Inverse Protocol Prediction from Spheroid Microscopy Imaging via Morphology-Aware Structured Learning
Mittal, P.; Srivastava, A.; Chauhan, J.
Show abstract
We introduce Inverse Protocol Prediction (IPP), which is a task of inferring experimental culture conditions directly from a single bright-field spheroid image. We formulate IPP as a structured multi-label prediction problem and propose a protocol-aware learning framework that integrates morphology extraction, multimodal representation learning, and dependency-aware inference. Morphometric descriptors derived from automated spheroid segmentation are fused with deep visual embeddings via a morphometry vision fusion module. To capture biological and procedural dependencies, we develop a Hierarchical Multi-Task Transformer that conditions predictions across protocol attributes. The framework is trained with domainadversarial supervision and morphology-preserving augmentation to improve robustness to acquisition variability. Hybrid convolution attention encoders achieve the best performance, reaching 95.7% multi-attribute accuracy. We further evaluate cross dataset transfer and temporal morphology forecasting. Results demonstrate that structured, dependency-aware modeling enables reliable reconstruction of experimental protocols from imaging alone, supporting reproducibility auditing and protocol validation in 3D cell culture systems.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- RETINA: Reconstruction-based Pre-Trained Enhanced TransUNet for Electron Microscopy Segmentation on the CEM500K Dataset 96%
- A Deep Learning approach for time-consistent cell cycle phase prediction from microscopy data 96%
- Cell-TRACTR: A transformer-based model for end-to-end segmentation and tracking of cells 96%
Similar papers in this journal
Similar papers in this journal
- Batch Equalization with a Generative Adversarial Network 94%
- Stitching and registering highly multiplexed whole slide images of tissues and tumors using ASHLAR 94%
- Digitally Predicting Protein Localization and Manipulating Protein Activity in Fluorescence Images Using Four-dimensional Reslicing GAN 94%
Similar papers in this journal
- A systematic evaluation of computational methods for cell segmentation 96%
- CSRefiner: A lightweight framework for fine-tuning cell segmentation models with small datasets 95%
- SHEST: Single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell type prediction and spatial transcriptomics reconstruction 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.