Using MsfNet to Predict the ISUP Grade of Renal Clear Cell Carcinoma in Digital Pathology Images
Source abstract
Abstract
Clear cell renal cell carcinoma (ccRCC) represents the most frequent form of renal cell carcinoma (RCC), and accurate International Society of Urological Pathology (ISUP) grading is crucial for prognosis and treatment selection. This study presents a new deep network called Multi-scale Fusion Network (MsfNet), which aims to enhance the automatic ISUP grade of ccRCC with digital histopathology pathology images. The MsfNet overcomes the limitations of traditional ResNet50 by multi-scale information fusion and dynamic allocation of channel quantity. The model was trained and tested using 90 Hematoxylin and Eosin (H&E) stained whole slide images (WSIs), which were all cropped into 320 × 320-pixel patches at 40× magnification. MsfNet achieved a microaveraged area under the curve (AUC) of 0.9807, a macro-averaged AUC of 0.9778 on the test dataset. The Gradient-weighted Class Activation Mapping (Grad-CAM) visually demonstrated MsfNet’s ability to distinguish and highlight abnormal areas more effectively than ResNet50. The t-Distributed Stochastic Neighbor Embedding (t-SNE) plot indicates our model can efficiently extract critical features from images, reducing the impact of noise and redundant information. The results suggest that MsfNet offers an accurate ISUP grade of ccRCC in digital images, emphasizing the potential of AI-assisted histopathological systems in clinical practice.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Advanced Neural Network Applications · Radiomics and Machine Learning in Medical Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (46)
Show source-provided references
1. Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life-years for 32 cancer groups, 1990 to 201510.1001/jamaoncol.2016.5688 ↗
2. 682The prognostic value of histologic subtypes in renal cell carcinoma. A multicenter experience in 4063 patients10.1016/S1569-9056(05)80686-4 ↗
3. Trends in renal tumor surgery in the united states and germany between 2006 and 2014: Organ preservation rate is improving10.1245/s10434-019-08108-x ↗
4. A deep learning method for breast cancer classification in the pathology images10.1109/JBHI.2022.3187765 ↗
5. A deep learning framework for automated classification of histopathological kidney whole-slide images10.1016/j.jpi.2022.100093 ↗
6. Prostate cancer risk stratification via nondestructive 3D pathology with deep learning—assisted gland analysis10.1158/0008-5472.CAN-21-2843 ↗
7. Assessment of deep learning assistance for the pathological diagnosis of gastric cancer10.1038/s41379-022-01073-z ↗
8. Automated histological classification for digital pathology images of colonoscopy specimen via deep learning10.1038/s41598-022-16885-x ↗
9. Empowering renal cancer management with AI and digital pathology: Pathology, diagnostics and prognosis10.3390/biomedicines11112875 ↗
10. A weakly supervised deep learning model and human-machine fusion for accurate grading of renal cell carcinoma from histopathology slides10.3390/cancers15123198 ↗
11. Development and validation of a deep-learning model to assist with renal cell carcinoma histopathologic interpretation10.1016/j.urology.2020.05.094 ↗
12. Development and evaluation of a novel deep-learning-based framework for the classification of renal histopathology images10.3390/bioengineering9090423 ↗
13. Trends in renal tumor surgery in the United States and Germany between 2006 and 2014: Organ preservation rate is improving10.1371/journal.pone.0272656 ↗
14. Grading of renal cell carcinoma10.1111/his.13735 ↗
15. The 2016 WHO classification of tumours of the urinary system and male genital organs—Part B: Prostate and bladder tumours10.1016/j.eururo.2016.02.028 ↗
16. Recent advances of deep learning for computational histopathology: Principles and applications10.3390/cancers14051199 ↗
17. Moncayo · 20th Iberoamerican Congress · 2015 · 75
18. Glioma grading via analysis of digital pathology images using machine learning10.3390/cancers12030578 ↗
19. Ensemble of classifiers and wavelet transformation for improved recognition of Fuhrman grading in clear-cell renal carcinoma10.1016/j.bbe.2017.04.005 ↗
20. Prediction of early recurrence of hepatocellular carcinoma after resection using digital pathology images assessed by machine learning10.1038/s41379-020-00671-z ↗
21. Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks10.1016/j.patcog.2018.07.022 ↗
22. Interpretable deep learning systems for multi-class segmentation and classification of non-melanoma skin cancer10.1016/j.media.2020.101915 ↗
23. Lin · IEEE Access · 2021 · 9 · 3314410.1109/ACCESS.2021.3060765 ↗
24. Deep learning-based risk stratification for HER2-negative breast cancer patients
25. A self-supervised vision transformer to predict survival from histopathology in renal cell carcinoma10.1007/s00345-023-04489-7 ↗
26. TGMIL: A hybrid multi-instance learning model based on the transformer and the graph attention network for whole-slide images classification of renal cell carcinoma10.1016/j.cmpb.2023.107789 ↗
27. Online estimation of SOH for lithium-ion battery based on SSA-elman neural network10.1186/s41601-022-00261-y ↗
28. Self-powered electronic skin for remote human-machine synchronization10.1021/acsaelm.2c01476 ↗
29. Computer-aided diagnosis for tuberculosis classification with water strider optimization algorithm10.32604/csse.2023.035253 ↗
30. A survey of convolutional neural networks: Analysis, applications, and prospects10.1109/TNNLS.2021.3084827 ↗
31. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
32. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
33. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
34. Deep residual learning for image recognition
35. Encoder-decoder with atrous separable convolution for semantic image segmentation
36. A survey on image data augmentation for deep learning10.1186/s40537-019-0197-0 ↗
37. A survey of transfer learning10.1186/s40537-016-0043-6 ↗
38. Grad-CAM: Visual explanations from deep networks via gradient-based localization10.1007/s11263-019-01228-7 ↗
39. Parametric nonlinear dimensionality reduction using kernel t-SNE10.1016/j.neucom.2013.11.045 ↗
40. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai et al., “An image is worth 16 × 16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
41. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei et al., “Swin transformer: Hierarchical vision transformer using shifted windows,” arXiv preprint arXiv:2103.14030, 2021.10.1109/ICCV48922.2021.00986 ↗
42. Moldovanu · European Congress of Radiology-ECR 2020 · 2020 · C-10149
43. A preliminary study of radiomics in predicting WHO/ISUP grading of clear cell renal cell carcinoma based on unenhanced CT texture analysis
44. Identification of ISUP grade of clear cell renal cell carcinoma by radiomics on multi-phase CT images10.1007/s42058-022-00087-5 ↗
45. Y. Gao, X. Wang, X. Zhao, C. Zhu, C. Li et al., “Multiphase CT radiomics nomogram for preoperatively predicting the WHO/ISUP nuclear grade of small (< 4 cm) clear cell renal cell carcinoma,” [Online]. Available: https://www.researchsquare.com/article/rs-2612246/v1 (accessed on 10/02/2023)10.1186/s12885-023-11454-5 ↗
46. Development and evaluation of a deep neural network for histologic classification of renal cell carcinoma on biopsy and surgical resection slides