Dilanga Abeyrathna

University of Nebraska at Omaha

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Mahadevan Subramaniam

University of Nebraska at Omaha

Parvathi Chundi

University of Nebraska at Omaha

Vidya Bommanapally

University of Nebraska at Omaha

Venkataramana Gadhamshetty

South Dakota School of Mines and Technology

Rajesh K. Sani

South Dakota School of Mines and Technology

Maheshi B. Dissanayake

University of Peradeniya

Adithi Deborah Chakravarthy

University of Nebraska at Omaha

Murat Hasanreisoğlu

Koç University

Shailabh Rauniyar

South Dakota School of Mines and Technology

Quan Dong Nguyen

Princeton University

Cooperative Institutions

Park University

University of Nebraska at Omaha

Chinese Academy of Sciences

Central South University

Weatherford College

South Dakota School of Mines and Technology

Peking University

Shanghai Jiao Tong University

Wuhan University

Sun Yat-sen University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Machine Learning Approach to Estimate Volumetric Quantification of 2D SEM Images of Biofilms

2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (2024)

Dilanga Abeyrathna Ram Singh Samira Badrloo Rajesh K. Sani Mahadevan Subramaniam

10.1109/bibm62325.2024.10822770

Cite

Citations (0)

Semantic Image Segmentation Using Scant Pixel Annotations

Machine Learning and Knowledge Extraction (2022)

Adithi Deborah Chakravarthy Dilanga Abeyrathna Mahadevan Subramaniam Parvathi Chundi Venkataramana Gadhamshetty

The success of deep networks for the semantic segmentation of images is limited by the availability of annotated training data. The manual annotation of images for segmentation is a tedious and time-consuming task that often requires sophisticated users with significant domain expertise to create high-quality annotations over hundreds of images. In this paper, we propose the segmentation with scant pixel annotations (SSPA) approach to generate high-performing segmentation models using a scant set of expert annotated images. The models are generated by training them on images with automatically generated pseudo-labels along with a scant set of expert annotated images selected using an entropy-based algorithm. For each chosen image, experts are directed to assign labels to a particular group of pixels, while a set of replacement rules that leverage the patterns learned by the model is used to automatically assign labels to the remaining pixels. The SSPA approach integrates active learning and semi-supervised learning with pseudo-labels, where expert annotations are not essential but generated on demand. Extensive experiments on bio-medical and biofilm datasets show that the SSPA approach achieves state-of-the-art performance with less than 5% cumulative annotation of the pixels of the training data by the experts.

Leverage (statistics)

Training set

10.3390/make4030029

Cite

Citations (6)

Temporal analysis of Disinformation

Akshay Kale Dilanga Abeyrathna

Disinformation

Source

Cite

Citations (0)

Author Index

2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (2021)

Oliver Aalami Ahmed Abbasi Hanin Abdulrahman Dilanga Abeyrathna Rashmie Abeysinghe

10.1109/bibm52615.2021.9669315

Cite

Citations (0)

An Overview of Machine Learning

CRC Press eBooks (2023)

Dilanga Abeyrathna Mahadevan Subramaniam Parvathi Chundi

This chapter provides an overview of the field of machine learning. Machine learning is a classic subfield of artificial intelligence and computer science. In the last couple of decades, innovations in computational and storage technologies have led to an enormous growth in the field of machine learning which contributed to innovative technologies in many other fields including science and engineering. The field of machine learning is obviously vast, and this chapter provides an overview of the concept of learning and some popular machine learning techniques that underlie the innovative technologies across diverse applications. An important aspect of any technique is to assess its effectiveness at the task it is performing. This is no different for machine learning techniques. Therefore, this chapter also describes typical methodologies that are employed to evaluate learning techniques in general.

10.1201/9781003132981-3

Cite

Citations (4)

Directed Fine Tuning Using Feature Clustering for Instance Segmentation of Toxoplasmosis Fundus Images

Dilanga Abeyrathna Mahadevan Subramaniam Parvathi Chundi Murat Hasanreisoğlu Muhammad Sohail Halim

Medical image segmentation is a challenging problem for computer vision approaches where deep learning networks have achieved impressive successes in recent years. In this paper, we propose a directed, fine tuning approach for instance segmentation networks by using feature clustering of predictions along with labeled training instances to improve network performance. The approach directs and limits analyses of predicted instances by experts to similar training instances only and reduces manual overheads by managing the number of instances that need to be examined. Sub-optimal network predictions are handled either by retraining the networks on data augmented with the relevant training instances, correcting training labels, and/or by readjusting network inference parameters. We first develop a state-of-the-art Mask R-CNN based network for instance segmentation of fundus images with retinal lesions and scars caused by Ocular Toxoplasmosis. Then, we show how the proposed approach can be applied to fine tune this network in a directed manner using feature clustering using a pre-trained CNN network. We demonstrate the robustness of our proposed approach with the evaluation results - mask average IoU increased by 7% and mAP under 0.5 IoU threshold increased by 20%. Our experiments also show that fine tuning by analyzing 66% of the predicted instances achieves the same improvement as that obtained by all of the predicted instances, a significant reduction of the manual overheads for fine tuning.

Feature (linguistics)

Robustness

10.1109/bibe50027.2020.00130

Cite

Citations (2)

A Morphological Post-Processing Approach for Overlapped Segmentation of Bacterial Cell Images

Machine Learning and Knowledge Extraction (2022)

Dilanga Abeyrathna Shailabh Rauniyar Rajesh K. Sani Pei-Chi Huang

Scanning electron microscopy (SEM) techniques have been extensively performed to image and study bacterial cells with high-resolution images. Bacterial image segmentation in SEM images is an essential task to distinguish an object of interest and its specific region. These segmentation results can then be used to retrieve quantitative measures (e.g., cell length, area, cell density) for the accurate decision-making process of obtaining cellular objects. However, the complexity of the bacterial segmentation task is a barrier, as the intensity and texture of foreground and background are similar, and also, most clustered bacterial cells in images are partially overlapping with each other. The traditional approaches for identifying cell regions in microscopy images are labor intensive and heavily dependent on the professional knowledge of researchers. To mitigate the aforementioned challenges, in this study, we tested a U-Net-based semantic segmentation architecture followed by a post-processing step of morphological over-segmentation resolution to achieve accurate cell segmentation of SEM-acquired images of bacterial cells grown in a rotary culture system. The approach showed an 89.52% Dice similarity score on bacterial cell segmentation with lower segmentation error rates, validated over several cell overlapping object segmentation approaches with significant performance improvement.

Segmentation-based object categorization

Region growing

10.3390/make4040052

Cite

Citations (7)

Machine Learning-Assisted Optical Detection of Multilayer Hexagonal Boron Nitride for Enhanced Characterization and Analysis

2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (2023)

Md Hasan-Ur Rahman Vidya Bommanapally Dilanga Abeyrathna Md Ashaduzzman Manoj Tripathi

Biofilms are ubiquitous in aqueous environments, exerting significant influence on diverse surfaces, including metals prone to microbiologically influenced corrosion (MIC). This multifaceted phenomenon demands interdisciplinary collaborations to combat its far-reaching implications. In this context, our research delves into the intricate characterization of twodimensional (2D) materials, particularly hexagonal boron nitride (hBN), which is crucial for advancing corrosion prevention coatings. The nanoscale dimensions of 2D materials pose challenges in microstructural analysis and defect identification, necessitating labor-intensive traditional techniques. To address these complexities, we utilized two unsupervised machine learning models, namely, (a) K-means clustering, and (b) Gaussian Mixture Model (GMM), which enabled clear differentiation between multilayer hBN (MLhBN) and cracks. Our approach will streamline the characterization process and facilitate the extraction of thin layers with enhanced accuracy.

Characterization

Hexagonal boron nitride

Identification

10.1109/bibm58861.2023.10385944

Cite

Citations (2)

Performance Comparison of HEVC and H.264/AVC Standards in Broadcasting Environments

Journal of Information Processing Systems (2015)

Maheshi B. Dissanayake Dilanga Abeyrathna

High Efficiency Video Coding (HEVC) is the most recent video codec standard of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group. The main goal of this newly introduced standard is for catering to high-resolution video in low bandwidth environments with a higher compression ratio. This paper provides a performance comparison between HEVC and H.264/AVC video compression standards in terms of objective quality, delay, and complexity in the broadcasting environment. The experimental investigation was carried out using six test sequences in the random access configuration of the HEVC test model (HM), the HEVC reference software. This was also carried out in similar configuration settings of the Joint Scalable Video Module (JSVM), the official scalable H.264/AVC reference implementation, running on a single layer mode. According to the results obtained, the HM achieves more than double the compression ratio compared to that of JSVM and delivers the same video quality at half the bitrate. Yet, the HM encodes two times slower (at most) than JSVM. Hence, it can be concluded that the application scenarios of HM and JSVM should be judiciously selected considering the availability of system resources. For instance, HM is not suitable for low delay applications, but it can be used effectively in low bandwidth environments.

10.3745/jips.03.0036

Cite

Citations (11)

Segmentation of Bacterial Cells in Biofilms Using an Overlapped Ellipse Fitting Technique

2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (2021)

Dilanga Abeyrathna Terrance Life Shailabh Rauniyar Shankarachary Ragi Rajesh K. Sani

Accurate detection and segmentation of bacterial cells in the microscopy images of a biofilm is essential to develop technologies to resist microbial corrosion. The traditional approach of manually identifying cell regions in microscopy images is a time-consuming and error-prone task. Nonetheless, many of the existing approaches, including automated systems adopting advanced machine learning models, find it challenging to detect and segment cell instances in clustered biofilms where cells are overlapping and touching each other. In this paper, we develop a method to segment and extract the size properties of all cells. The proposed method consists of two stages, a semantic segmentation stage based on a U-Net architecture followed by a region-based ellipse fitting technique for instance segmentation and size property extraction. We compared the performance of our approach against a widely used object segmentation approach namely Mask R-CNN and found that our algorithm outperformed Mask R-CNN in terms of the segmentation efficiency and cell size estimation for images of Bacillus subtilis biofilms.

Ellipse

10.1109/bibm52615.2021.9669774

Cite

Citations (8)