1
|
Tiankanon K, Aniwan S, Kerr SJ, Mekritthikrai K, Kongtab N, Wisedopas N, Piyachaturawat P, Kulpatcharapong S, Linlawan S, Phromnil P, Muangpaisarn P, Orprayoon T, Chanyaswad J, Sunthornwechapong P, Vateekul P, Kullavanijaya P, Rerknimitr R. Improvement of adenoma detection rate by two computer-aided colonic polyp detection systems in high adenoma detectors: a randomized multicenter trial. Endoscopy 2024; 56:273-282. [PMID: 37963587 DOI: 10.1055/a-2210-7999] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/16/2023]
Abstract
BACKGROUND This study aimed to evaluate the benefits of a self-developed computer-aided polyp detection system (SD-CADe) and a commercial system (CM-CADe) for high adenoma detectors compared with white-light endoscopy (WLE) as a control. METHODS Average-risk 50-75-year-old individuals who underwent screening colonoscopy at five referral centers were randomized to SD-CADe, CM-CADe, or WLE groups (1:1:1 ratio). Trainees and staff with an adenoma detection rate (ADR) of ≥35% were recruited. The primary outcome was ADR. Secondary outcomes were the proximal adenoma detection rate (pADR), advanced adenoma detection rate (AADR), and the number of adenomas, proximal adenomas, and advanced adenomas per colonoscopy (APC, pAPC, and AAPC, respectively). RESULTS The study enrolled 1200 participants. The ADR in the control, CM-CADe, and SD-CADe groups was 38.3%, 50.0%, and 54.8%, respectively. The pADR was 23.0%, 32.3%, and 38.8%, respectively. AADR was 6.0%, 10.3%, and 9.5%, respectively. After adjustment, the ADR and pADR in both intervention groups were significantly higher than in controls (all P<0.05). The APC in the control, CM-CADe, and SD-CADe groups was 0.66, 1.04, and 1.16, respectively. The pAPC was 0.33, 0.53, and 0.64, respectively, and the AAPC was 0.07, 0.12, and 0.10, respectively. Both CADe systems showed significantly higher APC and pAPC than WLE. AADR and AAPC were improved in both CADe groups versus control, although the differences were not statistically significant. CONCLUSION Even in high adenoma detectors, CADe significantly improved ADR and APC. The AADR tended to be higher with both systems, and this may enhance colorectal cancer prevention.
Collapse
Affiliation(s)
- Kasenee Tiankanon
- Division of Gastroenterology, Chulalongkorn University, Bangkok, Thailand
- Gastrointestinal Endoscopy Excellence Center, King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Satimai Aniwan
- Division of Gastroenterology, Chulalongkorn University, Bangkok, Thailand
- Gastrointestinal Endoscopy Excellence Center, King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Stephen J Kerr
- Biostatistics Excellence Center, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
- The Kirby Institute, University of New South Wales, Sydney, Australia
| | - Krittaya Mekritthikrai
- Division of Gastroenterology, Chulalongkorn University, Bangkok, Thailand
- Gastrointestinal Endoscopy Excellence Center, King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Natanong Kongtab
- Division of Gastroenterology, Chulalongkorn University, Bangkok, Thailand
- Gastrointestinal Endoscopy Excellence Center, King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Naruemon Wisedopas
- Department of Pathology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | | | | | | | - Poonrada Phromnil
- Department of Medicine, Khlong Khlung Hospital, Kamphaeng Phet, Thailand
| | - Puth Muangpaisarn
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Prapokklao Hospital, Chanthaburi, Thailand
| | - Theerapat Orprayoon
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Prapokklao Hospital, Chanthaburi, Thailand
| | - Jaruwan Chanyaswad
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Prapokklao Hospital, Chanthaburi, Thailand
| | | | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Pinit Kullavanijaya
- Division of Gastroenterology, Chulalongkorn University, Bangkok, Thailand
- Gastrointestinal Endoscopy Excellence Center, King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Rungsun Rerknimitr
- Division of Gastroenterology, Chulalongkorn University, Bangkok, Thailand
- Gastrointestinal Endoscopy Excellence Center, King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| |
Collapse
|
2
|
Tiankanon K, Karuehardsuwan J, Aniwan S, Mekaroonkamol P, Sunthornwechapong P, Navadurong H, Tantitanawat K, Mekritthikrai K, Samutrangsi S, Vateekul P, Rerknimitr R. Performance comparison between two computer-aided detection colonoscopy models by trainees using different false positive thresholds: a cross-sectional study in Thailand. Clin Endosc 2024; 57:217-225. [PMID: 38556473 PMCID: PMC10984740 DOI: 10.5946/ce.2023.145] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 07/24/2023] [Accepted: 09/25/2023] [Indexed: 04/02/2024] Open
Abstract
BACKGROUND/AIMS This study aims to compare polyp detection performance of "Deep-GI," a newly developed artificial intelligence (AI) model, to a previously validated AI model computer-aided polyp detection (CADe) using various false positive (FP) thresholds and determining the best threshold for each model. METHODS Colonoscopy videos were collected prospectively and reviewed by three expert endoscopists (gold standard), trainees, CADe (CAD EYE; Fujifilm Corp.), and Deep-GI. Polyp detection sensitivity (PDS), polyp miss rates (PMR), and false-positive alarm rates (FPR) were compared among the three groups using different FP thresholds for the duration of bounding boxes appearing on the screen. RESULTS In total, 170 colonoscopy videos were used in this study. Deep-GI showed the highest PDS (99.4% vs. 85.4% vs. 66.7%, p<0.01) and the lowest PMR (0.6% vs. 14.6% vs. 33.3%, p<0.01) when compared to CADe and trainees, respectively. Compared to CADe, Deep-GI demonstrated lower FPR at FP thresholds of ≥0.5 (12.1 vs. 22.4) and ≥1 second (4.4 vs. 6.8) (both p<0.05). However, when the threshold was raised to ≥1.5 seconds, the FPR became comparable (2 vs. 2.4, p=0.3), while the PMR increased from 2% to 10%. CONCLUSION Compared to CADe, Deep-GI demonstrated a higher PDS with significantly lower FPR at ≥0.5- and ≥1-second thresholds. At the ≥1.5-second threshold, both systems showed comparable FPR with increased PMR.
Collapse
Affiliation(s)
- Kasenee Tiankanon
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Julalak Karuehardsuwan
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Satimai Aniwan
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Parit Mekaroonkamol
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | | | - Huttakan Navadurong
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Kittithat Tantitanawat
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Krittaya Mekritthikrai
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Salin Samutrangsi
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Rungsun Rerknimitr
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai red cross, Bangkok, Thailand
| |
Collapse
|
3
|
Phuenpathom W, Panyakaew P, Vateekul P, Surangsrirat D, Bhidayasiri R. Residual effects of combined vibratory and plantar stimulation while seated influences plantar pressure and spatiotemporal gait measures in individuals with Parkinson's disease exhibiting freezing of gait. Front Aging Neurosci 2024; 15:1280324. [PMID: 38264550 PMCID: PMC10803580 DOI: 10.3389/fnagi.2023.1280324] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2023] [Accepted: 12/27/2023] [Indexed: 01/25/2024] Open
Abstract
Introduction Combined plantar pressure and vibratory stimulation has been shown to decrease freezing of gait (FOG) episodes and improve spatiotemporal gait parameters compared to single stimulation in Parkinson's disease (PD) patients with FOG. However, the effect of combined plantar stimulations on plantar pressure analysis has never been explored. Methods Forty PD patients with frequent FOG were allocated to either FOG shoes embedded with a 100 Hz vibratory stimulation at the Achilles tendons and a soft thickened silicone pad at the hallux and sole, or sham shoes with a non-working vibratory motor and a flat non-pressure silicone pad (20 patients per arm) while seated for 96 s. The objective gait and plantar pressure analysis were measured immediately after the stimulation. Outcomes included the normalized percentage of changes in percent FOG (%FOG) and plantar pressure in the heel-strike and push-off phase that were compared between pre- and post-stimulations. Results The FOG shoes group showed significantly decreased %FOG (81.5 ± 28.9% vs. 6.8 ± 22.1%, p < 0.001), plantar pressure in the heel-strike (47.8 ± 43.7% vs. 4.3 ± 9.8%, p < 0.001), plantar pressure in the push-off (57.7 ± 59.6% vs. 6.2 ± 11.6%, p < 0.001), force time integral (FTI) (40.9 ± 32.5% vs. 6.6 ± 17.3%, p < 0.001), and decreased heel contact time (19.3 ± 12.3% vs. 22.7 ± 32.5%, p < 0.001) when compared to the sham group. There was a strong negative correlation between %FOG and peak plantar pressure (r = -0.440, p = 0.005), plantar pressure in the heel-strike (r = -0.847, p < 0.001). Conclusion Our study demonstrated that the FOG shoe could decrease FOG episodes by improving the heel-strike pressure, toe push-off and normalized heel-to-toe plantar pressure, suggesting that modification inputs from the peripheral sensory systems might significant improvement in FOG in PD.
Collapse
Affiliation(s)
- Warongporn Phuenpathom
- Chulalongkorn Centre of Excellence for Parkinson’s Disease and Related Disorders, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Pattamon Panyakaew
- Chulalongkorn Centre of Excellence for Parkinson’s Disease and Related Disorders, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Decho Surangsrirat
- Assistive Technology and Medical Devices Research Center, National Science and Technology Development Agency, Pathum Thani, Thailand
| | - Roongroj Bhidayasiri
- Chulalongkorn Centre of Excellence for Parkinson’s Disease and Related Disorders, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
- The Academy of Science, The Royal Society of Thailand, Bangkok, Thailand
| |
Collapse
|
4
|
Mahayossanunt Y, Nupairoj N, Hemrungrojn S, Vateekul P. Explainable Depression Detection Based on Facial Expression Using LSTM on Attentional Intermediate Feature Fusion with Label Smoothing. Sensors (Basel) 2023; 23:9402. [PMID: 38067773 PMCID: PMC10708765 DOI: 10.3390/s23239402] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 10/26/2023] [Accepted: 11/23/2023] [Indexed: 12/18/2023]
Abstract
Machine learning is used for a fast pre-diagnosis approach to prevent the effects of Major Depressive Disorder (MDD). The objective of this research is to detect depression using a set of important facial features extracted from interview video, e.g., radians, gaze at angles, action unit intensity, etc. The model is based on LSTM with an attention mechanism. It aims to combine those features using the intermediate fusion approach. The label smoothing was presented to further improve the model's performance. Unlike other black-box models, the integrated gradient was presented as the model explanation to show important features of each patient. The experiment was conducted on 474 video samples collected at Chulalongkorn University. The data set was divided into 134 depressed and 340 non-depressed categories. The results showed that our model is the winner, with a 88.89% F1-score, 87.03% recall, 91.67% accuracy, and 91.40% precision. Moreover, the model can capture important features of depression, including head turning, no specific gaze, slow eye movement, no smiles, frowning, grumbling, and scowling, which express a lack of concentration, social disinterest, and negative feelings that are consistent with the assumptions in the depressive theories.
Collapse
Affiliation(s)
- Yanisa Mahayossanunt
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand; (Y.M.); (N.N.)
| | - Natawut Nupairoj
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand; (Y.M.); (N.N.)
- Center of Excellence in Digital and AI Innovation for Mental Health (AIMET), Chulalongkorn Unversity, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand
| | - Solaphat Hemrungrojn
- Center of Excellence in Digital and AI Innovation for Mental Health (AIMET), Chulalongkorn Unversity, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand
- Department of Psychiatry, Faculty of Medicine, Chulalongkorn University, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand
- Cognitive Fitness and Biopsychiatry Technology Research Unit, Faculty of Medicine, Chulalongkorn University, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand; (Y.M.); (N.N.)
- Center of Excellence in Digital and AI Innovation for Mental Health (AIMET), Chulalongkorn Unversity, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand
- Cognitive Fitness and Biopsychiatry Technology Research Unit, Faculty of Medicine, Chulalongkorn University, Phayathai Rd, Pathumwan, Bangkok 10330, Thailand
| |
Collapse
|
5
|
Pornvoraphat P, Tiankanon K, Pittayanon R, Sunthornwetchapong P, Vateekul P, Rerknimitr R. Real-time gastric intestinal metaplasia diagnosis tailored for bias and noisy-labeled data with multiple endoscopic imaging. Comput Biol Med 2023; 154:106582. [PMID: 36738708 DOI: 10.1016/j.compbiomed.2023.106582] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Revised: 01/11/2023] [Accepted: 01/22/2023] [Indexed: 01/26/2023]
Abstract
This work presents real-time segmentation viz. gastric intestinal metaplasia (GIM). Recently, GIM segmentation of endoscopic images has been carried out to differentiate GIM from a healthy stomach. However, real-time detection is difficult to achieve. Conditions are challenging, and include multiple color modes (white light endoscopy and narrow-band imaging), other abnormal lesions (erosion and ulcer), noisy labels etc. Herein, our model is based on BiSeNet and can overcome the many issues regarding GIM. Application of auxiliary head and additional loss are seen to improve performance as well as enhance multiple color modes accurately. Further, multiple pre-processing techniques are utilized for leveraging detection performance: namely, location-wise negative sampling, jigsaw augmentation, and label smoothing. Finally, the decision threshold can be adjusted separately for each color mode. Work undertaken at King Chulalongkorn Memorial Hospital examined 940 histologically proven GIM images and 1239 non-GIM images, obtained over 173 frames per second (FPS). In terms of accuracy, our model is seen to outperform all baselines. Our results demonstrate sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union (IoU), achieving GIM segmentation values of 91%, 96%, 91%, 91%, 96%, and 55%, respectively.
Collapse
Affiliation(s)
- Passin Pornvoraphat
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Pathumwan, Bangkok, Thailand
| | - Kasenee Tiankanon
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Rapat Pittayanon
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Phanukorn Sunthornwetchapong
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Pathumwan, Bangkok, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Pathumwan, Bangkok, Thailand.
| | - Rungsun Rerknimitr
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand.
| |
Collapse
|
6
|
Phuenpathom W, Panyakaew P, Vateekul P, Surangsrirat D, Hiransuthikul A, Bhidayasiri R. Vibratory and plantar pressure stimulation: Steps to improve freezing of gait in Parkinson's disease. Parkinsonism Relat Disord 2022; 105:43-51. [PMID: 36347154 DOI: 10.1016/j.parkreldis.2022.10.024] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Revised: 10/20/2022] [Accepted: 10/23/2022] [Indexed: 11/08/2022]
Abstract
INTRODUCTION Freezing of gait (FOG) is a devastating symptom that develops in patients with advanced Parkinson's disease (PD) and is often unresponsive to pharmacological treatment. Recent research suggests that FOG may result from dysfunctional plantar peripheral sensory systems. The impact of combined plantar pressure and vibratory stimulation over vibratory or pressure alone on FOG remains unexplored. METHODS PD patients with FOG were randomised into four groups and treated with combined vibratory and pressure stimulation, vibratory stimulation alone, pressure stimulation alone, or controls (no stimulation). Vibratory stimulation targeted both Achilles' tendons. Simultaneous bilateral pressure stimulation was applied to the first hallux, first metatarsal bone, and the sole. The primary outcome included normalized percent changes in percent FOG measured both pre- and immediately post-stimulation. Other outcomes including clinical rating scale, response to questionnaires, number and duration of freezing episodes, and spatiotemporal gait parameters at pre- and freezing episodes were also explored. RESULTS Sixty PD patients participated in the study. Patients who were treated with combined vibratory and pressure stimulation responded with significant decreases in normalized percent changes of percent FOG (62.75 ± 25.54%, p < 0.001) compared with those treated with vibration alone (11.38 ± 8.29%, p < 0.001), pressure alone (15.15 ± 16.18%, p < 0.001), or controls (8.59 ± 16.85%, p < 0.001). CONCLUSION Our study demonstrated the benefit of combined vibratory and pressure stimulation on FOG suggesting that this strategy might be developed as a novel treatment modality for PD patients with FOG.
Collapse
Affiliation(s)
- Warongporn Phuenpathom
- Chulalongkorn Centre of Excellence for Parkinson's Disease & Related Disorders, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand; Doctor of Philosophy Programme in Medicine (Neurology), Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Pattamon Panyakaew
- Chulalongkorn Centre of Excellence for Parkinson's Disease & Related Disorders, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Decho Surangsrirat
- Assistive Technology and Medical Devices Research Center, National Science and Technology Development Agency, Pathum Thani, Thailand
| | - Akarin Hiransuthikul
- Department of Preventive and Social Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Roongroj Bhidayasiri
- Chulalongkorn Centre of Excellence for Parkinson's Disease & Related Disorders, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Thai Red Cross Society, Bangkok, Thailand; The Academy of Science, The Royal Society of Thailand, Bangkok, 10330, Thailand.
| |
Collapse
|
7
|
Siripoppohn V, Pittayanon R, Tiankanon K, Faknak N, Sanpavat A, Klaikaew N, Vateekul P, Rerknimitr R. Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach. Clin Endosc 2022; 55:390-400. [PMID: 35534933 PMCID: PMC9178134 DOI: 10.5946/ce.2022.005] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/24/2021] [Accepted: 01/26/2022] [Indexed: 11/14/2022] Open
Abstract
Background/Aims Previous artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy.
Methods Investigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values.
Results From the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively.
Conclusions The bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.
Collapse
Affiliation(s)
- Vitchaya Siripoppohn
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Rapat Pittayanon
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Kasenee Tiankanon
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Natee Faknak
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Anapat Sanpavat
- Department of Pathology, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Naruemon Klaikaew
- Department of Pathology, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
- Correspondence: Peerapon Vateekul Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, 254 Phaya Thai Rd, Wang Mai, Pathum Wan, Bangkok 10330, Thailand E-mail:
| | - Rungsun Rerknimitr
- Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
- Correspondence: Rungsun Rerknimitr Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Rama 4 Road, Patumwan, Bangkok 10330, Thailand E-mail:
| |
Collapse
|
8
|
Dayan I, Roth HR, Zhong A, Harouni A, Gentili A, Abidin AZ, Liu A, Costa AB, Wood BJ, Tsai CS, Wang CH, Hsu CN, Lee CK, Ruan P, Xu D, Wu D, Huang E, Kitamura FC, Lacey G, de Antônio Corradi GC, Nino G, Shin HH, Obinata H, Ren H, Crane JC, Tetreault J, Guan J, Garrett JW, Kaggie JD, Park JG, Dreyer K, Juluru K, Kersten K, Rockenbach MABC, Linguraru MG, Haider MA, AbdelMaseeh M, Rieke N, Damasceno PF, E Silva PMC, Wang P, Xu S, Kawano S, Sriswasdi S, Park SY, Grist TM, Buch V, Jantarabenjakul W, Wang W, Tak WY, Li X, Lin X, Kwon YJ, Quraini A, Feng A, Priest AN, Turkbey B, Glicksberg B, Bizzo B, Kim BS, Tor-Díez C, Lee CC, Hsu CJ, Lin C, Lai CL, Hess CP, Compas C, Bhatia D, Oermann EK, Leibovitz E, Sasaki H, Mori H, Yang I, Sohn JH, Murthy KNK, Fu LC, de Mendonça MRF, Fralick M, Kang MK, Adil M, Gangai N, Vateekul P, Elnajjar P, Hickman S, Majumdar S, McLeod SL, Reed S, Gräf S, Harmon S, Kodama T, Puthanakit T, Mazzulli T, de Lavor VL, Rakvongthai Y, Lee YR, Wen Y, Gilbert FJ, Flores MG, Li Q. Federated learning for predicting clinical outcomes in patients with COVID-19. Nat Med 2021; 27:1735-1743. [PMID: 34526699 PMCID: PMC9157510 DOI: 10.1038/s41591-021-01506-3] [Citation(s) in RCA: 152] [Impact Index Per Article: 50.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2020] [Accepted: 08/13/2021] [Indexed: 02/08/2023]
Abstract
Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.
Collapse
Affiliation(s)
- Ittai Dayan
- MGH Radiology and Harvard Medical School, Boston, MA, USA
| | | | - Aoxiao Zhong
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
- School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA
| | | | | | | | | | | | - Bradford J Wood
- Radiology & Imaging Sciences/Clinical Center, National Institutes of Health, Bethesda, MD, USA
- National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
| | - Chien-Sung Tsai
- Division of Cardiovascular Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan
| | - Chih-Hung Wang
- Department of Otolaryngology-Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan
- Graduate Institute of Medical Sciences, National Defense Medical Center, Taipei, Taiwan
| | - Chun-Nan Hsu
- Center for Research in Biological Systems, University of California, San Diego, CA, USA
| | - C K Lee
- NVIDIA, Santa Clara, CA, USA
| | | | | | - Dufan Wu
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | | | | | | | | | - Gustavo Nino
- Division of Pediatric Pulmonary and Sleep Medicine, Children's National Hospital, Washington, DC, USA
| | - Hao-Hsin Shin
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | | | - Hui Ren
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Jason C Crane
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA
| | | | | | - John W Garrett
- Departments of Radiology and Medical Physics, The University of Wisconsin-Madison School of Medicine and Public Health, Madison, WI, USA
| | - Joshua D Kaggie
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge, Cambridge, UK
| | - Jung Gil Park
- Department of Internal Medicine, Yeungnam University College of Medicine, Daegu, South Korea
| | - Keith Dreyer
- MGH Radiology and Harvard Medical School, Boston, MA, USA
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA, USA
| | - Krishna Juluru
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | | | | | - Marius George Linguraru
- Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, USA
- Departments of Radiology and Pediatrics, The George Washington University School of Medicine and Health Sciences, Washington, DC, USA
| | - Masoom A Haider
- Joint Dept. of Medical Imaging, Sinai Health System, University of Toronto, Toronto, Ontario, Canada
- Lunenfeld-Tanenbaum Research Institute, Toronto, Ontario, Canada
| | | | | | - Pablo F Damasceno
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA
| | | | - Pochuan Wang
- MeDA Lab Institute of Applied Mathematical Sciences, National Taiwan University, Taipei, Taiwan
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Sheng Xu
- Radiology & Imaging Sciences/Clinical Center, National Institutes of Health, Bethesda, MD, USA
- National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
| | | | - Sira Sriswasdi
- Research Affairs, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
- Center for Artificial Intelligence in Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Soo Young Park
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | - Thomas M Grist
- Departments of Radiology, Medical Physics, and Biomedical Engineering, The University of Wisconsin-Madison School of Medicine and Public Health, Madison, WI, USA
| | - Varun Buch
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA, USA
| | - Watsamon Jantarabenjakul
- Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
- Thai Red Cross Emerging Infectious Diseases Clinical Center, King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Weichung Wang
- MeDA Lab Institute of Applied Mathematical Sciences, National Taiwan University, Taipei, Taiwan
- Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Won Young Tak
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | - Xiang Li
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Xihong Lin
- Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA, USA
| | - Young Joon Kwon
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | | | | | - Andrew N Priest
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, Cambridge University Hospital, Cambridge, UK
| | - Baris Turkbey
- National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
- Department of Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD, USA
| | - Benjamin Glicksberg
- Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai and Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Bernardo Bizzo
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA, USA
| | - Byung Seok Kim
- Department of Internal Medicine, Catholic University of Daegu School of Medicine, Daegu, South Korea
| | - Carlos Tor-Díez
- Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, USA
| | - Chia-Cheng Lee
- Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan
| | - Chia-Jung Hsu
- Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan
| | - Chin Lin
- School of Medicine, National Defense Medical Center, Taipei, Taiwan
- School of Public Health, National Defense Medical Center, Taipei, Taiwan
- Graduate Institute of Life Sciences, National Defense Medical Center, Taipei, Taiwan
| | - Chiu-Ling Lai
- Medical Review and Pharmaceutical Benefits Division, National Health Insurance Administration, Taipei, Taiwan
| | - Christopher P Hess
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA
| | | | | | - Eric K Oermann
- Department of Neurosurgery, NYU Grossman School of Medicine, New York, NY, USA
| | - Evan Leibovitz
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA, USA
| | | | - Hitoshi Mori
- Self-Defense Forces Central Hospital, Tokyo, Japan
| | | | - Jae Ho Sohn
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA
| | | | - Li-Chen Fu
- MOST/NTU All Vista Healthcare Center, Center for Artificial Intelligence and Advanced Robotics, National Taiwan University, Taipei, Taiwan
| | | | - Mike Fralick
- Division of General Internal Medicine and Geriatrics (Fralick), Sinai Health System, Toronto, Ontario, Canada
| | - Min Kyu Kang
- Department of Internal Medicine, Yeungnam University College of Medicine, Daegu, South Korea
| | | | - Natalie Gangai
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | | | - Sarah Hickman
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge, Cambridge, UK
| | - Sharmila Majumdar
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA
| | - Shelley L McLeod
- Schwartz/Reisman Emergency Medicine Institute, Sinai Health, Toronto, Ontario, Canada
- Department of Family and Community Medicine, University of Toronto, Toronto, Ontario, Canada
| | - Sheridan Reed
- Radiology & Imaging Sciences/Clinical Center, National Institutes of Health, Bethesda, MD, USA
- National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
| | - Stefan Gräf
- Department of Medicine and NIHR BioResource for Translational Research, NIHR Cambridge Biomedical Research Centre, University of Cambridge, Cambridge, UK
| | - Stephanie Harmon
- National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
- Clinical Research Directorate, Frederick National Laboratory for Cancer, National Cancer Institute, Frederick, MD, USA
| | | | - Thanyawee Puthanakit
- Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
- Thai Red Cross Emerging Infectious Diseases Clinical Center, King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Tony Mazzulli
- Department of Microbiology, Sinai Health/University Health Network, Toronto, Ontario, Canada
- Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Ontario, Canada
- Public Health Ontario Laboratories, Toronto, Ontario, Canada
| | | | - Yothin Rakvongthai
- Chulalongkorn University Biomedical Imaging Group and Division of Nuclear Medicine, Department of Radiology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Yu Rim Lee
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | | | - Fiona J Gilbert
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge, Cambridge, UK
| | | | - Quanzheng Li
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
9
|
Phokaewvarangkul O, Vateekul P, Wichakam I, Anan C, Bhidayasiri R. Using Machine Learning for Predicting the Best Outcomes With Electrical Muscle Stimulation for Tremors in Parkinson's Disease. Front Aging Neurosci 2021; 13:727654. [PMID: 34566628 PMCID: PMC8461308 DOI: 10.3389/fnagi.2021.727654] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2021] [Accepted: 08/16/2021] [Indexed: 11/21/2022] Open
Abstract
Recent studies have identified that peripheral stimulation in Parkinson’s disease (PD) is effective in tremor reduction, indicating that a peripheral feedback loop plays an important role in the tremor reset mechanism. This was an open-label, quasi-experimental, pre- and post-test design, single-blind, single-group study involving 20 tremor-dominant PD patients. The objective of this study is to explore the effect of electrical muscle stimulation (EMS) as an adjunctive treatment for resting tremor during “on” period and to identify the best machine learning model to predict the suitable stimulation level that will yield the longest period of tremor reduction or tremor reset time. In this study, we used a Parkinson’s glove to evaluate, stimulate, and quantify the tremors of PD patients. This adjustable glove incorporates a 3-axis gyroscope to measure tremor signals and an EMS to provide an on-demand muscle stimulation to suppress tremors. Machine learning models were applied to identify the suitable pulse amplitude (stimulation level) in five classes that led to the longest tremor reset time. The study was registered at the www.clinicaltrials.gov under the name “The Study of Rest Tremor Suppression by Using Electrical Muscle Stimulation” (NCT02370108). Twenty tremor-dominant PD patients were recruited. After applying an average pulse amplitude of 6.25 (SD 2.84) mA and stimulation period of 440.7 (SD 560.82) seconds, the total time of tremor reduction, or tremor reset time, was 329.90 (SD 340.91) seconds. A significant reduction in tremor parameters during stimulation was demonstrated by a reduction of Unified Parkinson’s Disease Rating Scale (UPDRS) scores, and objectively, with a reduction of gyroscopic data (p < 0.05, each). None of the subjects reported any serious adverse events. We also compared gyroscopic data with five machine learning techniques: Logistic Regression, Random Forest, Support Vector Machine (SVM), Neural Network (NN), and Long-Short-Term-Memory (LSTM). The machine learning model that gave the highest accuracy was LSTM, which obtained: accuracy = 0.865 and macro-F1 = 0.736. This study confirms the efficacy of EMS in the reduction of resting tremors in PD. LSTM was identified as the most effective model for predicting pulse amplitude that would elicit the longest tremor reset time. Our study provides further insight on the tremor reset mechanism in PD.
Collapse
Affiliation(s)
- Onanong Phokaewvarangkul
- Department of Medicine, Faculty of Medicine, Chulalongkorn Centre of Excellence for Parkinson's Disease and Related Disorders, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Itsara Wichakam
- Department of Medicine, Faculty of Medicine, Chulalongkorn Centre of Excellence for Parkinson's Disease and Related Disorders, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Chanawat Anan
- Department of Medicine, Faculty of Medicine, Chulalongkorn Centre of Excellence for Parkinson's Disease and Related Disorders, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Roongroj Bhidayasiri
- Department of Medicine, Faculty of Medicine, Chulalongkorn Centre of Excellence for Parkinson's Disease and Related Disorders, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand.,The Academy of Science, The Royal Society of Thailand, Bangkok, Thailand
| |
Collapse
|
10
|
Flores M, Dayan I, Roth H, Zhong A, Harouni A, Gentili A, Abidin A, Liu A, Costa A, Wood B, Tsai CS, Wang CH, Hsu CN, Lee CK, Ruan C, Xu D, Wu D, Huang E, Kitamura F, Lacey G, César de Antônio Corradi G, Shin HH, Obinata H, Ren H, Crane J, Tetreault J, Guan J, Garrett J, Park JG, Dreyer K, Juluru K, Kersten K, Bezerra Cavalcanti Rockenbach MA, Linguraru M, Haider M, AbdelMaseeh M, Rieke N, Damasceno P, Cruz E Silva PM, Wang P, Xu S, Kawano S, Sriswasdi S, Park SY, Grist T, Buch V, Jantarabenjakul W, Wang W, Tak WY, Li X, Lin X, Kwon F, Gilbert F, Kaggie J, Li Q, Quraini A, Feng A, Priest A, Turkbey B, Glicksberg B, Bizzo B, Kim BS, Tor-Diez C, Lee CC, Hsu CJ, Lin C, Lai CL, Hess C, Compas C, Bhatia D, Oermann E, Leibovitz E, Sasaki H, Mori H, Yang I, Sohn JH, Keshava Murthy KN, Fu LC, Furtado de Mendonça MR, Fralick M, Kang MK, Adil M, Gangai N, Vateekul P, Elnajjar P, Hickman S, Majumdar S, McLeod S, Reed S, Graf S, Harmon S, Kodama T, Puthanakit T, Mazzulli T, de Lima Lavor V, Rakvongthai Y, Lee YR, Wen Y. Federated Learning used for predicting outcomes in SARS-COV-2 patients. Res Sq 2021:rs.3.rs-126892. [PMID: 33442676 PMCID: PMC7805458 DOI: 10.21203/rs.3.rs-126892/v1] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
'Federated Learning' (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the "EXAM" (EMR CXR AI Model) model. EXAM achieved an average Area Under the Curve (AUC) of over 0.92, an average improvement of 16%, and a 38% increase in generalisability over local models. The FL paradigm was successfully applied to facilitate a rapid data science collaboration without data exchange, resulting in a model that generalised across heterogeneous, unharmonized datasets. This provided the broader healthcare community with a validated model to respond to COVID-19 challenges, as well as set the stage for broader use of FL in healthcare.
Collapse
Affiliation(s)
| | | | | | - Aoxiao Zhong
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | | | | | | | | | | | - Bradford Wood
- Radiology & Imaging Sciences / Clinical Center, National Institutes of Health
| | - Chien-Sung Tsai
- Division of Cardiovascular Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C
| | - Chih-Hung Wang
- Tri-Service General Hospital, National Defense Medical Center
| | - Chun-Nan Hsu
- Center for Research in Biological Systems, University of California, San Diego
| | | | | | | | - Dufan Wu
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | | | | | | | | | | | | | - Hui Ren
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | - Jason Crane
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA
| | | | | | - John Garrett
- The University of Wisconsin-Madison School of Medicine and Public Health
| | | | - Keith Dreyer
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA
| | | | | | | | - Marius Linguraru
- Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital and School of Medicine and Health Sciences, George Washington University, Washington, DC
| | - Masoom Haider
- Joint Dept. of Medical Imaging, Sinai Health System, University of Toronto, Toronto, Canada and Lunenfeld-Tanenbaum Research Institute, Toronto, Canada
| | | | | | - Pablo Damasceno
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA
| | | | - Pochuan Wang
- MeDA Lab and Institute of Applied Mathematical Sciences, National Taiwan University, Taipei, Taiwan
| | - Sheng Xu
- Center for Interventional Oncology, National Institutes of Health, Bethesda, MD, USA
| | | | | | - Soo Young Park
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | | | - Varun Buch
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA
| | - Watsamon Jantarabenjakul
- Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand and Thai Red Cross Emerging Infectious Diseases Clinical Center, King Chulalongkorn Memorial Hospital, Bang
| | | | - Won Young Tak
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | - Xiang Li
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | - Xihong Lin
- Harvard T.H. Chan School of Public Health
| | | | | | - Josh Kaggie
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge
| | - Quanzheng Li
- Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | | | | | - Andrew Priest
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, Cambridge University Hospital
| | | | | | - Bernardo Bizzo
- Center for Clinical Data Science, Massachusetts General Brigham, Boston, MA
| | - Byung Seok Kim
- Department of Internal Medicine, Catholic University of Daegu School of Medicine, Daegu, South Korea
| | - Carlos Tor-Diez
- Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC
| | - Chia-Cheng Lee
- Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C. and Division of Colorectal Surgery, Department of Surgery, Tri-Service General H
| | - Chia-Jung Hsu
- Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C
| | - Chin Lin
- School of Medicine, National Defense Medical Center, Taipei, Taiwan, R.O.C. and School of Public Health, National Defense Medical Center, Taipei, Taiwan, R.O.C. and Graduate Institute of Life Scienc
| | - Chiu-Ling Lai
- Medical Review and Pharmaceutical Benefits Division, National Health Insurance Administration, Taipei. Taiwan
| | | | | | | | | | - Evan Leibovitz
- The Center for Clinical Data Science, Mass General Brigham
| | | | | | | | - Jae Ho Sohn
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA
| | | | - Li-Chen Fu
- MOST/NTU All Vista Healthcare Center, Center for Artificial Intelligence and Advanced Robotics, National Taiwan University, Taipei, Taiwan
| | | | - Mike Fralick
- Division of General Internal Medicine and Geriatrics (Fralick), Sinai Health System, Toronto, Canada
| | - Min Kyu Kang
- Department of Internal Medicine, Yeungnam University College of Medicine, Daegu, South Korea
| | | | | | - Peerapon Vateekul
- Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University
| | | | - Sarah Hickman
- Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge
| | - Sharmila Majumdar
- Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA
| | - Shelley McLeod
- Schwartz/Reisman Emergency Medicine Institute, Sinai Health, Toronto, ON, Canada and Department of Family and Community Medicine, University of Toronto, Toronto, ON, Canada
| | - Sheridan Reed
- Center for Interventional Oncology, National Institutes of Health, Bethesda, MD, USA
| | | | | | | | - Thanyawee Puthanakit
- Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Center of Excellence in Pediatric Infectious Diseases and Vaccine, Chulalongkorn University
| | - Tony Mazzulli
- Department of Microbiology, Sinai Health/University Health Network, Toronto, Canada and Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto. Canada Public Health Ontar
| | | | - Yothin Rakvongthai
- Chulalongkorn University Biomedical Imaging Group and Division of Nuclear Medicine, Department of Radiology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Yu Rim Lee
- Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea
| | | |
Collapse
|
11
|
Udomcharoenchaikit C, Boonkwan P, Vateekul P. Adversarial Evaluation of Robust Neural Sequential Tagging Methods for Thai Language. ACM T ASIAN LOW-RESO 2020. [DOI: 10.1145/3383201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
Abstract
Sequential tagging tasks, such as Part-Of-Speech (POS) tagging and Named-Entity Recognition, are the building blocks of many natural language processing applications. Although prior works have reported promising results in standard settings, they often underperform on non-standard text, such as microblogs and social media. In this article, we introduce an adversarial evaluation scheme for the Thai language by creating adversarial examples based on known spelling errors. Furthermore, we propose novel methods including UNK masking, condition initialization with affixation embeddings, and untied-directional self-attention mechanism to enhance robustness and interpretability of the neural networks. We conducted experiments on two Thai corpora: BEST2010 and ORCHID. Our adversarial evaluation schemes reveal that bidirectional LSTM (BiLSTM) do not perform well on adversarial examples. Our best methods match the performance of the BiLSTM baseline model and outperform it on adversarial examples.
Collapse
|
12
|
Saetia C, Chalothorn T, Chuangsuwanich E, Vateekul P. Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations. ACM T ASIAN LOW-RESO 2020. [DOI: 10.1145/3389037] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Abstract
A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the task of sentence segmentation that includes three main contributions. First, we integrate n-gram embedding as a local representation to capture word groups near sentence boundaries. Second, to focus on the keywords of dependent clauses, we combine the model with a distant representation obtained from self-attention modules. Finally, due to the scarcity of labeled data, for which annotation is difficult and time-consuming, we also investigate and adapt Cross-View Training (CVT) as a semi-supervised learning technique, allowing us to utilize unlabeled data to improve the model representations. In the Thai sentence segmentation experiments, our model reduced the relative error by 7.4% and 10.5% compared with the baseline models on the Orchid and UGWC datasets, respectively. We also applied our model to the task of pronunciation recovery on the IWSLT English dataset. Our model outperformed the prior sequence tagging models, achieving a relative error reduction of 2.5%. Ablation studies revealed that utilizing n-gram presentations was the main contributing factor for Thai, while the semi-supervised training helped the most for English.
Collapse
|
13
|
Jettakul A, Wichadakul D, Vateekul P. Relation extraction between bacteria and biotopes from biomedical texts with attention mechanisms and domain-specific contextual representations. BMC Bioinformatics 2019; 20:627. [PMID: 31795930 PMCID: PMC6889521 DOI: 10.1186/s12859-019-3217-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2019] [Accepted: 11/12/2019] [Indexed: 12/21/2022] Open
Abstract
BACKGROUND The Bacteria Biotope (BB) task is a biomedical relation extraction (RE) that aims to study the interaction between bacteria and their locations. This task is considered to pertain to fundamental knowledge in applied microbiology. Some previous investigations conducted the study by applying feature-based models; others have presented deep-learning-based models such as convolutional and recurrent neural networks used with the shortest dependency paths (SDPs). Although SDPs contain valuable and concise information, some parts of crucial information that is required to define bacterial location relationships are often neglected. Moreover, the traditional word-embedding used in previous studies may suffer from word ambiguation across linguistic contexts. RESULTS Here, we present a deep learning model for biomedical RE. The model incorporates feature combinations of SDPs and full sentences with various attention mechanisms. We also used pre-trained contextual representations based on domain-specific vocabularies. To assess the model's robustness, we introduced a mean F1 score on many models using different random seeds. The experiments were conducted on the standard BB corpus in BioNLP-ST'16. Our experimental results revealed that the model performed better (in terms of both maximum and average F1 scores; 60.77% and 57.63%, respectively) compared with other existing models. CONCLUSIONS We demonstrated that our proposed contributions to this task can be used to extract rich lexical, syntactic, and semantic features that effectively boost the model's performance. Moreover, we analyzed the trade-off between precision and recall to choose the proper cut-off to use in real-world applications.
Collapse
Affiliation(s)
- Amarin Jettakul
- Chulalongkorn University Big Data Analytics and IoT Center (CUBIC), Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Duangdao Wichadakul
- Chulalongkorn University Big Data Analytics and IoT Center (CUBIC), Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Peerapon Vateekul
- Chulalongkorn University Big Data Analytics and IoT Center (CUBIC), Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand.
| |
Collapse
|
14
|
Affiliation(s)
- Peerapon Vateekul
- Department of Computer Engineering, Chulalongkorn University, Bangkok, Thailand
| | - Miroslav Kubat
- Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA
| | | |
Collapse
|
15
|
Affiliation(s)
- Sareewan Dendamrongvit
- Department of Electrical & Computer Engineering, University of Miami, Coral Gables, FL, USA
| | - Peerapon Vateekul
- Department of Electrical & Computer Engineering, University of Miami, Coral Gables, FL, USA
| | - Miroslav Kubat
- Department of Electrical & Computer Engineering, University of Miami, Coral Gables, FL, USA
| |
Collapse
|