Deep Learning–based Recurrence Prediction in Patients with Non–muscle-invasive Bladder Cancer

Lucas, Marit; Jansen, Ilaria; Leeuwen, Ton G. van; Oddens, Jorg R.; Bruin, Daniël M. de; Marquering, Henk A.

doi:10.1016/j.euf.2020.12.008

Cited by 31 publications

(32 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, AI-based studies in bladder cancer used end-to-end deep learning to predict molecular subtypes of MIBC [14], but without focusing on a specific molecular alteration. Other related studies in bladder cancer analyzed the classification of MIBC and non-MIBC [15], grading of non-MIBC [16], recurrence prediction of non-MIBC [17], and tumor budding/staging of MIBC [18]. However, to the best of our knowledge, our histology-based deep learning approach is the first study identifying clinically relevant molecular treatment targets in bladder cancer samples in two independent patient cohorts.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence–based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing?

Loeffler

Bruechle

Jung

et al. 2022

European Urology Focus

View full text Add to dashboard Cite

Background: Fibroblast growth factor receptor (FGFR) inhibitor treatment has become the first clinically approved targeted therapy in bladder cancer. However, it requires previous molecular testing of each patient, which is costly and not ubiquitously available. Objective: To determine whether an artificial intelligence system is able to predict mutations of the FGFR3 gene directly from routine histology slides of bladder cancer. Design, setting, and participants: We trained a deep learning network to detect FGFR3 mutations on digitized slides of muscle-invasive bladder cancers stained with hematoxylin and eosin from the Cancer Genome Atlas (TCGA) cohort (n = 327) and validated the algorithm on the "Aachen" cohort (n = 182; n = 121 pT2-4, n = 34 stroma-invasive pT1, and n = 27 noninvasive pTa tumors). Outcome measurements and statistical analysis: The primary endpoint was the area under the receiver operating curve (AUROC) for mutation detection. Performance of the deep learning system was compared with visual scoring by an uropathologist. Results and limitations: In the TCGA cohort, FGFR3 mutations were detected with an AUROC of 0.701 (p < 0.0001). In the Aachen cohort, FGFR3 mutants were found with an AUROC of 0.725 (p < 0.0001). When trained on TCGA, the network generalized to the Aachen cohort, and detected FGFR3 mutants with an AUROC of 0.625 (p = 0.0112). A subgroup analysis and histological evaluation found highest accuracy in papillary growth, luminal gene expression subtypes, females, and American Joint Committee on Cancer (AJCC) stage II tumors. In a head-to-head comparison, the deep learning system outperformed the uropathologist in detecting FGFR3 mutants. Conclusions: Our computer-based artificial intelligence system was able to detect genetic alterations of the FGFR3 gene of bladder cancer patients directly from histological slides. In the future, this system could be used to preselect patients for further molecular testing. However, analyses of larger, multicenter, muscle-invasive bladder cancer cohorts are now needed in order to validate and extend our findings.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence–based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing?

Loeffler

Bruechle

Jung

et al. 2022

European Urology Focus

View full text Add to dashboard Cite

show abstract

“…The majority of CAD research conducted on histological images utilize two or more seperate models in their methods [21] [22] [16] [23] [24]. First, a segmentation algorithm or region of interest (ROI) selection step is performed to narrow down the area which needs additional processing.…”

Section: Previous Workmentioning

confidence: 99%

“…From the same research group, the work of Lucas et al [24] utilized the same urothelium segmentation model as presented in [22]. Regions of urothelium were then fed into a selection network which classified tiles into recurrence vs. no recurrence.…”

Section: Previous Workmentioning

confidence: 99%

Automatic Diagnostic Tool for Predicting Cancer Grade in Bladder Cancer Patients Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

The most common type of bladder cancer is urothelial carcinoma, which is among the cancer types with the highest recurrence rate and lifetime treatment cost per patient. Diagnosed patients are stratified into risk groups, mainly based on grade and stage. However, it is well known that correct grading of bladder cancer suffers from intra-and interobserver variability and inconsistent reproducibility between pathologists, potentially leading to under-or overtreatment of the patients. The economic burden, unnecessary patient suffering, and additional load on the health care system illustrate the importance of developing new tools to aid pathologists. We propose a pipeline, called TRI grade , that will identify diagnostic relevant regions in the whole-slide image (WSI) and collectively predict the grade of the current WSI. The system consists of two main models, trained on weak slide-level grade labels. First, a WSI is segmented into the different tissue classes (urothelium, stroma, muscle, blood, damaged tissue, and background). Next, tiles are extracted from the diagnostic relevant urothelium tissue from three magnification levels (25x, 100x, and 400x) and processed sequentially by a convolutional neural network (CNN) based model. Ten models were trained for the slide-level grading experiment, where the best model achieved an F1-score of 0.90 on a test set consisting of 50 WSIs. The best model was further evaluated on a smaller segmentation test set, consisting of 14 WSIs where low-and high-grade regions were annotated by a pathologist. The TRI grade pipeline achieved an average F1-score of 0.91 for both the low-grade and high-grade classes.INDEX TERMS Automated cancer grading, bladder cancer, convolutional neural networks, multiscale classification, urothelial carcinoma, weakly labelled data, whole-slide image.

show abstract

“…For that reason, many studies in the state of the art have proposed artificial-intelligence algorithms to help pathologists in terms of cost-effectiveness and subjectivity ratio. Most of them focused on machinelearning techniques applied on H & E-stained histological images for segmentation [14][15][16] and classification [12,13,[17][18][19][20][21][22] problems.…”

Section: Related Workmentioning

confidence: 99%

“…Regarding the segmentation-based studies, Lucas et al [14] used the popular U-net architecture to segment normal and malignant cases of bladder images. Then, they used the common VGG16 network as a backbone to extract histological features from patches of 224×224 pixels.…”

Section: Related Workmentioning

confidence: 99%

A Novel Self-Learning Framework for Bladder Cancer Grading Using Histopathological Images

Garcı́a¹,

Esteve²,

Colomer³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, bladder cancer has been significantly increased in terms of incidence and mortality. Currently, two subtypes are known based on tumour growth: non-muscle invasive (NMIBC) and muscle-invasive bladder cancer (MIBC). In this work, we focus on the MIBC subtype because it is of the worst prognosis and can spread to adjacent organs. We present a self-learning framework to grade bladder cancer from histological images stained via immunohistochemical techniques. Specifically, we propose a novel Deep Convolutional Embedded Attention Clustering (DCEAC) which allows classifying histological patches into different severity levels of the disease, according to the patterns established in the literature. The proposed DCEAC model follows a two-step fully unsupervised learning methodology to discern between non-tumour, mild and infiltrative patterns from high-resolution samples of 512 × 512 pixels. Our system outperforms previous clustering-based methods by including a convolutional attention module, which allows refining the features of the latent space before the classification stage. The proposed network exceeds state-of-the-art approaches by 2−3% across different metrics, achieving a final average accuracy of 0.9034 in a multi-class scenario. Furthermore, the reported class activation maps evidence that our model is able to learn by itself the same patterns that clinicians consider relevant, without incurring prior annotation steps. This fact supposes a breakthrough in muscle-invasive bladder cancer grading which bridges the gap with respect to train the model on labelled data.

show abstract

Deep Learning–based Recurrence Prediction in Patients with Non–muscle-invasive Bladder Cancer

Cited by 31 publications

References 23 publications

Artificial Intelligence–based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing?

Artificial Intelligence–based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing?

Automatic Diagnostic Tool for Predicting Cancer Grade in Bladder Cancer Patients Using Deep Learning

A Novel Self-Learning Framework for Bladder Cancer Grading Using Histopathological Images

Contact Info

Product

Resources

About