DSpace-CRIS

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
Mammogram Analysis with YOLO Models on an Affordable Embedded System
(2026-01-01)
Intasam, Anongnat
;
Piyawattanametha, Nicholas
;
Promworn, Yuttachon
;
Jiranantanakorn, Titipon
;
Thawornwanchai, Soonthorn
Background/Objectives: Breast cancer persists as a leading cause of female mortality globally. Mammograms are a key screening tool for early detection, although many resource-limited hospitals lack access to skilled radiologists and advanced diagnostic tools. Deep learning-based computer-aided detection (CAD) systems can assist radiologists by automating lesion detection and classification. This study investigates the performance of various You Only Look Once (YOLO) models and a Hybrid Convolutional-Transformer Architecture (YOLOv5, YOLOv8, YOLOv10, YOLOv11, and Real-Time-DEtection Transformer (RT-DETR)) for detecting mammographic lesions on an affordable embedded system. Methods: We developed a custom web-based annotation tool to enhance mammogram labeling accuracy, using a dataset of 3169 patients from Thailand and expert annotations from three radiologists. Lesions were classified into six categories: Masses Benign (MB), Calcifications Benign (CB), Associated Features Benign (AFB), Masses Malignant (MM), Calcifications Malignant (CM), and Associated Features Malignant (AFM). Results: Our results show that the YOLOv11n model is the optimal choice for the NVIDIA Jetson Nano, achieving an accuracy of 0.86 and an inference speed of 6.16 ± 0.31 frames per second. A comparative analysis with a graphics processing unit (GPU)-powered system revealed that the Jetson Nano achieves comparable detection performance at a fraction of the cost. Conclusions: The current research landscape has not yet integrated advanced YOLO versions for embedded deployment in mammography. This method could facilitate screening in clinics without high-end workstations, demonstrating the feasibility of deploying CAD systems in low-resource environments and underscoring its potential for real-world clinical applications.
Some of the metrics are blocked by your
consent settings
Optimizing the Hyperparameter Tuning of YOLOv5 for Breast Cancer Detection
(2023-01-01)
Intasam, Anongnat
;
Promworn, Yuttachon
;
Juhong, Aniwat
;
Thanasitthichai, Somchai
;
Khwayotha, Sirihattaya
This research aims to find the best use optimizer for the task while reducing training time. We optimized the YOLOv5s model and focused on three optimizers, including the Stochastic Gradient Descent (SGD) optimizer, Adaptive Moment Estimation (Adam) optimizer, and Adam with Weight Decay Regularization (AdamW) optimizer. This research utilized 1,471 mammogram images from National Cancer Institute and Udonthani Cancer Hospital, Thailand. A dataset of mammograms was labeled into six classes, including Masses Benign, Masses Malignant, Calcifications Benign, Calcifications Malignant, Associated Features Benign, and Associated Features Malignant, to classify the results accurately. We found that the SGD optimizer outperformed the others, with a mean average precision (mAP) of 0.91, a precision of 0.92, a recall of 0.85, and the shortest training time of about 5.453 hr.
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.
Some of the metrics are blocked by your
consent settings
Comparisons of pap smear classification with deep learning models
(2019-04-01)
Promworn, Yuttachon
;
Pattanasak, Satjana
;
Pintavirooj, Chuchart
;
Piyawattanametha, Wibool
We presented a comparative work of deep learning models for Pap smear classification. The benchmark parameters used to compare are accuracy, specificity, computation time, and sensitivity. Five convolution neural network models were employed to compare performance in detecting the presence of cervical precancerous or cancerous cells from a Pap smear database. The best deep learning model for multiclass classification is the densenet161 with an efficiency of 68.0% which will use to implement in our custom-made whole slide imager.
Some of the metrics are blocked by your
consent settings
A comparative study of 3 deep learning models for Pap smear screening
(2019-01-10)
Promworn, Yuttachon
;
Pintavirooj, C.
;
Piyawattanametha, Wibool
This work presents a comparative study of automated screening procedure for Pap smear with deep learning technology. Three convolution neural network models (AlexNet, densenet161 and resnet101) were employed for detecting the presence of cervical precancerous or cancerous cells from Pap smear database. The study compares accuracy, sensitivity, specificity, and computation time for each deep learning model. The best model is the densenet161 due to its high sensitivity and accuracy which are key factors in an automated Pap smear screening procedure to offer the best early detection of cervical cancer to better treatment outcomes.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results