IRO Journals
Journal of Innovative Image Processing

Benchmarking a Modular Deep Learning Pipeline for High-Throughput ASC-Speck Image Classification in Drug Discovery

Open Access
Published: 24 September, 2026
Pages: 1370-1392
  • Sifeddine Elkardoudi , Sifeddine Elkardoudi
    Information Processing Laboratory, Faculty of Sciences Ben M’sik, University Hassan II, Casablanca, Morocco
    Information Processing Laboratory, Faculty of Sciences Ben M’sik, University Hassan II, Casablanca, Morocco
  • Khalil Ladrham , Khalil Ladrham
    Intelligent Processing and Security of Systems, Faculty of Sciences, Mohammed V University, Rabat, Morocco
    Intelligent Processing and Security of Systems, Faculty of Sciences, Mohammed V University, Rabat, Morocco
  • Abdelilah Majdoubi , Abdelilah Majdoubi
    Microbiology and Immunology, Department of Microbiology, Infectiology and Immunology, Faculty of Medicine, University of Montreal, Montreal, Canada
    Microbiology and Immunology, Department of Microbiology, Infectiology and Immunology, Faculty of Medicine, University of Montreal, Montreal, Canada
  • Ahmed Eddaoui , Ahmed Eddaoui
    Information Processing Laboratory, Faculty of Sciences Ben M’sik, University Hassan II, Casablanca, Morocco
    Information Processing Laboratory, Faculty of Sciences Ben M’sik, University Hassan II, Casablanca, Morocco
  • Mohamed Talea Mohamed Talea
    Information Processing Laboratory, Faculty of Sciences Ben M’sik, University Hassan II, Casablanca, Morocco
    Information Processing Laboratory, Faculty of Sciences Ben M’sik, University Hassan II, Casablanca, Morocco
view PDF
view PDF

How to Cite

Elkardoudi, Sifeddine, Khalil Ladrham, Abdelilah Majdoubi, Ahmed Eddaoui, and Mohamed Talea. 2026. “Benchmarking a Modular Deep Learning Pipeline for High-Throughput ASC-Speck Image Classification in Drug Discovery”. Journal of Innovative Image Processing 8 (4): 1370-92. https://doi.org/10.36548/jiip.2026.4.003.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Fluorescence Microscopy
Deep Learning
EfficientNetB0
High-throughput Screening
Speck Classification
Computational Efficiency
Drug Discovery

Abstract

Inflammasome drug screening using THP-1-ASC-GFP reporter cells produces fluorescence microscopy datasets that are difficult to assess manually in high-throughput screening. A modular four-step pipeline for automated ASC-speck classification in drug discovery is presented. The pipeline includes image acquisition, quality-controlled pre-processing, deep learning inference, and a decision output that is compatible with the Laboratory Information Management System (LIMS). Five architectures, EfficientNetB0, MobileNetV2, ResNet18, ResNet50, and ViT-B/16, were systematically benchmarked on 1,580 curated fluorescence micrographs (740 negative, 840 positive) under stratified five-fold cross-validation. EfficientNetB0 was also assessed using strict well-isolated group-stratified validation across 158 micro-wells. EfficientNetB0 provided the most favourable balance between predictive performance and computational efficiency with 89.56% accuracy, 96.47% precision, 83.57% recall, 96.35% specificity and an AUC-ROC of 0.9812 with 5.29 million parameters and 0.39 GFLOPs. Under grouped validation the accuracy was 88.15%, with little inflation of performance from replicate-level leakage. The highest AUC-ROC was achieved by ResNet18 with 0.9847 while MobileNetV2 provided a lower-complexity alternative. ViT-B/16 showed substantially lower balanced performance under the present data regime; this may reflect limited data scale and a possible mismatch between its 16-by-16 patch representation and the subcellular ASC puncta. Offline profiling showed that EfficientNetB0 processed images at 3.24 ms per image on an NVIDIA T4 GPU. Ambiguous predictions were retained for expert review using the confidence-based review band. Overall, the pipeline supports efficient primary screening with traceable outputs, although external multi-centre validation remains necessary before broader deployment. The framework also includes probability-calibration assessment (ECE = 3.42%), confidence reporting, and structured CSV/JSON export compatible with laboratory information management systems.

References

  1. Yao, Jing, Keenan Sterling, Zhe Wang, Yun Zhang, and Weihong Song. ”The Role of Inflammasomes in Human Diseases and their Potential as Therapeutic Targets.” Signal transduction and targeted therapy 9, no. 1 (2024): 10.
  2. Almeida-da-Silva, Cassio Luiz Coutinho, Aline Cristina de Abreu Moreira-Souza, and David M. Ojcius. ”Traditional Approaches and Recent Tools for Studying Inflammasome Activity.” Journal of Immunological Methods 533 (2024): 113744.
  3. Chen, Daniel, Tempest Plott, Michael Wiest, Will Van Trump, Ben Komalo, Dat Nguyen, Charlie Marsh et al. ”A Combined AI and Cell Biology Approach Surfaces Targets and Mechanistically Distinct Inflammasome Inhibitors.” Iscience 27, no. 12 (2024).
  4. Shi, Cheng, Xiangyu Zhang, Xiaowei Chi, Yi Ran Zhou, Weiping Lyu, Tongfei Gao, Jiaxu Zhou et al. ”Discovery of NLRP3 Inhibitors Using Machine Learning: Identification of a Hit Compound to Treat NLRP3 Activation-Driven Diseases.” European Journal of Medicinal Chemistry 260 (2023): 115784.
  5. Li, Jun, Junyu Chen, Yucheng Tang, Ce Wang, Bennett A. Landman, and S. Kevin Zhou. ”Transforming Medical Imaging with Transformers? A Comparative Review of Key Properties, Current Progresses, and Future Perspectives.” Medical image analysis 85 (2023): 102762.
  6. Wittmann, Nico, Ann-Kathrin Behrendt, Neha Mishra, Lukas Bossaller, and Almut Meyer-Bahlburg. ”Instructions for Flow Cytometric Detection of ASC Specks as a Readout of Inflammasome Activation in Human Blood.” Cells 10, no. 11 (2021): 2880.
  7. Lau, Tannia A., Elmar Mair, Beverley M. Rabbitts, Akshar Lohith, and R. Scott Lokey. ”High‐Content Image‐Based Screening and Deep Learning for the Detection of Anti‐Inflammatory Drug Leads.” Chembiochem 25, no. 2 (2024): e202300136.
  8. Zhou, S. Kevin, Hayit Greenspan, Christos Davatzikos, James S. Duncan, Bram Van Ginneken, Anant Madabhushi, Jerry L. Prince, Daniel Rueckert, and Ronald M. Summers. ”A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies with Progress Highlights, and Future Promises.” Proceedings of the IEEE 109, no. 5 (2021): 820-838.
  9. Shafiq, Muhammad, and Zhaoquan Gu. ”Deep Residual Learning for Image Recognition: A Survey.” Applied sciences 12, no. 18 (2022): 8972.
  10. Tan, Mingxing, and Quoc Le. ”Efficientnetv2: Smaller Models and Faster Training.” In International conference on machine learning, PMLR, 2021, 10096-10106.
  11. Dosovitskiy, Alexey, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani et al. ”An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.” arXiv preprint arXiv:2010.11929 (2020).
  12. Bradshaw, Tyler J., Zachary Huemann, Junjie Hu, and Arman Rahmim. ”A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging.” Radiology: Artificial Intelligence 5, no. 4 (2023): e220232.
  13. Bilodeau, Anthony, Constantin VL Delmas, Martin Parent, Paul De Koninck, Audrey Durand, and Flavie Lavoie-Cardinal. ”Microscopy Analysis Neural Network to Solve Detection, Enumeration and Segmentation From Image-Level Annotations.” Nature Machine Intelligence 4, no. 5 (2022): 455-466.
  14. Stringer, Carsen, Tim Wang, Michalis Michaelos, and Marius Pachitariu. ”Cellpose: A Generalist Algorithm for Cellular Segmentation.” Nature methods 18, no. 1 (2021): 100-106.
  15. Raufeisen, Johannes, Kunpeng Xie, Fabian Hörst, Till Braunschweig, Jianning Li, Jens Kleesiek, Rainer Röhrig et al. ”Cyto R-CNN and CytoNuke Dataset: Towards Reliable Whole-Cell Segmentation in Bright-Field Histological Images.” Computer methods and programs in biomedicine 252 (2024): 108215.
  16. Moshkov, Nikita, Michael Bornholdt, Santiago Benoit, Matthew Smith, Claire McQuin, Allen Goodman, Rebecca A. Senft et al. ”Learning Representations for Image-Based Profiling of Perturbations.” Nature communications 15, no. 1 (2024): 1594.
  17. Griebel, Matthias, Dennis Segebarth, Nikolai Stein, Nina Schukraft, Philip Tovote, Robert Blum, and Christoph M. Flath. ”Deep Learning-Enabled Segmentation of Ambiguous Bioimages with Deepflash2.” Nature communications 14, no. 1 (2023): 1679.
  18. Greenwald, Noah F., Geneva Miller, Erick Moen, Alex Kong, Adam Kagel, Thomas Dougherty, Christine Camacho Fullaway et al. ”Whole-cell Segmentation of Tissue Images with Human-Level Performance Using Large-Scale Data Annotation and Deep Learning.” Nature biotechnology 40, no. 4 (2022): 555-565.
  19. Zuiderveld, Karel. ”Contrast Limited Adaptive Histogram Equalization.” In Graphics gems IV, 1994, 474-485.
  20. Otsu, Nobuyuki. ”A Threshold Selection Method from Gray-Level Histograms.” IEEE transactions on systems, man, and cybernetics 9, no. 1 (1979): 62-66.
  21. Sandler, Mark, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. ”Mobilenetv2: Inverted Residuals and Linear Bottlenecks.” In 2018 IEEE/CVF conference on computer vision and pattern recognition, IEEE, 2018, 4510-4520.
  22. Liu, Ze, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. ”Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows.” In 2021 IEEE/CVF international conference on computer vision (ICCV), IEEE, 2021, 9992-10002.
  23. Kingma, Diederik P., and Jimmy Ba. ”Adam: A Method for Stochastic Optimization.” arXiv preprint arXiv:1412.6980 (2014).
  24. Paszke, Adam, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen et al. ”PyTorch: An Imperative Style, High-Performance Deep Learning Library.” Advances in neural information processing systems 32 (2019).
  25. Brima, Yusuf, and Marcellin Atemkeng. ”Saliency-driven Explainable Deep Learning in Medical Imaging: Bridging Visual Explainability and Statistical Quantitative Analysis.” BioData mining 17, no. 1 (2024): 18.