scholarly journals Multiresolution Application of Artificial Intelligence in Digital Pathology for Prediction of Positive Lymph Nodes From Primary Tumors in Bladder Cancer

2020 ◽  
pp. 367-382 ◽  
Author(s):  
Stephanie A. Harmon ◽  
Thomas H. Sanford ◽  
G. Thomas Brown ◽  
Chris Yang ◽  
Sherif Mehralivand ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Digital Pathology ◽  
Area Under The Curve ◽  
The Cancer Genome Atlas ◽  
Clinicopathologic Features ◽  
Combined Model ◽  
Primary Tumors ◽  
Logistic Regression Models ◽  
Spatially Resolved ◽  
Digital Evaluation

PURPOSE To develop an artificial intelligence (AI)–based model for identifying patients with lymph node (LN) metastasis based on digital evaluation of primary tumors and train the model using cystectomy specimens available from The Cancer Genome Atlas (TCGA) Project; patients from our institution were included for validation of the leave-out test cohort. METHODS In all, 307 patients were identified for inclusion in the study (TCGA, n = 294; in-house, n = 13). Deep learning models were trained from image patches at 2.5×, 5×, 10×, and 20× magnifications, and spatially resolved prediction maps were combined with microenvironment (lymphocyte infiltration) features to derive a final patient-level AI score (probability of LN metastasis). Training and validation included 219 patients (training, n = 146; validation, n = 73); 89 patients (TCGA, n = 75; in-house, n = 13) were reserved as an independent testing set. Multivariable logistic regression models for predicting LN status based on clinicopathologic features alone and a combined model with AI score were fit to training and validation sets. RESULTS Several patients were determined to have positive LN metastasis in TCGA (n = 105; 35.7%) and in-house (n = 3; 23.1%) cohorts. A clinicopathologic model that considered using factors such as age, T stage, and lymphovascular invasion demonstrated an area under the curve (AUC) of 0.755 (95% CI, 0.680 to 0.831) in the training and validation cohorts compared with the cross validation of the AI score (likelihood of positive LNs), which achieved an AUC of 0.866 (95% CI, 0.812 to 0.920; P = .021). Performance in the test cohort was similar, with a clinicopathologic model AUC of 0.678 (95% CI, 0.554 to 0.802) and an AI score of 0.784 (95% CI, 0.702 to 0.896; P = .21). In addition, the AI score remained significant after adjusting for clinicopathologic variables ( P = 1.08 × 10−9), and the combined model significantly outperformed clinicopathologic features alone in the test cohort with an AUC of 0.807 (95% CI, 0.702 to 0.912; P = .047). CONCLUSION Patients who are at higher risk of having positive LNs during cystectomy can be identified on primary tumor samples using novel AI-based methodologies applied to digital hematoxylin and eosin–stained slides.

scholarly journals PAI-WSIT: a Comprehensive Curated Resource for Cancerous Pathology With Deep Learning

2021 ◽  
Author(s):  
Changjiang Zhou ◽  
Xiaobing Feng ◽  
Yi Jin ◽  
Harvest F. Gu ◽  
Youcai Zhao ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Data Collection ◽  
Function Analysis ◽  
Digital Pathology ◽  
Clinical Information ◽  
Improve Patient Care ◽  
The Cancer Genome Atlas ◽  
Precision Oncology ◽  
Region Detection

Abstract BackgroundThe possibility of digitizing whole-slide images (WSI) of tissue has led to the advent of artificial intelligence (AI) in digital pathology. Advances in precision oncology have resulted in an increasing demand for predictive assays that enable mining of subvisual morphometric phenotypes and might improve patient care ultimately. Hence, a pathologist-annotated and artificial intelligence-empowered platform for integration and analysis of WSI data and molecular detection data in tumors was established, called PAI-WSIT (http://www.paiwsit.com).MethodsThe standardized data collection process was used for data collection in PAI-WSIT, while a multifunctional annotation tool was developed and a user-friendly search engine and web interface were integrated for the database access. Furthermore, deep learning frameworks were applied in two tasks to detect malignant regions and classify phenotypic subtypes in colorectal cancers (CRCs), respectively.ResultsPAI-WSIT recorded 8633 WSIs of 1772 tumor cases, of which CRC from four regional hospitals in China and The Cancer Genome Atlas (TCGA) were the main ones, as well as cancers in breast, lung, prostate, bladder, and kidneys from two Chinese hospitals. A total of 1298 WSIs with high-quality annotations were evaluated by a panel of 8 pathologists. Gene detection reports of 582 tumor cases were collected. Clinical information of all tumor cases was documented. Besides, we reached overall accuracy of 0.933 in WSI classification for malignant region detection of CRC, and aera under the curves (AUC) of 0.719 on colorectal subtype dataset.ConclusionsCollectively, the annotation function, data integration and AI function analysis of PAI-WSIT provide support for AI-assisted tumor diagnosis, all of which have provided a comprehensive curation of carcinomas pathology.

scholarly journals Accurate Segmentation of Nuclear Regions with Multi-Organ Histopathology Images Using Artificial Intelligence for Cancer Diagnosis in Personalized Medicine

2021 ◽  
Vol 11 (6) ◽  
pp. 515
Author(s):  
Tahir Mahmood ◽  
Muhammad Owais ◽  
Kyoung Jun Noh ◽  
Hyo Sik Yoon ◽  
Ja Hyung Koo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Digital Pathology ◽  
The Cancer Genome Atlas ◽  
Cell Phenotype ◽  
Dice Coefficient ◽  
Significant Performance ◽  
Histopathology Images ◽  
Nuclear Regions ◽  
Tcga Dataset ◽  
Nuclear Segmentation

Accurate nuclear segmentation in histopathology images plays a key role in digital pathology. It is considered a prerequisite for the determination of cell phenotype, nuclear morphometrics, cell classification, and the grading and prognosis of cancer. However, it is a very challenging task because of the different types of nuclei, large intraclass variations, and diverse cell morphologies. Consequently, the manual inspection of such images under high-resolution microscopes is tedious and time-consuming. Alternatively, artificial intelligence (AI)-based automated techniques, which are fast and robust, and require less human effort, can be used. Recently, several AI-based nuclear segmentation techniques have been proposed. They have shown a significant performance improvement for this task, but there is room for further improvement. Thus, we propose an AI-based nuclear segmentation technique in which we adopt a new nuclear segmentation network empowered by residual skip connections to address this issue. Experiments were performed on two publicly available datasets: (1) The Cancer Genome Atlas (TCGA), and (2) Triple-Negative Breast Cancer (TNBC). The results show that our proposed technique achieves an aggregated Jaccard index (AJI) of 0.6794, Dice coefficient of 0.8084, and F1-measure of 0.8547 on TCGA dataset, and an AJI of 0.7332, Dice coefficient of 0.8441, precision of 0.8352, recall of 0.8306, and F1-measure of 0.8329 on the TNBC dataset. These values are higher than those of the state-of-the-art methods.

scholarly journals Circulating let-7e-5p, miR-106a-5p, miR-28-3p, and miR-542-5p as a Promising microRNA Signature for the Detection of Colorectal Cancer

Cancers ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1493
Author(s):  
Camila Meirelles S. Silva ◽  
Mateus C. Barros-Filho ◽  
Deysi Viviana T. Wong ◽  
Julia Bette H. Mello ◽  
Livia Maria S. Nobre ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Unmet Need ◽  
Area Under The Curve ◽  
Discrimination Performance ◽  
Colorectal Carcinogenesis ◽  
The Cancer Genome Atlas ◽  
Colon Perforation ◽  
Data Series ◽  
Predictive Tool ◽  
Incidence And Mortality

Colorectal cancer (CRC) is a disease with high incidence and mortality. Colonoscopy is a gold standard among tests used for CRC traceability. However, serious complications, such as colon perforation, may occur. Non-invasive diagnostic procedures are an unmet need. We aimed to identify a plasma microRNA (miRNA) signature for CRC detection. Plasma samples were obtained from subjects (n = 109) at different stages of colorectal carcinogenesis. The patients were stratified into a non-cancer (27 healthy volunteers, 17 patients with hyperplastic polyps, 24 with adenomas), and a cancer group (20 CRC and 21 metastatic CRC). miRNAs (381) were screened by TaqMan Low-Density Array. A classifier based on four differentially expressed miRNAs (miR-28-3p, let-7e-5p, miR-106a-5p, and miR-542-5p) was able to discriminate cancer versus non-cancer cases. The overexpression of these miRNAs was confirmed by RT-qPCR, and a cross-study validation step was implemented using eight data series retrieved from Gene Expression Omnibus (GEO). In addition, another external data validation using CRC surgical specimens from The Cancer Genome Atlas (TCGA) was carried out. The predictive model’s performance in the validation set was 76.5% accuracy, 59.4% sensitivity, and 86.8% specificity (area under the curve, AUC = 0.716). The employment of our model in the independent publicly available datasets confirmed a good discrimination performance in five of eight datasets (median AUC = 0.823). Applying this algorithm to the TCGA cohort, we found 99.5% accuracy, 99.7% sensitivity, and 90.9% specificity (AUC = 0.998) when the model was applied to solid colorectal tissues. Overall, we suggest a novel signature of four circulating miRNAs, i.e., miR-28-3p, let-7e-5p, miR-106a-5p, and miR-542-5p, as a predictive tool for the detection of CRC.

scholarly journals Mining the plasma-proteome associated genes in patients with gastro-esophageal cancers for biomarker discovery

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Frederick S. Vizeacoumar ◽  
Hongyu Guo ◽  
Lynn Dwernychuk ◽  
Adnan Zaidi ◽  
Andrew Freywald ◽  
...  
Keyword(s):  
Biomarker Discovery ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Cancer Recurrence ◽  
The Cancer Genome Atlas ◽  
Svm Classifier ◽  
Plasma Proteome ◽  
Cancer Genome Atlas ◽  
Novel Biomarkers ◽  
Evaluation Metric

AbstractGastro-esophageal (GE) cancers are one of the major causes of cancer-related death in the world. There is a need for novel biomarkers in the management of GE cancers, to yield predictive response to the available therapies. Our study aims to identify leading genes that are differentially regulated in patients with these cancers. We explored the expression data for those genes whose protein products can be detected in the plasma using the Cancer Genome Atlas to identify leading genes that are differentially regulated in patients with GE cancers. Our work predicted several candidates as potential biomarkers for distinct stages of GE cancers, including previously identified CST1, INHBA, STMN1, whose expression correlated with cancer recurrence, or resistance to adjuvant therapies or surgery. To define the predictive accuracy of these genes as possible biomarkers, we constructed a co-expression network and performed complex network analysis to measure the importance of the genes in terms of a ratio of closeness centrality (RCC). Furthermore, to measure the significance of these differentially regulated genes, we constructed an SVM classifier using machine learning approach and verified these genes by using receiver operator characteristic (ROC) curve as an evaluation metric. The area under the curve measure was > 0.9 for both the overexpressed and downregulated genes suggesting the potential use and reliability of these candidates as biomarkers. In summary, we identified leading differentially expressed genes in GE cancers that can be detected in the plasma proteome. These genes have potential to become diagnostic and therapeutic biomarkers for early detection of cancer, recurrence following surgery and for development of targeted treatment.

scholarly journals Identification of prognostic alternative splicing events in sarcoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hongshuai Li ◽  
Jie Yang ◽  
Guohui Yang ◽  
Jia Ren ◽  
Yu Meng ◽  
...  
Keyword(s):  
Alternative Splicing ◽  
Cox Regression ◽  
Univariate Analysis ◽  
Area Under The Curve ◽  
Gene Signature ◽  
The Cancer Genome Atlas ◽  
Cox Regression Analysis ◽  
Functional Roles ◽  
Cancer Pathogenesis ◽  
Rare Malignancy

AbstractSarcoma is a rare malignancy with unfavorable prognoses. Accumulating evidence indicates that aberrant alternative splicing (AS) events are generally involved in cancer pathogenesis. The aim of this study was to identify the prognostic value of AS-related survival genes as potential biomarkers, and highlight the functional roles of AS events in sarcoma. RNA-sequencing and AS-event datasets were downloaded from The Cancer Genome Atlas (TCGA) sarcoma cohort and TCGA SpliceSeq, respectively. Survival-related AS events were further assessed using a univariate analysis. A multivariate Cox regression analysis was also performed to establish a survival-gene signature to predict patient survival, and the area-under-the-curve method was used to evaluate prognostic reliability. KOBAS 3.0 and Cytoscape were used to functionally annotate AS-related genes and to assess their network interactions. We detected 9674 AS events in 40,184 genes from 236 sarcoma samples, and the 15 most significant genes were then used to construct a survival regression model. We further validated the involvement of ten potential survival-related genes (TUBB3, TRIM69, ZNFX1, VAV1, KCNN2, VGLL3, AK7, ARMC4, LRRC1, and CRIP1) in the occurrence and development of sarcoma. Multivariate survival model analyses were also performed, and validated that a model using these ten genes provided good classifications for predicting patient outcomes. The present study has increased our understanding of AS events in sarcoma, and the gene-based model using AS-related events may serve as a potential predictor to determine the survival of sarcoma patients.

scholarly journals Predicting drowning from sea and weather forecasts: development and validation of a model on surf beaches of southwestern France

2021 ◽  
pp. injuryprev-2020-044092
Author(s):  
Éric Tellier ◽  
Bruno Simonnet ◽  
Cédric Gil-Jardiné ◽  
Marion Lerouge-Bailhache ◽  
Bruno Castelle ◽  
...  
Keyword(s):  
Regression Models ◽  
Area Under The Curve ◽  
Temperature Wave ◽  
Medical Emergency ◽  
Emergency Center ◽  
Logistic Regression Models ◽  
Weather Forecasts ◽  
Step Model ◽  
Daily Risk ◽  
Development And Validation

ObjectiveTo predict the coast-wide risk of drowning along the surf beaches of Gironde, southwestern France.MethodsData on rescues and drownings were collected from the Medical Emergency Center of Gironde (SAMU 33). Seasonality, holidays, weekends, weather and metocean conditions were considered potentially predictive. Logistic regression models were fitted with data from 2011 to 2013 and used to predict 2015–2017 events employing weather and ocean forecasts.ResultsAir temperature, wave parameters, seasonality and holidays were associated with drownings. Prospective validation was performed on 617 days, covering 232 events (rescues and drownings) reported on 104 different days. The area under the curve (AUC) of the daily risk prediction model (combined with 3-day forecasts) was 0.82 (95% CI 0.79 to 0.86). The AUC of the 3-hour step model was 0.85 (95% CI 0.81 to 0.88).ConclusionsDrowning events along the Gironde surf coast can be anticipated up to 3 days in advance. Preventative messages and rescue preparations could be increased as the forecast risk increased, especially during the off-peak season, when the number of available rescuers is low.

scholarly journals DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks

Cancers ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 3308
Author(s):  
Won Sang Shim ◽  
Kwangil Yim ◽  
Tae-Jung Kim ◽  
Yeoun Eun Sung ◽  
Gyeongyun Lee ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Early Stage ◽  
External Validation ◽  
Area Under The Curve ◽  
The Cancer Genome Atlas ◽  
Deep Convolutional Neural Networks ◽  
Prognostic Features ◽  
Multi Scale ◽  
Model Based ◽  
Number Of Patients

The prognosis of patients with lung adenocarcinoma (LUAD), especially early-stage LUAD, is dependent on clinicopathological features. However, its predictive utility is limited. In this study, we developed and trained a DeepRePath model based on a deep convolutional neural network (CNN) using multi-scale pathology images to predict the prognosis of patients with early-stage LUAD. DeepRePath was pre-trained with 1067 hematoxylin and eosin-stained whole-slide images of LUAD from the Cancer Genome Atlas. DeepRePath was further trained and validated using two separate CNNs and multi-scale pathology images of 393 resected lung cancer specimens from patients with stage I and II LUAD. Of the 393 patients, 95 patients developed recurrence after surgical resection. The DeepRePath model showed average area under the curve (AUC) scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Owing to low performance, DeepRePath cannot be used as an automated tool in a clinical setting. When gradient-weighted class activation mapping was used, DeepRePath indicated the association between atypical nuclei, discohesive tumor cells, and tumor necrosis in pathology images showing recurrence. Despite the limitations associated with a relatively small number of patients, the DeepRePath model based on CNNs with transfer learning could predict recurrence after the curative resection of early-stage LUAD using multi-scale pathology images.

scholarly journals The Artificial Intelligence in Digital Pathology and Digital Radiology: Where Are We?

Healthcare ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 30
Author(s):  
Daniele Giansanti
Keyword(s):  
Artificial Intelligence ◽  
Information And Communication Technology ◽  
Communication Technology ◽  
Mobile Health ◽  
Digital Pathology ◽  
Digital Radiology ◽  
Cellular Diagnostics ◽  
Information And Communication ◽  
Electronic Health ◽  
New Applications

Thanks to the incredible changes promoted by Information and Communication Technology (ICT) conveyed today by electronic-health (eHealth) and mobile-health (mHealth), many new applications of both organ and cellular diagnostics are now possible [...]

An Integrated Digital Pathology Platform for Tumors Using Artificial Intelligence Analysis

2021 ◽  
Author(s):  
Changjiang Zhou ◽  
Xiaobing Feng ◽  
Hongbin Cai ◽  
Yi Jin ◽  
Harvest F. Gu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Digital Pathology ◽  
Intelligence Analysis
Sign in / Sign up

Export Citation Format

Share Document