EfficientNet family U-Net models for deep learning semantic segmentation of kidney tumors on CT images

Abstract

IntroductionKidney tumors are common cancer in advanced age, and providing early detection is crucial. Medical imaging and deep learning methods are increasingly attractive for identifying and segmenting kidney tumors. Convolutional neural networks have successfully classified and segmented images, enabling clinicians to recognize and segment tumors effectively. CT scans of kidneys aid in tumor assessment and morphology study, using semantic segmentation techniques for pixel-level identification of kidney and surrounding anatomy. Accurate diagnostic procedures are crucial for early detection of kidney cancer.MethodsThis paper proposes an EfficientNet model for complex segmentation by linking the encoder stage EfficientNet with U-Net. This model represents a more successful system with improved encoder and decoder features. The Intersection over Union (IoU) metric quantifies model performance.Results and DiscussionThe EfficientNet models showed high IoU_Scores for background, kidney, and tumor segmentation, with mean IoU_Scores ranging from 0.976 for B0 to 0.980 for B4. B7 received the highest IoU_Score for segmenting kidneys, while B4 received the highest for segmenting tumors. The study utilizes the KiTS19 dataset for contrast-enhanced CT images. Using Semantic segmentation for EfficientNet Family U-Net Models, our method proved even more reliable and will aid doctors in accurate tumor detection and image classification for early diagnosis.

Advancing Human Action Recognition and Medical Image Segmentation using GRU Networks with V-Net Architecture

“…The performance assessment measures for both models, UCFkinect and Ensemble for HAR, and U-net, IRU-net, and Optimised V-net for medical picture segmentation, are discussed. The optimised GRU and V-Net models outperform their counterparts in terms of accuracy, precision, recall, and F1 score [31] [32]. The training and testing accuracy analysis demonstrates the models' good learning and generalisation, demonstrating their potential for real-world applications in medical imaging and human behaviour detection.…”

EfficientNet Ensemble Learning: Identifying Ethiopian Medicinal Plant Species and Traditional Uses by Integrating Modern Technology with Ethnobotanical Wisdom

“…EfficientNet-based U-Net models were used for segmenting CT images of kidney tumors, achieving impressive IoU scores (0.976 to 0.980) [56]. Notably, B7 excelled in kidney segmentation, while B4 performed best in tumor segmentation.…”

“…Notably, B7 excelled in kidney segmentation, while B4 performed best in tumor segmentation. Thus, the EfficientNet framework offers high accuracy in kidney disease segmentation and classification [56]. The EfficientNet-based models have gained recognition for their innovative scaling approach, which results in exceptional accuracy.…”

A Comprehensive Review of Artificial Intelligence Approaches in Kidney Cancer Medical Images Diagnosis, Datasets, Challenges and Issues and Future Directions

“…In contrast to the fully supervised method used in the KITS19 challenge, which achieved a Dice score of 0.974 for renal segmentation and 0.851 for segmentation of tumors, the method shows impressive outcomes (Dice score of 0.823 for kidney segmentation and 0.583 for tumor segmentation) using solely image-level labels. Also, [52] proposes a technology that utilizes semantic segmentation to detect kidney cancers by merging the encoder stage of EfficientNet with U-Net models. from the EfficientNet family.…”