Shafiullah Soomro

Shafiullah Soomro

Auto-generated profile, based on publicly available information

Shafiullah Soomro

Department of Computer Science and Media Technology, Linnaeus University, Vxj, Sweden

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 June 2022 in IEEE Reviews in Biomedical Engineering
Verified
Journal Article
Closed access
TSToufique Ahmed Soomro
Toufique Ahmed Soomro
Lihong ZhengLihong Zheng
Lihong Zheng
Ahmed J. AfifiAhmed J. Afifi
Ahmed J. Afifi
AAAhmed Ali
Ahmed Ali
SSShafiullah Soomro
Shafiullah Soomro
JGJunbin Gao
Junbin Gao
Magnetic Resonance Imaging (MRI) has commonly been used to detect and diagnose brain disease and monitor treatment as non-invasive imaging technology. MRI produces three-dimensional images that help neurologists to identify anomalies from brain images precisely. However, this is a time-consuming and labor-intensive process. The improvement in machine learning and efficient computation provides a computer-aid solution to analyze MRI images and identify the abnormality quickly and accurately. Image segmentation has become a hot and research-oriented area in the medical image analysis community. The computer-aid system for brain abnormalities identification provides the possibility for quickly classifying the disease for early treatment. This article presents a review of the research papers (from 1998 to 2020) on brain tumors segmentation from MRI images. We examined the core segmentation algorithms of each research paper in detail. This article provides readers with a complete overview of the topic and new dimensions of how numerous machine learning and image segmentation approaches are applied to identify brain tumors. By comparing the state-of-the-art and new cutting-edge methods, the deep learning methods are more effective for the segmentation of the tumor from MRI images of the brain.

29 July 2024 in IEEE Access
Verified
Journal Article
Open access
ANAsim Niaz
Asim Niaz
SASareer Ul Amin
Sareer Ul Amin
SSShafiullah Soomro
Shafiullah Soomro
HZHamza Zia
Hamza Zia
KCKwang Nam Choi
Kwang Nam Choi
Surveillance videos are crucial for crime prevention and public safety, yet the challenge of defining abnormal events hinders their effectiveness, limiting the applicability of supervised methods. This paper introduces an unsupervised end-to-end architecture for video anomaly detection that applies spatial and temporal features to identify anomalies in surveillance footage. The model employs a three-dimensional (3D) convolutional autoencoder, with an encoder-decoder structure that learns spatiotemporal representations and reconstructs the input through the latent space. Skip connections linking the encoder and decoder blocks facilitate the transfer of information across various scales of feature representations, enhancing the reconstruction process and improving the overall performance. The architecture incorporates spatial attention modules that highlight informative regions in the input, enabling improved anomaly detection. Spatial and contextual dependencies are further acquired using 3D convolutional filters. The performance of the proposed model is assessed on four benchmark datasets: UCSD Pedestrian 1, UCSD Pedestrian 2, CUHK Avenue, and ShanghaiTech. Notably, the proposed model achieves frame-based Area Under the Curve (AUC) scores of 94.6% on UCSD Ped 1, 96.7% on UCSD Ped 2, 84.7% on CUHK Avenue, and 74.8% on ShanghaiTech. These results demonstrate the state-of-the-art performance of the proposed approach, highlighting its efficacy in real-world anomaly detection scenarios.

19 October 2020 in IEEE Access
Verified
Journal Article
Open access
AJAditi Joshi
Aditi Joshi
MKMohammed Saquib Khan
Mohammed Saquib Khan
SSShafiullah Soomro
Shafiullah Soomro
ANAsim Niaz
Asim Niaz
BHBeom Seok Han
Beom Seok Han
KCKwang Nam Choi
Kwang Nam Choi
Noise or artifacts in an image, such as shadow artifacts, deteriorate the performance of state-of-the-art models for the segmentation of an image. In this study, a novel saliency-based region detection and image segmentation (SRIS) model is proposed to overcome the problem of image segmentation in the existence of noise and intensity inhomogeneity. Herein, a novel adaptive level-set evolution protocol based on the internal and external functions is designed to eliminate the initialization sensitivity, thereby making the proposed SRIS model robust to contour initialization. In the level-set energy function, an adaptive weight function is formulated to adaptively alter the intensities of the internal and external energy functions based on image information. In addition, the sign of energy function is modulated depending on the internal and external regions to eliminate the effects of noise in an image. Finally, the performance of the proposed SRIS model is illustrated on complex real and synthetic images and compared with that of the previously reported state-of-the-art models. Moreover, statistical analysis has been performed on coronavirus disease (COVID-19) computed tomography images and THUS10000 real image datasets to confirm the superior performance of the SRIS model from the viewpoint of both segmentation accuracy and time efficiency. Results suggest that SRIS is a promising approach for early screening of COVID-19.

7 October 2020 in IEEE Access
Verified
Journal Article
Open access
ANAsim Niaz
Asim Niaz
AMAsif Aziz Memon
Asif Aziz Memon
KRKaynat Rana
Kaynat Rana
AJAditi Joshi
Aditi Joshi
SSShafiullah Soomro
Shafiullah Soomro
KCKwang Nam Choi
Kwang Nam Choi
The most fatal and frequent cancer amongst women is breast cancer. Mammography provides timely detection of lumps and masses in breast tissue, but effective diagnosis requires accurately identifying malignant tumor boundaries, which remains challenging, particularly for images with inhomogeneous regions. Therefore, we propose an active contour method based on a reformed combined local and global fitted function to address breast tumor segmentation. This combined function is strengthened by a proposed average energy driving function to capture obscure boundaries for regions of interest more precisely from inhomogeneous images. Including a p-Laplace term eliminates reinitialization requirements and suppresses false contours in the segmentation. Bias field signal, which causes image homogeneity corruption, is estimated by bias field initialization to ensure independence from the initial contour position. Local and global fitted models are incorporated by introducing bias fields within them. The proposed method was tested on the MIAS MiniMammographic Database, with quantitative analysis to calculate its accuracy, effectiveness, and efficiency. Experimentation confirmed the proposed method provided superior results compared with previous state-of-the-art methods.

16 February 2019
Verified
Book Chapter
Open access
PDF file
TSToufique Ahmed Soomro
Toufique Ahmed Soomro
JGJunbin Gao
Junbin Gao
Lihong ZhengLihong Zheng
Lihong Zheng
Ahmed J. AfifiAhmed J. Afifi
Ahmed J. Afifi
SSShafiullah Soomro
Shafiullah Soomro
Manoranjan PaulManoranjan Paul
Manoranjan Paul
Retinal fundus examination is necessary for the early diagnosis of eye disease, especially diabetic retinopathy. Population screening often results in poor quality retinal images that complicate the automated diagnosis of retinal features, such as precise segmentation of blood vessels, microaneurysms, cotton stains, and hard exudates. Fluorescein fundus angiogram (FFA) has solved some problems, but it is invasive and has side effects. In this research work, we proposed a method of image enhancement based on contrast-sensitive steps as a valuable aid for the automatic segmentation of pathological (unhealthy) images. Experimental results based on the Digital retinal images for vessel extraction (DRIVE) and STructured analysis of the retina (STARE) databases showed that the proposed image enhancement method improved the performance over other existing methods, from 92% to 95% in accuracy and from 71% to 75% in sensitivity. This significant improvement in the contrast of retinal background images of retinal color has the potential to provide better vessel images for observing ocular diseases.

18 April 2024 in IEEE Access
Verified
Journal Article
Open access
HZHamza Zia
Hamza Zia
SSShafiullah Soomro
Shafiullah Soomro
KCKwang Nam Choi
Kwang Nam Choi
Deep learning-based image segmentation methods require densely annotated and massive datasets to produce effective results. On the other hand, active contours-based methods are excellent alternatives to the situation, producing acceptable segmentation results. Earlier active contour models, including local and global region information, struggle with their limitations, such as spurious contours appearing in inhomogeneous images. Bias correction is utilized to solve the bias field’s energy, considering the intensity inhomogeneity and the level set functions that suggest an image domain division. In our approach, we combine the advantages of local and global information in the image level set function, resulting in a combined energy function that aids in the efficient evolution of contours on images and can judge the relevance of the item and its surroundings. The proposed model computes data force by extracting local information from an in-homogeneous image using image-fitting energy and then computing all pixel values simultaneously. Objects with high differences between grey levels or more in-homogeneity can be segmented. The outcome demonstrates that our method is more dependable and computationally efficient than previous methods.