Relational Classification of Biological Cells in Microscopy Images

Authors: Ping Liu, Mustafa Bilgic344-352

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on both synthetic and real datasets show that R-LSTM performs comparable to or better than six baselines.
Researcher Affiliation Academia Ping Liu and Mustafa Bilgic Illinois Institute of Technology, Chicago, IL pliu19@hawk.iit.edu, mbilgic@iit.edu
Pseudocode Yes Algorithm 1 Synthetic data generation; Algorithm 2 Stratified fold generation
Open Source Code Yes The code to replicate the experimental results in this paper is available at https://github.com/IITML/AAAI21-relational-cell-classification.
Open Datasets Yes Histology Images of Colorectal Cancer (CRC) This dataset is introduced by Sirinukunwattana et al. (2016)... Human MCF7 Breast Cancer Cells (MCF-7) MCF-7 is a public image set that was collected and labeled... by Broad Bioimage Benchmark Collection2. ... (Piccinini et al. (2017); Toth et al. (2018))... Urinary Bladder Cancer Tissue Sections (UBC) UBC image dataset (Toth et al. 2018) is a collection of microscopy images... Footnote 2: https://data.broadinstitute.org/bbbc/BBBC021/
Dataset Splits Yes We perform 10-fold stratified cross validation, where eight folds are used for training, one fold for validation, and one fold for testing.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No For the deep learning models (AE, CNN, LCNN, RLSTM) we used Py Torch (Paszke et al. 2017). For SVM, we used scikit-learn (Pedregosa et al. 2011). The text does not specify version numbers for PyTorch or scikit-learn.
Experiment Setup No The paper describes the model architectures, datasets, and cross-validation strategy, but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) for the deep learning models.