TSThanongchai Siriapisith

Thanongchai Siriapisith

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Thanongchai Siriapisith has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Detecting COVID-19 in chest X-ray images

    by Worapan Kusakunniran, Punyanuch Borwarnginn, Thanongchai Siriapisith, Sarattha Karnjanapreechakorn, Krittanat Sutassananon, Trongtum Tongdee, Pairash Saiviroonporn

    One reliable way of detecting coronavirus disease 2019 (COVID-19) is using a chest x-ray image due to its complications in the lung parenchyma. This paper proposes a solution for COVID-19 detection in chest x-ray images based on a convolutional neural network (CNN). This CNN-based solution is developed using a modified InceptionV3 as a backbone architecture. Self-attention layers are inserted to modify the backbone such that the number of trainable parameters is reduced and meaningful areas of COVID-19 in chest x-ray images are focused on a training process. The proposed CNN architecture is then learned to construct a model to classify COVID-19 cases from non-COVID-19 cases. It achieves sensitivity, specificity, and accuracy values of 93%, 96%, and 96%, respectively. The model is also further validated on the so-called other normal and abnormal, which are non-COVID-19 cases. Cases of other normal contain chest x-ray images of elderly patients with minimal fibrosis and spondylosis of the spine, whereas other abnormal cases contain chest x-ray images of tuberculosis, pneumonia, and pulmonary edema. The proposed solution could correctly classify them as non-COVID-19 with 92% accuracy. This is a practical scenario where non-COVID-19 cases could cover more than just a normal condition.


  • Open Access

    A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm

    by Thanongchai Siriapisith, Worapan Kusakunniran, Peter Haddawy

    Abdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentation task will be addressed automatically using a deep learning based approach which has been proved to successfully solve several medical imaging problems with excellent performances. This article therefore proposes a new solution of AAA segmentation using deep learning in a type of 3D convolutional neural network (CNN) architecture that also incorporates coordinate information. The tested CNNs are UNet, AG-DSV-UNet, VNet, ResNetMed and DenseVoxNet. The 3D-CNNs are trained with a dataset of high resolution (256 × 256) non-contrast and post-contrast CT images containing 64 slices from each of 200 patients. The dataset consists of contiguous CT slices without augmentation and no post-processing step. The experiments show that incorporation of coordinate information improves the segmentation results. The best accuracies on non-contrast and contrast-enhanced images have average dice scores of 97.13% and 96.74%, respectively. Transfer learning from a pre-trained network of a pre-operative dataset to post-operative endovascular aneurysm repair (EVAR) was also performed. The segmentation accuracy of post-operative EVAR using transfer learning on non-contrast and contrast-enhanced CT datasets achieved the best dice scores of 94.90% and 95.66%, respectively.


  • Open Access

    Multi-level pooling encoder–decoder convolution neural network for MRI reconstruction

    by Sarattha Karnjanapreechakorn, Worapan Kusakunniran, Thanongchai Siriapisith, Pairash Saiviroonporn

    MRI reconstruction is one of the critical processes of MRI machines, along with the acquisition. Due to a slow processing time of signal acquiring, parallel imaging and reconstruction techniques are applied for acceleration. To accelerate the acquisition process, fewer raw data are sampled simultaneously with all RF coils acquisition. Then, the reconstruction uses under-sampled data from all RF coils to restore the final MR image that resembles the fully sampled MR image. These processes have been a traditional procedure inside the MRI system since the invention of the multi-coils MRI machine. This paper proposes the deep learning technique with a lightweight network. The deep neural network is capable of generating the high-quality reconstructed MR image with a high peak signal-to-noise ratio (PSNR). This also opens a high acceleration factor for MR data acquisition. The lightweight network is called Multi-Level Pooling Encoder–Decoder Net (MLPED Net). The proposed network outperforms the traditional encoder–decoder networks on 4-fold acceleration with a significant margin on every evaluation metric. The network can be trained end-to-end, and it is a lightweight structure that can reduce training time significantly. Experimental results are based on a publicly available MRI Knee dataset from the fastMRI competition.


  • Open Access

    A 3D deep learning approach to epicardial fat segmentation in non-contrast and post-contrast cardiac CT images

    by Thanongchai Siriapisith, Worapan Kusakunniran, Peter Haddawy

    Epicardial fat (ECF) is localized fat surrounding the heart muscle or myocardium and enclosed by the thin-layer pericardium membrane. Segmenting the ECF is one of the most difficult medical image segmentation tasks. Since the epicardial fat is infiltrated into the groove between cardiac chambers and is contiguous with cardiac muscle, segmentation requires location and voxel intensity. Recently, deep learning methods have been effectively used to solve medical image segmentation problems in several domains with state-of-the-art performance. This paper presents a novel approach to 3D segmentation of ECF by integrating attention gates and deep supervision into the 3D U-Net deep learning architecture. The proposed method shows significant improvement of the segmentation performance, when compared with standard 3D U-Net. The experiments show excellent performance on non-contrast CT datasets with average Dice scores of 90.06%. Transfer learning from a pre-trained model of a non-contrast CT to contrast-enhanced CT dataset was also performed. The segmentation accuracy on the contrast-enhanced CT dataset achieved a Dice score of 88.16%.


  • Open Access

    COVID-19 detection and heatmap generation in chest x-ray images

    by Worapan Kusakunniran, Punyanuch Borwarnginn, Krittanat Sutassananon, Trongtum Tongdee, Pairash Saiviroonporn, Sarattha Karnjanapreechakorn, Thanongchai Siriapisith

    Chest x-ray images could be used in an automatic image analysis for detecting and classifying abnormalities, including diseases of atelectasis, consolidation, infiltration, pneumothorax, edema, emphysema, fibrosis, effusion, pneumonia, pleural thickening, cardiomegaly, nodule mass, and hernia, as mentioned in the NIH chest x-ray dataset.1 On top of these diseases, which are commonly diagnosed using chest x-ray images, this paper focuses on the new disease of COVID-19 which causes lung damage and can also be detected in chest x-ray images.2 Several methods were proposed recently to address this research domain. Existing methods are reviewed below. All of them were developed based on the convolutional neural network (CNN).


  • A General Approach to Segmentation in CT Grayscale Images using Variable Neighborhood Search

    by Thanongchai Siriapisith, Worapan Kusakunniran, Peter Haddawy

    Medical image segmentation is essential for several tasks including pre-treatment planning and tumor monitoring. Computed tomography (CT) is the most useful imaging modality for abdominal organs and tumors, with benefits of high imaging resolution and few motion artifacts. Unfortunately, CT images contain only limited information of intensity and gradient, which makes accurate segmentation a challenge. In this paper, we propose a 2D segmentation method that applies the concept of variable neighborhood search (VNS) by iteratively alternating search through intensity and gradient spaces. By alternating between the two search spaces, the technique can escape local minima that occur when segmenting in a single search space. The main techniques used in the proposed framework are graph-cut with probability density function (GCPDF) and graph-cut based active contour (GCBAC). The presented method is quantitatively evaluated on a public clinical dataset, which includes various sizes of liver tumor, kidney and spleen. The segmentation performance is evaluated using dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), and volume difference (VD). The presented method achieves the outstanding segmentation performance with a DSC of 84.48±5.84%, 76.93±8.24%, 91.70±2.68% and 89.27±5.21%, for large liver tumor, small liver tumor, kidney and spleen, respectively.


  • Outer Wall Segmentation of Abdominal Aortic Aneurysm by Variable Neighborhood Search Through Intensity and Gradient Spaces

    by Thanongchai Siriapisith, Worapan Kusakunniran, Peter Haddawy

    Aortic aneurysm segmentation remains a challenge. Manual segmentation is a time-consuming process which is not practical for routine use. To address this limitation, several automated segmentation techniques for aortic aneurysm have been developed, such as edge detection-based methods, partial differential equation methods, and graph partitioning methods. However, automatic segmentation of aortic aneurysm is difficult due to high pixel similarity to adjacent tissue and a lack of color information in the medical image, preventing previous work from being applicable to difficult cases. This paper uses uses a variable neighborhood search that alternates between intensity-based and gradient-based segmentation techniques. By alternating between intensity and gradient spaces, the search can escape from local optima of each space. The experimental results demonstrate that the proposed method outperforms the other existing segmentation methods in the literature, based on measurements of dice similarity coefficient and jaccard similarity coefficient at the pixel level. In addition, it is shown to perform well for cases that are difficult to segment.


    • 1 April 2016
      • Vol. 99  (4) , 424-32

    The Outcome of Radiofrequency Ablation of Metastatic Liver Tumors.

    by Somrach Thamtorawat, Satit Rojwatcharapibarn, Trongtum Tongdee, Thanongchai Siriapisith

    To determine outcome of radiofrequency ablation (RFA) in metastatic liver tumor and to evaluate related factors of residual or local tumor recurrences. With Institutional Review Board approval, we retrospectively reviewed RFA procedure between June 2006 and September 2013. Fifty-seven metastatic nodules in 36 patients were treated. The primary tumors were colorectal carcinoma (n = 30), neuroendocrine tumor (n = 2), gallbladder carcinoma (n = 1), adenocarcinoma of head of pancreas (n = 1), and gastrointestinal stromal tumor (n = 2). Tumor characteristics, RFA techniques, success rate, complication, and follow-up imaging were reviewed and recorded Clinical outcome and overall survival were analyzed. Complete ablation were found in 48/57 nodules (84.2%). The mean follow-up time was 17.9 ± 13.1 months (range, 1 to 47 months). Local tumor recurrence were noted in 12/57 nodules (21.1%), which mean time to recurrence was 8.3 ± 3.8 months (2 to 15 months). Residual tumor was associate with tumor larger than 3 cm (p = 0.009). The 1-, 3-, and 5-year overall survival rates were 93.6%, 56.2%, and 20%, respectively. Median overall survival was 37.8 ± 10.9 months. Major complication rate occurred about 5.3%. Radiofrequency ablation is effective and feasible method to treat small metastatic liver tumor Tumor size larger than 3 cm is significant risk factor of residual tumor. Tumor in high-risk location is not associated either incomplete ablation or local tumor recurrence.


    • 1 September 2015
      • Vol. 98  (9) , 902-9

    Growth Rate of Aortic Diameter in Post Treatment of Aortic Dissection.

    by Jitladda Wasinrat, Methininat Lertkowit, Thanongchai Siriapisith

    To evaluate growth rate of aortic diameter true lumen, and false lumen in post endovascular aortic repair of aortic dissection. Between January 2005 and September 2010, 48 consecutive patients with aortic dissection were followed with computed tomographic angiography (CTA), including 18 post-surgical repaired type A patients and 30 type B (14 conservative treatment and 16 post stent-grafting therapy). CTA were performed with a mean of 5.2 scans per patient, and a meanfollow-up of 37.08 months. The diameter ofthe aorta, true lumen, andfalse lumen were measured by axial scan images and multi-planar reformatting (MPR). In medically managed patients with type B aortic dissection, the aortic diameter increased over time at mean rate 1.49 mm/year at proximal descending aorta with greater increased in size ofthe false lumen diameters than the true lumen diameter. In post-surgical repaired type A and post stent-grafting therapy type B aortic dissection, aortic diameter did not change over time. In addition, 12 of 16 patients (75%)patients with post stent-grafting therapy type B dissection hadpartial thrombosed in false lumen and 4 of 16 patients (25%) had complete resolution offalse lumen. In post-surgical repaired type A and post stent-grafting therapy type B aortic dissection, aortic diameter did not change over time. Type B aortic dissection with medical treatment had minimal increased in aortic diameter over time. The results suggested that uncomplicated type B aortic dissection requires on-going medical treatment.