GPRTransNet: A deep learning–based ground-penetrating radar translation network

Tunnelling and Underground Space Technology, Journal Year: 2025, Volume and Issue: 161, P. 106557 - 106557

Published: March 13, 2025

Language: Английский

---

MSHV-Net: A Multi-Scale Hybrid Vision Network for Skin Image Segmentation

Digital Signal Processing, Journal Year: 2025, Volume and Issue: unknown, P. 105166 - 105166

Published: March 1, 2025

Language: Английский

---

A novel intelligent grade classification architecture for Patent Foramen Ovale by Contrast Transthoracic Echocardiography based on deep learning

Computerized Medical Imaging and Graphics, Journal Year: 2025, Volume and Issue: unknown, P. 102538 - 102538

Published: April 1, 2025

Language: Английский

---

Touching the limit of Rolling Multilayer Perceptron for efficient two-dimensional medical image segmentation

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 153, P. 110899 - 110899

Published: April 24, 2025

Language: Английский

---

ETC-Net: an efficient collaborative transformer and convolutional network combining edge constraints for medical image segmentation

Evolving Systems, Journal Year: 2025, Volume and Issue: 16(2)

Published: May 3, 2025

Language: Английский

---

APG-SAM: Automatic prompt generation for SAM-based breast lesion segmentation with boundary-aware optimization

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127048 - 127048

Published: March 1, 2025

Language: Английский

---

Research on recognition of diabetic retinopathy hemorrhage lesions based on fine tuning of segment anything model

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 25, 2025

Diabetic Retinopathy (DR) demands precise hemorrhage detection for early diagnosis, yet manual identification faces challenges due to hemorrhagic lesions' varied sizes, complex shapes, and color similarities surrounding tissues, which obscure boundaries reduce contrast. To address this, we propose SAM-ada-Res, a novel dual-encoder model integrating pre-trained Segment Anything Model (SAM) ResNet101. SAM captures global semantic context distinguish ambiguous lesions from vessels, while ResNet101 extracts fine-grained details through its deep hierarchical layers. Feature maps both encoders are fused via channel-wise concatenation, enabling the decoder localize with high precision. A lightweight Adapter fine-tunes retinal tasks without retraining backbone, ensuring task-specific adaptation. Evaluated on three datasets (OIA-DDR, IDRiD, JYFY-HE), SAM-ada-Res outperforms state-of-the-art methods in nDice (0.6040 JYFY-HE) nIoU (0.4182 IDRiD), demonstrating superior generalization robustness. An online platform further streamlines clinical deployment, enhancing diagnostic efficiency. By synergizing SAM's generalizable vision capabilities ResNet's localized feature extraction, overcomes key DR detection, offering robust tool intervention. This work bridges technical innovation practicality, advancing automated diagnosis.

Language: Английский

---

IDSNet: Unifying local and global context for skin lesion image segmentation

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 108, P. 107961 - 107961

Published: April 27, 2025

Language: Английский

---

MOM-BUS: A Multi-Output Framework for Precise Breast Lesion Segmentation in Ultrasound Images

Measurement Science and Technology, Journal Year: 2025, Volume and Issue: 36(5), P. 055702 - 055702

Published: May 1, 2025

Abstract Accurate breast tumor segmentation in ultrasound images is essential for cancer diagnosis and treatment planning. However, challenges such as low image contrast, irregular shapes boundary ambiguity often hinder the process. To address these issues, this study proposes a novel deep learning framework termed MOM-BUS, which utilizes multi-tumoral area approach. It leverages shared characteristics among multiple tasks to enhance performance. Specifically, delineates intra-tumoral (ITA), peri-tumoral area, enlarged tumoral (ETA) simultaneously, using their interconnected features produce more accurate results. Furthermore, conditional test-time ensemble approach introduced handle outliers refine results by eliminating undesired elements from network output. The effectiveness of proposed has been validated through extensive experiments on two distinct datasets five different backbone models. Experimental consistently demonstrate that achieves superior performance compared single-output counterparts, with improvements Dice coefficient Jaccard Index values up 5.35% 5.39%, respectively. These improvement gains highlight reliability our accurately delineating tumor, offering significant potential improve subsequent malignancy assessment clinical decision-making processes.

Language: Английский

---

MPKU‐Net: A U‐Shaped Medical Image Segmentation Network Based on MLP and KAN

International Journal of Imaging Systems and Technology, Journal Year: 2025, Volume and Issue: 35(3)

Published: May 1, 2025

ABSTRACT The UNET architecture has been widely adopted for image segmentation across various domains, owing to its efficient and powerful performance in recent years. Its application enhancement medical primarily involve convolutional neural network (CNN) Transformer. However, both methods have fundamental limitations. CNN struggle capture global features, which greatly reduces the computational complexity but compromises effectiveness. Transformers excel at capturing features demand substantial parameters computations fail effectively extract local features. To address these challenges, we propose a U‐shaped model, MPKU‐NET, integrates multilayer perception (MLP) with Knowledge‐Aware Networks (KAN) architecture, aiming characteristics coordinated manner. MPKU‐NET flexible rolling Flip operation that, along MLP Network (KAN), creates WE‐MPK modules thorough learning of effectiveness is proven by extensive testing on BUSI, CVC, GlaS datasets. results demonstrate that MPKU‐Net consistently outperforms several used networks, including U‐KAN, Rolling‐U‐net, U‐Net ++, terms model accuracy, highlighting as scalable solution segmentation. code uploaded: https://github.com/cp668688/MPKU‐Net .

Language: Английский

---