MyMedR

Displaying all 6 publications

Abstract:

Sort:

Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G

Lim WX, Chen Z

Med Biol Eng Comput, 2024 Apr 23.
PMID: 38649629 DOI: 10.1007/s11517-024-03093-0

Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter (SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.
Fulltext The adoption of deep learning interpretability techniques on diabetic retinopathy analysis: a review

Lim WX, Chen Z, Ahmed A

Med Biol Eng Comput, 2022 Mar;60(3):633-642.
PMID: 35083634 DOI: 10.1007/s11517-021-02487-8

Diabetic retinopathy (DR) is a chronic eye condition that is rapidly growing due to the prevalence of diabetes. There are challenges such as the dearth of ophthalmologists, healthcare resources, and facilities that are unable to provide patients with appropriate eye screening services. As a result, deep learning (DL) has the potential to play a critical role as a powerful automated diagnostic tool in the field of ophthalmology, particularly in the early detection of DR when compared to traditional detection techniques. The DL models are known as black boxes, despite the fact that they are widely adopted. They make no attempt to explain how the model learns representations or why it makes a particular prediction. Due to the black box design architecture, DL methods make it difficult for intended end-users like ophthalmologists to grasp how the models function, preventing model acceptance for clinical usage. Recently, several studies on the interpretability of DL methods used in DR-related tasks such as DR classification and segmentation have been published. The goal of this paper is to provide a detailed overview of interpretability strategies used in DR-related tasks. This paper also includes the authors' insights and future directions in the field of DR to help the research community overcome research problems.
Remission of Sjogren's syndrome after Roux-en-Y gastric bypass for morbid obesity

Lim SY, Lim WX, Gee T

Obes Surg, 2018 Feb;28(2):557-558.
PMID: 29248981 DOI: 10.1007/s11695-017-3048-0
Fulltext Fracture Liaison Service and Its Role in Secondary Fracture Prevention in Malaysia: A Scoping Review

Lim WX, Khor HM, Lee JK, Ong T

Malays Orthop J, 2023 Jul;17(2):1-6.
PMID: 37583523 DOI: 10.5704/MOJ.2307.001

INTRODUCTION: Fragility fractures, which occur after a low-trauma injury, increases with advancing age. Such fracture doubles the life-time risk of sustaining another fracture. This risk is highest in the immediate 18 months after the index fracture. However, most patients do not receive the appropriate risk assessment and intervention to reduce this risk. A coordinated model of care termed Fracture Liaison Service (FLS) has been reported to address this treatment gap.
MATERIALS AND METHODS: This scoping review aims to explore the potential role and delivery of FLS services in Malaysia. Scientific and non-scientific sources relevant to FLS were identified from electronic bibliographic databases, specialist journals and relevant websites. Findings were categorised into themes and presented narratively.
RESULTS: FLS services remain concentrated in the Klang Valley. Even within FLS services, many do not have extensive coverage to risk assess all fracture patients. These services are multidisciplinary in nature where there are links between different departments, such as orthopaedics, osteoporosis expertise, bone densitometry, rehabilitation, falls services and primary care. FLS was able to increase the number of people undergoing fracture risk assessment and treatment. The importance of FLS was highlighted by local experts and stakeholders. Its implementation and delivery are supported by a number of national guidelines.
CONCLUSION: FLS is central to our national efforts to reduce the impending fragility fracture crisis in the coming years. Continued effort is needed to increase coverage within FLS services and across the country. Training, awareness of the problem, research, and policy change will support this endeavour.
Fulltext Utility and usability evaluation of an information diary tool to measure health information access and exposure among patients with high cardiovascular risk

Lim HM, Ng CJ, Abdullah A, Dalmazzo J, Lim WX, Lee KH, et al.

Front Public Health, 2023;11:1132397.
PMID: 37228723 DOI: 10.3389/fpubh.2023.1132397

BACKGROUND: Online health misinformation about statins potentially affects health decision-making on statin use and adherence. We developed an information diary platform (IDP) to measure topic-specific health information exposure where participants record what information they encounter. We evaluated the utility and usability of the smartphone diary from the participants' perspective.
METHODS: We used a mixed-method design to evaluate how participants used the smartphone diary tool and their perspectives on usability. Participants were high cardiovascular-risk patients recruited from a primary care clinic and used the tool for a week. We measured usability with the System Usability Scale (SUS) questionnaire and interviewed participants to explore utility and usability issues.
RESULTS: The information diary was available in three languages and tested with 24 participants. The mean SUS score was 69.8 ± 12.9. Five themes related to utility were: IDP functions as a health information diary; supporting discussion of health information with doctors; wanting a feedback function about credible information; increasing awareness of the need to appraise information; and wanting to compare levels of trust with other participants or experts. Four themes related to usability were: ease of learning and use; confusion about selecting the category of information source; capturing offline information by uploading photos; and recording their level of trust.
CONCLUSION: We found that the smartphone diary can be used as a research instrument to record relevant examples of information exposure. It potentially modifies how people seek and appraise topic-specific health information.
Fulltext Middle East Respiratory Syndrome (MERS) Virus-Pathophysiological Axis and the Current Treatment Strategies

Alnuqaydan AM, Almutary AG, Sukamaran A, Yang BTW, Lee XT, Lim WX, et al.

AAPS PharmSciTech, 2021 Jun 08;22(5):173.
PMID: 34105037 DOI: 10.1208/s12249-021-02062-2

Middle East respiratory syndrome (MERS) is a lethal respiratory disease with its first case reported back in 2012 (Jeddah, Saudi Arabia). It is a novel, single-stranded, positive-sense RNA beta coronavirus (MERS-CoV) that was isolated from a patient who died from a severe respiratory illness. Later, it was found that this patient was infected with MERS. MERS is endemic to countries in the Middle East regions, such as Saudi Arabia, Jordan, Qatar, Oman, Kuwait and the United Arab Emirates. It has been reported that the MERS virus originated from bats and dromedary camels, the natural hosts of MERS-CoV. The transmission of the virus to humans has been thought to be either direct or indirect. Few camel-to-human transmissions were reported earlier. However, the mode of transmission of how the virus affects humans remains unanswered. Moreover, outbreaks in either family-based or hospital-based settings were observed with high mortality rates, especially in individuals who did not receive proper management or those with underlying comorbidities, such as diabetes and renal failure. Since then, there have been numerous reports hypothesising complications in fatal cases of MERS. Over the years, various diagnostic methods, treatment strategies and preventive measures have been strategised in containing the MERS infection. Evidence from multiple sources implicated that no treatment options and vaccines have been developed in specific, for the direct management of MERS-CoV infection. Nevertheless, there are supportive measures outlined in response to symptom-related management. Health authorities should stress more on infection and prevention control measures, to ensure that MERS remains as a low-level threat to public health.