De-noising Method in the Wavelet Packets Domain for Phase Images

Digital holography is a very efficient technique for 3D imaging and the characterization of changes at the surfaces of objects. However, during the process of holographic interferometry, the reconstructed phase images suffer from speckle noise. In this paper, de-noising is addressed with phase images corrupted with speckle noise. To do so, DnCNN residual networks with different depths were built and trained with various holographic noisy phase data. The possibility of using a network pre-trained on natural images with Gaussian noise is also investigated. All models are evaluated in terms of phase error with HOLODEEP benchmark data and with three unseen images corresponding to different experimental conditions. The best results are obtained using a network with only four convolutional blocks and trained with a wide range of noisy phase patterns.

Download Full-text

CT Simplified Radiomic Approach to Assess the Metastatic Ductal Adenocarcinoma of the Pancreas

Cancers ◽

10.3390/cancers13081843 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1843

Author(s):

Mirko D’Onofrio ◽

Riccardo De Robertis ◽

Gregorio Aluffi ◽

Camilla Cadore ◽

Alessandro Beleù ◽

...

Keyword(s):

Pancreatic Ductal Adenocarcinoma ◽

Ductal Adenocarcinoma ◽

Newly Diagnosed ◽

Inclusion Criteria ◽

Permeability Index ◽

Metastatic Tumors ◽

Qualitative And Quantitative ◽

Portal Phase ◽

Phase Images ◽

Adenocarcinoma Of The Pancreas

The aim of this study was to perform a simplified radiomic analysis of pancreatic ductal adenocarcinoma based on qualitative and quantitative tumor features and to compare the results between metastatic and non-metastatic patients. A search of our radiological, surgical, and pathological databases identified 1218 patients with a newly diagnosed pancreatic ductal adenocarcinoma who were referred to our Institution between January 2014 and December 2018. Computed Tomography (CT) examinations were reviewed analyzing qualitative and quantitative features. Two hundred eighty-eight patients fulfilled the inclusion criteria and were included in this study. Overall, metastases were present at diagnosis in 86/288 patients, while no metastases were identified in 202/288 patients. Ill-defined margins and a hypodense appearance on portal-phase images were significantly more common among patients with metastases compared to non-metastatic patients (p < 0.05). Metastatic tumors showed a significantly larger size and significantly lower arterial index, perfusion index, and permeability index compared to non-metastatic tumors (p < 0.05). In the management of pancreatic ductal adenocarcinoma, early detection and correct staging are key elements. The study of computerized tomography characteristics of pancreatic ductal adenocarcinoma showed substantial differences, both qualitative and quantitative, between metastatic and non-metastatic disease.

Download Full-text

EYE DETECTION USING OPTIMAL WAVELET PACKETS AND RADIAL BASIS FUNCTIONS (RBFs)

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001499000562 ◽

1999 ◽

Vol 13 (07) ◽

pp. 1009-1025 ◽

Cited By ~ 62

Author(s):

JEFFREY HUANG ◽

HARRY WECHSLER

Keyword(s):

Radial Basis Functions ◽

Detection Task ◽

Basis Functions ◽

Wavelet Packets ◽

Eye Detection ◽

Robust Performance ◽

Image Normalization ◽

Entropy Minimization ◽

Novel Approach ◽

Radial Basis

The eyes are important facial landmarks, both for image normalization due to their relatively constant interocular distance, and for post processing due to the anchoring on model-based schemes. This paper introduces a novel approach for the eye detection task using optimal wavelet packets for eye representation and Radial Basis Functions (RBFs) for subsequent classification ("labeling") of facial areas as eye versus non-eye regions. Entropy minimization is the driving force behind the derivation of optimal wavelet packets. It decreases the degree of data dispersion and it thus facilitates clustering ("prototyping") and capturing the most significant characteristics of the underlying (eye regions) data. Entropy minimization is thus functionally compatible with the first operational stage of the RBF classifier, that of clustering, and this explains the improved RBF performance on eye detection. Our experiments on the eye detection task prove the merit of this approach as they show that eye images compressed using optimal wavelet packets lead to improved and robust performance of the RBF classifier compared to the case where original raw images are used by the RBF classifier.

Download Full-text