Computational and Mathematical Methods in Medicine, 2022
Computed tomography (CT) is a common modality for liver diagnosis, treatment, and follow-up proce... more Computed tomography (CT) is a common modality for liver diagnosis, treatment, and follow-up process. Providing accurate liver segmentation using CT images is a crucial step towards those tasks. In this paper, we propose a stacked 2-U-Nets model with three different types of skip connections. The proposed connections work to recover the loss of high-level features on the convolutional path of the first U-Net due to the pooling and the loss of low-level features during the upsampling path of the first U-Net. The skip connections concatenate all the features that are generated at the same level from the previous paths to the inputs of the convolutional layers in both paths of the second U-Net in a densely connected manner. We implement two versions of the model with different number of filters at each level of each U-Net by maximising the Dice similarity between the predicted liver region and that of the ground truth. The proposed models were trained with 3Dircadb public dataset that w...
The Journal of The Institution of Engineers, Malaysia, 2021
After becoming independent in 1957, Malaysia continued as an agricultural country but quickly gre... more After becoming independent in 1957, Malaysia continued as an agricultural country but quickly grew into a manufacturing nation in a relatively short time. Literally from nowhere, the manufacturing sector now commands more than 38% of the nation’s GDP overtaking the agriculture sector which commands just slightly above 7%. In addition to the multinational manufacturers who are mainly in the electrical and electronics sectors, there are also other smaller producers who produce for the rest of the world. Nevertheless in order to compete, they cannot just rely on manual labour whether local or foreign, to produce high volume and high quality goods at a competitive price. With intense competition, even the old way of making many products to satisfy the global appetite for good products from both the brick-and-mortar shops to your huge online shops is no longer adequate. Manual operations in the manufacturing process can come in various forms, ranging from the very simple but monotonous a...
Pattern Recognition and Information Forensics, 2018
Race determination of skulls of individuals is a continually growing subject in forensic anthropo... more Race determination of skulls of individuals is a continually growing subject in forensic anthropology. Traditionally, race determination has been conducted either entirely subjectively by qualified forensic anthropologists, or has been conducted through a semi-automated fashion through multivariate discriminant functions. This paper describes a novel method for completely automated race determination of CT scans of skulls, wherein skulls are preprocessed, reduced to a low dimensional model and segregated into one of two racial classes through a classifier. The classifier itself is chosen from a survey conducted against four different classification techniques. This method can both be used as a tool for completely automated race determination, or as decision support for forensic anthropologists. A total of 341 skulls with variance in race have been gathered by the University of Nottingham Malaysia Campus and used to train and test the method. The resultant accuracy of this method is 79%.
Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all... more Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all polyps during colonoscopy would increase the chances of a better prognoses. However, endoscopists are facing difficulties due to the heavy workload of analyzing endoscopic images. Hence, assisting endoscopist while screening would decrease polyp miss rate. In this study, we propose a new deep learning segmentation model to segment polyps found in endoscopic images extracted during Colonoscopy screening. The propose model modifies SegNet architecture to embed Gated recurrent units (GRU) units within the convolution layers to collect contextual information. Therefore, both global and local information are extracted and propagated through the entire layers. This has led to better segmentation performance compared to that of using state of the art SegNet. Four experiments were conducted and the proposed model achieved a better intersection over union “IoU” by 1.36%, 1.71%, and 1.47% on vali...
Diabetes is a global epidemic and it is increasing at an alarming rate. The International Diabete... more Diabetes is a global epidemic and it is increasing at an alarming rate. The International Diabetes Federation (IDF) projected that the total number of people with diabetes globally may increase by 48%, from 425 million (year 2017) to 629 million (year 2045). Moreover, diabetes had caused millions of deaths and the number is increasing drastically. Therefore, this paper addresses the background of diabetes and its complications. In addition, this paper investigates innovative applications and past researches in the areas of diabetes management system with applied eye fundus and tongue digital images. Different types of existing applied eye fundus and tongue digital image processing with diabetes management systems in the market and state-of-the-art machine learning techniques from previous literature have been reviewed. The implication of this paper is to have an overview in diabetic research and what new machine learning techniques can be proposed in solving this global epidemic.
The growing capacity of neural networks has strongly contributed to their success at complex mach... more The growing capacity of neural networks has strongly contributed to their success at complex machine learning tasks and the computational demand of such large models has, in turn, stimulated a significant improvement in the hardware necessary to accelerate their computations. However, models with high latency aren't suitable for limited-resource environments such as hand-held and IoT devices. Hence, many deep learning techniques aim to address this problem by developing models with reasonable accuracy without violating the limited-resource constraint. In this work, we use a one-shot neural architecture search model to implicitly evaluate the performance of an intractable number of multipath neural networks. Combining this architecture search with a pruning technique and architecture sample evaluation, we can model the relation between the accuracy and the latency of a spectrum of models with graded complexity. We show that our method can accurately model the relative performance...
In this paper, we aim to enhance the segmentation capabilities of DeeplabV3 by employing Gated Re... more In this paper, we aim to enhance the segmentation capabilities of DeeplabV3 by employing Gated Recurrent Neural Network (GRU). A 1-by-1 convolution in DeeplabV3 was replaced by GRU after the Atrous Spatial Pyramid Pooling (ASSP) layer to combine the input feature maps. The convolution and GRU have sharable parameters, though, the latter has gates that enable/disable the contribution of each input feature map. The experiments on unseen test sets demonstrate that employing GRU instead of convolution would produce better segmentation results. The used datasets are public datasets provided by MedAI competition.
Sex determination in forensic analysis involves individual examination of different sites of the ... more Sex determination in forensic analysis involves individual examination of different sites of the skull and combination of these sites to understand their impact on the estimation results. Conventionally, forensic experts perform a stepwise combination of several skull region assessment parameters to determine the most important regions with regard to the sex estimation results. This paper introduces a novel group variable selection algorithm: Graph Laplacian Based Group Lasso with split augmented Lagrangian shrinkage algorithm (SALSA) to automatically learn from data by structuring the data into a set of disjointed groups and imposing a number of group sparsity to discover the salient groups which influence the sex determination results. In order to attain this, the skull is partitioned into smaller regions (local regions) using fuzzy c-means (FCM), which are further arranged into clusters as structured groups. Then, we implement the SALSA based group lasso algorithm to impose spars...
The first step in the forensic identification is sex determination followed by age and stature es... more The first step in the forensic identification is sex determination followed by age and stature estimation, as both are sex-dependent. The mandible is the largest, strongest and most durable bone in the face. Mandible is important for sex confirmation in absence of a complete pelvis and skull. The aim of the present study was to determine sex of human mandible from morphology, morphometric measurements as well as discriminant function analysis from the CT scan. The present retrospective study comprised 79 subjects (48 males, 31 females), with age group between 18 and 74 years, and were obtained from the post mortem computed tomography data in the Hospital Kuala Lumpur. The parameters were divided into three morphologic and nine morphometric parameters, which were measured by using Osirix MD Software 3D Volume Rendering. The Chi-square test showed that men were significantly association with square-shaped chin (92%), prominent muscle marking (85%) and everted gonial glare, whereas wom...
Computational and Mathematical Methods in Medicine, 2022
Computed tomography (CT) is a common modality for liver diagnosis, treatment, and follow-up proce... more Computed tomography (CT) is a common modality for liver diagnosis, treatment, and follow-up process. Providing accurate liver segmentation using CT images is a crucial step towards those tasks. In this paper, we propose a stacked 2-U-Nets model with three different types of skip connections. The proposed connections work to recover the loss of high-level features on the convolutional path of the first U-Net due to the pooling and the loss of low-level features during the upsampling path of the first U-Net. The skip connections concatenate all the features that are generated at the same level from the previous paths to the inputs of the convolutional layers in both paths of the second U-Net in a densely connected manner. We implement two versions of the model with different number of filters at each level of each U-Net by maximising the Dice similarity between the predicted liver region and that of the ground truth. The proposed models were trained with 3Dircadb public dataset that w...
The Journal of The Institution of Engineers, Malaysia, 2021
After becoming independent in 1957, Malaysia continued as an agricultural country but quickly gre... more After becoming independent in 1957, Malaysia continued as an agricultural country but quickly grew into a manufacturing nation in a relatively short time. Literally from nowhere, the manufacturing sector now commands more than 38% of the nation’s GDP overtaking the agriculture sector which commands just slightly above 7%. In addition to the multinational manufacturers who are mainly in the electrical and electronics sectors, there are also other smaller producers who produce for the rest of the world. Nevertheless in order to compete, they cannot just rely on manual labour whether local or foreign, to produce high volume and high quality goods at a competitive price. With intense competition, even the old way of making many products to satisfy the global appetite for good products from both the brick-and-mortar shops to your huge online shops is no longer adequate. Manual operations in the manufacturing process can come in various forms, ranging from the very simple but monotonous a...
Pattern Recognition and Information Forensics, 2018
Race determination of skulls of individuals is a continually growing subject in forensic anthropo... more Race determination of skulls of individuals is a continually growing subject in forensic anthropology. Traditionally, race determination has been conducted either entirely subjectively by qualified forensic anthropologists, or has been conducted through a semi-automated fashion through multivariate discriminant functions. This paper describes a novel method for completely automated race determination of CT scans of skulls, wherein skulls are preprocessed, reduced to a low dimensional model and segregated into one of two racial classes through a classifier. The classifier itself is chosen from a survey conducted against four different classification techniques. This method can both be used as a tool for completely automated race determination, or as decision support for forensic anthropologists. A total of 341 skulls with variance in race have been gathered by the University of Nottingham Malaysia Campus and used to train and test the method. The resultant accuracy of this method is 79%.
Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all... more Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all polyps during colonoscopy would increase the chances of a better prognoses. However, endoscopists are facing difficulties due to the heavy workload of analyzing endoscopic images. Hence, assisting endoscopist while screening would decrease polyp miss rate. In this study, we propose a new deep learning segmentation model to segment polyps found in endoscopic images extracted during Colonoscopy screening. The propose model modifies SegNet architecture to embed Gated recurrent units (GRU) units within the convolution layers to collect contextual information. Therefore, both global and local information are extracted and propagated through the entire layers. This has led to better segmentation performance compared to that of using state of the art SegNet. Four experiments were conducted and the proposed model achieved a better intersection over union “IoU” by 1.36%, 1.71%, and 1.47% on vali...
Diabetes is a global epidemic and it is increasing at an alarming rate. The International Diabete... more Diabetes is a global epidemic and it is increasing at an alarming rate. The International Diabetes Federation (IDF) projected that the total number of people with diabetes globally may increase by 48%, from 425 million (year 2017) to 629 million (year 2045). Moreover, diabetes had caused millions of deaths and the number is increasing drastically. Therefore, this paper addresses the background of diabetes and its complications. In addition, this paper investigates innovative applications and past researches in the areas of diabetes management system with applied eye fundus and tongue digital images. Different types of existing applied eye fundus and tongue digital image processing with diabetes management systems in the market and state-of-the-art machine learning techniques from previous literature have been reviewed. The implication of this paper is to have an overview in diabetic research and what new machine learning techniques can be proposed in solving this global epidemic.
The growing capacity of neural networks has strongly contributed to their success at complex mach... more The growing capacity of neural networks has strongly contributed to their success at complex machine learning tasks and the computational demand of such large models has, in turn, stimulated a significant improvement in the hardware necessary to accelerate their computations. However, models with high latency aren't suitable for limited-resource environments such as hand-held and IoT devices. Hence, many deep learning techniques aim to address this problem by developing models with reasonable accuracy without violating the limited-resource constraint. In this work, we use a one-shot neural architecture search model to implicitly evaluate the performance of an intractable number of multipath neural networks. Combining this architecture search with a pruning technique and architecture sample evaluation, we can model the relation between the accuracy and the latency of a spectrum of models with graded complexity. We show that our method can accurately model the relative performance...
In this paper, we aim to enhance the segmentation capabilities of DeeplabV3 by employing Gated Re... more In this paper, we aim to enhance the segmentation capabilities of DeeplabV3 by employing Gated Recurrent Neural Network (GRU). A 1-by-1 convolution in DeeplabV3 was replaced by GRU after the Atrous Spatial Pyramid Pooling (ASSP) layer to combine the input feature maps. The convolution and GRU have sharable parameters, though, the latter has gates that enable/disable the contribution of each input feature map. The experiments on unseen test sets demonstrate that employing GRU instead of convolution would produce better segmentation results. The used datasets are public datasets provided by MedAI competition.
Sex determination in forensic analysis involves individual examination of different sites of the ... more Sex determination in forensic analysis involves individual examination of different sites of the skull and combination of these sites to understand their impact on the estimation results. Conventionally, forensic experts perform a stepwise combination of several skull region assessment parameters to determine the most important regions with regard to the sex estimation results. This paper introduces a novel group variable selection algorithm: Graph Laplacian Based Group Lasso with split augmented Lagrangian shrinkage algorithm (SALSA) to automatically learn from data by structuring the data into a set of disjointed groups and imposing a number of group sparsity to discover the salient groups which influence the sex determination results. In order to attain this, the skull is partitioned into smaller regions (local regions) using fuzzy c-means (FCM), which are further arranged into clusters as structured groups. Then, we implement the SALSA based group lasso algorithm to impose spars...
The first step in the forensic identification is sex determination followed by age and stature es... more The first step in the forensic identification is sex determination followed by age and stature estimation, as both are sex-dependent. The mandible is the largest, strongest and most durable bone in the face. Mandible is important for sex confirmation in absence of a complete pelvis and skull. The aim of the present study was to determine sex of human mandible from morphology, morphometric measurements as well as discriminant function analysis from the CT scan. The present retrospective study comprised 79 subjects (48 males, 31 females), with age group between 18 and 74 years, and were obtained from the post mortem computed tomography data in the Hospital Kuala Lumpur. The parameters were divided into three morphologic and nine morphometric parameters, which were measured by using Osirix MD Software 3D Volume Rendering. The Chi-square test showed that men were significantly association with square-shaped chin (92%), prominent muscle marking (85%) and everted gonial glare, whereas wom...
Uploads
Papers by Iman Liao