EDRNet: An attention-based model for multi-type tumor and polyp segmentation in medical imaging

Displays, Год журнала: 2025, Номер unknown, С. 103031 - 103031

Опубликована: Март 1, 2025

Язык: Английский

---

Modelling Radiological Features Fusion and Explainable AI in Pneumonia Detection: A Graph- Based Deep Learning and Transformer Approach

Results in Engineering, Год журнала: 2025, Номер 26, С. 105225 - 105225

Опубликована: Май 5, 2025

Язык: Английский

---

Attention-enhanced Separable Residual with Dilation Net for Medical Image Segmentation

Neurocomputing, Год журнала: 2025, Номер unknown, С. 130434 - 130434

Опубликована: Май 1, 2025

Язык: Английский

---

ANALYSIS OF DIFFERENT POOLING FUNCTIONS ON A CONVOLUTION NEURAL NETWORK BASED MODEL

International Journal of 3D Printing Technologies and Digital Industry, Год журнала: 2024, Номер 8(2), С. 266 - 276

Опубликована: Авг. 29, 2024

The common denominator of deep learning models used in many different fields today is the pooling functions their internal architecture. These not only directly affect performance study, but also training time. For this reason, it extremely important to measure and share success values. In performances commonly soft pooling, max spatial pyramid average were measured on a dataset as benchmarking literature. purpose, new CNN based architecture was developed. Accuracy, F1 score, precision, recall categorical cross entropy metrics studies literature developed As result obtained, 97.79, 92.50, 91.60 89.09 values from best worst for accuracy obtained functions, respectively. light these results, study have provided better conceptual comparative understanding impact CNN-based model.

Язык: Английский

---

State-of-the-Art Deep Learning Methods for Microscopic Image Segmentation: Applications to Cells, Nuclei, and Tissues

Journal of Imaging, Год журнала: 2024, Номер 10(12), С. 311 - 311

Опубликована: Дек. 6, 2024

Microscopic image segmentation (MIS) is a fundamental task in medical imaging and biological research, essential for precise analysis of cellular structures tissues. Despite its importance, the process encounters significant challenges, including variability conditions, complex structures, artefacts (e.g., noise), which can compromise accuracy traditional methods. The emergence deep learning (DL) has catalyzed substantial advancements addressing these issues. This systematic literature review (SLR) provides comprehensive overview state-of-the-art DL methods developed over past six years microscopic images. We critically analyze key contributions, emphasizing how specifically tackle challenges cell, nucleus, tissue segmentation. Additionally, we evaluate datasets performance metrics employed studies. By synthesizing current identifying gaps existing approaches, this not only highlights transformative potential enhancing diagnostic research efficiency but also suggests directions future research. findings study have implications improving methodologies applications, ultimately fostering better patient outcomes advancing scientific understanding.

Язык: Английский

---

Improving Cell Image Segmentation by Using Isotropic Undecimated Wavelet Transform

IEEE Access, Год журнала: 2024, Номер 12, С. 159902 - 159912

Опубликована: Янв. 1, 2024

Язык: Английский

---

White blood cell segmentation using U-Net and its variants to improve leukemia diagnosis

Neural Computing and Applications, Год журнала: 2024, Номер 37(5), С. 3265 - 3286

Опубликована: Дек. 12, 2024

Язык: Английский

---

Innovative modified-net architecture: enhanced segmentation of deep vein thrombosis

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Дек. 28, 2024

Язык: Английский

---

Semantic Segmentation of Remote Sensing Images Based on U-Net

Communications in computer and information science, Год журнала: 2024, Номер unknown, С. 363 - 374

Опубликована: Дек. 21, 2024

Язык: Английский

---