Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC44109.2020.9175804 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Radiogenomics-based prediction of and gene mutation in non-small cell lung cancer patients.
Zhong Nan Da Xue Xue Bao Yi Xue Ban
May 2025
Department of Geriatric Pulmonary and Critical Care Medicine, Xiangya Hospital, Central South University; National Clinical Research Center for Geriatric Disorders (Xiangya Hospital), Changsha 410008.
Objectives: Non-small cell lung cancer (NSCLC) is associated with poor prognosis, with 30% of patients diagnosed at an advanced stage. Mutations in the and genes are important prognostic factors for NSCLC, and targeted therapies can significantly improve survival in these patients. Although tissue biopsy remains the gold standard for detecting gene mutations, it has limitations, including invasiveness, sampling errors due to tumor heterogeneity, and poor reproducibility.
View Article and Find Full Text PDFArtificial Intelligence in Contact Dermatitis: Current and Future Perspectives.
Dermatitis
September 2025
From the Department of Dermatology, Venereology and Leprology, All India Institute of Medical Sciences (AIIMS), Bhopal, India.
Contact dermatitis (CD), which includes both allergic CD and irritant CD, is a common inflammatory condition that can pose significant diagnostic challenges. Although patch testing is the gold standard for identifying causative allergens for allergic contact dermatitis (ACD), it is time-consuming, subjective, and requires expert interpretation. Recent advancements in artificial intelligence (AI), particularly in machine learning (ML) and deep learning, have shown promise in improving the accuracy, efficiency, and accessibility of CD diagnosis and management.
View Article and Find Full Text PDFOptimized node-level capsule graph neural network for subject-independent emotion recognition from EEG signals.
Electromagn Biol Med
September 2025
Computer Science and Business Systems, Sri Krishna College of Engineering and Technology, Coimbatore, India.
Subject-independent emotion detection using EEG (Electroencephalography) using Vibrational Mode Decomposition and deep learning is made possible by the scarcity of labelled EEG datasets encompassing a variety of emotions. Labelled EEG data collection over a wide range of emotional states from a broad and varied population is challenging and resource-intensive. As a result, models trained on small or biased datasets may fail to generalize well to unknown individuals or emotional states, resulting in lower accuracy and robustness in real-world applications.
View Article and Find Full Text PDFAccelerated Patient-specific Non-Cartesian MRI Reconstruction using Implicit Neural Representations.
Int J Radiat Oncol Biol Phys
September 2025
Radiation Oncology, University of California, San Francisco, 505 Parnassus Ave, San Francisco, CA 94143. Electronic address:
Purpose: Accelerating MR acquisition is essential for image guided therapeutic applications. Compressed sensing (CS) has been developed to minimize image artifacts in accelerated scans, but the required iterative reconstruction is computationally complex and difficult to generalize. Convolutional neural networks (CNNs)/Transformers-based deep learning (DL) methods emerged as a faster alternative but face challenges in modeling continuous k-space, a problem amplified with non-Cartesian sampling commonly used in accelerated acquisition.
View Article and Find Full Text PDFShifted windowing vision transformer-based skin cancer classification via transfer learning.
Clinics (Sao Paulo)
September 2025
Shandong Qinlu Energy Technology Co., Ltd, Jinan, 250357, China.
Objective: Skin cancer is widely recognized as one of the most perilous diseases on a global scale. Early identification of skin lesions can significantly enhance the treatment effects by aiding in clinical decision-making, hence mitigating the risk of disease progression and metastasis. Unfortunately, the skin images used for training are usually limited and imbalanced.
View Article and Find Full Text PDF