Transcriptome-supervised classification of tissue morphology using deep learning (2312.04605v1)
Abstract: Deep learning has proven to successfully learn variations in tissue and cell morphology. Training of such models typically relies on expensive manual annotations. Here we conjecture that spatially resolved gene expression, e.i., the transcriptome, can be used as an alternative to manual annotations. In particular, we trained five convolutional neural networks with patches of different size extracted from locations defined by spatially resolved gene expression. The network is trained to classify tissue morphology related to two different genes, general tissue, as well as background, on an image of fluorescence stained nuclei in a mouse brain coronal section. Performance is evaluated on an independent tissue section from a different mouse brain, reaching an average Dice score of 0.51. Results may indicate that novel techniques for spatially resolved transcriptomics together with deep learning may provide a unique and unbiased way to find genotype-phenotype relationships.
- “Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study,” The Lancet Oncology, 2020.
- “Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features,” J. of Medical Imaging, vol. 1, no. 3, pp. 034003, Oct. 2014.
- “Automated classification of cell morphology by coherence-controlled holographic microscopy,” J. of biomedical optics, vol. 22, no. 8, pp. 086008, 2017.
- “Inter-observer variability between general pathologists and a specialist in breast pathology in the diagnosis of lobular neoplasia, columnar cell lesions, atypical ductal hyperplasia and ductal carcinoma in situ of the breast,” Diagnostic Pathology, vol. 9, no. 1, pp. 121, 2014.
- “Interobserver variability by pathologists in the distinction between cellular fibroadenomas and phyllodes tumors,” Int. J. of Surgical Pathology, vol. 22, no. 8, pp. 695–698, Aug. 2014.
- “In silico labeling: predicting fluorescent labels in unlabeled images,” Cell, vol. 173, no. 3, pp. 792–803, 2018.
- “Label-free prediction of three-dimensional fluorescence images from transmitted-light microscopy,” Nature methods, vol. 15, no. 11, pp. 917, 2018.
- “In situ sequencing for RNA analysis in preserved tissue and cells,” Nature Methods, vol. 10, no. 9, pp. 857–860, July 2013.
- “A spatial atlas of inhibitory cell types in mouse hippocampus,” bioRxiv preprint doi:10.1101/431957, 2018.
- “Identification of spatial compartments in tissue from in situ sequencing data,” bioRxiv preprint doi:10.1101/765842, 2019.
- “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.