ANAnand K. Nambisan

Anand K. Nambisan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anand K. Nambisan has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features

    by Akanksha Maurya, R. Joe Stanley, Hemanth Y. Aradhyula, Norsang Lama, Anand K. Nambisan, Gehana Patel, Daniyal Saeed, Samantha Swinfard, Colin Smith, Sadhika Jagannathan, et al.

    In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. However, most approaches lack clinical inputs supported by dermatologists that could aid in higher accuracy and explainability. To dermatologists, the presence of telangiectasia, or narrow blood vessels that typically appear serpiginous or arborizing, is a critical indicator of basal cell carcinoma (BCC). Exploiting the feature information present in telangiectasia through a combination of DL-based techniques could create a pathway for both, improving DL results as well as aiding dermatologists in BCC diagnosis. This study demonstrates a novel “fusion” technique for BCC vs non-BCC classification using ensemble learning on a combination of (a) handcrafted features from semantically segmented telangiectasia (U-Net-based) and (b) deep learning features generated from whole lesion images (EfficientNet-B5-based). This fusion method achieves a binary classification accuracy of 97.2%, with a 1.3% improvement over the corresponding DL-only model, on a holdout test set of 395 images. An increase of 3.7% in sensitivity, 1.5% in specificity, and 1.5% in precision along with an AUC of 0.99 was also achieved. Metric improvements were demonstrated in three stages: (1) the addition of handcrafted telangiectasia features to deep learning features, (2) including areas near telangiectasia (surround areas), (3) discarding the noisy lower-importance features through feature importance. Another novel approach to feature finding with weak annotations through the examination of the surrounding areas of telangiectasia is offered in this study. The experimental results show state-of-the-art accuracy and precision in the diagnosis of BCC, compared to three benchmark techniques. Further exploration of deep learning techniques for individual dermoscopy feature detection is warranted.


  • Open Access

    Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis

    by Akanksha Maurya, R. Joe Stanley, Norsang Lama, Anand K. Nambisan, Gehana Patel, Daniyal Saeed, Samantha Swinfard, Colin Smith, Sadhika Jagannathan, Jason R. Hagerty, et al.

    A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.


  • Open Access

    Chemical Classification by Monitoring Liquid Evaporation Using Extrinsic Fabry-Perot Interferometer With Microwave Photonics

    by Abhishek Prakash Hungund, Bohong Zhang, Anand Nambisan, Wassana Naku, Rex E. Gerald, Jie Huang

    Identification of liquids is essential in chemical analysis, safety, environmental protection, quality control, and research. A novel liquid identification system based on Microwave Photonics (MWP) measured time transient evaporation signals is investigated. An extrinsic Fabry-Perot Interferometer (EFPI) based optical probe using single-mode fiber (SMF) is proposed to monitor evaporation of different liquids. The MWP system is used to measure the optical path changes during liquid evaporation due to its high sensitivity, selectivity, and Signal-to-Noise Ratio (SNR). The measured S21 continuous wave (CW) time Magnitude and Phase signals were processed to extract features such as histogram and Fast Fourier Transform (FFT) peaks. Using features extracted from droplet evaporation time transient events, machine learning classification accurately identified chemicals in each liquid with an accuracy rate of over 99%, employing three algorithms: Decision Trees, Support Vector Machine (SVM), and K-nearest neighbors (KNN). The classification results demonstrate accurate liquid identification based on evaporation measurements by the MWP system.


  • Open Access

    Plant Identification in a Combined-Imbalanced Leaf Dataset

    by Viraj K. Gajjar, Anand K. Nambisan, Kurt L. Kosbar

    Plant identification has applications in ethnopharmacology and agriculture. Since leaves are one of a distinguishable feature of a plant, they are routinely used for identification. Recent developments in deep learning have made it possible to accurately identify the majority of samples in five publicly available leaf datasets. However, each dataset captures the images in a highly controlled environment. This paper evaluates the performance of EfficientNet and several other convolutional neural network (CNN) architectures when applied to a combination of the LeafSnap, Middle European Woody Plants 2014, Flavia, Swedish, and Folio datasets. To normalize the impact of imbalance resulting from combining the original datasets, oversampling, undersampling, and transfer learning techniques were used to construct an end-to-end CNN classifier. Greater emphasis was placed on metrics that are appropriate for a diverse-imbalanced dataset, rather than stressing high performance on any one of the original datasets. A model from EfficientNet’s family of CNN models was able to achieve a highly accurate F-score of 0.9861 on the combined dataset.