KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Intelligent identification of medical and veterinary intracellular protozoa by using self-supervised learning
(2026-12-01)
Kittichai, Veerayuth
;
Kaewthamasorn, Morakot
;
Soiphet, Naruchit
;
Tongloy, Teerawat
;
Chuwongin, Santhad
Background: Zoonotic diseases pose a major threat to both human and animal health, contributing significantly to global morbidity and mortality. Accurate diagnosis is crucial for effective control and treatment, with microscopic examination serving as the gold standard, supplemented by highly sensitive molecular biology techniques. However, these confirmatory methods require skilled personnel and are subject to inter- and intra-rater variability. An innovative solution lies in artificial intelligence (AI)-powered automated tools, which offer a promising alternative. This study aimed to develop a self-supervised learning (SSL) approach using the Distillation with No Labels (DiNOv2) algorithm to extract features of protozoa from Giemsa-stained blood samples. Methods: The development of self-supervised learning algorithms, including DiNOv2, was based on archived samples of clinically significant and significant veterinary microorganisms. These models were evaluated in comparison to a baseline Vision Transformer (ViT). Results: Among the tested SSL models, the DiNOv2-Small version achieved exceptional performance, surpassing 99% accuracy and specificity while maintaining the lowest misclassification rate (0.263). It also demonstrated a high area under the curve (AUC) value of 0.990, underscoring its robust classification capability. Remarkably, even when trained on only 20% of the dataset, the SSL models retained performance levels comparable to baseline models trained on the full dataset. However, further reducing the sample size below 20% led to notable declines in evaluation metrics: accuracy dropped by 5–7%, recall decreased from 37.9% to 35.1%, precision fell from 35% to 25.2%, and the F1 score declined from 31.1% to 21.5%. Additionally, the AUC decreased by 4–11%, while the misclassification rate increased, indicating reduced robustness. A key limitation of this study was the highly imbalanced fine-tuned dataset between classes. Nevertheless, the inconsistent performance observed may be mitigated by employing the larger DiNOv2 model, which improves the F1 score and enhances the model’s ability to handle imbalanced data while reducing reliance on labeled data. Conclusions: The proposed method can assist laboratory technicians, particularly in resource-limited healthcare settings. Furthermore, the findings support the potential deployment of this AI-based tool for automated screening in both medical and veterinary applications.
Some of the metrics are blocked by your
consent settings
Performance validation of deep-learning-based approach in stool examination
(2025-12-01)
Corpuz, Kristal Dale Felimon
;
Kusolsuk, Teera
;
Wongphan, Benjamaporn
;
Chonsawat, Putza
;
Naing, Kaung Myat
Background: Human intestinal parasitic infections (IPI) pose a significant global health issue caused by parasitic helminths and protozoa, affecting around 3.5 billion people worldwide, with more than 200,000 deaths annually. Despite advancements in molecular methods with higher sensitivity and specificity, the Kato-Katz or formalin-ethyl acetate centrifugation technique (FECT) remains the gold standard and a routine diagnostic procedure suitable for its simplicity and cost-effectiveness. However, these techniques have limitations that must be addressed. Thus, this study evaluated the performance of a deep-learning-based approach for intestinal parasite identification and compared it with that of human experts. Methods: Human experts performed FECT and Merthiolate-iodine-formalin (MIF) techniques to serve as ground truth and reference for parasite species. Subsequently, a modified direct smear was conducted to gather images for the training (80%) and testing (20%) datasets. State-of-the-art models, including YOLOv4-tiny, YOLOv7-tiny, YOLOv8-m, ResNet-50, and DINOv2 (base, small, and large), were employed and were operated using in-house CIRA CORE platform. Overall performance was evaluated using confusion matrices, the metrics of which were calculated on the basis of the one-versus-rest and micro-averaging approaches. Moreover, the receiver operating characteristic (ROC) and precision-recall (PR) curves were determined for visual comparison. Lastly, Cohen’s Kappa and Bland–Altman analyses were used to statistically measure the significant differences and visualize the association levels between the human experts and the deep learning models’ classification performance in intestinal parasite identification. Results: Findings demonstrated the potential of a deep-learning-based approach, particularly of models DINOv2-large (accuracy: 98.93%; precision: 84.52%; sensitivity: 78.00%; specificity: 99.57%; F1 score: 81.13%; AUROC: 0.97) and YOLOv8-m (accuracy: 97.59%; precision: 62.02%; sensitivity: 46.78%; specificity: 99.13%; F1 score: 53.33%; AUROC: 0.755; AUPR: 0.556) for their high metric values in intestinal parasite identification. Class-wise prediction showed high precision, sensitivity, and F1 scores for helminthic eggs and larvae due to more distinct morphology. Moreover, all models obtained a > 0.90 k score, which indicates a strong level of agreement compared with the medical technologists. The Bland–Altman analysis also presented the best agreement between FECT performed by medical technologist A and YOLOv4-tiny, while the MIF technique performed by medical technologist B and DINOv2-small demonstrated the best bias-free agreement, with mean differences of 0.0199 and −0.0080, and standard deviation differences of 0.6012 and 0.5588, respectively. Conclusions: The results highlight the potential of integrating a deep-learning-based approach into parasite identification. The models showcased superiority in automated detection, suggesting a significant leap toward improving diagnostic procedures for IPI. This hybridization could enhance early detection and diagnosis, facilitating timely and targeted interventions to reduce the burden of IPI through more effective management and prevention strategies.
Some of the metrics are blocked by your
consent settings
Enhancing mosquito classification through self-supervised learning
(2024-12-01)
Charoenpanyakul, Ratana
;
Kittichai, Veerayuth
;
Eiamsamang, Songpol
;
Sriwichai, Patchara
;
Pinetsuksai, Natchapon
Traditional mosquito identification methods, relied on microscopic observation and morphological characteristics, often require significant expertise and experience, which can limit their effectiveness. This study introduces a self-supervised learning-based image classification model using the Bootstrap Your Own Latent (BYOL) algorithm, designed to enhance mosquito species identification efficiently. The BYOL algorithm offers a key advantage by eliminating the need for labeled data during pretraining, as it autonomously learns important features. During fine-tuning, the model requires only a small fraction of labeled data to achieve accurate results. Our approach demonstrates impressive performance, achieving over 96.77% accuracy in mosquito image analysis, with minimized both false positives and false negatives. Additionally, the model’s overall accuracy, measured by the area under the ROC curve, surpasses 99.55%, highlighting its robustness and reliability. A notable finding is that fine-tuning with just 10% of labeled data produces results comparable to using the full dataset. This is particularly valuable for resource-limited settings with limited access to advanced equipment and expertise. Our model provides a practical solution for mosquito identification, overcoming the challenges of traditional microscopic methods, such as the time-consuming process and reliance on specialized knowledge in healthcare services. Overall, this model supports personnel in resource-constrained environments by facilitating mosquito vector density analysis and paving the way for future mosquito species identification methodologies.
Some of the metrics are blocked by your
consent settings
Superior Automatic Screening for Human Helminthic Ova by Using Self-supervised Learning Approach-Based Object Classification
(2023-01-01)
Pinetsuksai, Natchapon
;
Kittichai, Veerayuth
;
Jomtarak, Rangsan
;
Jaksukam, Komgrit
;
Tongloy, Teerawat
Human parasitic infections remain one of public health concerns for 1.5 billion people worldwide including Thailand. Conventional microscopic examination is a gold standard method and often used to identify the helminth ova and filariform larvae and also protozoa cyst in stool-dependent simple smear. The benefits of traditional techniques are diminished by time-consuming, complicated procedures, massive labor, and skilled and trained parasitologists. An automatically rapid screening of the most in need of treatment is considered to replace the conventional technique. Here, we aim to develop a deep convolutional residual network based self-supervised learning model to identify mostly common parasite ova in Thailand. Although small amounts of training data was used to train the proposed model, the result shows superior performance over 95% accuracy. As a result, low values of false positive and false negative based confusion matrix table found revealed the robustness of the proposed models. General accuracy of self-supervised learning based the area under a ROC curve proposed with greater than 94% is also support an outstanding model studied. Therefore, rank of 1% to 10% of fine-tuning data labelled used bring us about a comparable model to that of using a 100% labelled training data. These findings emphasize the transformative potential of the BYOL method for screening of parasitic infection, particularly in resource-limited settings where is a lack of supportive lab equipment and skilled parasitologists to manage a large amount of challenging data in the future.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results