Piyawattanametha, Wibool

Preferred name

Main Affiliation

School of Engineering

wibool.pi@kmitl.ac.th

Now showing 1 - 10 of 52

Some of the metrics are blocked by your
consent settings
Centralized pap test diagnosis with artificial neural network and internet of things
(2016-07-02)
Dumripatanachod, Manatchakorn
;
Piyawattanametha, Wibool
In this work, we propose a utilization of a serverclient system model that using the Internet of Things (IoT) technology to process Pap smear imaging data derived from high-resolution microscopes and to classify the those images by employing the Artificial Neural Network (ANN) learning algorithm on the server. The IoT can enable those microscopes to communicate with one another while the ANN enables a new method of imaging classification with high accuracy. We utilize 917 high-resolution images as an input for our proposed method. The method achieves a root mean square error of 0.8834 and correlation coefficient of 0.6643.
Some of the metrics are blocked by your
consent settings
Monocular depth estimation based on deep learning for intraoperative guidance using surface-enhanced Raman scattering imaging
(2025-02-01)
Juhong, Aniwat
;
Li, Bo
;
Liu, Yifan
;
Yao, Cheng You
;
Yang, Chia Wei
Imaging of surface-enhanced Raman scattering (SERS) nanoparticles (NPs) has been intensively studied for cancer detection due to its high sensitivity, unconstrained low signal-to-noise ratios, and multiplexing detection capability. Furthermore, conjugating SERS NPs with various biomarkers is straightforward, resulting in numerous successful studies on cancer detection and diagnosis. However, Raman spectroscopy only provides spectral data from an imaging area without co-registered anatomic context. This is not practical and suitable for clinical applications. Here, we propose a custom-made Raman spectrometer with computer-vision-based positional tracking and monocular depth estimation using deep learning (DL) for the visualization of 2D and 3D SERS NPs imaging, respectively. In addition, the SERS NPs used in this study (hyaluronic acid-conjugated SERS NPs) showed clear tumor targeting capabilities (target CD44 typically overexpressed in tumors) by an ex vivo experiment and immunohistochemistry. The combination of Raman spectroscopy, image processing, and SERS molecular imaging, therefore, offers a robust and feasible potential for clinical applications.
Some of the metrics are blocked by your
consent settings
Whole slide imaging based on a low-cost camera
(2018-08-13)
Sasivimolkul, Suvicha
;
Jittichaiwet, Tanakit
;
Piyawattanametha, Wibool
This work presents a new low-cost digital single-lens reflex camera whole slide imaging (DC-WSI) system, which is the most recent imaging modality being employed by pathology departments worldwide due to its high-throughput routine and high-speed capabilities. The DC-WSI system field of view achieves 22.6 times larger than that of the equivalent magnification of a conventional microscope system. The DC-WSI is capable of performing the whole slide scanning (2 cm2) under 2 seconds.
Some of the metrics are blocked by your
consent settings
MEMS-Based Medical Endomicroscopes
(2015-07-01)
Qiu, Zhen
;
Piyawattanametha, Wibool
Progress toward early diagnosis of cancer would have significant clinical benefits in reducing mortality or prolonging life in cancer patients; thus, there is an important unmet clinical need to image cellular features of cancer in vivo and in real time to correlate pathological symptoms and underlying cells responsible for such symptoms. In this paper, we describe a review of microelectromechanical systems scanners-based endoscopic optical coherence tomography, confocal, two-photon, and photoacoustic microscopy imaging. These advanced optical imaging modalities can provide subcellular (micron-scale) resolution and deep tissue penetration to reveal both cells and molecular features for early cancer diagnosis, cancer staging, and surgical guidance.
Some of the metrics are blocked by your
consent settings
MEMS actuators for optical microendoscopy
(2019-01-24)
Qiu, Zhen
;
Piyawattanametha, Wibool
Growing demands for affordable, portable, and reliable optical microendoscopic imaging devices are attracting research institutes and industries to find new manufacturing methods. However, the integration of microscopic components into these subsystems is one of today's challenges in manufacturing and packaging. Together with this kind of miniaturization more and more functional parts have to be accommodated in ever smaller spaces. Therefore, solving this challenge with the use of microelectromechanical systems (MEMS) fabrication technology has opened the promising opportunities in enabling a wide variety of novel optical microendoscopy to be miniaturized. MEMS fabrication technology enables abilities to apply batch fabrication methods with high-precision and to include a wide variety of optical functionalities to the optical components. As a result, MEMS technology has enabled greater accessibility to advance optical microendoscopy technology to provide high-resolution and high-performance imaging matching with traditional table-top microscopy. In this review the latest advancements of MEMS actuators for optical microendoscopy will be discussed in detail.
Some of the metrics are blocked by your
consent settings
Virtual biopsies with handheld dual-axis confocal microscope
(2018-01-01)
Piyawattanametha, Wibool
We demonstrate a novel microelectromechanical system (MEMS) based Dual-Axes confocal (DAC) microscope in a 10-mm diameter handheld package. Miniaturization is achieved by using a barbell-shaped, gimbaled, two-dimensional (2-D) MEMS scanner that is actuated by self-aligned vertical comb actuators. The maximum DC optical scan angles are ±4.25° on the inner axis and ±1.5° on the outer axis, and the corresponding resonance frequencies are 3.4 and 1.2 kHz. The maximum imaging rate is 5 frames/s. The miniature DAC microscope operating at 785-nm-wavelength achieves full-width-half-maximum (FWHM) transverse and axial resolutions of 4.5 μm and 5 μm, respectively.
Some of the metrics are blocked by your
consent settings
Wide-field high-resolution fiber bundle based endomicroscope for cervical epithelium cells imaging
(2017-02-21)
Dumripatanachod, Manatchakorn
;
Piyawattanametha, Wibool
Endomicroscope is commonly used in epithelium diagnosis. We have designed a low-cost wide-field high-resolution fiber bundle based endomicroscope with off-The-shelf optical components and a commercial CMOS camera. We compensated the low sensitivity of the CMOS sensor in the camera with a suitable magnification of the optical system and image processing algorithm which is running on an embedded system. In this paper, the prototype of the designed endomicroscope can resolve a spatial resolution of 70 microns and capable of fluorescence imaging.
Some of the metrics are blocked by your
consent settings
Super-resolution and segmentation deep learning for breast cancer histopathology image analysis
(2023-01-01)
Juhong, Aniwat
;
Li, Bo
;
Yao, Cheng You
;
Yang, Chia Wei
;
Agnew, Dalen W.
Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminator networks so-called super-resolution generative adversarial network-based on aggregated residual transformation (SRGAN-ResNeXt) to facilitate cancer diagnosis in low resource settings. The results provide high enhancement in image quality where the peak signal-to-noise ratio and structural similarity of our network results are over 30 dB and 0.93, respectively. The derived performance is superior to the results obtained from both the bicubic interpolation and the well-known SRGAN deep-learning methods. In addition, another custom CNN is used to perform image segmentation from the generated high-resolution breast cancer images derived with our model with an average Intersection over Union of 0.869 and an average dice similarity coefficient of 0.893 for the H&E image segmentation results. Finally, we propose the jointly trained SRGAN-ResNeXt and Inception U-net Models, which applied the weights from the individually trained SRGAN-ResNeXt and inception U-net models as the pre-trained weights for transfer learning. The jointly trained model’s results are progressively improved and promising. We anticipate these custom CNNs can help resolve the inaccessibility of advanced microscopes or whole slide imaging (WSI) systems to acquire high-resolution images from low-performance microscopes located in remote-constraint settings.
Some of the metrics are blocked by your
consent settings
MEMS based fiber optical microendoscopes
(2015-01-01)
Qiu, Zhen
;
Piyawattanametha, Wibool
Fiber-optical microendoscopy has recently been an essential medical diagnostic tool for patients in investigating tissues in vivo due to affordable cost, high quality imaging performance, compact size, high-speed imaging, and flexible movement. Microelectromechanical systems (MEMS) scanner technology has been playing a key role in shaping the miniaturization and enabling high-speed imaging of fiber-optical microendoscopy for over 20 years. In this article, both review of MEMS based fiber-optical microendoscopy for optical coherence tomography, confocal, and two-photon imaging will be discussed. These advanced optical endoscopic imaging modalities provide cellular and molecular features with deep tissue penetration enabling guided resections and early cancer assessment.
Some of the metrics are blocked by your
consent settings
A comparative study of convolutional neural networks for mammogram diagnosis
(2022-01-01)
Intasam, Anongnat
;
Promworn, Yuttachon
;
Thanasitthichai, Somchai
;
Piyawattanametha, Wibool
This work evaluates and compares the architectures: Inceptionv4, InceptionResnetV2, and Resnet152, to classify benign and malignant. We evaluate the architectures with a statistical analysis base on the received operational characteristics (ROC), accuracy, precision, recall, and F1 score. We generate the best results with the CNN InceptionResnetV2 trained with two classes on a balanced mammogram database. The results for benign cases have a ROC of 0.93, a precision of 0.8319, a recall of 0.9216, and an F1-score of 0.8744. The results for malignant cases have a ROC of 0.91, a precision of 0.9121, a recall of 0.8137, and an F1-score of 0.8601.

Piyawattanametha, Wibool

Filters

Settings

Sort By

Results per page