Dr. Trupti Kolur Profile

Dr. Trupti Kolur

SPIE Involvement:

Author

Publications (6)

SPIE Journal Paper | 3 November 2022 Open Access

Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images

Bofan Song, Shaobai Li, Sumsum Sunny, Keerthi Gurushanth, Pramila Mendonca, Nirza Mukhia, Sanjana Patrick, Tyler Peterson, Shubha Gurudath, Subhashini Raghavan, Imchen Tsusennaro, Shirley Leivon, Trupti Kolur, Vivek Shetty, Vidya Bushan, Rohan Ramesh, Vijay Pillai, Petra Wilder-Smith, Amritha Suresh, Moni Abraham Kuriakose, Praveen Birur, Rongguang Liang

JBO, Vol. 27, Issue 11, 115001, (November 2022) https://doi.org/10.1117/12.10.1117/1.JBO.27.11.115001

KEYWORDS: Image segmentation, Cancer, Tumor growth modeling, Performance modeling, Convolution, Instrument modeling, Reliability, Medical research, Inspection, Skin cancer

Read Abstract +

SignificanceOral cancer is one of the most prevalent cancers, especially in middle- and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output.AimWe aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions.ApproachThis work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists.ResultsThe proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings.ConclusionsOur study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model’s prediction can be improved.

DOWNLOAD PAPER

SPIE Journal Paper | 12 January 2022 Open Access

Interpretable deep learning approach for oral cancer classification using guided attention inference network

Kevin Figueroa, Bofan Song, Sumsum Sunny, Shaobai Li, Keerthi Gurushanth, Pramila Mendonca, Nirza Mukhia, Sanjana Patrick, Shubha Gurudath, Subhashini Raghavan, Imchen Tsusennaro, Shirley Leivon, Trupti Kolur, Vivek Shetty, Vidya Bushan, Rohan Ramesh, Vijay Pillai, Petra Wilder-Smith, Alben Sigamani, Amritha Suresh, Moni Kuriakose, Praveen Birur, Rongguang Liang

JBO, Vol. 27, Issue 01, 015001, (January 2022) https://doi.org/10.1117/12.10.1117/1.JBO.27.1.015001

KEYWORDS: Cancer, Image classification, Network architectures, Visualization, Mining, Lithium, Tongue, Image segmentation, Image processing, Teeth

Read Abstract +

Significance: Convolutional neural networks (CNNs) show the potential for automated classification of different cancer lesions. However, their lack of interpretability and explainability makes CNNs less than understandable. Furthermore, CNNs may incorrectly concentrate on other areas surrounding the salient object, rather than the network’s attention focusing directly on the object to be recognized, as the network has no incentive to focus solely on the correct subjects to be detected. This inhibits the reliability of CNNs, especially for biomedical applications. Aim: Develop a deep learning training approach that could provide understandability to its predictions and directly guide the network to concentrate its attention and accurately delineate cancerous regions of the image. Approach: We utilized Selvaraju et al.’s gradient-weighted class activation mapping to inject interpretability and explainability into CNNs. We adopted a two-stage training process with data augmentation techniques and Li et al.’s guided attention inference network (GAIN) to train images captured using our customized mobile oral screening devices. The GAIN architecture consists of three streams of network training: classification stream, attention mining stream, and bounding box stream. By adopting the GAIN training architecture, we jointly optimized the classification and segmentation accuracy of our CNN by treating these attention maps as reliable priors to develop attention maps with more complete and accurate segmentation. Results: The network’s attention map will help us to actively understand what the network is focusing on and looking at during its decision-making process. The results also show that the proposed method could guide the trained neural network to highlight and focus its attention on the correct lesion areas in the images when making a decision, rather than focusing its attention on relevant yet incorrect regions. Conclusions: We demonstrate the effectiveness of our approach for more interpretable and reliable oral potentially malignant lesion and malignant lesion classification.

DOWNLOAD PAPER

SPIE Journal Paper | 23 October 2021 Open Access

Classification of imbalanced oral cancer image data from high-risk population

Bofan Song, Shaobai Li, Sumsum Sunny, Keerthi Gurushanth, Pramila Mendonca, Nirza Mukhia, Sanjana Patrick, Shubha Gurudath, Subhashini Raghavan, Imchen Tsusennaro, Shirley Leivon, Trupti Kolur, Vivek Shetty, Vidya Bushan, Rohan Ramesh, Tyler Peterson, Vijay Pillai, Petra Wilder-Smith, Alben Sigamani, Amritha Suresh, Moni Kuriakose, Praveen Birur, Rongguang Liang

JBO, Vol. 26, Issue 10, 105001, (October 2021) https://doi.org/10.1117/12.10.1117/1.JBO.26.10.105001

KEYWORDS: Cancer, Image classification, Data modeling, Tumor growth modeling, Medical imaging, Neural networks, Medical research, Breast cancer, Biomedical optics, Mobile devices

Read Abstract +

DOWNLOAD PAPER

SPIE Journal Paper | 23 June 2021 Open Access

Mobile-based oral cancer classification for point-of-care screening

Bofan Song, Sumsum Sunny, Shaobai Li, Keerthi Gurushanth, Pramila Mendonca, Nirza Mukhia, Sanjana Patrick, Shubha Gurudath, Subhashini Raghavan, Tsusennaro Imchen, Shirley Leivon, Trupti Kolur, Vivek Shetty, Vidya Bushan, Rohan Ramesh, Natzem Lima, Vijay Pillai, Petra Wilder-Smith, Alben Sigamani, Amritha Suresh, Moni Kuriakose, Praveen Birur, Rongguang Liang

JBO, Vol. 26, Issue 06, 065003, (June 2021) https://doi.org/10.1117/12.10.1117/1.JBO.26.6.065003

KEYWORDS: Cancer, Image classification, Point-of-care devices, Internet, Convolution, Optimization (mathematics), Image processing, Tumor growth modeling, Light emitting diodes, Gold

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 9 March 2020 Presentation

Dual-modal oral cancer screening platform and automatic classification algorithm for low-resource settings (Conference Presentation)

Bofan Song, Sumsum Sunny, Ross Uthoff, Sanjana Patrick, Amritha Suresh, Trupti Kolur, G. Keerthi, Afarin Anbarani, Petra Wilder-Smith, Moni Kuriakose, Praveen Birur, Jeffrey Rodriguez, Rongguang Liang

Proceedings Volume 11230, 112300V (2020) https://doi.org/10.1117/12.2552213

Read Abstract +

SPIE Journal Paper | 22 October 2019 Open Access

Small form factor, flexible, dual-modality handheld probe for smartphone-based, point-of-care oral and oropharyngeal cancer screening

Ross Uthoff, Bofan Song, Sumsum Sunny, Sanjana Patrick, Amritha Suresh, Trupti Kolur, Keerthi Gurushanth, Kimberly Wooten, Vishal Gupta, Mary Platek, Anurag Singh, Petra Wilder-Smith, Moni Abraham Kuriakose, Praveen Birur, Rongguang Liang

JBO, Vol. 24, Issue 10, 106003, (October 2019) https://doi.org/10.1117/12.10.1117/1.JBO.24.10.106003

KEYWORDS: Cameras, Light emitting diodes, Cancer, Silicon, Imaging systems, Head, Modulation transfer functions, Point-of-care devices, Biomedical optics, Optical filters

Read Abstract +

DOWNLOAD PAPER

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years