Prediction of early colorectal cancer metastasis by machine learning using digital slide images

Lymph node metastasis detection using artificial intelligence in T1 colorectal cancer: A comprehensive systematic review

We systematically reviewed the application of artificial intelligence (AI) in predicting lymph node metastasis (LNM) in T1 colorectal cancer (CRC). Thirteen studies with 8417 patients were included. AI demonstrated high potential in predicting LNM with sensitivity, specificity, and AUC ranging from 0.561 to 1.0, 0.45 to 1.0, and 0.717 to 1.0, respectively, reducing unnecessary surgeries by approximately 70%.

Advantages of automated immunostain analyses for complex membranous immunostains: An exemplar investigating loss of E-cadherin expression in colorectal cancer

As pathology moves towards digitisation, biomarker profiling through automated image analysis provides potentially objective and time-efficient means of assessment. This study set out to determine how a complex membranous immunostain, E-cadherin, assessed using an automated digital platform fares in comparison to manual evaluation in terms of clinical correlations and prognostication. Tissue microarrays containing 1000 colorectal cancer samples, stained with clinical E-cadherin antibodies were assessed through both manual scoring and automated image analysis. Both manual and automated scores were correlated to clinicopathological and survival data. E-cadherin data generated through digital image analysis was superior to manual evaluation when investigating for clinicopathological correlations in colorectal cancer. Loss of membranous E-cadherin, assessed on automated platforms, correlated with: right sided tumours (p = <0.001), higher T-stage (p = <0.001), higher grade (p = <0.001), N2 nodal stage (p = <0.001), intramural lymphovascular invasion (p = 0.006), perineural invasion (p = 0.028), infiltrative tumour edge (p = 0.001) high tumour budding score (p = 0.038), distant metastasis (p = 0.035), and poorer 5-year (p= 0.042) survival status. Manual assessment was only correlated with higher grade tumours, though other correlations become apparent only when assessed for morphological expression pattern (circumferential, basolateral, parallel) irrespective of intensity. Digital assessment of E-cadherin is effective for prognostication of colorectal cancer and may potentially offer benefits of improved objectivity, accuracy, and economy of time. Incorporating tools to assess patterns of staining may further improve such digital assessment in the future.

SOX9 immunosuppression in primary colorectal cancer tumors with lymph node metastasis

INTRODUCTION AND AIMS

Colorectal cancer is the most frequent malignant tumor of the digestive system. Its pathogeny is complex and involves the APC/β-catenin sequence. Lymph node metastases are a significant indicator for determining treatment and are a prognostic factor. SOX9 overexpression is related to oncogenic qualities and the capacity for metastasis. Our aim was to analyze SOX9 immunoexpression in primary colorectal cancer and lymph node metastasis status.

MATERIAL AND METHODS

Seventy-nine available cases were divided into the group with lymph node metastasis (n=38) and the group without lymph node metastasis (n=41), evaluating their SOX9 expression. The IBM SPSS version 27 program in Spanish was utilized to carry out the statistical analysis, obtaining measures of central tendency, the kappa index, standard deviation, Wilcoxon Mann-Whitney nonparametric measurements, Spearman's correlation coefficient, and chi-square test and Student's t test values. SOX9 immunoexpression was evaluated through the mean-based H-score, with high immunoexpression as a score ≥145 and low immunoexpression as a score ≤144.

RESULTS

A p=0.73 was obtained that was not statistically significant, regarding the relation of SOX9 expression in primary colorectal cancer to lymph node metastasis.

CONCLUSIONS

The absence or presence of lymph node metastasis was independent from SOX9 immunoexpression in primary colorectal cancer. However, due to the limited size of the population analyzed, further research is needed.

Refining Risk Criteria May Substantially Reduce Unnecessary Additional Surgeries after Local Resection of T1 Colorectal Cancer

BACKGROUND

The low positive predictive value for lymph node metastases (LNM) of common practice risk criteria (CPRC) in T1 colorectal carcinoma (CRC) leads to manyunnecessary additional surgeries following local resection. This study aimed to identify criteria that may improve on the CPRC.

METHODS

Logistic regression analysis was performed to determine the association of diverse variables with LNM or 'poor outcome' (LNM and/or distant metastases and/or recurrence) in a single center T1 CRC cohort. The diagnostic capacity of the set of variables obtained was compared with that of the CPRC.

RESULTS

The study comprised 161 cases. Poorly differentiated clusters (PDC) and tumor budding grade > 1 (TB > 1) were the only independent variables associated with LNM. The area under the curve (AUC) for these criteria was 0.808 (CI 95% 0.717-0.880) compared to 0.582 (CI 95% 0.479-0.680) for CPRC. TB > 1 and lymphovascular invasion (LVI) were independently associated with 'poor outcome', with an AUC of 0.801 (CI 95% 0.731-0.859), while the AUC for CPRC was 0.691 (CI 95% 0.603-0.752). TB > 1, combined either with PDC or LVI, would reduce false positives between 41.5% and 45% without significantly increasing false negatives.

CONCLUSIONS

Indicating additional surgery in T1 CRC only when either TB > 1, PDC, or LVI are present could reduce unnecessary surgeries significantly.

Morphometric Analysis of Lateral Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Using Digital Pathology

Digital pathology uses digitized images for cancer research. We aimed to assess morphometric parameters using digital pathology for predicting recurrence in patients with papillary thyroid carcinoma (PTC) and lateral cervical lymph node (LN) metastasis. We analyzed 316 PTC patients and assessed the longest diameter and largest area of metastatic focus in LNs using a whole slide imaging scanner. In digital pathology assessment, the longest diameters and largest areas of metastatic foci in LNs were positively correlated with traditional optically measured diameters (R = 0.928 and R2 = 0.727, p < 0.001 and p < 0.001, respectively). The optimal cutoff diameter was 8.0 mm in both traditional microscopic (p = 0.009) and digital pathology (p = 0.016) evaluations, with significant differences in progression-free survival (PFS) observed at this cutoff (p = 0.006 and p = 0.002, respectively). The predictive area's cutoff was 35.6 mm2 (p = 0.005), which significantly affected PFS (p = 0.015). Using an 8.0-mm cutoff in traditional microscopic evaluation and a 35.6-mm2 cutoff in digital pathology showed comparable predictive results using the proportion of variation explained (PVE) methods (2.6% vs. 2.4%). Excluding cases with predominant cystic changes in LNs, the largest metastatic areas by digital pathology had the highest PVE at 3.9%. Furthermore, high volume of LN metastasis (p = 0.001), extranodal extension (p = 0.047), and high ratio of metastatic LNs (p = 0.006) were associated with poor prognosis. Both traditional microscopic and digital pathology evaluations effectively measured the longest diameter of metastatic foci in LNs. Moreover, digital pathology offers limited advantages in predicting PFS of patients with lateral cervical LN metastasis of PTC, especially those without predominant cystic changes in LNs.

Prediction of Lymph Node Metastasis in T1 Colorectal Cancer Using Artificial Intelligence with Hematoxylin and Eosin-Stained Whole-Slide-Images of Endoscopic and Surgical Resection Specimens

According to the current guidelines, additional surgery is performed for endoscopically resected specimens of early colorectal cancer (CRC) with a high risk of lymph node metastasis (LNM). However, the rate of LNM is 2.1-25.0% in cases treated endoscopically followed by surgery, indicating a high rate of unnecessary surgeries. Therefore, this study aimed to develop an artificial intelligence (AI) model using H&E-stained whole slide images (WSIs) without handcrafted features employing surgically and endoscopically resected specimens to predict LNM in T1 CRC. To validate with an independent cohort, we developed a model with four versions comprising various combinations of training and test sets using H&E-stained WSIs from endoscopically (400 patients) and surgically resected specimens (881 patients): Version 1, Train and Test: surgical specimens; Version 2, Train and Test: endoscopic and surgically resected specimens; Version 3, Train: endoscopic and surgical specimens and Test: surgical specimens; Version 4, Train: endoscopic and surgical specimens and Test: endoscopic specimens. The area under the curve (AUC) of the receiver operating characteristic curve was used to determine the accuracy of the AI model for predicting LNM with a 5-fold cross-validation in the training set. Our AI model with H&E-stained WSIs and without annotations showed good performance power with the validation of an independent cohort in a single center. The AUC of our model was 0.758-0.830 in the training set and 0.781-0.824 in the test set, higher than that of previous AI studies with only WSI. Moreover, the AI model with Version 4, which showed the highest sensitivity (92.9%), reduced unnecessary additional surgery by 14.2% more than using the current guidelines (68.3% vs. 82.5%). This revealed the feasibility of using an AI model with only H&E-stained WSIs to predict LNM in T1 CRC.

Use of artificial intelligence for the prediction of lymph node metastases in early-stage colorectal cancer: systematic review

BACKGROUND

Risk evaluation of lymph node metastasis for early-stage (T1 and T2) colorectal cancers is critical for determining therapeutic strategies. Traditional methods of lymph node metastasis prediction have limited accuracy. This systematic review aimed to review the potential of artificial intelligence in predicting lymph node metastasis in early-stage colorectal cancers.

METHODS

A comprehensive search was performed of papers that evaluated the potential of artificial intelligence in predicting lymph node metastasis in early-stage colorectal cancers. Studies were appraised using the Joanna Briggs Institute tools. The primary outcome was summarizing artificial intelligence models and their accuracy. Secondary outcomes included influential variables and strategies to address challenges.

RESULTS

Of 3190 screened manuscripts, 11 were included, involving 8648 patients from 1996 to 2023. Due to diverse artificial intelligence models and varied metrics, no data synthesis was performed. Models included random forest algorithms, support vector machine, deep learning, artificial neural network, convolutional neural network and least absolute shrinkage and selection operator regression. Artificial intelligence models' area under the curve values ranged from 0.74 to 0.9993 (slide level) and 0.9476 to 0.9956 (single-node level), outperforming traditional clinical guidelines.

CONCLUSION

Artificial intelligence models show promise in predicting lymph node metastasis in early-stage colorectal cancers, potentially refining clinical decisions and improving outcomes.

PROSPERO REGISTRATION NUMBER

CRD42023409094.

Management after non-curative endoscopic resection of T1 rectal cancer

Since the introduction of population-based screening, increasing numbers of T1 rectal cancers are detected and removed by local endoscopic resection. Patients can be cured with endoscopic resection alone, but there is a possibility of residual tumor cells remaining after the initial resection. These can be located intraluminally at the resection site or extraluminally in the form of (lymph node) metastases. To decrease the risk of residual cells progressing towards more advanced disease, additional treatment is usually needed. However, with the currently available risk stratification models, it remains challenging to determine who should and should not be further treated after non-curative endoscopic resection. In this review, the different management strategies for patients with non-curatively treated T1 rectal cancers are discussed, along with the available evidence for each strategy and relevant considerations for clinical decision making. Furthermore, we provide practical guidance on the management and surveillance following non-curative endoscopic resection of T1 rectal cancer.

Use of artificial intelligence in the management of T1 colorectal cancer: a new tool in the arsenal or is deep learning out of its depth?

The field of artificial intelligence is rapidly evolving, and there has been an interest in its use to predict the risk of lymph node metastasis in T1 colorectal cancer. Accurately predicting lymph node invasion may result in fewer patients undergoing unnecessary surgeries; conversely, inadequate assessments will result in suboptimal oncological outcomes. This narrative review aims to summarize the current literature on deep learning for predicting the probability of lymph node metastasis in T1 colorectal cancer, highlighting areas of potential application and barriers that may limit its generalizability and clinical utility.

Disseminating cells in human oral tumours possess an EMT cancer stem cell marker profile that is predictive of metastasis in image-based machine learning

Cancer stem cells (CSCs) undergo epithelial-mesenchymal transition (EMT) to drive metastatic dissemination in experimental cancer models. However, tumour cells undergoing EMT have not been observed disseminating into the tissue surrounding human tumour specimens, leaving the relevance to human cancer uncertain. We have previously identified both EpCAM and CD24 as CSC markers that, alongside the mesenchymal marker Vimentin, identify EMT CSCs in human oral cancer cell lines. This afforded the opportunity to investigate whether the combination of these three markers can identify disseminating EMT CSCs in actual human tumours. Examining disseminating tumour cells in over 12,000 imaging fields from 74 human oral tumours, we see a significant enrichment of EpCAM, CD24 and Vimentin co-stained cells disseminating beyond the tumour body in metastatic specimens. Through training an artificial neural network, these predict metastasis with high accuracy (cross-validated accuracy of 87-89%). In this study, we have observed single disseminating EMT CSCs in human oral cancer specimens, and these are highly predictive of metastatic disease.

Whole slide image-based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence

OBJECTIVES

Lymph node metastasis (LNM) prediction for T1 colorectal cancer (CRC) is critical for determining the need for surgery after endoscopic resection because LNM occurs in 10%. We aimed to develop a novel artificial intelligence (AI) system using whole slide images (WSIs) to predict LNM.

METHODS

We conducted a retrospective single center study. To train and test the AI model, we included LNM status-confirmed T1 and T2 CRC between April 2001 and October 2021. These lesions were divided into two cohorts: training (T1 and T2) and testing (T1). WSIs were cropped into small patches and clustered by unsupervised K-means. The percentage of patches belonging to each cluster was calculated from each WSI. Each cluster's percentage, sex, and tumor location were extracted and learned using the random forest algorithm. We calculated the areas under the receiver operating characteristic curves (AUCs) to identify the LNM and the rate of over-surgery of the AI model and the guidelines.

RESULTS

The training cohort contained 217 T1 and 268 T2 CRCs, while 100 T1 cases (LNM-positivity 15%) were the test cohort. The AUC of the AI system for the test cohort was 0.74 (95% confidence interval [CI] 0.58-0.86), and 0.52 (95% CI 0.50-0.55) using the guidelines criteria (P = 0.0028). This AI model could reduce the 21% of over-surgery compared to the guidelines.

CONCLUSION

We developed a pathologist-independent predictive model for LNM in T1 CRC using WSI for determination of the need for surgery after endoscopic resection.

TRIAL REGISTRATION

UMIN Clinical Trials Registry (UMIN000046992, https://center6.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000053590).

SnapEnsemFS: a snapshot ensembling-based deep feature selection model for colorectal cancer histological analysis

Colorectal cancer is the third most common type of cancer diagnosed annually, and the second leading cause of death due to cancer. Early diagnosis of this ailment is vital for preventing the tumours to spread and plan treatment to possibly eradicate the disease. However, population-wide screening is stunted by the requirement of medical professionals to analyse histological slides manually. Thus, an automated computer-aided detection (CAD) framework based on deep learning is proposed in this research that uses histological slide images for predictions. Ensemble learning is a popular strategy for fusing the salient properties of several models to make the final predictions. However, such frameworks are computationally costly since it requires the training of multiple base learners. Instead, in this study, we adopt a snapshot ensemble method, wherein, instead of the traditional method of fusing decision scores from the snapshots of a Convolutional Neural Network (CNN) model, we extract deep features from the penultimate layer of the CNN model. Since the deep features are extracted from the same CNN model but for different learning environments, there may be redundancy in the feature set. To alleviate this, the features are fed into Particle Swarm Optimization, a popular meta-heuristic, for dimensionality reduction of the feature space and better classification. Upon evaluation on a publicly available colorectal cancer histology dataset using a five-fold cross-validation scheme, the proposed method obtains a highest accuracy of 97.60% and F1-Score of 97.61%, outperforming existing state-of-the-art methods on the same dataset. Further, qualitative investigation of class activation maps provide visual explainability to medical practitioners, as well as justifies the use of the CAD framework in screening of colorectal histology. Our source codes are publicly accessible at: https://github.com/soumitri2001/SnapEnsemFS .

Lifespan and medical expenditure prognosis for cancer metastasis - a simulation modeling using semi-Markov process

BACKGROUND AND OBJECTIVE

A key reason of high mortality of cancers is attributed to the metastasized cancer, whereas, the medical expense for the treatment of cancer metastases generates heavily financial burden. The population size of metastases cases is small and comprehensive inferencing and prognosis is hard to conduct.

METHODS

Because metastases and finance state can develop dynamic transitions over time, this study proposes a semi-Markov model to perform risk and economic evaluation associated to major cancer metastasis (i.e., lung, brain, liver and lymphoma cancer) against rare cases. A nationwide medical database in Taiwan was employed to derive a baseline study population and costs data. The time until development of metastasis and survivability from metastasis, as well as the medical costs were estimated through a semi-Markov based Monte Carlo simulation.

RESULTS

In terms of the survivability and risk associated to metastatic cancer patients, 80% lung and liver cancer cases are tended to metastasize to other part of the body. The highest cost is generated by brain cancer-liver metastasis patients. The survivors group generated approximately 5 times more costs, in average, than the non-survivors group.

CONCLUSIONS

The proposed model provides a healthcare decision-support tool to evaluate the survivability and expenditure of major cancer metastases.

Prognostic significance of p16, p21, and Ki67 expression at the invasive front of colorectal cancers

Cancer cells at the invasive front are believed to be responsible for invasion/metastasis. This has led to examining various morphological features and protein expressions at the invasive front. However, accurate assessment of the pathological section requires long-time training, and inter-observer disagreement is problematic. Immunohistochemistry and digital imaging analysis may mitigate these problems; however, the choice of which proteins to stain and the best analysis method remains controversial. We used the "go-or-grow" hypothesis to select markers with the greatest prognostic relevance. Importantly, nonproliferating cells can migrate. We used Ki67 as a proliferation marker, with p16 and p21 designating nonproliferating cells. We established a semi-automated quantification workflow to study protein expression in serial pathological sections. A total of 51 patients with completely resected colorectal cancer (stages I-IV) were analyzed, and 44 patients were followed up. Patients with cancer cells with p16-high/p21-low or p21-low/Ki67-low at the deepest invasive front demonstrated a significantly worse prognosis than those who did not display these characteristics. These results suggest that the nonproliferating cancer cells at the invasion front possess invasion/metastatic property with heterogeneity of senescence.

Experiences of cancer survivors in Europe: Has anything changed? Can artificial intelligence offer a solution?

Introduction

Cancer is a major global health issue. Despite technological advancements in oncology, challenges remain in many aspects related to cancer management. This study constitutes one part of the user requirement definition of INCISIVE EU H2020 project, which has been designed to explore the full potential of artificial intelligence (AI) based technologies in cancer imaging. The study aimed to explore cancer survivors’ experiences of cancer care in five European countries.

Methods

A qualitative study employing semi-structured interviews was conducted. A purposive sampling strategy was used to recruit participants across the five validation countries of INCISIVE project: Greece, Cyprus, Spain, Italy, and Serbia. Forty cancer survivors were interviewed between November 2020 and March 2021. Data was analysed thematically using the framework approach and coded using NVivo12 software.

Results

The analysis yielded several gaps within the cancer care pathway which reflected on the participants experiences. Five key themes were revealed; (1) perceived challenges during the cancer journey, (2) the importance of accurate and prompt diagnosis, (3) perceived need for improving cancer diagnosis, (4) absence of well-established/designated support services within the pathway and (5) suggestions to improve cancer care pathway.

Conclusion

Cancer survivors experienced significant burdens pertaining to cancer diagnosis and treatment. Our findings underscored some main gaps within the cancer care pathway which contributed to the challenges articulated by the participants including lack of resources and delays in diagnostic and treatment intervals. Additionally, several suggestions were provided by the cancer survivors which could be considered towards the improvement of the current state of care, some of which can be optimised using new technologies involving AI such as the one proposed by INCISIVE.

Utility of artificial intelligence with deep learning of hematoxylin and eosin-stained whole slide images to predict lymph node metastasis in T1 colorectal cancer using endoscopically resected specimens; prediction of lymph node metastasis in T1 colorectal cancer

BACKGROUND

When endoscopically resected specimens of early colorectal cancer (CRC) show high-risk features, surgery should be performed based on current guidelines because of the high-risk of lymph node metastasis (LNM). The aim of this study was to determine the utility of an artificial intelligence (AI) with deep learning (DL) of hematoxylin and eosin (H&E)-stained endoscopic resection specimens without manual-pixel-level annotation for predicting LNM in T1 CRC. In addition, we assessed AI performance for patients with only submucosal (SM) invasion depth of 1000 to 2000 μm known to be difficult to predict LNM in clinical practice.

METHODS

H&E-stained whole slide images (WSIs) were scanned for endoscopic resection specimens of 400 patients who underwent endoscopic treatment for newly diagnosed T1 CRC with additional surgery. The area under the curve (AUC) of the receiver operating characteristic curve was used to determine the accuracy of AI for predicting LNM with a fivefold cross-validation in the training set and in a held-out test set.

RESULTS

We developed an AI model using a two-step attention-based DL approach without clinical features (AUC, 0.764). Incorporating clinical features into the model did not improve its prediction accuracy for LNM. Our model reduced unnecessary additional surgery by 15.1% more than using the current guidelines (67.4% vs. 82.5%). In patients with SM invasion depth of 1000 to 2000 μm, the AI avoided 16.1% of unnecessary additional surgery than using the JSCCR guidelines.

CONCLUSIONS

Our study is the first to show that AI trained with DL of H&E-stained WSIs has the potential to predict LNM in T1 CRC using only endoscopically resected specimens with conventional histologic risk factors.

Deep Neural Network Models for Colon Cancer Screening

Simple Summary

Deep learning models have been shown to achieve high performance in diagnosing colon cancer compared to conventional image processing and hand-crafted machine learning methods. Hence, several studies have focused on developing hybrid learning, end-to-end, and transfer learning techniques to reduce manual interaction and for labelling the regions of interest. However, these weak learning techniques do not always provide a clear diagnosis. Therefore, it is necessary to develop a clear explainable learning method that can highlight factors and form the basis of clinical decisions. However, there has been little research carried out employing such transparent approaches. This study discussed the aforementioned models for colon cancer diagnosis.

Abstract

Early detection of colorectal cancer can significantly facilitate clinicians’ decision-making and reduce their workload. This can be achieved using automatic systems with endoscopic and histological images. Recently, the success of deep learning has motivated the development of image- and video-based polyp identification and segmentation. Currently, most diagnostic colonoscopy rooms utilize artificial intelligence methods that are considered to perform well in predicting invasive cancer. Convolutional neural network-based architectures, together with image patches and preprocesses are often widely used. Furthermore, learning transfer and end-to-end learning techniques have been adopted for detection and localization tasks, which improve accuracy and reduce user dependence with limited datasets. However, explainable deep networks that provide transparency, interpretability, reliability, and fairness in clinical diagnostics are preferred. In this review, we summarize the latest advances in such models, with or without transparency, for the prediction of colorectal cancer and also address the knowledge gap in the upcoming technology.

Current Status and Future Perspectives of Artificial Intelligence in Colonoscopy

The early endoscopic identification, resection, and treatment of precancerous adenoma and early-stage cancer has been shown to reduce not only the prevalence of colorectal cancer but also its mortality rate. Recent advances in endoscopic devices and imaging technology have dramatically improved our ability to detect colorectal lesions and predict their pathological diagnosis. In addition to this, rapid advances in artificial intelligence (AI) technology mean that AI-related research and development is now progressing in the diagnostic imaging field, particularly colonoscopy, and AIs (i.e., devices that mimic cognitive abilities, such as learning and problem-solving) already approved as medical devices are now being introduced into everyday clinical practice. Today, there is an increasing expectation that sophisticated AIs will be able to provide high-level diagnostic performance irrespective of the level of skill of the endoscopist. In this paper, we review colonoscopy-related AI research and the AIs that have already been approved and discuss the future prospects of this technology.

Applications of Artificial Intelligence in Screening, Diagnosis, Treatment, and Prognosis of Colorectal Cancer

Colorectal cancer (CRC) is one of the most common cancers worldwide. Accurate early detection and diagnosis, comprehensive assessment of treatment response, and precise prediction of prognosis are essential to improve the patients’ survival rate. In recent years, due to the explosion of clinical and omics data, and groundbreaking research in machine learning, artificial intelligence (AI) has shown a great application potential in clinical field of CRC, providing new auxiliary approaches for clinicians to identify high-risk patients, select precise and personalized treatment plans, as well as to predict prognoses. This review comprehensively analyzes and summarizes the research progress and clinical application value of AI technologies in CRC screening, diagnosis, treatment, and prognosis, demonstrating the current status of the AI in the main clinical stages. The limitations, challenges, and future perspectives in the clinical implementation of AI are also discussed.

Prediction of Recurrence Pattern of Pancreatic Cancer Post-Pancreatic Surgery Using Histology-Based Supervised Machine Learning Algorithms: A Single-Center Retrospective Study

BACKGROUND

Patients with pancreatic cancer (PC) have poor prognosis and a high incidence of recurrence. Since further treatment is applicable for specific recurrent events, it is important to predict recurrence patterns after surgery. This study aimed to identify and predict early and late recurrence patterns of PC using a histology-based machine learning model.

PATIENTS AND METHODS

Patients who underwent upfront curative surgery for PC between 2001 and 2014 were included. The timing of recurrence and prognosis of each first recurrence site were examined. A histology-based supervised machine learning method, which combined convolutional neural networks and random forest, was used to predict the recurrence and respective sites of metastasis. Accuracy was evaluated using area under the receiver operating characteristic curve (AUC).

RESULTS

In total, 524 patients were included. Recurrence in the liver accounted for 47.8% of all recurrence events in the first year after surgery. Meanwhile, recurrence in the lung occurred later and could become apparent more than 5 years post-surgery, with indications for further surgery. In terms of substantial distant organ metastases, liver and lung metastases were identified as representative early and late recurrence events. The predictive AUCs of the machine learning model for training and test data were 1.000 and 0.861, respectively, and for predicting nonrecurrence were 1.000 for both.

CONCLUSIONS

We identified the liver and lung as early and late recurrence sites, which could be distinguished with high probability using a machine learning model. Prediction of recurrence sites using this model may be useful for further treatment of patients with PC.

Prediction of lymph node metastasis in early colorectal cancer based on histologic images by artificial intelligence

Risk evaluation of lymph node metastasis (LNM) for endoscopically resected submucosal invasive (T1) colorectal cancers (CRC) is critical for determining therapeutic strategies, but interobserver variability for histologic evaluation remains a major problem. To address this issue, we developed a machine-learning model for predicting LNM of T1 CRC without histologic assessment. A total of 783 consecutive T1 CRC cases were randomly split into 548 training and 235 validation cases. First, we trained convolutional neural networks (CNN) to extract cancer tile images from whole-slide images, then re-labeled these cancer tiles with LNM status for re-training. Statistical parameters of the tile images based on the probability of primary endpoints were assembled to predict LNM in cases with a random forest algorithm, and defined its predictive value as random forest score. We evaluated the performance of case-based prediction models for both training and validation datasets with area under the receiver operating characteristic curves (AUC). The accuracy for classifying cancer tiles was 0.980. Among cancer tiles, the accuracy for classifying tiles that were LNM-positive or LNM-negative was 0.740. The AUCs of the prediction models in the training and validation sets were 0.971 and 0.760, respectively. CNN judged the LNM probability by considering histologic tumor grade.

Deep Learning identifies inflamed fat as a risk factor for lymph node metastasis in early colorectal cancer

The spread of early-stage (T1 and T2) adenocarcinomas to loco-regional lymph nodes is a key event in disease progression of colorectal cancer (CRC). The cellular mechanisms behind this event are not completely understood and existing predictive biomarkers are imperfect. Here, we used an end-to-end Deep Learning algorithm to identify risk factors for lymph node metastasis (LNM) status in digitized histopathology slides of the primary CRC and its surrounding tissue. In two large population-based cohorts, we show that this system can predict the presence of more than one LNM in pT2 CRC patients with an area under the receiver operating curve (AUROC) of 0.733 (0.67-0.758) and patients with any LNM with an AUROC of 0.711 (0.597-0.797). Similarly, in pT1 CRC patients, the presence of more than one LNM or any LNM was predictable with an AUROC of 0.733 (0.644-0.778) and 0.567 (0.542-0.597), respectively. Based on these findings, we used the Deep Learning system to guide human pathology experts towards highly predictive regions for LNM in the whole slide images. This hybrid human observer and Deep Learning approach identified inflamed adipose tissue as the highest predictive feature for LNM presence. Our study is a first proof of concept that artificial intelligence (AI) systems may be able to discover potentially new biological mechanisms in cancer progression. Our Deep Learning algorithm is publicly available and can be used for biomarker discovery in any disease setting. This article is protected by copyright. All rights reserved.

Early gastrointestinal cancer: The application of artificial intelligence

Early gastrointestinal (GI) cancer has been the core of clinical endoscopic work. Its early detection and treatment are tightly associated with patients’ prognoses. As a novel technology, artificial intelligence has been improved and applied in the field of endoscopy. Studies on detection, diagnosis, risk, and prognosis evaluation of diseases in the GI tract have been in development, including precancerous lesions, adenoma, early GI cancers, and advanced GI cancers. In this review, research on esophagus, stomach, and colon was concluded, and associated with the process from precancerous lesions to early GI cancer, such as from Barrett’s esophagus to early esophageal cancer, from dysplasia to early gastric cancer, and from adenoma to early colonic cancer. A status quo of research on early GI cancers and artificial intelligence was provided.

Clinicopathological models for predicting lymph node metastasis in patients with early-stage lung adenocarcinoma: the application of machine learning algorithms

Background

Lymph node metastasis (LNM) status can be a critical decisive factor for clinical management of lung cancer. Accurately evaluating the risk of LNM during or after the surgery can be helpful for making clinical decisions. This study aims to incorporate clinicopathological characteristics to develop reliable machine learning (ML)-based models for predicting LNM in patients with early-stage lung adenocarcinoma.

Methods

A total of 709 lung adenocarcinoma patients with tumor size ≤2 cm were enrolled for analysis and modeling by multiple ML algorithms. The receiver operating characteristic (ROC) curve and decision curve were used for evaluating model’s predictive performance and clinical usefulness. Feature selection based on potential models was performed to identify most-contributed predictive factors.

Results

LNM occurred in 11.3% (80/709) of patients with lung adenocarcinoma. Most models reached high areas under the ROC curve (AUCs) >0.9. In the decision curve, all models performed better than the treat-all and treat-none lines. The random forest classifier (RFC) model, with a minimal number of five variables introduced (including carcinoembryonic antigen, solid component, micropapillary component, lymphovascular invasion and pleural invasion), was identified as the optimal model for predicting LNM, because of its excellent performance in both ROC and decision curves.

Conclusions

The cost-efficient application of RFC model could precisely predict LNM during or after the operation of early-stage adenocarcinomas (sensitivity: 87.5%; specificity: 82.2%). Incorporating clinicopathological characteristics, it is feasible to predict LNM intraoperatively or postoperatively by ML algorithms.

Predicting Colorectal Cancer Recurrence and Patient Survival Using Supervised Machine Learning Approach: A South African Population-Based Study

Background: South Africa (SA) has the highest incidence of colorectal cancer (CRC) in Sub-Saharan Africa (SSA). However, there is limited research on CRC recurrence and survival in SA. CRC recurrence and overall survival are highly variable across studies. Accurate prediction of patients at risk can enhance clinical expectations and decisions within the South African CRC patients population. We explored the feasibility of integrating statistical and machine learning (ML) algorithms to achieve higher predictive performance and interpretability in findings.

Methods: We selected and compared six algorithms:- logistic regression (LR), naïve Bayes (NB), C5.0, random forest (RF), support vector machine (SVM) and artificial neural network (ANN). Commonly selected features based on OneR and information gain, within 10-fold cross-validation, were used for model development. The validity and stability of the predictive models were further assessed using simulated datasets.

Results: The six algorithms achieved high discriminative accuracies (AUC-ROC). ANN achieved the highest AUC-ROC for recurrence (87.0%) and survival (82.0%), and other models showed comparable performance with ANN. We observed no statistical difference in the performance of the models. Features including radiological stage and patient's age, histology, and race are risk factors of CRC recurrence and patient survival, respectively.

Conclusions: Based on other studies and what is known in the field, we have affirmed important predictive factors for recurrence and survival using rigorous procedures. Outcomes of this study can be generalised to CRC patient population elsewhere in SA and other SSA countries with similar patient profiles.

State of machine and deep learning in histopathological applications in digestive diseases

Machine learning (ML)- and deep learning (DL)-based imaging modalities have exhibited the capacity to handle extremely high dimensional data for a number of computer vision tasks. While these approaches have been applied to numerous data types, this capacity can be especially leveraged by application on histopathological images, which capture cellular and structural features with their high-resolution, microscopic perspectives. Already, these methodologies have demonstrated promising performance in a variety of applications like disease classification, cancer grading, structure and cellular localizations, and prognostic predictions. A wide range of pathologies requiring histopathological evaluation exist in gastroenterology and hepatology, indicating these as disciplines highly targetable for integration of these technologies. Gastroenterologists have also already been primed to consider the impact of these algorithms, as development of real-time endoscopic video analysis software has been an active and popular field of research. This heightened clinical awareness will likely be important for future integration of these methods and to drive interdisciplinary collaborations on emerging studies. To provide an overview on the application of these methodologies for gastrointestinal and hepatological histopathological slides, this review will discuss general ML and DL concepts, introduce recent and emerging literature using these methods, and cover challenges moving forward to further advance the field.

Detection of cancer metastasis: past, present and future

The clinical importance of metastatic spread of cancer has been recognized for centuries, and melanoma has loomed large in historical descriptions of metastases, as well as the numerous mechanistic theories espoused. The "fatal black tumor" described by Hippocrates in 5000 BC that was later termed "melanose" by Rene Laennec in 1804 was recognized to have the propensity to metastasize by William Norris in 1820. And while the prognosis of melanoma was uniformly acknowledged to be dire, Samuel Cooper described surgical removal as having the potential to improve prognosis. Subsequent to this, in 1898 Herbert Snow was the first to recognize the potential clinical benefit of removing clinically normal lymph nodes at the time of initial cancer surgery. In describing "anticipatory gland excision," he noted that "it is essential to remove, whenever possible, those lymph glands which first receive the infective protoplasm, and bar its entrance into the blood, before they have undergone increase in bulk". This revolutionary concept marked the beginning of a debate that rages today: are regional lymph nodes the first stop for metastases ("incubator" hypothesis) or does their involvement serve as an indicator of aggressive disease with inherent metastatic potential ("marker" hypothesis). Is there a better way to improve prediction of disease outcome? This article attempts to address some of the resultant questions that were the subject of the session "Novel Frontiers in the Diagnosis of Cancer" at the 8th International Congress on Cancer Metastases, held in San Francisco, CA in October 2019. Some of these questions addressed include the significance of sentinel node metastasis in melanoma, and the optimal method for their pathologic analysis. The finding of circulating tumor cells in the blood may potentially supplant surgical techniques for detection of metastatic disease, and we are beginning to perfect techniques for their detection, understand how to apply the findings clinically, and develop clinical followup treatment algorithms based on these results. Finally, we will discuss the revolutionary field of machine learning and its applications in cancer diagnosis. Computer-based learning algorithms have the potential to improve efficiency and diagnostic accuracy of pathology, and can be used to develop novel predictors of prognosis, but significant challenges remain. This review will thus encompass latest concepts in the detection of cancer metastasis via the lymphatic system, the circulatory system, and the role of computers in enhancing our knowledge in this field.

Developing a clinical decision support system based on the fuzzy logic and decision tree to predict colorectal cancer

Background: Colorectal Cancer (CRC) is the most prevalent digestive system- related cancer and has become one of the deadliest diseases worldwide. Given the poor prognosis of CRC, it is of great importance to make a more accurate prediction of this disease. Early CRC detection using computational technologies can significantly improve the overall survival possibility of patients. Hence this study was aimed to develop a fuzzy logic-based clinical decision support system (FL-based CDSS) for the detection of CRC patients. Methods: This study was conducted in 2020 using the data related to CRC and non-CRC patients, which included the 1162 cases in the Masoud internal clinic, Tehran, Iran. The chi-square method was used to determine the most important risk factors in predicting CRC. Furthermore, the C4.5 decision tree was used to extract the rules. Finally, the FL-based CDSS was designed in a MATLAB environment and its performance was evaluated by a confusion matrix. Results: Eleven features were selected as the most important factors. After fuzzification of the qualitative variables and evaluation of the decision support system (DSS) using the confusion matrix, the accuracy, specificity, and sensitivity of the system was yielded 0.96, 0.97, and 0.96, respectively. Conclusion: We concluded that developing the CDSS in this field can provide an earlier diagnosis of CRC, leading to a timely treatment, which could decrease the CRC mortality rate in the community.

Development of a Novel Prognostic Model for Predicting Lymph Node Metastasis in Early Colorectal Cancer: Analysis Based on the Surveillance, Epidemiology, and End Results Database

Background

Identification of a simplified prediction model for lymph node metastasis (LNM) for patients with early colorectal cancer (CRC) is urgently needed to determine treatment and follow-up strategies. Therefore, in this study, we aimed to develop an accurate predictive model for LNM in early CRC.

Methods

We analyzed data from the 2004-2016 Surveillance Epidemiology and End Results database to develop and validate prediction models for LNM. Seven models, namely, logistic regression, XGBoost, k-nearest neighbors, classification and regression trees model, support vector machines, neural network, and random forest (RF) models, were used.

Results

A total of 26,733 patients with a diagnosis of early CRC (T1) were analyzed. The models included 8 independent prognostic variables; age at diagnosis, sex, race, primary site, histologic type, tumor grade, and, tumor size. LNM was significantly more frequent in patients with larger tumors, women, younger patients, and patients with more poorly differentiated tumor. The RF model showed the best predictive performance in comparison to the other method, achieving an accuracy of 96.0%, a sensitivity of 99.7%, a specificity of 92.9%, and an area under the curve of 0.991. Tumor size is the most important features in predicting LNM in early CRC.

Conclusion

We established a simplified reproducible predictive model for LNM in early CRC that could be used to guide treatment decisions. These findings warrant further confirmation in large prospective clinical trials.

Deep Convolutional Neural Network-Based Lymph Node Metastasis Prediction for Colon Cancer Using Histopathological Images

Background

Human evaluation of pathological slides cannot accurately predict lymph node metastasis (LNM), although accurate prediction is essential to determine treatment and follow-up strategies for colon cancer. We aimed to develop accurate histopathological features for LNM in colon cancer.

Methods

We developed a deep convolutional neural network model to distinguish the cancer tissue component of colon cancer using data from the tissue bank of the National Center for Tumor Diseases and the pathology archive at the University Medical Center Mannheim, Germany. This model was applied to whole-slide pathological images of colon cancer patients from The Cancer Genome Atlas (TCGA). The predictive value of the peri-tumoral stroma (PTS) score for LNM was assessed.

Results

A total of 164 patients with stages I, II, and III colon cancer from TCGA were analyzed. The mean PTS score was 0.380 (± SD = 0.285), and significantly higher PTS scores were observed in patients in the LNM-positive group than those in the LNM-negative group (P < 0.001). In the univariate analyses, the PTS scores for the LNM-positive group were significantly higher than those for the LNM-negative group (P < 0.001). Further, the PTS scores in lymphatic invasion and any one of perineural, lymphatic, or venous invasion were significantly increased in the LNM-positive group (P < 0.001 and P < 0.001).

Conclusion

We established the PTS score, a simplified reproducible parameter, for predicting LNM in colon cancer using computer-based analysis that could be used to guide treatment decisions. These findings warrant further confirmation through large-scale prospective clinical trials.

LASSO-Based Machine Learning Algorithm for Prediction of Lymph Node Metastasis in T1 Colorectal Cancer

PURPOSE

The role of tumor-infiltrating lymphocytes (TILs) in predicting lymph node metastasis (LNM) in patients with T1 colorectal cancer (CRC) remains unclear. Furthermore, clinical utility of a machine learning-based approach has not been widely studied.

MATERIALS AND METHODS

Immunohistochemistry for TILs against CD3, CD8, and forkhead box P3 in both center and invasive margin of the tumor were performed using surgically resected T1 CRC slides. Three hundred and sixteen patients were enrolled and categorized into training (n=221) and validation (n=95) sets via random sampling. Using clinicopathologic variables including TILs, the least absolute shrinkage and selection operator (LASSO) regression model was applied for variable selection and predictive signature building in the training set. The predictive accuracy of our model and the Japanese criteria were compared using area under the receiver operating characteristic (AUROC), net reclassification improvement (NRI)/integrated discrimination improvement (IDI), and decision curve analysis (DCA) in the validation set.

RESULTS

LNM was detected in 29 (13.1%) and 12 (12.6%) patients in training and validation sets, respectively. Nine variables were selected and used to generate the LASSO model. Its performance was similar in training and validation sets (AUROC, 0.795 vs. 0.765; p=0.747). In the validation set, the LASSO model showed better outcomes in predicting LNM than Japanese criteria, as measured by AUROC (0.765 vs. 0.518, p=0.003) and NRI (0.447, p=0.039)/IDI (0.121, p=0.034). DCA showed positive net benefits in using our model.

CONCLUSION

Our LASSO model incorporating histopathologic parameters and TILs showed superior performance compared to conventional Japanese criteria in predicting LNM in patients with T1 CRC.

Artificial intelligence in gastrointestinal cancer: Recent advances and future perspectives

Artificial intelligence (AI) using machine or deep learning algorithms is attracting increasing attention because of its more accurate image recognition ability and prediction performance than human-aid analyses. The application of AI models to gastrointestinal (GI) clinical oncology has been investigated for the past decade. AI has the capacity to automatically detect and diagnose GI tumors with similar diagnostic accuracy to expert clinicians. AI may also predict malignant potential, such as tumor histology, metastasis, patient survival, resistance to cancer treatments and the molecular biology of tumors, through image analyses of radiological or pathological imaging data using complex deep learning models beyond human cognition. The introduction of AI-assisted diagnostic systems into clinical settings is expected in the near future. However, limitations associated with the evaluation of GI tumors by AI models have yet to be resolved. Recent studies on AI-assisted diagnostic models of gastric and colorectal cancers in the endoscopic, pathological, and radiological fields were herein reviewed. The limitations and future perspectives for the application of AI systems in clinical settings have also been discussed. With the establishment of a multidisciplinary team containing AI experts in each medical institution and prospective studies, AI-assisted medical systems will become a promising tool for GI cancer.

The emerging role of super enhancer-derived noncoding RNAs in human cancer

Super enhancers (SEs) are large clusters of adjacent enhancers that drive the expression of genes which regulate cellular identity; SE regions can be enriched with a high density of transcription factors, co-factors, and enhancer-associated epigenetic modifications. Through enhanced activation of their target genes, SEs play an important role in various diseases and conditions, including cancer. Recent studies have shown that SEs not only activate the transcriptional expression of coding genes to directly regulate biological functions, but also drive the transcriptional expression of non-coding RNAs (ncRNAs) to indirectly regulate biological functions. SE-derived ncRNAs play critical roles in tumorigenesis, including malignant proliferation, metastasis, drug resistance, and inflammatory response. Moreover, the abnormal expression of SE-derived ncRNAs is closely related to the clinical and pathological characterization of tumors. In this review, we summarize the functions and roles of SE-derived ncRNAs in tumorigenesis and discuss their prospective applications in tumor therapy. A deeper understanding of the potential mechanism underlying the action of SE-derived ncRNAs in tumorigenesis may provide new strategies for the early diagnosis of tumors and targeted therapy.

Artificial intelligence for the study of colorectal cancer tissue slides

Artificial intelligence (AI) is gaining incredible momentum as a companion diagnostic in a number of fields in oncology. In the present mini-review, we summarize the main uses and findings of AI applied to the analysis of digital histopathological images of slides from colorectal cancer (CRC) patients. Machine learning tools have been developed to automatically and objectively recognize specific CRC subtypes, such as those with microsatellite instability and high lymphocyte infiltration that would optimally respond to specific therapies. Also, AI-based classification in distinct prognostic groups with no studies of the basic biological features of the tumor have been attempted in a methodological approach that we called “biology-agnostic”.

Preoperative Prediction of Lymph Node Metastasis in Patients With Early-T-Stage Non-small Cell Lung Cancer by Machine Learning Algorithms

Background: Lymph node metastasis (LNM) is difficult to precisely predict before surgery in patients with early-T-stage non-small cell lung cancer (NSCLC). This study aimed to develop machine learning (ML)-based predictive models for LNM.

Methods: Clinical characteristics and imaging features were retrospectively collected from 1,102 NSCLC ≤ 2 cm patients. A total of 23 variables were included to develop predictive models for LNM by multiple ML algorithms. The models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance and decision curve analysis (DCA) for clinical values. A feature selection approach was used to identify optimal predictive factors.

Results: The areas under the ROC curve (AUCs) of the 8 models ranged from 0.784 to 0.899. Some ML-based models performed better than models using conventional statistical methods in both ROC curves and decision curves. The random forest classifier (RFC) model with 9 variables introduced was identified as the best predictive model. The feature selection indicated the top five predictors were tumor size, imaging density, carcinoembryonic antigen (CEA), maximal standardized uptake value (SUV_max), and age.

Conclusions: By incorporating clinical characteristics and radiographical features, it is feasible to develop ML-based models for the preoperative prediction of LNM in early-T-stage NSCLC, and the RFC model performed best.

The Effects of Neoadjuvant Treatment on the Tumor Microenvironment in Rectal Cancer: Implications for Immune Activation and Therapy Response

BACKGROUND

Because more than one neoadjuvant treatment is available for advanced rectal cancer, the aim of this study was to compare the differential clinical and pathologic effects of different combinations of chemoradiation regimens, treatment sequencing, and timing to surgery on patient outcomes.

PATIENTS AND METHODS

Between January 2015 and October 2018, 126 newly diagnosed patients with rectal cancer with magnetic resonance imaging-based cT3-4 or N+ rectal disease for curative-intent treatment received 1 of 4 neoadjuvant regimens, followed by immediate surgery or delayed surgery. Whole post-neoadjuvant surgical specimens were assessed by 3-dimensional digital whole-tumor microarray imaging and immunostaining in pathology to analyze the global tumor pathologic regression grades, residual tumor distribution patterns, the extent of lymphovascular permeation, lymph node positivity, and the overall density of lymphocyte infiltration in the tumor microenvironment. These factors were further examined to identify possible correlations with clinical outcomes.

RESULTS

Among the 4 neoadjuvant treatment groups, including 2 conventional regimens, we found a significant increase of stromal CD3+ and CD8+ immune infiltrates in the postneoadjuvant tumor microenvironment in the 3 groups with delayed surgery after different chemoradiation regimens compared with the group with immediate surgery after a short course of RT alone. Independent of neoadjuvant chemoradiation regimens, the post-induction high-intermediate-low stromal-infiltrating CD8+ T-cell densities corresponded to tumor regression grades, distant metastasis rates, and disease-free survival and were prognostic factors for the further stratification of patients with American Joint Committee on Cancer stage III rectal cancer into different risk groups after surgery.

CONCLUSION

The effectiveness of induction strategies on tumor remission and disease recurrence in advanced rectal cancer was significantly correlated with an enhanced cytotoxic immune response in the tumor microenvironment.