
| title_fullStr | Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors |
| title_full_unstemmed | Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors |
| title_short | Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors |
| title_sort | dual stage ai model for enhanced ct imaging precision segmentation of kidney and tumors |
| topic | kidney cancer tumor detection and segmentation deep learning CECT vision transformers convolutional neural networks |
| url | https://www.mdpi.com/2379-139X/11/1/3 |
| work_keys_str_mv | AT nalankarunanayake dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT linlu dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT haoyang dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT pengfeigeng dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT oguzakin dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT helenafurberg dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT lawrencehschwartz dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors AT binshengzhao dualstageaimodelforenhancedctimagingprecisionsegmentationofkidneyandtumors |