Image-Based Deep Learning for Brain Tumour Transcriptomics: A Benchmark of DeepInsight, Fotomics, and Saliency-Guided CNNs
Shranjeno v:
| izdano v: | Machine Learning and Knowledge Extraction vol. 7, no. 4 (2025), p. 119-134 |
|---|---|
| Glavni avtor: | |
| Drugi avtorji: | , , |
| Izdano: |
MDPI AG
|
| Teme: | |
| Online dostop: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Oznake: |
Brez oznak, prvi označite!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3286316618 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2504-4990 | ||
| 024 | 7 | |a 10.3390/make7040119 |2 doi | |
| 035 | |a 3286316618 | ||
| 045 | 2 | |b d20251001 |b d20251231 | |
| 100 | 1 | |a Alyatimi Ali |u Faculty of Engineering, School of Computer Science, The University of Sydney, Sydney, NSW 2008, Australia | |
| 245 | 1 | |a Image-Based Deep Learning for Brain Tumour Transcriptomics: A Benchmark of DeepInsight, Fotomics, and Saliency-Guided CNNs | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Classifying brain tumour transcriptomic data is crucial for precision medicine but remains challenging due to high dimensionality and limited interpretability of conventional models. This study benchmarks three image-based deep learning approaches, DeepInsight, Fotomics, and a novel saliency-guided convolutional neural network (CNN), for transcriptomic classification. DeepInsight utilises dimensionality reduction to spatially arrange gene features, while Fotomics applies Fourier transforms to encode expression patterns into structured images. The proposed method transforms each single-cell gene expression profile into an RGB image using PCA, UMAP, or t-SNE, enabling CNNs such as ResNet to learn spatially organised molecular features. Gradient-based saliency maps are employed to highlight gene regions most influential in model predictions. Evaluation is conducted on two biologically and technologically different datasets: single-cell RNA-seq from glioblastoma GSM3828672 and bulk microarray data from medulloblastoma GSE85217. Outcomes demonstrate that image-based deep learning methods, particularly those incorporating saliency guidance, provide a robust and interpretable framework for uncovering biologically meaningful patterns in complex high-dimensional omics data. For instance, ResNet-18 achieved the highest accuracy of 97.25% on the GSE85217 dataset and 91.02% on GSM3828672, respectively, outperforming other baseline models across multiple metrics. | |
| 653 | |a Datasets | ||
| 653 | |a Accuracy | ||
| 653 | |a Tumors | ||
| 653 | |a Gene expression | ||
| 653 | |a Deep learning | ||
| 653 | |a Classification | ||
| 653 | |a Brain cancer | ||
| 653 | |a Fourier transforms | ||
| 653 | |a Salience | ||
| 653 | |a Artificial neural networks | ||
| 653 | |a Neural networks | ||
| 653 | |a Glioma | ||
| 653 | |a Quality control | ||
| 653 | |a Brain | ||
| 653 | |a Images | ||
| 653 | |a Algorithms | ||
| 653 | |a Machine learning | ||
| 653 | |a Benchmarks | ||
| 700 | 1 | |a Chung, Vera |u Faculty of Engineering, School of Computer Science, The University of Sydney, Sydney, NSW 2008, Australia | |
| 700 | 1 | |a Iqbal, Muhammad Atif |u Faculty of Engineering, School of Computer Science, The University of Sydney, Sydney, NSW 2008, Australia | |
| 700 | 1 | |a Anaissi Ali |u Faculty of Engineering, School of Computer Science, The University of Sydney, Sydney, NSW 2008, Australia | |
| 773 | 0 | |t Machine Learning and Knowledge Extraction |g vol. 7, no. 4 (2025), p. 119-134 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3286316618/abstract/embedded/75I98GEZK8WCJMPQ?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3286316618/fulltextwithgraphics/embedded/75I98GEZK8WCJMPQ?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3286316618/fulltextPDF/embedded/75I98GEZK8WCJMPQ?source=fedsrch |