A quantization assisted U-Net study with ICA and deep features fusion for breast cancer identification using ultrasonic data

Breast cancer is one of the leading causes of death in women worldwide—the rapid increase in breast cancer has brought about more accessible diagnosis resources. The ultrasonic breast cancer modality for diagnosis is relatively cost-effective and valuable. Lesion isolation in ultrasonic images is a challenging task due to its robustness and intensity similarity. Accurate detection of breast lesions using ultrasonic breast cancer images can reduce death rates. In this research, a quantization-assisted U-Net approach for segmentation of breast lesions is proposed. It contains two step for segmentation: (1) U-Net and (2) quantization. The quantization assists to U-Net-based segmentation in order to isolate exact lesion areas from sonography images. The Independent Component Analysis (ICA) method then uses the isolated lesions to extract features and are then fused with deep automatic features. Public ultrasonic-modality-based datasets such as the Breast Ultrasound Images Dataset (BUSI) and the Open Access Database of Raw Ultrasonic Signals (OASBUD) are used for evaluation comparison. The OASBUD data extracted the same features. However, classification was done after feature regularization using the lasso method. The obtained results allow us to propose a computer-aided design (CAD) system for breast cancer identification using ultrasonic modalities.

Carbonate Reservoir Characterization with High-Resolution Logging-While-Drilling Dual-Images in Oil-Based Mud

Fracture evaluation and vuggy feature understanding are of prime importance in carbonate reservoirs. Commonly the related features are extracted from high resolution borehole images in water-based mud environments. To reduce the formation damage from drilling fluids, many wells are drilled with oil-based muds (OBM) in carbonate reservoirs. There are no appropriate measurements to resolve the reservoir characterization in OBM with the existing technologies in horizontal wells—especially in real-time—to make decisions at an early stage. In this paper, we would like to introduce a workflow for geological characterization using a new dual-images logging while drilling tool in oil-based mud. This new tool provides high resolution resistivity and ultrasonic images at the same time. Structural features, such as bedding boundaries, faults, fractures can be identified efficiently from resistivity images; while detailed sedimentary features, for example, cross beddings, vugs, stylolite are easily characterized using ultrasonic images. Benefiting from the dual images, an innovative workflow was proposed to estimate the vug feature more accurately; and the fractures can be identified from images and classified based on tool measurement principles. One case study from the Middle East demonstrated the benefits of this new measurement. A near well structure model was constructed from bed boundaries picked from borehole images. The fractures were picked and classified confidently using the dual images. Additionally, fracture density statistics are available along the well trajectory. The vug features were extracted efficiently, which indicates the secondary porosity development information. Rock typing is achieved by combining fracture and vug analysis to provide zonation for completion and production stimulation. The dual-images provide the capability for geological characterization in carbonate reservoir in an oil-based mud environment. The image-based rock typing helps segment the drain-hole for completion and production stimulation. The reservoir mapping with rock typing provides detailed information for in-filling well design.

A New LWD Dual Imager with Incorporated Feedback Improves Image Quality in OBM: Some Learnings form Abu Dhabi Offshore Carbonates

Recent developments in Logging-While-Drilling (LWD) technology have enabled high-resolution borehole imaging in oil-base mud that used to be a long-standing challenge. New applications to enhance image interpretation and maintain feature-integrity were developed with feedback from Abu Dhabi field examples of recently deployed LWD dual imager where hostile drilling conditions impacted the high-resolution ultrasonic image quality. The new dual imager has 4 ultrasonic sensors and 2 electromagnetic sensors (for resistivity image) mounted on a 15-ft sub in the drilling bottom-hole assembly (BHA). It provides ultrasonic amplitude and travel-time images at two central frequencies in addition to apparent resistivity images composed of four operating frequency measurements. A long lateral of around 8000-ft was drilled with this new imager through challenging heterogeneous carbonates and data was analyzed for geological interpretation. Based on the feedback for data quality improvement in certain intervals, the impact of shock & vibration on high-resolution (0.2") ultrasonic images was analyzed in time domain with simulated data first to understand the behavior of causative factors independently. Afterwards, the new algorithms were developed and deployed to maintain feature integrity of the data. The validation on field-data provided much-needed validation for the results in hostile drilling conditions. Resistivity images provided all the bedding and textural information (vugs, stylolites) with high confidence images at around 0.8" resolution. Higher resolution (0.2") ultrasonic images provided concrete information about vugs distribution for secondary porosity with quantitative interpretation on vug-indices. In addition, feedback provided from real time data was incorporated in subsequent processing and development of an image processing app that effectively fixes the depth-filtering related to drilling-induced events and stick-slip. Re-processing of the data provided high quality images that were used for high-resolution geological interpretation. Confident feature recognition was input into interpretation application hitherto available only in water-base mud while drilling. Results of this study with feedback incorporated to field-data from Abu Dhabi helped better the geological interpretation in hostile drilling condition as well, minimizing the need for e-line imaging.

A Spatial Compounding Method for Non-Delayed Sequential Beamforming

We present a new spatial compounding method to improve the contrast of ultrasonic images for non-delayed sequential beamforming (NDSB). Sequential beamforming adopts more than one beamformer to reconstruct B-mode images which has the advantage of simple front-end electronics and fast data transfer rate. Via field pattern analysis, we propose a compounding method where two more sub-images can be reconstructed along with the NDSB sub-image. These sub-images can be seen as being produced with different transmit origins; thus, their summation enhances image contrast. Image quality was analyzed in terms of spatial resolution, contrast ratio (CR), and contrast-to-noise ratio (CNR). The proposed compounding method improves the lateral resolution up to 41%. In vitro results confirm a 13.0-dB CR and 4.0-dB CNR improvement. In vivo results reveal 10.9-dB and 6.0-dB improvement in CR and CNR for cross-section jugular vein and 8.0-dB and 4.5-dB improvement in CR and CNR for the longitudinal-section carotid artery.

Adaptive Data Acquisition for Fast Ultrasonic Imaging Using Laser Induced Phased Arrays

This study introduces a novel data acquisition method, the Selective Matrix Capture (SMC), that can adapt the array geometry during data acquisition, to the demands of the inspected structure, such as the defects encountered. The adaptive data acquisition method is enabled by the use of Laser Induced Phased Arrays (LIPAs). We have previously demonstrated high-resolution ultrasonic images of the interior of components using Full Matrix Capture (FMC) and the Total Focusing Method (TFM). However, capturing the FMC requires long synthesis time due to signal averaging and mechanical laser scanning, compromising the application potential of LIPAs. Given that most components are defect free, significant time savings can be obtained by only acquiring high-fidelity data when a defect is indicated. The paper presents the Selective Matrix Capture that acquires data more efficiently without a priori knowledge of the location of the defects, while still achieving the superior imaging quality provided by an FMC data set.