Maria Tariq
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maria Tariq has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Agha Muhammad Hammad Khan
Oncology, Aga Khan University, Karachi, PAK
1 shared publication - Bilal Mazhar
School of Media and Communication, Shenzhen University, Shenzhen, China
1 shared publication - Fatima Shaukat
UE Business School, Division of Management & Administrative Science, University of Education Lahore, Pakistan
1 shared publication Humaira Azam
Alam Medical Hospital, Attock
1 shared publication- Mehwish Nisar
Institute for Electromagnetic Sensing of the Environment (IREA), National Research Council (CNR), Naples, Italy
1 shared publication - Muhammad Waqas Khan
Mechanical and Civil Engineering Northumbria University Newcastle upon Tyne UK
1 shared publication
Latest Publications
- Open Access
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 182814-182827
Effective Diabetic Retinopathy Classification With Siamese Neural Network: A Strategy for Small Dataset Challenges
Early detection of diabetic retinopathy, a complication of vision loss in advanced stages of diabetes, is essential to avoid permanent blindness. However, the automatic detection of diabetic retinopathy through medical image processing requires a large number of training data to build a model with good performance. This poses a challenge when working with small datasets as these models need large datasets to perform well on unseen data. In this paper, we design a few-shot Siamese Neural Networks combined with pre-trained models, such as VGG16, ResNet50, and DenseNet121, to effectively differentiate between classes using small lesions in the retinal images. The proposed model is trained based on the similarity between the pair of images using a comparatively small dataset and performs well for a five-class classification problem. We use the Fine-Grained Annotated Diabetic Retinopathy (FGADR) and APTOS 2019 Blindness Detection dataset, where a small ratio of training images is used to train the model. To evaluate our model, we conduct the testing on the remaining data and achieve good accuracy when trained on limited images, with fewer epochs and fewer parameters. The proposed model achieves high accuracy rates on five-class classification of 80% on FGADR and 81% on APTOS 2019 datasets, with a consistent quadratic weighted kappa (QWK) score of 0.89 across both datasets. Furthermore, we conduct an in-depth analysis of hyperparameter optimisation, specifically investigating different pair selection techniques, loss functions, and distance layers to thoroughly evaluate their impact on the performance of the model. Our proposed model demonstrates promising results when combined with an attention mechanism to perform multiclass classification of diabetic retinopathy using a limited number of eye fundus images, outperforming existing approaches with only a small number of epochs in training.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 182814-182827
Open AccessEffective Diabetic Retinopathy Classification With Siamese Neural Network: A Strategy for Small Dataset Challenges
Early detection of diabetic retinopathy, a complication of vision loss in advanced stages of diabetes, is essential to avoid permanent blindness. However, the automatic detection of diabetic retinopathy through medical image processing requires a large number of training data to build a model with good performance. This poses a challenge when working with small datasets as these models need large datasets to perform well on unseen data. In this paper, we design a few-shot Siamese Neural Networks combined with pre-trained models, such as VGG16, ResNet50, and DenseNet121, to effectively differentiate between classes using small lesions in the retinal images. The proposed model is trained based on the similarity between the pair of images using a comparatively small dataset and performs well for a five-class classification problem. We use the Fine-Grained Annotated Diabetic Retinopathy (FGADR) and APTOS 2019 Blindness Detection dataset, where a small ratio of training images is used to train the model. To evaluate our model, we conduct the testing on the remaining data and achieve good accuracy when trained on limited images, with fewer epochs and fewer parameters. The proposed model achieves high accuracy rates on five-class classification of 80% on FGADR and 81% on APTOS 2019 datasets, with a consistent quadratic weighted kappa (QWK) score of 0.89 across both datasets. Furthermore, we conduct an in-depth analysis of hyperparameter optimisation, specifically investigating different pair selection techniques, loss functions, and distance layers to thoroughly evaluate their impact on the performance of the model. Our proposed model demonstrates promising results when combined with an attention mechanism to perform multiclass classification of diabetic retinopathy using a limited number of eye fundus images, outperforming existing approaches with only a small number of epochs in training.
- Open Access
- 15 June 2022
- Published by Ecancer Global Foundation in ecancermedicalscience
- Vol. 16, 1412
Acute dermatitis in adult female patients receiving hypofractionated radiotherapy for breast cancer: experience from a low- and middle-income country
Acute dermatitis in adult female patients receiving hypofractionated radiotherapy for breast cancer: experience from a low- and middle-income country Yumna
- 15 June 2022
- Published by Ecancer Global Foundation in ecancermedicalscience
- Vol. 16, 1412
Open AccessAcute dermatitis in adult female patients receiving hypofractionated radiotherapy for breast cancer: experience from a low- and middle-income country
Acute dermatitis in adult female patients receiving hypofractionated radiotherapy for breast cancer: experience from a low- and middle-income country Yumna
- Open Access
- 31 January 2022
- Published by CrossLinks International Publishers in Pakistan BioMedical Journal
- Vol. 5 (1) , 304-307
Relation of Hysterectomy with Urinary Incontinence
Urinary incontinence is defined by international continence society as “a condition in which involuntary loss of urine is objectively demonstrable and is a social hygiene problem “It refers to the involuntary leakage of urine can be associated with a systemic complication. Its prevalence is higher in women than in men thought it can affect men and women equally. It has the high prevalence due to its impact on the quality of life. The presence of urinary incontinence can be associated with anger; embarrassment related to any clinical condition, with loss of self-esteem and decrease motivation and decrease social, physical quality of life. Moment plausibility is that the bladder is presently overactive because of the surgery or changes in the pelvic floor musculature related with hysterectomy. Urge incontinence causes spillage of urine all of a sudden, related with critical ness and the powerlessness to smother such inclinations. Objective: Aim of this study is to determine urinary incontinence in women with hysterectomy. To assess the impact of urinary incontinence on quality of life of women undergone hysterectomy. Background: Furthermore, this study highlighted the presence of pain, discomfort, alteration of Quality of life and functional limitation due to incontinence of urine associated after Hysterectomy. An observational survey from different hospitals of Rawalpindi and Islamabad was conducted to collect relevant information. Methods: Standard questionnaire tools (UDI-6) and (KHQ) was used to collect data from 100 women using convenient random sampling technique in different hospitals of Rawalpindi and Islamabad. Results: The result revealed that urinary incontinence in women with hysterectomies strongly associated with altered quality of life causing loss of self-esteem leading to an impairment. Conclusion: This study concluded urinary incontinence associated with hysterectomy had pronounced effects on quality of life of women causing physical, social and psychological role limitations and participation restriction.
- 31 January 2022
- Published by CrossLinks International Publishers in Pakistan BioMedical Journal
- Vol. 5 (1) , 304-307
Open AccessRelation of Hysterectomy with Urinary Incontinence
Urinary incontinence is defined by international continence society as “a condition in which involuntary loss of urine is objectively demonstrable and is a social hygiene problem “It refers to the involuntary leakage of urine can be associated with a systemic complication. Its prevalence is higher in women than in men thought it can affect men and women equally. It has the high prevalence due to its impact on the quality of life. The presence of urinary incontinence can be associated with anger; embarrassment related to any clinical condition, with loss of self-esteem and decrease motivation and decrease social, physical quality of life. Moment plausibility is that the bladder is presently overactive because of the surgery or changes in the pelvic floor musculature related with hysterectomy. Urge incontinence causes spillage of urine all of a sudden, related with critical ness and the powerlessness to smother such inclinations. Objective: Aim of this study is to determine urinary incontinence in women with hysterectomy. To assess the impact of urinary incontinence on quality of life of women undergone hysterectomy. Background: Furthermore, this study highlighted the presence of pain, discomfort, alteration of Quality of life and functional limitation due to incontinence of urine associated after Hysterectomy. An observational survey from different hospitals of Rawalpindi and Islamabad was conducted to collect relevant information. Methods: Standard questionnaire tools (UDI-6) and (KHQ) was used to collect data from 100 women using convenient random sampling technique in different hospitals of Rawalpindi and Islamabad. Results: The result revealed that urinary incontinence in women with hysterectomies strongly associated with altered quality of life causing loss of self-esteem leading to an impairment. Conclusion: This study concluded urinary incontinence associated with hysterectomy had pronounced effects on quality of life of women causing physical, social and psychological role limitations and participation restriction.