A High-resolution dataset for AI-driven segmentation and analysis of drug-treated breast tumor spheroids
Amir Tahmasbi1, Akram Ahvaraki2, Ebrahim Behroodi3
1Department of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran.
Background And Objective:
Three-dimensional (3D) tumor spheroids are widely adopted in preclinical drug screening for their ability to mimic the complexity of in vivo tumor microenvironments. Nevertheless, the high-throughput analysis of such models, especially for quantifying drug responses, remains a significant challenge. This study aims to introduce a high-resolution, publicly available dataset to facilitate AI-driven segmentation and analysis of drug-treated breast tumor spheroids.
Methods:
Heterotypic spheroids consisting of MDA-MB-231 breast cancer cells and human fibroblasts were cultured in a microfluidic chip and subjected to either treatment with liposomal doxorubicin or left untreated. Microscopic imaging was conducted over eight consecutive days, resulting in 95 high-resolution images. These were preprocessed and divided into 2980 image tiles (512 × 512 pixels), followed by semi-automated annotation. The dataset was evaluated using three deep learning segmentation models: U-Net, Fully Convolutional Network (FCN), Mask R-CNN, YOLOv12-Seg, and DeepLab. Morphological features extracted from the segmented spheroids were analyzed using both statistical and machine learning techniques.
Results:
Among the models tested, DeepLab achieved the highest segmentation accuracy with a Jaccard index of 91.17 %. Key morphological descriptors-area, perimeter, inradius, and boundary complexity-were extracted and analyzed using Generalized Estimating Equations, revealing statistically significant differences (p < 0.05) between control and treated spheroids. Classification using a Support Vector Machine trained on features reduced via Principal Component Analysis resulted in 96 % accuracy in distinguishing the two groups.
Conclusions:
The HTS-Seg dataset provides a high-quality image resource with corresponding annotations and morphological features, supporting the development and validation of segmentation and classification models in biomedical image analysis. This work enables more accurate in vitro evaluation of drug effects on 3D tumor spheroid models and contributes to advancements in AI-assisted cancer research.
Insights
This study introduces a new dataset for AI-driven analysis of 3D breast tumor spheroids, enabling precise drug response quantification in cancer research.
Area of Science:
- Biomedical imaging
- Artificial intelligence in oncology
- 3D cell culture models
Background:
- Three-dimensional (3D) tumor spheroids are crucial for preclinical drug screening, mimicking in vivo tumor microenvironments.
- High-throughput analysis and drug response quantification in these models remain challenging.
- A need exists for advanced computational tools to analyze complex spheroid data.
Purpose of the Study:
- To introduce a high-resolution, publicly available dataset for AI-driven segmentation and analysis of drug-treated breast tumor spheroids.
- To facilitate the development of computational models for evaluating drug efficacy.
- To support advancements in AI-assisted cancer research.
Main Methods:
- Heterotypic breast tumor spheroids (MDA-MB-231 cells and fibroblasts) were cultured and treated with liposomal doxorubicin.
- High-resolution microscopy images were acquired over eight days and processed into smaller tiles.
- The dataset was used to evaluate deep learning segmentation models, including DeepLab, U-Net, FCN, Mask R-CNN, and YOLOv12-Seg.
- Morphological features were extracted and analyzed using statistical and machine learning techniques.
Main Results:
- DeepLab demonstrated the highest segmentation accuracy (Jaccard index of 91.17%).
- Key morphological features showed statistically significant differences between control and treated spheroids (p < 0.05).
- A Support Vector Machine classifier achieved 96% accuracy in distinguishing treatment groups based on reduced features.
Conclusions:
- The HTS-Seg dataset offers a valuable resource for developing and validating AI models in biomedical image analysis.
- This resource enables more accurate in vitro evaluation of drug effects on 3D tumor spheroid models.
- The study advances AI-assisted cancer research by improving the analysis of complex 3D cell culture data.
