Tasnim Jahan Tonni

Ms. Tasnim Jahan Tonni

Computer science and engineering, Daffodil International University, Dhaka, Bangladesh
orcid
TASNIM JAHAN TONNI is a final-semester Bachelor of Science c...

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
29 April 2024 in Sensors
Verified
Journal Article
Open access
PDF file
Shakil RanaShakil Rana
Shakil Rana
Md Jabed HosenMd Jabed Hosen
Md Jabed Hosen
Tasnim Jahan TonniTasnim Jahan Tonni
Tasnim Jahan Tonni
MD. Awlad Hossen RonyMD. Awlad Hossen Rony
MD. Awlad Hossen Rony
KFKaniz Fatema
Kaniz Fatema
MWMd Whaiduzzaman
Md Whaiduzzaman
Lung diseases are the third-leading cause of mortality in the world. Due to compromised lung function, respiratory difficulties, and physiological complications, lung disease brought on by toxic substances, pollution, infections, or smoking results in millions of deaths every year. Chest X-ray images pose a challenge for classification due to their visual similarity, leading to confusion among radiologists. To imitate those issues, we created an automated system with a large data hub that contains 17 datasets of chest X-ray images for a total of 71,096, and we aim to classify ten different disease classes. For combining various resources, our large datasets contain noise and annotations, class imbalances, data redundancy, etc. We conducted several image pre-processing techniques to eliminate noise and artifacts from images, such as resizing, de-annotation, CLAHE, and filtering. The elastic deformation augmentation technique also generates a balanced dataset. Then, we developed DeepChestGNN, a novel medical image classification model utilizing a deep convolutional neural network (DCNN) to extract 100 significant deep features indicative of various lung diseases. This model, incorporating Batch Normalization, MaxPooling, and Dropout layers, achieved a remarkable 99.74% accuracy in extensive trials. By combining graph neural networks (GNNs) with feedforward layers, the architecture is very flexible when it comes to working with graph data for accurate lung disease classification. This study highlights the significant impact of combining advanced research with clinical application potential in diagnosing lung diseases, providing an optimal framework for precise and efficient disease identification and classification.

25 June 2025 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
Md Ibrahim Patwary KhokanMd Ibrahim Patwary Khokan
Md Ibrahim Patwary Khokan
Tasnim Jahan TonniTasnim Jahan Tonni
Tasnim Jahan Tonni
MD. Awlad Hossen RonyMD. Awlad Hossen Rony
MD. Awlad Hossen Rony
KFKaniz Fatema
Kaniz Fatema
MHMd. Zahid Hasan
Md. Zahid Hasan

18 December 2024 in Computational Intelligence
Verified
Journal Article
Closed access
Tasnim Jahan TonniTasnim Jahan Tonni
Tasnim Jahan Tonni
SRShakil Rana
Shakil Rana
KFKaniz Fatema
Kaniz Fatema
AKAsif Karim
Asif Karim
ARAwlad Hossen Rony
Awlad Hossen Rony
Sami AzamSami Azam
Sami Azam

5 May 2026 in IEEE Access
Verified
Journal Article
Open access
Md Ibrahim Patwary KhokanMd Ibrahim Patwary Khokan
Md Ibrahim Patwary Khokan
Tasnim Jahan TonniTasnim Jahan Tonni
Tasnim Jahan Tonni
KFKaniz Fatema
Kaniz Fatema
MHMd. Zahid Hasan
Md. Zahid Hasan
ARAwlad Hossen Rony
Awlad Hossen Rony
ASM Ashraf MahmudASM Ashraf Mahmud
ASM Ashraf Mahmud
Ovarian cancer is the eighth most common cancer in women. Early diagnosis is vital for effective treatment, but it presents challenges that require reliable diagnostic tools. This study proposes an automated Decision Support System (DSS) to enhance the accuracy of ovarian tumor classification, differentiating between normal, abnormal, benign, and malignant cases based on clinical features. The proposed DSS integrates a distance transform–based regional mapping approach to systematically categorize ovarian cystic structures into three configurations: single, multiple, and overlapping regions. This approach enables robust handling of diverse regional types and complex spatial patterns. Although an overlap-handling routine is included in the system, it remains disabled for the current dataset since no overlapping lesions are present. Clinically significant markers are extracted from ovarian ultrasound images, emphasizing key visual properties such as tumor location, size, shape, and architectural distortion. From each Region of Interest (ROI), obtained through bitwise segmentation, twelve prominent clinical features, such as solidity, SIFT key points, and circularity, are derived. Feature relevance is evaluated using the Random Forest Feature Importance method, and a probability density function (PDF) graph is employed to differentiate between normal and abnormal tumors. The proposed DSS achieves outstanding accuracy, with a classification performance of 97.92% in distinguishing normal vs. abnormal and benign vs. malignant tumors. Furthermore, its performance is compared against eight different machine learning models, demonstrating its effectiveness in ovarian tumor diagnosis. The automated DSS effectively enhances diagnostic accuracy for ovarian tumors, providing healthcare professionals with a reliable, time-efficient tool to support clinical decision-making. Integrating clinically significant features and regional mapping capabilities highlights its potential to improve patient outcomes in ovarian tumor diagnosis.