Dr. Janaka Senarathna Profile

Dr. Janaka Senarathna

Postdoc Fellow at Johns Hopkins Univ

SPIE Involvement:

Author

Area of Expertise:

Biomedical Engineering , Optics , Instrumentation , Image processing

Websites:

Personal Website | Company Website

Dr. Senarathna specializes in designing miniature optical imaging instruments for biomedical applications. He has a B.Sc. in Electronics and Telecommunications Eng. form the University of Moratuwa in Katubedda, Sri Lanka and an M.S.E (wtih Dr. Nitish Thakor) and a Ph.D. (with Dr. Arvind Pathak) in Biomedical Engineering from the Johns Hopkins University in Baltimore, Maryland, USA. He is currently a Kavli Neuroscience Discovery Institute Postdoc Scholar, and studies brain injury using the the instruments he developed. He is also a past Toastmaster.

Proceedings Article | 2 April 2024 Poster + Paper

Predicting animal behavior from neuronal miniscope data: a deep learning approach

Subhrajit Das, Janaka Senarathna, Emma Ouyang, Amit Banerjee, Arvind Pathak

Proceedings Volume 12926, 1292622 (2024) https://doi.org/10.1117/12.3006089

KEYWORDS: Data modeling, Neuroimaging, Animals, Performance modeling, Animal model studies, Deep learning, Education and training, Data acquisition, Brain, Machine learning

Read Abstract +

The field of systems neuroscience strives to comprehend the intricate links between brain activity and behavior, with the goal of understanding neurological disorders and targeted interventions, notably in feedback-based therapies like Deep Brain Stimulation (DBS). However, challenges persist in correlating neuroimaging data with behavior, especially in freely behaving animals and across different imaging modalities. In the last decade, deep learning has emerged as a crucial tool for analyzing image data and enabling the correlation or prediction from different imaging modalities. This study investigates the application of a sophisticated deep learning architecture, specifically a pre-trained ResNet50-BiLSTM model, to predict behaviors from neuroimaging data. This study acquired multicontrast neuroimaging data (fluorescence or FL, intrinsic optical signal or IOS, and laser speckle contrast or LSC) synchronized with behavioral data from five awake, healthy mice. Behavioral "syllables" (i.e. running, nest building/eating, and minimally mobile) or classes were annotated using Behavior Cloud software. Neural activity (i.e. FL channel) image sequences were associated with behavioral syllables, consisting of 12 image frames spanning one minute. A pre-trained ResNet50-BiLSTM architecture was used for image sequence classification. We added a fully connected layer after BiLSTM and fine-tuned it to compute class scores. Since we had only five mice, we evaluated the model’s performance and generalizability using a 5-fold cross-testing strategy. Test accuracy was utilized to assess the reliability and robustness of predictions, and performance evaluation. Generalizability results showcase the promising performance of the ResNet50-BiLSTM model for predicting behavior from neural activity images with test accuracy reaching 93.75%. We intend to conduct additional research on this pipeline’s generalizability by analyzing confusion matrices, ROC curves, and AUCs, within a One-vs-All (OvA) framework. This initial study lays the groundwork for the exploration of multi-modal approaches (e.g. vision transformers and autoencoders) that encompass different neuroimaging modalities for accurate behavior prediction.

Proceedings Article | 1 March 2019 Presentation + Paper

Design considerations for a miniature multicontrast neuroimager

Janaka Senarathna, Qihong Wang, Betty Tyler, Nitish Thakor, Arvind Pathak

Proceedings Volume 10864, 108640P (2019) https://doi.org/10.1117/12.2524622

KEYWORDS: Tumors, Imaging systems, Image sensors, Brain, Neuroimaging, Light emitting diodes, Semiconductor lasers, Optical imaging, Blood

Read Abstract +

Proceedings Article | 19 April 2017 Presentation

Wide-area mapping of resting state hemodynamic correlations at microvascular resolution with multi-contrast optical imaging (Conference Presentation)

Janaka Senarathna, Darian Hadjiabadi, Stacy Gil, Nitish Thakor, Arvind Pathak, Namrata Batra

Proceedings Volume 10051, 100510Z (2017) https://doi.org/10.1117/12.2255518

KEYWORDS: Brain mapping, Imaging systems, Brain, Laser speckle contrast imaging, Optical imaging, Hemodynamics, Image resolution, Optical resolution, Visualization, Functional magnetic resonance imaging

Read Abstract +

Proceedings Article | 9 March 2016 Presentation + Paper

Effect of cranial window type on monitoring neurovasculature using laser speckle contrast imaging

Hang Yu, Janaka Senarathna, Betty Tyler, Syed Hossain, Nitish Thakor, Arvind Pathak

Proceedings Volume 9690, 969009 (2016) https://doi.org/10.1117/12.2213989

KEYWORDS: Windows, Cranial windows, Laser speckle contrast imaging, Cerebral blood flow, Optical imaging, Speckle, Neuroimaging, Brain, Skull, Surgery, In vivo imaging, Blood vessels, Image segmentation, Blood circulation, Image analysis

Read Abstract +

Keywords/Phrases

Search In:

Publication Years