Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study

Yamashita, Rikiya; Jin, Long; Longacre, Teri A.; Peng, Lan; Berry, Gerald J.; Martin, Brock A.; Higgins, Julian P T; Rubin, Daniel L.; Shen, Jeanne

doi:10.1016/s1470-2045(20)30535-0

Cited by 266 publications

(184 citation statements)

References 26 publications

Supporting

Mentioning

181

Contrasting

Unclassified

Order By: Relevance

“…40). In more recent work, Yashmita and colleagues trained and tested MSINet, a transfer learning model based on MobileNetV2 architecture, to classify tissue and subsequently classify MSI status in H&E-stained histopathology slides (40× magnification) from a colorectal cancer cohort of 100 primary tumors from Stanford Medical Center (41). The group reported an AUC of 0.93, which is a good improvement over the previously reported ResNet18 model (40,41).…”

Section: Making the Most Of Mutationsmentioning

confidence: 97%

Artificial Intelligence in Cancer Research and Precision Medicine

Bhinder

Gilvary²,

Madhukar³

et al. 2021

Cancer Discovery

356

153

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have been the most popular deep learning architectures used for image classification in cancer ( Fig. 1 ). CNNs apply a series of nonlinear transformations to structured data (such as raw pixels of an image) to learn relevant features automatically, unlike conventional machine learning models that frequently require manual feature curation. On the fl ip side, it is diffi cult to tell what features are learned by the CNNs, making them what many have referred to as a "black box." One consequence is that images used for CNNs should be carefully prepro cessed to reduce the risk that the model learns from image artifacts. There are two major approaches for CNN models; one is transfer learning that uses images from a large collection of natural objects (such as in ImageNet) to train the initial layers of a model (where the model learns to identify general features such as shapes and edges) and then uses the diseasespecifi c data to fi ne-tune the training parameters in the last layers. The second variation of CNN is based on an autoencoder where the model learns background features from a subset of representative images and encodes a compressed representation of the basic features later used to initialize the CNN. In the CAMELYON16 Challenge-a crowdsourced competition to identify and classify lymph node metastasis in patients with breast cancer from whole slide images (WSI) of hematoxylin and eosin (H&E)-stained tumors-25 of the 32 submitted algorithms were CNNs, and the top 5 classifi cation models were exclusively based on transfer learning, which were GoogLeNet, ResNet, VGG-16 ( 2 ). Khosravi and colleagues trained and tested several state-of-the-art deep learning models to classify WSI from H&E-stained tumor tissues of The Cancer Genome Atlas (TCGA) cohort and reported on the

show abstract

Section: Making the Most Of Mutationsmentioning

confidence: 97%

Artificial Intelligence in Cancer Research and Precision Medicine

Bhinder

Gilvary²,

Madhukar³

et al. 2021

Cancer Discovery

356

153

View full text Add to dashboard Cite

show abstract

“…In order to make up for the deficiency of the current TNM staging system, some related biomarkers have been explored, studied, and applied in clinical practice. For example, Mismatch repair (MMR) status or microsatellite instability (MSI) has been commonly recommended as the most used and significant molecular marker in clinical management of CRC patients (3,4). In addition, the expression status of various genes, such as Serine/threonine-protein kinase B-Raf (BRAF) and V-Ki-ras2 Kirsten rat sarcoma viral oncogene homolog (KRAS), were also found to be closely associated with the metastasis of CRC patients (5).…”

Section: Introductionmentioning

confidence: 99%

A Nomogram for Predicting Multiple Metastases in Metastatic Colorectal Cancer Patients: A Large Population-Based Study

Xiang

Ren

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

ObjectivesThe present study aims to discover the risk factors of multiple metastases and develop a functional nomogram to forecast multiple metastases in metastatic colorectal cancer (mCRC) patients.MethodsmCRC cases were retrospectively collected from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2016. Survival times between multiple metastases and single metastasis were compared using Kaplan–Meier analysis and log-rank tests. Risk factors for multiple metastases were determined by univariate and multivariate logistic regression analyses, and a nomogram was developed to forecast the probability of multiple metastases in mCRC patients. We assessed the nomogram performance in terms of discrimination and calibration, including concordance index (C-index), area under the curve (AUC), and decision curve analysis (DCA). Bootstrap resampling was used as an internal verification method, and at the same time we select external data from Renmin Hospital of Wuhan University as independent validation sets.ResultsA total of 5,302 cases were included in this study as training group, while 120 cases were as validation group. The patients with single metastasis and multiple metastases were 3,531 and 1,771, respectively. The median overall survival (OS) and cancer-specific survival (CSS) for patients with multiple metastases or single metastasis were 19 vs. 31 months, and 20 vs. 33 months, respectively. Based on the univariate and multivariate analyses, clinicopathological characteristics were associated with number of metastasis and were used to establish nomograms to predict the risk of multiple metastases. The C-indexes and AUC for the forecast of multiple metastases were 0.715 (95% confidence interval (CI), 0.707–0.723), which showed the nomogram had good discrimination and calibration curves of the nomogram showed no significant bias from the reference line, indicating a good degree of calibration. In the validation group, the AUC was 0.734 (95% CI, 0.653–0.834), and calibration curve also showed no significant bias, indicating the favorable effects of our nomogram.ConclusionsWe developed a new nomogram to predict the risk of multiple metastases. The nomogram shows the good prediction effect and can provide assistance for clinical diagnosis and treatment.

show abstract

“…In the present study, we evaluated and optimized a convolutional neuronal network (CNN) for the classification of histopathological images of tumor-free LNs, SLL/CLL, and DLBCL. The principal capacity of CNN for the classification of malignant and benign diseases on scanned histopathological tissue of conventionally stained sections was previously demonstrated and is well documented [ 19 , 25 , 26 , 27 , 28 ]. Specifically, the technique has been shown to be capable of classifying carcinoma subtypes and of identifying LN metastases of carcinomas [ 19 , 29 , 30 , 31 ].…”

Section: Discussionmentioning

confidence: 99%

Deep Learning for the Classification of Non-Hodgkin Lymphoma on Histopathological Images

Steinbuß

Kriegsmann

Zgorzelski

et al. 2021

Cancers

View full text Add to dashboard Cite

The diagnosis and the subtyping of non-Hodgkin lymphoma (NHL) are challenging and require expert knowledge, great experience, thorough morphological analysis, and often additional expensive immunohistological and molecular methods. As these requirements are not always available, supplemental methods supporting morphological-based decision making and potentially entity subtyping are required. Deep learning methods have been shown to classify histopathological images with high accuracy, but data on NHL subtyping are limited. After annotation of histopathological whole-slide images and image patch extraction, we trained and optimized an EfficientNet convolutional neuronal network algorithm on 84,139 image patches from 629 patients and evaluated its potential to classify tumor-free reference lymph nodes, nodal small lymphocytic lymphoma/chronic lymphocytic leukemia, and nodal diffuse large B-cell lymphoma. The optimized algorithm achieved an accuracy of 95.56% on an independent test set including 16,960 image patches from 125 patients after the application of quality controls. Automatic classification of NHL is possible with high accuracy using deep learning on histopathological images and routine diagnostic applications should be pursued.

show abstract

Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study

Cited by 266 publications

References 26 publications

Artificial Intelligence in Cancer Research and Precision Medicine

Artificial Intelligence in Cancer Research and Precision Medicine

A Nomogram for Predicting Multiple Metastases in Metastatic Colorectal Cancer Patients: A Large Population-Based Study

Deep Learning for the Classification of Non-Hodgkin Lymphoma on Histopathological Images

Contact Info

Product

Resources

About