Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer

Correlation between 18F-FDG PET/CT metabolic parameters and microvascular invasion before liver transplantation in patients with hepatocellular carcinoma

BACKGROUND

Microvascular infiltration (MVI) before liver transplantation (LT) in patients with hepatocellular carcinoma (HCC) is associated with postoperative tumor recurrence and survival. MVI is mainly assessed by pathological analysis of tissue samples, which is invasive and heterogeneous. PET/computed tomography (PET/CT) with 18F-labeled fluorodeoxyglucose (18F-FDG) as a tracer has been widely used in the examination of malignant tumors. This study investigated the association between 18F-FDG PET/CT metabolic parameters and MVI before LT in HCC patients.

METHODS

About 124 HCC patients who had 18F-FDG PET/CT examination before LT were included. The patients' clinicopathological features and 18F-FDG PET/CT metabolic parameters were recorded. Correlations between clinicopathological features, 18F-FDG PET/CT metabolic parameters, and MVI were analyzed. ROC curve was used to determine the optimal diagnostic cutoff value, area under the curve (AUC), sensitivity, and specificity for predictors of MVI.

RESULT

In total 72 (58.06%) patients were detected with MVI among the 124 HCC patients. Univariate analysis showed that tumor size (P = 0.001), T stage (P < 0.001), maximum standardized uptake value (SUVmax) (P < 0.001), minimum standardized uptake value (SUVmin) (P = 0.031), mean standardized uptake value (SUVmean) (P = 0.001), peak standardized uptake value (SUVpeak) (P = 0.001), tumor-to-liver ratio (SUVratio) (P = 0.010), total lesion glycolysis (TLG) (P = 0.006), metabolic tumor volume (MTV) (P = 0.011) and MVI were significantly different. Multivariate logistic regression showed that tumor size (P = 0.018), T stage (P = 0.017), TLG (P = 0.023), and MTV (P = 0.015) were independent predictors of MVI. In the receiver operating characteristic curve, TLG predicted MVI with an AUC value of 0.645. MTV predicted MVI with an AUC value of 0.635. Patients with tumor size ≥5 cm, T3-4, TLG > 400.67, and MTV > 80.58 had a higher incidence of MVI.

CONCLUSION

18F-FDG PET/CT metabolic parameters correlate with MVI and may be used as a noninvasive technique to predict MVI before LT in HCC patients.

Interpretable deep learning model to predict lymph node metastasis in early gastric cancer using whole slide images

In early gastric cancer (EGC), the presence of lymph node metastasis (LNM) is a crucial factor for determining the treatment options. Endoscopic resection is used for treatment of EGC with minimal risk of LNM. However, owing to the lack of definitive criteria for identifying patients who require additional surgery, some patients undergo unnecessary additional surgery. Considering that histopathologic patterns are significant factor for predicting lymph node metastasis in gastric cancer, we aimed to develop a machine learning algorithm which can predict LNM status using hematoxylin and eosin (H&E)-stained images. The images were obtained from several institutions. Our pipeline comprised two sequential approaches including a feature extractor and a risk classifier. For the feature extractor, a segmentation network (DeepLabV3+) was trained on 243 WSIs across three datasets to differentiate each histological subtype. The risk classifier was trained with XGBoost using 70 morphological features inferred from the trained feature extractor. The trained segmentation network, the feature extractor, achieved high performance, with pixel accuracies of 0.9348 and 0.8939 for the internal and external datasets in patch level, respectively. The risk classifier achieved an overall AUC of 0.75 in predicting LNM status. Remarkably, one of the datasets also showed a promising result with an AUC of 0.92. This is the first multi-institution study to develop machine learning algorithm for predicting LNM status in patients with EGC using H&E-stained histopathology images. Our findings have the potential to improve the selection of patients who require surgery among those with EGC showing high-risk histological features.

Deep learning-based pathological prediction of lymph node metastasis for patient with renal cell carcinoma from primary whole slide images

BACKGROUND

Metastasis renal cell carcinoma (RCC) patients have extremely high mortality rate. A predictive model for RCC micrometastasis based on pathomics could be beneficial for clinicians to make treatment decisions.

METHODS

A total of 895 formalin-fixed and paraffin-embedded whole slide images (WSIs) derived from three cohorts, including Shanghai General Hospital (SGH), Clinical Proteomic Tumor Analysis Consortium (CPTAC) and Cancer Genome Atlas (TCGA) cohorts, and another 588 frozen section WSIs from TCGA dataset were involved in the study. The deep learning-based strategy for predicting lymphatic metastasis was developed based on WSIs through clustering-constrained-attention multiple-instance learning method and verified among the three cohorts. The performance of the model was further verified in frozen-pathological sections. In addition, the model was also tested the prognosis prediction of patients with RCC in multi-source patient cohorts.

RESULTS

The AUC of the lymphatic metastasis prediction performance was 0.836, 0.865 and 0.812 in TCGA, SGH and CPTAC cohorts, respectively. The performance on frozen section WSIs was with the AUC of 0.801. Patients with high deep learning-based prediction of lymph node metastasis values showed worse prognosis.

CONCLUSIONS

In this study, we developed and verified a deep learning-based strategy for predicting lymphatic metastasis from primary RCC WSIs, which could be applied in frozen-pathological sections and act as a prognostic factor for RCC to distinguished patients with worse survival outcomes.

MAMILNet: advancing precision oncology with multi-scale attentional multi-instance learning for whole slide image analysis

BACKGROUND

Whole Slide Image (WSI) analysis, driven by deep learning algorithms, has the potential to revolutionize tumor detection, classification, and treatment response prediction. However, challenges persist, such as limited model generalizability across various cancer types, the labor-intensive nature of patch-level annotation, and the necessity of integrating multi-magnification information to attain a comprehensive understanding of pathological patterns.

METHODS

In response to these challenges, we introduce MAMILNet, an innovative multi-scale attentional multi-instance learning framework for WSI analysis. The incorporation of attention mechanisms into MAMILNet contributes to its exceptional generalizability across diverse cancer types and prediction tasks. This model considers whole slides as "bags" and individual patches as "instances." By adopting this approach, MAMILNet effectively eliminates the requirement for intricate patch-level labeling, significantly reducing the manual workload for pathologists. To enhance prediction accuracy, the model employs a multi-scale "consultation" strategy, facilitating the aggregation of test outcomes from various magnifications.

RESULTS

Our assessment of MAMILNet encompasses 1171 cases encompassing a wide range of cancer types, showcasing its effectiveness in predicting complex tasks. Remarkably, MAMILNet achieved impressive results in distinct domains: for breast cancer tumor detection, the Area Under the Curve (AUC) was 0.8872, with an Accuracy of 0.8760. In the realm of lung cancer typing diagnosis, it achieved an AUC of 0.9551 and an Accuracy of 0.9095. Furthermore, in predicting drug therapy responses for ovarian cancer, MAMILNet achieved an AUC of 0.7358 and an Accuracy of 0.7341.

CONCLUSION

The outcomes of this study underscore the potential of MAMILNet in driving the advancement of precision medicine and individualized treatment planning within the field of oncology. By effectively addressing challenges related to model generalization, annotation workload, and multi-magnification integration, MAMILNet shows promise in enhancing healthcare outcomes for cancer patients. The framework's success in accurately detecting breast tumors, diagnosing lung cancer types, and predicting ovarian cancer therapy responses highlights its significant contribution to the field and paves the way for improved patient care.

Harnessing artificial intelligence for prostate cancer management

Prostate cancer (PCa) is a common malignancy in males. The pathology review of PCa is crucial for clinical decision-making, but traditional pathology review is labor intensive and subjective to some extent. Digital pathology and whole-slide imaging enable the application of artificial intelligence (AI) in pathology. This review highlights the success of AI in detecting and grading PCa, predicting patient outcomes, and identifying molecular subtypes. We propose that AI-based methods could collaborate with pathologists to reduce workload and assist clinicians in formulating treatment recommendations. We also introduce the general process and challenges in developing AI pathology models for PCa. Importantly, we summarize publicly available datasets and open-source codes to facilitate the utilization of existing data and the comparison of the performance of different models to improve future studies.

Bioinformatics in urology - molecular characterization of pathophysiology and response to treatment

The application of bioinformatics has revolutionized the practice of medicine in the past 20 years. From early studies that uncovered subtypes of cancer to broad efforts spearheaded by the Cancer Genome Atlas initiative, the use of bioinformatics strategies to analyse high-dimensional data has provided unprecedented insights into the molecular basis of disease. In addition to the identification of disease subtypes - which enables risk stratification - informatics analysis has facilitated the identification of novel risk factors and drivers of disease, biomarkers of progression and treatment response, as well as possibilities for drug repurposing or repositioning; moreover, bioinformatics has guided research towards precision and personalized medicine. Implementation of specific computational approaches such as artificial intelligence, machine learning and molecular subtyping has yet to become widespread in urology clinical practice for reasons of cost, disruption of clinical workflow and need for prospective validation of informatics approaches in independent patient cohorts. Solving these challenges might accelerate routine integration of bioinformatics into clinical settings.

Deep learning-based radiomics model from pretreatment ADC to predict biochemical recurrence in advanced prostate cancer

Purpose

To develop deep-learning radiomics model for predicting biochemical recurrence (BCR) of advanced prostate cancer (PCa) based on pretreatment apparent diffusion coefficient (ADC) maps.

Methods

Data were collected retrospectively from 131 patients diagnosed with advanced PCa, randomly divided into training (n = 93) and test (n = 38) datasets. Pre-treatment ADC images were segmented using a pre-trained artificial intelligence (AI) model to identify suspicious PCa areas. Three models were constructed, including a clinical model, a conventional radiomics model and a deep-radiomics model. The receiver operating characteristic (ROC), precision-recall (PR) curve and decision curve analysis (DCA) were used to assess predictive performance in test dataset. The net reclassification index (NRI) and integrated discrimination improvement (IDI) were employed to compare the performance enhancement of the deep-radiomics model in relation to the other two models.

Results

The deep-radiomics model exhibited a significantly higher area under the curve (AUC) of ROC than the other two (P = 0.033, 0.026), as well as PR curve (AUC difference 0.420, 0.432). The DCA curve demonstrated superior performance for the deep-radiomics model across all risk thresholds than the other two. Taking the clinical model as reference, the NRI and IDI was 0.508 and 0.679 for the deep-radiomics model with significant difference. Compared with the conventional radiomics model, the NRI and IDI was 0.149 and 0.164 for the deep-radiomics model without significant difference.

Conclusion

The deep-radiomics model exhibits promising potential in predicting BCR in advanced PCa, compared to both the clinical model and the conventional radiomics model.

A non-invasive 25-Gene PLNM-Score urine test for detection of prostate cancer pelvic lymph node metastasis

BACKGROUND

Prostate cancer patients with pelvic lymph node metastasis (PLNM) have poor prognosis. Based on EAU guidelines, patients with >5% risk of PLNM by nomograms often receive pelvic lymph node dissection (PLND) during prostatectomy. However, nomograms have limited accuracy, so large numbers of false positive patients receive unnecessary surgery with potentially serious side effects. It is important to accurately identify PLNM, yet current tests, including imaging tools are inaccurate. Therefore, we intended to develop a gene expression-based algorithm for detecting PLNM.

METHODS

An advanced random forest machine learning algorithm screening was conducted to develop a classifier for identifying PLNM using urine samples collected from a multi-center retrospective cohort (n = 413) as training set and validated in an independent multi-center prospective cohort (n = 243). Univariate and multivariate discriminant analyses were performed to measure the ability of the algorithm classifier to detect PLNM and compare it with the Memorial Sloan Kettering Cancer Center (MSKCC) nomogram score.

RESULTS

An algorithm named 25 G PLNM-Score was developed and found to accurately distinguish PLNM and non-PLNM with AUC of 0.93 (95% CI: 0.85-1.01) and 0.93 (95% CI: 0.87-0.99) in the retrospective and prospective urine cohorts respectively. Kaplan-Meier plots showed large and significant difference in biochemical recurrence-free survival and distant metastasis-free survival in the patients stratified by the 25 G PLNM-Score (log rank P < 0.001 and P < 0.0001, respectively). It spared 96% and 80% of unnecessary PLND with only 0.51% and 1% of PLNM missing in the retrospective and prospective cohorts respectively. In contrast, the MSKCC score only spared 15% of PLND with 0% of PLNM missing.

CONCLUSIONS

The novel 25 G PLNM-Score is the first highly accurate and non-invasive machine learning algorithm-based urine test to identify PLNM before PLND, with potential clinical benefits of avoiding unnecessary PLND and improving treatment decision-making.

An automatic diagnostic system for the urodynamic study applying in lower urinary tract dysfunction

OBJECTIVE

To establish an automatic diagnostic system based on machine learning for preliminarily analysis of urodynamic study applying in lower urinary tract dysfunction (LUTD).

METHODS

The eight most common conditions of LUTDs were included in the present study. A total of 527 eligible patients with complete data, from the year of 2015 to 2020, were enrolled in this study. In total, two global parameters (patients' age and sex) and 13 urodynamic parameters were considered to be the input for machine learning algorithms. Three machine learning approaches were applied and evaluated in this study, including Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM).

RESULTS

By applying machine learning algorithms into the 8 common LUTDs, the DT models achieved the AUC of 0.63-0.98, the LR models achieved the AUC of 0.73-0.99, and the SVM models achieved the AUC of 0.64-1.00. For mutually exclusive diagnoses of underactive detrusor and acontractile detrusor, we developed a classification model that classifies the patients into either of these two diseases or double-negative class. For this classification method, the DT models achieved the AUC of 0.82-0.85 and the SVM models achieved the AUC of 0.86-0.90. Among all these models, the LR and the SVM models showed better performance. The best model of these diagnostic tasks achieved an average AUC of 0.90 (0.90 ± 0.08).

CONCLUSIONS

An automatic diagnostic system was developed using three machine learning models in urodynamic studies. This automated machine learning process could lead to promising assistance and enhancements of diagnosis and provide more useful reference for LUTD treatment.

Deep learning to predict breast cancer sentinel lymph node status on INSEMA histological images

BACKGROUND

Sentinel lymph node (SLN) status is a clinically important prognostic biomarker in breast cancer and is used to guide therapy, especially for hormone receptor-positive, HER2-negative cases. However, invasive lymph node staging is increasingly omitted before therapy, and studies such as the randomised Intergroup Sentinel Mamma (INSEMA) trial address the potential for further de-escalation of axillary surgery. Therefore, it would be helpful to accurately predict the pretherapeutic sentinel status using medical images.

METHODS

Using a ResNet 50 architecture pretrained on ImageNet and a previously successful strategy, we trained deep learning (DL)-based image analysis algorithms to predict sentinel status on hematoxylin/eosin-stained images of predominantly luminal, primary breast tumours from the INSEMA trial and three additional, independent cohorts (The Cancer Genome Atlas (TCGA) and cohorts from the University hospitals of Mannheim and Regensburg), and compared their performance with that of a logistic regression using clinical data only. Performance on an INSEMA hold-out set was investigated in a blinded manner.

RESULTS

None of the generated image analysis algorithms yielded significantly better than random areas under the receiver operating characteristic curves on the test sets, including the hold-out test set from INSEMA. In contrast, the logistic regression fitted on the Mannheim cohort retained a better than random performance on INSEMA and Regensburg. Including the image analysis model output in the logistic regression did not improve performance further on INSEMA.

CONCLUSIONS

Employing DL-based image analysis on histological slides, we could not predict SLN status for unseen cases in the INSEMA trial and other predominantly luminal cohorts.

Predicting Lymph Node Metastasis From Primary Cervical Squamous Cell Carcinoma Based on Deep Learning in Histopathologic Images

We developed a deep learning framework to accurately predict the lymph node status of patients with cervical cancer based on hematoxylin and eosin-stained pathological sections of the primary tumor. In total, 1524 hematoxylin and eosin-stained whole slide images (WSIs) of primary cervical tumors from 564 patients were used in this retrospective, proof-of-concept study. Primary tumor sections (1161 WSIs) were obtained from 405 patients who underwent radical cervical cancer surgery at the Fudan University Shanghai Cancer Center (FUSCC) between 2008 and 2014; 165 and 240 patients were negative and positive for lymph node metastasis, respectively (including 166 with positive pelvic lymph nodes alone and 74 with positive pelvic and para-aortic lymph nodes). We constructed and trained a multi-instance deep convolutional neural network based on a multiscale attention mechanism, in which an internal independent test set (100 patients, 228 WSIs) from the FUSCC cohort and an external independent test set (159 patients, 363 WSIs) from the Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma cohort of the Cancer Genome Atlas program database were used to evaluate the predictive performance of the network. In predicting the occurrence of lymph node metastasis, our network achieved areas under the receiver operating characteristic curve of 0.87 in the cross-validation set, 0.84 in the internal independent test set of the FUSCC cohort, and 0.75 in the external test set of the Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma cohort of the Cancer Genome Atlas program. For patients with positive pelvic lymph node metastases, we retrained the network to predict whether they also had para-aortic lymph node metastases. Our network achieved areas under the receiver operating characteristic curve of 0.91 in the cross-validation set and 0.88 in the test set of the FUSCC cohort. Deep learning analysis based on pathological images of primary foci is very likely to provide new ideas for preoperatively assessing cervical cancer lymph node status; its true value must be validated with cervical biopsy specimens and large multicenter datasets.

A 3-dimensional histology computer model of malignant melanoma and its implications for digital pathology

BACKGROUND

Historically, cancer diagnoses have been made by pathologists using two-dimensional histological slides. However, with the advent of digital pathology and artificial intelligence, slides are being digitised, providing new opportunities to integrate their information. Since nature is 3-dimensional (3D), it seems intuitive to digitally reassemble the 3D structure for diagnosis.

OBJECTIVE

To develop the first human-3D-melanoma-histology-model with full data and code availability. Further, to evaluate the 3D-simulation together with experienced pathologists in the field and discuss the implications of digital 3D-models for the future of digital pathology.

METHODS

A malignant melanoma of the skin was digitised via 3 µm cuts by a slide scanner; an open-source software was then leveraged to construct the 3D model. A total of nine pathologists from four different countries with at least 10 years of experience in the histologic diagnosis of melanoma tested the model and discussed their experiences as well as implications for future pathology.

RESULTS

We successfully constructed and tested the first 3D-model of human melanoma. Based on testing, 88.9% of pathologists believe that the technology is likely to enter routine pathology within the next 10 years; advantages include a better reflectance of anatomy, 3D assessment of symmetry and the opportunity to simultaneously evaluate different tissue levels at the same time; limitations include the high consumption of tissue and a yet inferior resolution due to computational limitations.

CONCLUSIONS

3D-histology-models are promising for digital pathology of cancer and melanoma specifically, however, there are yet limitations which need to be carefully addressed.

Artificial intelligence-assisted dermatology diagnosis: From unimodal to multimodal

Artificial Intelligence (AI) is progressively permeating medicine, notably in the realm of assisted diagnosis. However, the traditional unimodal AI models, reliant on large volumes of accurately labeled data and single data type usage, prove insufficient to assist dermatological diagnosis. Augmenting these models with text data from patient narratives, laboratory reports, and image data from skin lesions, dermoscopy, and pathologies could significantly enhance their diagnostic capacity. Large-scale pre-training multimodal models offer a promising solution, exploiting the burgeoning reservoir of clinical data and amalgamating various data types. This paper delves into unimodal models' methodologies, applications, and shortcomings while exploring how multimodal models can enhance accuracy and reliability. Furthermore, integrating cutting-edge technologies like federated learning and multi-party privacy computing with AI can substantially mitigate patient privacy concerns in dermatological datasets and further fosters a move towards high-precision self-diagnosis. Diagnostic systems underpinned by large-scale pre-training multimodal models can facilitate dermatology physicians in formulating effective diagnostic and treatment strategies and herald a transformative era in healthcare.

Identification of lymph node metastasis in pre-operation cervical cancer patients by weakly supervised deep learning from histopathological whole-slide biopsy images

BACKGROUND

Lymph node metastasis (LNM) significantly impacts the prognosis of individuals diagnosed with cervical cancer, as it is closely linked to disease recurrence and mortality, thereby impacting therapeutic schedule choices for patients. However, accurately predicting LNM prior to treatment remains challenging. Consequently, this study seeks to utilize digital pathological features extracted from histopathological slides of primary cervical cancer patients to preoperatively predict the presence of LNM.

METHODS

A deep learning (DL) model was trained using the Vision transformer (ViT) and recurrent neural network (RNN) frameworks to predict LNM. This prediction was based on the analysis of 554 histopathological whole-slide images (WSIs) obtained from Qilu Hospital of Shandong University. To validate the model's performance, an external test was conducted using 336 WSIs from four other hospitals. Additionally, the efficiency of the DL model was evaluated using 190 cervical biopsies WSIs in a prospective set.

RESULTS

In the internal test set, our DL model achieved an area under the curve (AUC) of 0.919, with sensitivity and specificity values of 0.923 and 0.905, respectively, and an accuracy (ACC) of 0.909. The performance of the DL model remained strong in the external test set. In the prospective cohort, the AUC was 0.91, and the ACC was 0.895. Additionally, the DL model exhibited higher accuracy compared to imaging examination in the evaluation of LNM. By utilizing the transformer visualization method, we generated a heatmap that illustrates the local pathological features in primary lesions relevant to LNM.

CONCLUSION

DL-based image analysis has demonstrated efficiency in predicting LNM in early operable cervical cancer through the utilization of biopsies WSI. This approach has the potential to enhance therapeutic decision-making for patients diagnosed with cervical cancer.

The predictive value of machine learning and nomograms for lymph node metastasis of prostate cancer: a systematic review and meta-analysis

BACKGROUND

In clinical practice, there are currently a variety of nomograms for predicting lymph node metastasis (LNM) of prostate cancer. At the same time, some scholars have introduced machine learning (ML) into the prediction of LNM of prostate cancer. However, the predictive value of nomograms and ML remains controversial. Based on this situation, this systematic review and meta-analysis was performed to explore the predictive value of various nomograms currently recommended and newly-developed ML models for LNM in prostate cancer patients.

EVIDENCE ACQUISITION

Cochrane, PubMed, Embase, and Web of Science were searched up to November 1, 2022. The risk of bias in the included studies was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). The concordance index (C-index), sensitivity, and specificity were adopted to evaluate the predictive accuracy of the models.

RESULTS

Thirty-one studies (18,803 patients) were included. Seven kinds of nomograms currently recommended, dominated by Briganti nomogram or MSKCC nomogram, were covered in the included studies. For newly-developed ML models, the C-index for LNM prediction in the training set and validation set was 0.846 [95%CI (0.818, 0.873)] and 0.862 [95%CI (0.819-0.905)] respectively. Most ML models in the training set were based on Logistic Regression (LR), which had a sensitivity of 0.78 [95%CI (0.70, 0.85)] and a specificity of 0.85 [95%CI (0.77, 0.90)] in the training set, and a sensitivity of 0.81 [95%CI (0.67, 0.89)] and a specificity of 0.82 [95%CI (0.75, 0.88)] in the validation set. For the recommended nomograms, the C-index in the validation set was 0.745 [95%CI (0.701, 0.790)] for the Briganti nomogram and 0.714 [95%CI (0.662, 0.765)] for the MSKCC nomogram.

CONCLUSION

The predictive accuracy of ML is superior to existing clinically recommended nomograms, and appropriate updates can be conducted to existing nomograms according to special situations.

Deep Learning Methodologies Applied to Digital Pathology in Prostate Cancer: A Systematic Review

Deep learning (DL), often called artificial intelligence (AI), has been increasingly used in Pathology thanks to the use of scanners to digitize slides which allow us to visualize them on monitors and process them with AI algorithms. Many articles have focused on DL applied to prostate cancer (PCa). This systematic review explains the DL applications and their performances for PCa in digital pathology. Article research was performed using PubMed and Embase to collect relevant articles. A Risk of Bias (RoB) was assessed with an adaptation of the QUADAS-2 tool. Out of the 77 included studies, eight focused on pre-processing tasks such as quality assessment or staining normalization. Most articles (n = 53) focused on diagnosis tasks like cancer detection or Gleason grading. Fifteen articles focused on prediction tasks, such as recurrence prediction or genomic correlations. Best performances were reached for cancer detection with an Area Under the Curve (AUC) up to 0.99 with algorithms already available for routine diagnosis. A few biases outlined by the RoB analysis are often found in these articles, such as the lack of external validation. This review was registered on PROSPERO under CRD42023418661.

Deep learning to predict cervical lymph node metastasis from intraoperative frozen section of tumour in papillary thyroid carcinoma: a multicentre diagnostic study

Background

Lymph node metastasis (LNM) assessment in patients with papillary thyroid carcinoma (PTC) is of great value. This study aimed to develop a deep learning model applied to intraoperative frozen section for prediction of LNM in PTC patients.

Methods

We established a deep-learning model (ThyNet-LNM) with the multiple-instance learning framework to predict LNM using whole slide images (WSIs) from intraoperative frozen sections of PTC. Data for the development and validation of ThyNet-LNM were retrospectively derived from four hospitals from January 2018 to December 2021. The ThyNet-LNM was trained using 1987 WSIs from 1120 patients obtained at the First Affiliated Hospital of Sun Yat-sen University. The ThyNet-LNM was then validated in the independent internal test set (479 WSIs from 280 patients) as well as three external test sets (1335 WSIs from 692 patients). The performance of ThyNet-LNM was further compared with preoperative ultrasound and computed tomography (CT).

Findings

The area under the receiver operating characteristic curves (AUCs) of ThyNet-LNM were 0.80 (95% CI 0.74-0.84), 0.81 (95% CI 0.77-0.86), 0.76 (95% CI 0.68-0.83), and 0.81 (95% CI 0.75-0.85) in internal test set and three external test sets, respectively. The AUCs of ThyNet-LNM were significantly higher than those of ultrasound and CT or their combination in all four test sets (all P < 0.01). Of 397 clinically node-negative (cN0) patients, the rate of unnecessary lymph node dissection decreased from 56.4% to 14.9% by ThyNet-LNM.

Interpretation

The ThyNet-LNM showed promising efficacy as a potential novel method in evaluating intraoperative LNM status, providing real-time guidance for decision. Furthermore, this led to a reduction of unnecessary lymph node dissection in cN0 patients.

Funding

National Natural Science Foundation of China, Guangzhou Science and Technology Project, and Guangxi Medical High-level Key Talents Training "139" Program.

Predicting Lymph Node Metastasis Status from Primary Muscle-Invasive Bladder Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study

BACKGROUND

Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC.

METHODS

We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets.

RESULTS

In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771-0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661-0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827-0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725-0.801) and 0.746 (95% CI, 0.687-0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence.

CONCLUSIONS

Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation.

Application of machine learning algorithm in prediction of lymph node metastasis in patients with intermediate and high-risk prostate cancer

PURPOSE

This study aims to establish the best prediction model of lymph node metastasis (LNM) in patients with intermediate- and high-risk prostate cancer (PCa) through machine learning (ML), and provide the guideline of accurate clinical diagnosis and precise treatment for clinicals.

METHODS

A total of 24,470 patients with intermediate- and high-risk PCa were included in this study. Multivariate logistic regression model was used to screen the independent risk factors of LNM. At the same time, six algorithms, namely random forest (RF), naive Bayesian classifier (NBC), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR) and decision tree (DT) are used to establish risk prediction models. Based on the best prediction performance of ML algorithm, a prediction model is established, and the performance of the model is evaluated from three aspects: area under curve (AUC), sensitivity and specificity.

RESULTS

In multivariate logistic regression analysis, T stage, PSA, Gleason score and bone metastasis were independent predictors of LNM in patients with intermediate- and high-risk PCa. By comprehensively comparing the prediction model performance of training set and test set, GBM model has the best prediction performance (F1 score = 0.838, AUROC = 0.804). Finally, we developed a preliminary calculator model that can quickly and accurately calculate the regional LNM in patients with intermediate- and high-risk PCa.

CONCLUSION

T stage, PSA, Gleason and bone metastasis were independent risk factors for predicting LNM in patients with intermediate- and high-risk PCa. The prediction model established in this study performs well; however, the GBM model is the best one.

Implementing deep learning models for the classification of Echinococcus multilocularis infection in human liver tissue

BACKGROUND

The histological diagnosis of alveolar echinococcosis can be challenging. Decision support models based on deep learning (DL) are increasingly used to aid pathologists, but data on the histology of tissue-invasive parasitic infections are missing. The aim of this study was to implement DL methods to classify Echinococcus multilocularis liver lesions and normal liver tissue and assess which regions and structures play the most important role in classification decisions.

METHODS

We extracted 15,756 echinococcus tiles from 28 patients using 59 whole slide images (WSI); 11,602 tiles of normal liver parenchyma from 18 patients using 33 WSI served as a control group. Different pretrained model architectures were used with a 60-20-20% random splitting. We visualized the predictions using probability-thresholded heat maps of WSI. The area-under-the-curve (AUC) value and other performance metrics were calculated. The GradCAM method was used to calculate and visualize important spatial features.

RESULTS

The models achieved a high validation and test set accuracy. The calculated AUC values were 1.0 in all models. Pericystic fibrosis and necrotic areas, as well as germinative and laminated layers of the metacestodes played an important role in decision tasks according to the superimposed GradCAM heatmaps.

CONCLUSION

Deep learning models achieved a high predictive performance in classifying E. multilocularis liver lesions. A possible next step could be to validate the model using other datasets and test it against other pathologic entities as well, such as, for example, Echinococcus granulosus infection.

Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning

Background

The presence of lymph node metastasis leads to a poor prognosis for prostate cancer (Pca). Recently, many studies have indicated that gene signatures may be able to predict the status of lymph nodes. The purpose of this study is to probe and validate a new tool to predict lymph node metastasis (LNM) based on alternative splicing (AS).

Methods

Gene expression profiles and clinical information of prostate adenocarcinoma cohort were retrieved from The Cancer Genome Atlas (TCGA) database, and the corresponding RNA-seq splicing events profiles were obtained from the TCGA SpliceSeq. Limma package was used to identify the differentially expressed alternative splicing (DEAS) events between LNM and non-LNM groups. Eight machine learning classifiers were built to train with stratified five-fold cross-validation. SHAP values was used to explain the model.

Results

333 differentially expressed alternative splicing (DEAS) events were identified. Using correlation filter and the least absolute shrinkage and selection operator (LASSO) method, a 96 AS signature was identified that had favorable discrimination in the training set and validated in the validation set. The linear discriminant analysis (LDA) was the best classifier after 100 iterations of training. The LDA classifier was able to distinguish between LNM and non-LNM with an area under the receiver operating curve of 0.962 ± 0.026 in the training set (D1 = 351) and 0.953 in the validation set (D2 = 62). The decision curve analysis plot proved the clinical application of the AS-based model.

Conclusion

Machine learning combined with AS data could robustly distinguish between LNM and non-LNM in Pca.

Machine-learning based investigation of prognostic indicators for oncological outcome of pancreatic ductal adenocarcinoma

Introduction

Pancreatic ductal adenocarcinoma (PDAC) is an aggressive malignancy with a poor prognosis. Surgical resection remains the only potential curative treatment option for early-stage resectable PDAC. Patients with locally advanced or micrometastatic disease should ideally undergo neoadjuvant therapy prior to surgical resection for an optimal treatment outcome. Computerized tomography (CT) scan is the most common imaging modality obtained prior to surgery. However, the ability of CT scans to assess the nodal status and resectability remains suboptimal and depends heavily on physician experience. Improved preoperative radiographic tumor staging with the prediction of postoperative margin and the lymph node status could have important implications in treatment sequencing. This paper proposes a novel machine learning predictive model, utilizing a three-dimensional convoluted neural network (3D-CNN), to reliably predict the presence of lymph node metastasis and the postoperative positive margin status based on preoperative CT scans.

Methods

A total of 881 CT scans were obtained from 110 patients with PDAC. Patients and images were separated into training and validation groups for both lymph node and margin prediction studies. Per-scan analysis and per-patient analysis (utilizing majority voting method) were performed.

Results

For a lymph node prediction 3D-CNN model, accuracy was 90% for per-patient analysis and 75% for per-scan analysis. For a postoperative margin prediction 3D-CNN model, accuracy was 81% for per-patient analysis and 76% for per-scan analysis.

Discussion

This paper provides a proof of concept that utilizing radiomics and the 3D-CNN deep learning framework may be used preoperatively to improve the prediction of positive resection margins as well as the presence of lymph node metastatic disease. Further investigations should be performed with larger cohorts to increase the generalizability of this model; however, there is a great promise in the use of convoluted neural networks to assist clinicians with treatment selection for patients with PDAC.

Artificial intelligence to predict oncological outcome directly from hematoxylin and eosin-stained slides in urology

INTRODUCTION

Artificial intelligence (AI) has been successfully applied for automatic tumor detection and grading in histopathological image analysis in urologic oncology. The aim of this review was to assess the applicability of these approaches in image-based oncological outcome prediction.

EVIDENCE ACQUISITION

A systematic literature search was conducted using the databases MEDLINE through PubMed and Web of Science up to April 20, 2021. Studies investigating AI approaches to determine the risk of recurrence, metastasis, or survival directly from H&E-stained tissue sections in prostate, renal cell or urothelial carcinoma were included. Characteristics of the AI approach and performance metrics were extracted and summarized. Risk of bias (RoB) was assessed using the PROBAST tool.

EVIDENCE SYNTHESIS

16 studies yielding a total of 6658 patients and reporting on 17 outcome predictions were included. Six studies focused on renal cell, six on prostate and three on urothelial carcinoma while one study investigated renal cell and urothelial carcinoma. Handcrafted feature extraction was used in five, a convolutional neural network (CNN) in six and a deep feature extraction in four studies. One study compared a CNN with handcrafted feature extraction. In seven outcome predictions, a multivariable comparison with clinicopathological parameters was reported. Five of them showed statistically significant hazard ratios for the AI's model's-prediction. However, RoB was high in 15 outcome predictions and unclear in two.

CONCLUSIONS

The included studies are promising but predominantly early pilot studies, therefore primarily highlighting the potential of AI approaches. Additional well-designed studies are needed to assess the actual clinical applicability.

Deep learning techniques for cancer classification using microarray gene expression data

Cancer is one of the top causes of death globally. Recently, microarray gene expression data has been used to aid in cancer’s effective and early detection. The use of DNA microarray technology to uncover information from the expression levels of thousands of genes has enormous promise. The DNA microarray technique can determine the levels of thousands of genes simultaneously in a single experiment. The analysis of gene expression is critical in many disciplines of biological study to obtain the necessary information. This study analyses all the research studies focused on optimizing gene selection for cancer detection using artificial intelligence. One of the most challenging issues is figuring out how to extract meaningful information from massive databases. Deep Learning architectures have performed efficiently in numerous sectors and are used to diagnose many other chronic diseases and to assist physicians in making medical decisions. In this study, we have evaluated the results of different optimizers on a RNA sequence dataset. The Deep learning algorithm proposed in the study classifies five different forms of cancer, including kidney renal clear cell carcinoma (KIRC), Breast Invasive Carcinoma (BRCA), lung adenocarcinoma (LUAD), Prostate Adenocarcinoma (PRAD) and Colon Adenocarcinoma (COAD). The performance of different optimizers like Stochastic gradient descent (SGD), Root Mean Squared Propagation (RMSProp), Adaptive Gradient Optimizer (AdaGrad), and Adaptive Momentum (AdaM). The experimental results gathered on the dataset affirm that AdaGrad and Adam. Also, the performance analysis has been done using different learning rates and decay rates. This study discusses current advancements in deep learning-based gene expression data analysis using optimized feature selection methods.

Deep Learning-Based Multi-Omics Integration Robustly Predicts Relapse in Prostate Cancer

Objective

Post-operative biochemical relapse (BCR) continues to occur in a significant percentage of patients with localized prostate cancer (PCa). Current stratification methods are not adequate to identify high-risk patients. The present study exploits the ability of deep learning (DL) algorithms using the H2O package to combine multi-omics data to resolve this problem.

Methods

Five-omics data from 417 PCa patients from The Cancer Genome Atlas (TCGA) were used to construct the DL-based, relapse-sensitive model. Among them, 265 (63.5%) individuals experienced BCR. Five additional independent validation sets were applied to assess its predictive robustness. Bioinformatics analyses of two relapse-associated subgroups were then performed for identification of differentially expressed genes (DEGs), enriched pathway analysis, copy number analysis and immune cell infiltration analysis.

Results

The DL-based model, with a significant difference (P = 6e-9) between two subgroups and good concordance index (C-index = 0.767), were proven to be robust by external validation. 1530 DEGs including 678 up- and 852 down-regulated genes were identified in the high-risk subgroup S2 compared with the low-risk subgroup S1. Enrichment analyses found five hallmark gene sets were up-regulated while 13 were down-regulated. Then, we found that DNA damage repair pathways were significantly enriched in the S2 subgroup. CNV analysis showed that 30.18% of genes were significantly up-regulated and gene amplification on chromosomes 7 and 8 was significantly elevated in the S2 subgroup. Moreover, enrichment analysis revealed that some DEGs and pathways were associated with immunity. Three tumor-infiltrating immune cell (TIIC) groups with a higher proportion in the S2 subgroup (p = 1e-05, p = 8.7e-06, p = 0.00014) and one TIIC group with a higher proportion in the S1 subgroup (P = 1.3e-06) were identified.

Conclusion

We developed a novel, robust classification for understanding PCa relapse. This study validated the effectiveness of deep learning technique in prognosis prediction, and the method may benefit patients and prevent relapse by improving early detection and advancing early intervention.

Prediction Performance of Deep Learning for Colon Cancer Survival Prediction on SEER Data

Colon and rectal cancers are the most common kinds of cancer globally. Colon cancer is more prevalent in men than in women. Early detection increases the likelihood of survival, and treatment significantly increases the likelihood of eradicating the disease. The Surveillance, Epidemiology, and End Results (SEER) programme is an excellent source of domestic cancer statistics. SEER includes nearly 30% of the United States population, covering various races and geographic locations. The data are made public via the SEER website when a SEER limited-use data agreement form is submitted and approved. We investigate data from the SEER programme, specifically colon cancer statistics, in this study. Our objective is to create reliable colon cancer survival and conditional survival prediction algorithms. In this study, we have presented an overview of cancer diagnosis methods and the treatments used to cure cancer. This paper presents an analysis of prediction performance of multiple deep learning approaches. The performance of multiple deep learning models is thoroughly examined to discover which algorithm surpasses the others, followed by an investigation of the network's prediction accuracy. The simulation outcomes indicate that automated prediction models can predict colon cancer patient survival. Deep autoencoders displayed the best performance outcomes attaining 97% accuracy and 95% area under curve-receiver operating characteristic (AUC-ROC).

Identification of metastatic primary cutaneous squamous cell carcinoma utilizing artificial intelligence analysis of whole slide images

Cutaneous squamous cell carcinoma (cSCC) harbors metastatic potential and causes mortality. However, clinical assessment of metastasis risk is challenging. We approached this challenge by harnessing artificial intelligence (AI) algorithm to identify metastatic primary cSCCs. Residual neural network-architectures were trained with cross-validation to identify metastatic tumors on clinician annotated, hematoxylin and eosin-stained whole slide images representing primary non-metastatic and metastatic cSCCs (n = 104). Metastatic primary tumors were divided into two subgroups, which metastasize rapidly (≤ 180 days) (n = 22) or slowly (> 180 days) (n = 23) after primary tumor detection. Final model was able to predict whether primary tumor was non-metastatic or rapidly metastatic with slide-level area under the receiver operating characteristic curve (AUROC) of 0.747. Furthermore, risk factor (RF) model including prediction by AI, Clark’s level and tumor diameter provided higher AUROC (0.917) than other RF models and predicted high 5-year disease specific survival (DSS) for patients with cSCC with 0 or 1 RFs (100% and 95.7%) and poor DSS for patients with cSCCs with 2 or 3 RFs (41.7% and 40.0%). These results indicate, that AI recognizes unknown morphological features associated with metastasis and may provide added value to clinical assessment of metastasis risk and prognosis of primary cSCC.

Artificial intelligence for renal cancer: From imaging to histology and beyond

Artificial intelligence (AI) has made considerable progress within the last decade and is the subject of contemporary literature. This trend is driven by improved computational abilities and increasing amounts of complex data that allow for new approaches in analysis and interpretation. Renal cell carcinoma (RCC) has a rising incidence since most tumors are now detected at an earlier stage due to improved imaging. This creates considerable challenges as approximately 10%–17% of kidney tumors are designated as benign in histopathological evaluation; however, certain co-morbid populations (the obese and elderly) have an increased peri-interventional risk. AI offers an alternative solution by helping to optimize precision and guidance for diagnostic and therapeutic decisions. The narrative review introduced basic principles and provide a comprehensive overview of current AI techniques for RCC. Currently, AI applications can be found in any aspect of RCC management including diagnostics, perioperative care, pathology, and follow-up. Most commonly applied models include neural networks, random forest, support vector machines, and regression. However, for implementation in daily practice, health care providers need to develop a basic understanding and establish interdisciplinary collaborations in order to standardize datasets, define meaningful endpoints, and unify interpretation.

Deep learning for evaluation of microvascular invasion in hepatocellular carcinoma from tumor areas of histology images

BACKGROUND

Microvascular invasion (MVI) is essential for the management of hepatocellular carcinoma (HCC). However, MVI is hard to evaluate in patients without sufficient peri-tumoral tissue samples, which account for over a half of HCC patients.

METHODS

We established an MVI deep-learning (MVI-DL) model with a weakly supervised multiple-instance learning framework, to evaluate MVI status using only tumor tissues from the histological whole slide images (WSIs). A total of 350 HCC patients (2917 WSIs) from the First Affiliated Hospital of Sun Yat-sen University (FAHSYSU cohort) were divided into a training and test set. One hundred and twenty patients (504 WSIs) from Dongguan People's Hospital and Shunde Hospital of Southern Medical University (DG-SD cohort) formed an external test set. Unsupervised clustering and class activation mapping were applied to visualize the key histological features.

RESULTS

In the FAHSYSU and DG-SD test set, the MVI-DL model achieved an AUC of 0.904 (95% CI 0.888-0.920) and 0.871 (95% CI 0.837-0.905), respectively. Visualization results showed that macrotrabecular architecture with rich blood sinus, rich tumor stroma and high intratumor heterogeneity were identified as the key features associated with MVI ( +), whereas severe immune infiltration and highly differentiated tumor cells were associated with MVI (-). In the simulation of patients with only one WSI or biopsies only, the AUC of the MVI-DL model reached 0.875 (95% CI 0.855-0.895) and 0.879 (95% CI 0.853-0.906), respectively.

CONCLUSION

The effective, interpretable MVI-DL model has potential as an important tool with practical clinical applicability in evaluating MVI status from the tumor areas on the histological slides.

Patients with Positive Lymph Nodes after Radical Prostatectomy and Pelvic Lymphadenectomy-Do We Know the Proper Way of Management?

Lymph node invasion in prostate cancer is a significant prognostic factor indicating worse prognosis. While it significantly affects both survival rates and recurrence, proper management remains a controversial and unsolved issue. The thorough evaluation of risk factors associated with nodal involvement, such as lymph node density or extracapsular extension, is crucial to establish the potential expansion of the disease and to substratify patients clinically. There are multiple strategies that may be employed for patients with positive lymph nodes. Nowadays, therapeutic methods are generally based on observation, radiotherapy, and androgen deprivation therapy. However, the current guidelines are incoherent in terms of the most effective management approach. Future management strategies are expected to make use of novel diagnostic tools and therapies, such as photodynamic therapy or diagnostic imaging with prostate-specific membrane antigen. Nevertheless, this heterogeneous group of men remains a great therapeutic concern, and both the clarification of the guidelines and the optimal substratification of patients are required.

Potential of Internet of Medical Things (IoMT) applications in building a smart healthcare system: A systematic review

Sudden spurting of Corona virus disease (COVID-19) has put the whole healthcare system on high alert. Internet of Medical Things (IoMT) has eased the situation to a great extent, also COVID-19 has motivated scientists to make new 'Smart' healthcare system focusing towards early diagnosis, prevention of spread, education and treatment and facilitate living in the new normal. This review aims to identify the role of IoMT applications in improving healthcare system and to analyze the status of research demonstrating effectiveness of IoMT benefits to the patient and healthcare system along with a brief insight into technologies supplementing IoMT and challenges faced in developing a smart healthcare system. An internet-based search in PUBMED, Google Scholar and IEEE Library for english language publications using relevant terms resulted in 987 articles. After screening title, abstract, and content related to IoMT in healthcare and excluding duplicate articles, 135 articles published in journal with impact factor ≥1 were eligible for inclusion. Also relevant articles from the references of the selected articles were considered. The habituation of IoMT and related technology has resolved several difficulties using remote monitoring, telemedicine, robotics, sensors etc. However mass adoption seems challenging due to factors like privacy and security of data, management of large amount of data, scalability and upgradation etc. Although ample knowledge has been compiled and exchanged, this structured systematic review will help the healthcare practitioners, policymakers/decision makers, scientists and researchers to gauge the applicability of IoMT in healthcare more efficiently.

Identifying the Candidates Who Will Benefit From Extended Pelvic Lymph Node Dissection at Radical Prostatectomy Among Patients With Prostate Cancer

PURPOSE

The therapeutic effect of extended pelvic lymph node dissection (PLND) in prostate cancer (PCa) patients is still controversial. The aim of this study was to identify the PCa patients who may benefit from extended PLND based on the 2012 Briganti nomogram.

MATERIALS AND METHODS

PCa patients who underwent radical prostatectomy (RP) plus PLND between 2010 and 2015 were identified from the Surveillance, Epidemiology, and End Results (SEER) database. The probability of lymph node invasion (LNI), determined using the 2012 Briganti nomogram, was used to stratify the patients. The endpoints were overall survival (OS) and cancer-specific survival (CSS). Propensity score matching (PSM) was performed to account for potential differences between patients with and without extended PLND. Univariable and multivariable Cox regression was used to analyze the association between the number of removed nodes (NRN) and survival. Kaplan-Meier analysis was performed to estimate OS and CSS. Extended PLND was defined as NRN >75th percentile.

RESULTS

A total of 27,690 patients were included in the study. NRN was not an independent predictor of OS (p = 0.564). However, in patients with probability of LNI ≥37, multivariable analyses showed that increased NRN was associated with improved OS (hazard ratio [HR] = 0.963; p = 0.002). The 5-y OS rate was significantly higher for patients with NRN ≥12 than those with NRN <12 (94.9% vs. 91.9%, respectively; p = 0.015). In the PSM cohort, among patients with probability of LNI ≥37, multivariable analyses showed that increased NRN was associated with improved OS (HR = 0.961; p = 0.004). In addition, the 5-y OS rate was significantly higher for patients with NRN ≥12 than those with NRN <12 (94.9% vs. 89.8%, respectively; p = 0.002). However, NRN was not an independent predictor of CSS in any LNI risk subgroup (all p >0.05).

CONCLUSION

Extensive PLND might be associated with improved survival in PCa patients with a high risk of LNI, which supports the use of extended PLND in highly selected PCa patients. The results need to be validated in prospective studies with long-term follow-up.

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.

Correlation of manual semi-quantitative and automated quantitative Ki-67 proliferative index with OncotypeDXTM recurrence score in invasive breast carcinoma

BACKGROUND

Ki-67 immunohistochemistry (IHC) staining is a widely used cancer proliferation assay; however, its limitations could be improved with automated scoring. The OncotypeDXTM Recurrence Score (ORS), which primarily evaluates cancer proliferation genes, is a prognostic indicator for breast cancer chemotherapy response; however, it is more expensive and slower than Ki-67.

OBJECTIVE

To compare manual Ki-67 (mKi-67) with automated Ki-67 (aKi-67) algorithm results based on manually selected Ki-67 "hot spots" in breast cancer, and correlate both with ORS.

METHODS

105 invasive breast carcinoma cases from 100 patients at our institution (2011-2013) with available ORS were evaluated. Concordance was assessed via Cohen's Kappa (κ).

RESULTS

57/105 cases showed agreement between mKi-67 and aKi-67 (κ 0.31, 95% CI 0.18-0.45), with 41 cases overestimated by aKi-67. Concordance was higher when estimated on the same image (κ 0.53, 95% CI 0.37-0.69). Concordance between mKi-67 score and ORS was fair (κ 0.27, 95% CI 0.11-0.42), and concordance between aKi-67 and ORS was poor (κ 0.10, 95% CI -0.03-0.23).

CONCLUSIONS

These results highlight the limits of Ki-67 algorithms that use manual "hot spot" selection. Due to suboptimal concordance, Ki-67 is likely most useful as a complement to, rather than a surrogate for ORS, regardless of scoring method.