Peer Reviewed Publications

Filter by type:

Sort by year:

Pathologist-level interpretable whole-slide cancer diagnosis with deep learning.

Zizhao Zhang, Pingjun Chen, Mason McGough, Fuyong Xing, Chunbao Wang, Marilyn Bui, Yuanpu Xie, Manish Sapkota, Lei Cui, Jasreman Dhillon, Nazeel Ahmad, Farah K. Khalil, Shohreh I. Dickinson, Xiaoshuang Shi, Fujun Liu, Hai Su, Jinzheng Cai, Lin Yang
Journal Papers Nature Machine Intelligence, 2019.

Deep Convolutional Hashing for Low Dimensional Binary Embedding of Histopathological Images.

Manish Sapkota, Xiaoshuang Shi, Fuyong Xing, Lin Yang
Journal Papers IEEE Transaction on Journal of Biomedical and Health Informatics, 2018.

Pairwise based Deep Ranking Hashing For Histopathology Image Classification and Retrieval.

Xiaoshuang Shi, Manish Sapkota, Fuyong Xing, Fujun Liu, L Cui, Lin Yang
Journal PapersPattern Recognition, 2018

TandemNet: Distilling Knowledge from Medical Images Using Diagnostic Reports as Optional Semantic References.

Zizhao Zhang, Pingjun Chen, Manish Sapkota, Lin Yang
Conference PapersInternational Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2017

AIIMDs: An Integrated Framework of Automatic Idiopathic Inflammatory Myopathy Diagnosis for Muscle.

Manish Sapkota, Fujun Liu, Yuanpu Xie, Hai Su, Fuyong Xing, Lin Yang
Journal Papers IEEE Transaction on Journal of Biomedical and Health Informatics, 2017.

Asymmetric Discrete Graph Hashing.

Xiaoshuang Shi, Fuyong Xing, Kaidi Xu, Manish Sapkota, Lin Yang
Conference Papers at the 31st AAAI Conference on Artificial Intelligence, 2017.

Spatial Clockwork Recurrent Neural Network for Muscle Perimysium Segmentation.

Yuanpu Xie, Zizhao Zhang, Manish Sapkota, Lin Yang
Conference Papers19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2016 Oct, 9901:185-193. doi: 10.1007/978-3-319-46723-8_22. Epub 2016 Oct 2.

Idiopathic Inflammatory Myopathies Classification Using Deep Convolution Neural Network.

Manish Sapkota, Fuyong Xing, Lin Yang
Abstract Biomedical Engineering Society Annual Meeting (BMES), 2015. (Oral).

Automatic Muscle Perimysium Annotation using Deep Convolutional Neural Network.

Manish Sapkota, Fuyong Xing, Hai Su, Lin Yang
Conference Papers Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on, New York, NY, 2015, pp. 205-208 | April 16-19, 2015 | doi: 10.1109/ISBI.2015.7163850
image

Diseased skeletal muscle expresses mononuclear cell infiltration in the regions of perimysium. Accurate annotation or segmentation of perimysium can help biologists and clinicians to determine individualized patient treatment and allow for reasonable prognostication. However, manual perimysium annotation is time consuming and prone to inter-observer variations. Meanwhile, the presence of ambiguous patterns in muscle images significantly challenge many traditional automatic annotation algorithms. In this paper, we propose an automatic perimysium annotation algorithm based on deep convolutional neural network (CNN). We formulate the automatic annotation of perimysium in muscle images as a pixel-wise classification problem, and the CNN is trained to label each image pixel with raw RGB values of the patch centered at the pixel. The algorithm is applied to 82 diseased skeletal muscle images. We have achieved an average precision of 94% on the test dataset.

Skeletal Muscle Cell Segmentation Using Distributed Convolutional Neural Network.

Manish Sapkota, Fuyong Xing, Fujun Liu, Lin Yang
Workshop PapersThe Eighth International Workshop on High Performance Computing for Biomedical Image Analysis (HPC-MICCAI)|September 2015.

Morphological characteristics of muscle cells, such as cross sectional areas (CSAs), are critical factors to determine the muscle health. Automatic muscle fiber segmentation is often the first prerequisite. However, it is challenging to achieve e ffective and efficient skeletal muscle cell segmentation on Hematoxylin and Eosin (H&E) stained muscle images due to the complex nature of histopathology imaging and a large number of cells on a single image. In this paper, we propose to formulate the cell segmentation as a pixel-wise classification problem and train a deep convolutional neural network (CNN) to segment out the cell boundaries. Considering the speed, we apply the CNN model training to multiple graphical processing units (GPUs), and implement the distributed testing on the Spark parallel computing platform. To further improve running time cost, we apply a fast scanning technique to the pixel-wise classi cation with the learned CNN model. We have presented the segmentation results on a set of 120 H& E stained muscle images using the trained CNN model, and evaluated the proposed framework with accuracy calculation and speed performance.