Tungjitkusolmun, Supan
Loading...
Preferred name
Tungjitkusolmun, Supan
Alternative Name
Tungjitkusolmun, S.
Main Affiliation
Email
supan.tu@kmitl.ac.th
16 results
Now showing 1 - 10 of 16
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Crack Localization Detection in Monolithic Zirconia Dental Crowns via 1D-Convolutional Neural Networks Algorithm-Based Acoustic Emission Analysis(2024-01-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Cross-Sensor and Cross-Population Generalization of Deep Learning Models for Digital Mammography: A Controlled Four-Country Benchmark of Five Backbone Architectures with Statistical Significance Testing(2026-06-01); Background/Objectives: Deep learning models for digital mammography sensor data are increasingly deployed across hospitals using different X-ray detector technologies and patient populations. Whether models trained on one sensor platform and population maintain accuracy when transferred to another has not been tested for the latest generation of mammography-specific foundation models under one controlled protocol. Methods: We fine-tuned five backbone architectures (ResNet-50, DINOv2-B14, Rad-DINO, Mammo-CLIP B5, and Mammo-FM) on CBIS-DDSM (film-digitized, USA, n = 714 validation) with three seeds, ablated a density-aware focal loss across three auxiliary weights, and evaluated transfer to three external sensor cohorts: CMMD (full-field digital, China, n = 1032), DMID (mixed digital, India, n = 509), and MIAS (film-digitized, UK, n = 322). Significance used paired DeLong z-tests with Benjamini–Hochberg FDR correction; temperature scaling tested post hoc recalibration at all transfer targets. Results: Within this single-source three-seed evaluation, ResNet-50 outperformed all four foundation models on CBIS-DDSM (AUC 0.867 vs. 0.847, 0.846, 0.813, and 0.703; all gaps p_adj < 0.05). The density-aware focal loss degraded both AUC and calibration at every weight tested. At transfer, every model lost 0.165 to 0.320 AUC points relative to in-distribution performance, with sensitivity at 95% specificity collapsing from 0.31 to 0.47 in-distribution to 0.11 to 0.22 across the three external targets. A per-seed Stouffer meta-analysis confirms that Mammo-CLIP B5 and Mammo-FM significantly outperformed ResNet-50 on DMID and Mammo-CLIP on CMMD, after BH-FDR; MIAS comparisons remained directional only. In the extremely dense subgroup (BI-RADS D4), Mammo-FM reached AUC 0.870 versus ResNet-50 at 0.842, a directional observation whose 95% CIs overlap heavily at the n = 140 sample size and which we do not interpret as a statistically supported advantage. Conclusions: In this single training-source, three-seed protocol, mammography-specific pretraining did not deliver the in-distribution AUC premium reported in the originating papers, and no architecture reached a level at which transfer deployment without local validation would be defensible. We frame these as observations specific to the present protocol rather than as broader conclusions about foundation models for mammography classification. The findings argue for sensor-stratified and population-stratified external validation and for local recalibration as practical prerequisites before clinical use. Code and weights are released under MIT license. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Message from Technical Program Chair(2023-01-01); ; - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automated Crack Detection in Monolithic Zirconia Crowns Using Acoustic Emission and Deep Learning Techniques(2024-09-01); ; Monolithic zirconia (MZ) crowns are widely utilized in dental restorations, particularly for substantial tooth structure loss. Inspection, tactile, and radiographic examinations can be time-consuming and error-prone, which may delay diagnosis. Consequently, an objective, automatic, and reliable process is required for identifying dental crown defects. This study aimed to explore the potential of transforming acoustic emission (AE) signals to continuous wavelet transform (CWT), combined with Conventional Neural Network (CNN) to assist in crack detection. A new CNN image segmentation model, based on multi-class semantic segmentation using Inception-ResNet-v2, was developed. Real-time detection of AE signals under loads, which induce cracking, provided significant insights into crack formation in MZ crowns. Pencil lead breaking (PLB) was used to simulate crack propagation. The CWT and CNN models were used to automate the crack classification process. The Inception-ResNet-v2 architecture with transfer learning categorized the cracks in MZ crowns into five groups: labial, palatal, incisal, left, and right. After 2000 epochs, with a learning rate of 0.0001, the model achieved an accuracy of 99.4667%, demonstrating that deep learning significantly improved the localization of cracks in MZ crowns. This development can potentially aid dentists in clinical decision-making by facilitating the early detection and prevention of crack failures. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automated segmentation of infarct lesions in t1‐weighted mri scans using variational mode decomposition and deep learning(2021-03-02); ; ; Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1‐weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non‐infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep‐learning‐based segmentation task. Finally, a three‐dimensional U‐Net model is developed to perform patch‐wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset are utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automatic detection of pulmonary nodules using three-dimensional chain coding and optimized random forest(2020-04-01); ; ; The detection of pulmonary nodules on computed tomography scans provides a clue for the early diagnosis of lung cancer. Manual detection mandates a heavy radiological workload as it identifies nodules slice-by-slice. This paper presents a fully automated nodule detection with three significant contributions. First, an automated seeded region growing is designed to segment the lung regions from the tomography scans. Second, a three-dimensional chain code algorithm is implemented to refine the border of the segmented lungs. Lastly, nodules inside the lungs are detected using an optimized random forest classifier. The experiments for our proposed detection are conducted using 888 scans from a public dataset, and achieves a favorable result of 93.11% accuracy, 94.86% sensitivity, and 91.37% specificity, with only 0.0863 false positives per exam. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, SCTFlow: 3D MRI-to-sCT with Conditional Rectified Flow(2026-01-01); Gulyanon, SarunMRI and CT images are both crucial for radiotherapy planning, since MRI provides superior soft-tissue contrast for tumor delineation, while CT provides Hounsfield units (HU) required for dose calculation. MR-only radiotherapy offers important advantages, including reduced registration errors, elimination of additional radiation exposure, and streamlined clinical workflows. Generating synthetic CT (sCT) from MRI remains challenging due to the need for realistic HU reconstruction and the high computational demands of processing large 3D image volumes.We propose sCTFlow, a Conditional Rectified Flow (CRF) framework for 3D MRI-to-sCT translation. Unlike diffusion probabilistic models (DDPMs), sCTFlow learns a deterministic velocity field mapping noise to data, ensuring stability and requiring fewer sampling steps. Our architecture, a 3D Attention U-Net, conditions on MRI and organ segmentation via feature-wise linear modulation to predict velocity fields, which are subsequently converted into HU estimates.We evaluated our approach on the SynthRAD2023 dataset. sCTFlow achieves an MAE of 81.18 +- 19.48 HU, PSNR of 26.93, and SSIM of 0.830. We also investigated our method and found that the model captures HU distributions rather than relying on simple intensity transformations, indicating its capacity to model underlying CT characteristics. These findings demonstrate that sCTFlow has potential for reliable and clinically applicable MR-only radiotherapy workflows. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Deep Learning Convolutional Neural Networks (CNNs) on Recognition and Classification of White Blood Cells (WBCs)(2023-01-01); The rapid evolution of Artificial Intelligence has brought significant advancements in Deep Learning, a widely applied subfield across various industries, including healthcare. This study focuses on leveraging Deep Learning and image processing techniques to classify white blood cells (WBCs). By comparing and evaluating multiple convolution neural network (CNN) models, such as GoogLeNet, ResNet50, VGG16, and Squeezenet, including YOLO (You Only Look Once) algorithm known for its segmentation capabilities, the objective is to improve the accuracy and efficiency of WBC recognition and classification. During training, both VGG16 and ResNet50 models achieved the highest accuracies, with VGG16 at 97.70% and ResNet50 at 97.38%. However, ResNet50 was chosen as the preferred model to be utilized alongside YOLO for improved classification and segmentation advancements. The testing phase of ResNet50 utilized 10% of the dataset from the initial data and demonstrated over 90% accuracy in each class. The process showed higher efficiency and lower capital costs, making it suitable for medical applications aided by Deep Learning Convolutional Neural Networks, addressing limitations in white blood cell classification. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Smart Diagnostics: Hierarchical Deep Learning of Acoustic Emission Signals for Early Crack Detection in Zirconia Dental Structures(2026-05-01); ; Sritart, HiranyaMonolithic zirconia restorations are frequently affected by the unnoticed growth of subcritical cracks, a failure process that is not captured by traditional imaging methods like radiographs and ultrasounds in sophisticated dental architectures. To address this evaluative inadequacy, this research introduces a hierarchical deep learning framework for microcrack detection and spatial localization. We promote a hierarchical deep learning system that integrates Acoustic Emission (AE) detection alongside signal processing. Raw AE signals utilized during dynamic loading are enhanced via Kalman filtering and Continuous Wavelet Transform (CWT) to construct high-fidelity time–frequency scalograms. The diagnostic pipeline operates in two stages: first, a hybrid CNN–BiGRU network with temporal attention fulfills zirconia component-level classification; second, a ResNet-18 backbone integrated with Bidirectional LSTM and Multi-Head Attention precisely localizes defects across five anatomical crown regions. This hierarchical design effectively captures the non-stationary, transient nature of fracture-induced stress waves. The framework achieved an F1-score of 99.00% and an AUC of 0.994, significantly outperforming conventional convolutional networks. By enabling predictive maintenance through early, non-invasive damage localization, this study demonstrates a promising laboratory framework for AE-based crack detection in zirconia dental structures and prosthetics and toward enhanced clinical reliability in digital dentistry. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Reconstruction of 3D Abdominal Aorta Aneurysm from Computed Tomographic Angiography Using 3D U-Net Deep Learning Network(2022-01-01); (1) Background: An abdominal aortic aneurysm (AAA) is a swelling (aneurysm) of the aorta that occurs when the wall of the aorta weakens. An AAA is a potentially life-threatening condition, especially if it eventually ruptures, causing severe bleeding. (2) Methods: We developed an automated segmentation method for 3D AAA reconstruction from computed tomography angiography (CTA) based on the 3D U-NET deep learning network approaches for AAA and AAA with thrombus on training dataset classified as 8 normal, 14 aneurysm volume, and 38 thrombus aneurysm volume with the data augmentations app, i.e., scaling, random crop, grayscale variation, axial y flip, and shear, were added to the training model, achieving better performance. (3) Results: The results confirm that the proposed method can provide accuracy in terms of the Dice Similar Coefficient (DSC) scores of 0.9669 for training performance and 0.9868 for testing evaluation with the 3D U-Net model.