Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors

Liang, Cher‐Wei; Fang, Pei-Wei; Huang, Hsuan‐Ying; Lo, Chung-Ming

doi:10.3390/cancers13225787

Cited by 11 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the performance of our model decreased from center 1 to center 2. This is probably related to the small size of our training set as the lack of diversity in small cohorts often leads to poor transferability of deep learning models due to domain shift 19 – 22 . Indeed, a shift in risk prediction was observed when applying our model in the testing cohort, resulting in an under estimation of patients’ risk of relapse.…”

Section: Discussionmentioning

confidence: 99%

“…These results suggest that the tumor cell morphology can only partially explain the mutational profile, and DL learns additional morphological features related to mutations. With this unprecedented large cohort of patients, the model performance and robustness have been greatly improved for predicting mutations at gene level compared to a previous study 19 . More importantly, DL was able to accurately predict mutations that have a great impact in patients’ treatment decision and prognostic estimation such as PDGFRA exon18 D842V mutation which is a predictor for imatinib resistance and avapritinib 25 sensitivity, and KIT del-inc 557/558 mutations which are associated with a worse prognosis and high-risk of relapse.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning predicts patients outcome and mutations from digitized histology slides in gastrointestinal stromal tumor

Fu¹,

Karanian

Perret

et al. 2023

npj Precis. Onc.

View full text Add to dashboard Cite

Risk assessment of gastrointestinal stromal tumor (GIST) according to the AFIP/Miettinen classification and mutational profiling are major tools for patient management. However, the AFIP/Miettinen classification depends heavily on mitotic counts, which is laborious and sometimes inconsistent between pathologists. It has also been shown to be imperfect in stratifying patients. Molecular testing is costly and time-consuming, therefore, not systematically performed in all countries. New methods to improve risk and molecular predictions are hence crucial to improve the tailoring of adjuvant therapy. We have built deep learning (DL) models on digitized HES-stained whole slide images (WSI) to predict patients’ outcome and mutations. Models were trained with a cohort of 1233 GIST and validated on an independent cohort of 286 GIST. DL models yielded comparable results to the Miettinen classification for relapse-free-survival prediction in localized GIST without adjuvant Imatinib (C-index=0.83 in cross-validation and 0.72 for independent testing). DL splitted Miettinen intermediate risk GIST into high/low-risk groups (p value = 0.002 in the training set and p value = 0.29 in the testing set). DL models achieved an area under the receiver operating characteristic curve (AUC) of 0.81, 0.91, and 0.71 for predicting mutations in KIT, PDGFRA and wild type, respectively, in cross-validation and 0.76, 0.90, and 0.55 in independent testing. Notably, PDGFRA exon18 D842V mutation, which is resistant to Imatinib, was predicted with an AUC of 0.87 and 0.90 in cross-validation and independent testing, respectively. Additionally, novel histological criteria predictive of patients’ outcome and mutations were identified by reviewing the tiles selected by the models. As a proof of concept, our study showed the possibility of implementing DL with digitized WSI and may represent a reproducible way to improve tailoring therapy and precision medicine for patients with GIST.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep learning predicts patients outcome and mutations from digitized histology slides in gastrointestinal stromal tumor

Fu¹,

Karanian

Perret

et al. 2023

npj Precis. Onc.

View full text Add to dashboard Cite

show abstract

“…Identifying these mutations is vital as there is specific therapy for them [ 69 , 70 ]. A CNN model was proposed by Liang et al (2021) [ 42 ] to identify the KIT and PDGFRA gene mutations based on the histologic images. Pre-trained models on ImageNet were used to predict these drug-sensitive mutations.…”

Section: Mutation Identificationmentioning

confidence: 99%

Transfer Learning in Cancer Genetics, Mutation Detection, Gene Expression Analysis, and Syndrome Recognition

Ashayeri,

Sobhi,

Pławiak

et al. 2024

Cancers

View full text Add to dashboard Cite

Artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), has revolutionized medical research, facilitating advancements in drug discovery and cancer diagnosis. ML identifies patterns in data, while DL employs neural networks for intricate processing. Predictive modeling challenges, such as data labeling, are addressed by transfer learning (TL), leveraging pre-existing models for faster training. TL shows potential in genetic research, improving tasks like gene expression analysis, mutation detection, genetic syndrome recognition, and genotype–phenotype association. This review explores the role of TL in overcoming challenges in mutation detection, genetic syndrome detection, gene expression, or phenotype–genotype association. TL has shown effectiveness in various aspects of genetic research. TL enhances the accuracy and efficiency of mutation detection, aiding in the identification of genetic abnormalities. TL can improve the diagnostic accuracy of syndrome-related genetic patterns. Moreover, TL plays a crucial role in gene expression analysis in order to accurately predict gene expression levels and their interactions. Additionally, TL enhances phenotype–genotype association studies by leveraging pre-trained models. In conclusion, TL enhances AI efficiency by improving mutation prediction, gene expression analysis, and genetic syndrome detection. Future studies should focus on increasing domain similarities, expanding databases, and incorporating clinical data for better predictions.

show abstract

“…Successful instances include polyp classification in colonoscopy 26 and genotype evaluation in gastrointestinal stromal tumors. 27 With respect to stroke estimation, a multicenter study suggested using deep learning to predict ischemic stroke lesions from MRI. 28 Noncontrast computed tomography was also proposed in the literature to detect strokes by deep learning features due to its efficiency.…”

Section: Introductionmentioning

confidence: 99%

“…With the development of computer‐aided diagnosis (CAD) systems, quantitative image features can be extracted and combined in a machine learning classifier to provide an objective and consistent diagnostic evaluation. Successful instances include polyp classification in colonoscopy 26 and genotype evaluation in gastrointestinal stromal tumors 27 . With respect to stroke estimation, a multicenter study suggested using deep learning to predict ischemic stroke lesions from MRI 28 .…”

Section: Introductionmentioning

confidence: 99%

Predictive stroke risk model with vision transformer‐based Doppler features

Lo,

Hung

2023

Medical Physics

View full text Add to dashboard Cite

BackgroundAcute stroke is the leading cause of death and disability globally, with an estimated 16 million cases each year. The progression of carotid stenosis reduces blood flow to the intracranial vasculature, causing stroke. Early recognition of ischemic stroke is crucial for disease treatment and management.PurposeA computer‐aided diagnosis (CAD) system was proposed in this study to rapidly evaluate ischemic stroke in carotid color Doppler (CCD).MethodsBased on the ground truth from the clinical examination report, the vision transformer (ViT) features extracted from all CCD images (513 stroke and 458 normal images) were combined in machine learning classifiers to generate the likelihood of ischemic stroke for each image. The pretrained weights from ImageNet reduced the time‐consuming training process. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were calculated to evaluate the stroke prediction model. The chi‐square test, DeLong test, and Bonferroni correction for multiple comparisons were applied to deal with the type‐I error. Only p values equal to or less than 0.00125 were considered to be statistically significant.ResultsThe proposed CAD system achieved an accuracy of 89%, a sensitivity of 94%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.95, outperforming the convolutional neural networks AlexNet (82%, p < 0.001), Inception‐v3 (78%, p < 0.001), ResNet101 (84%, p < 0.001), and DenseNet201 (85%, p < 0.01). The computational time in model training was only 30 s, which would be efficient and practical in clinical use.ConclusionsThe experiment shows the promising use of CCD images in stroke estimation. Using the pretrained ViT architecture, the image features can be automatically and efficiently generated without human intervention. The proposed CAD system provides a rapid and reliable suggestion for diagnosing ischemic stroke.

show abstract

Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors

Cited by 11 publications

References 29 publications

Deep learning predicts patients outcome and mutations from digitized histology slides in gastrointestinal stromal tumor

Deep learning predicts patients outcome and mutations from digitized histology slides in gastrointestinal stromal tumor

Transfer Learning in Cancer Genetics, Mutation Detection, Gene Expression Analysis, and Syndrome Recognition

Predictive stroke risk model with vision transformer‐based Doppler features

Contact Info

Product

Resources

About