Deep learning based prediction of prognosis in nonmetastatic clear cell renal cell carcinoma

The Current Application and Future Potential of Artificial Intelligence in Renal Cancer

Artificial intelligence (AI) is the integration of human tasks into machine processes. The role of AI in kidney cancer evaluation, management, and outcome predictions are constantly evolving. We performed a narrative review utilizing PubMed electronic database to query AI as a method of analysis in kidney cancer research. Key search-words included: Artificial Intelligence, Supervised/Unsupervised Machine Learning, Deep Learning, Natural Language Processing, Neural Networks, radiomics, pathomics, and kidney or renal neoplasms or cancer. 72 clinically relevant and impactful studies related to imaging, histopathology, and outcomes were recognized. We anticipate the incorporation of AI tools into future clinical decision-making for kidney cancer.

A deep learning model for accurately predicting cancer-specific survival in patients with primary bone sarcoma of the extremity: a population-based study

PURPOSE

Primary bone and joint sarcomas of the long bone are relatively rare neoplasms with poor prognosis. An efficient clinical tool that can accurately predict patient prognosis is not available. The current study aimed to use deep learning algorithms to develop a prediction model for the prognosis of patients with long bone sarcoma.

METHODS

Data of patients with long bone sarcoma in the extremities was collected from the Surveillance, Epidemiology, and End Results Program database from 2004 to 2014. Univariate and multivariate analyses were performed to select possible prediction features. DeepSurv, a deep learning model, was constructed for predicting cancer-specific survival rates. In addition, the classical cox proportional hazards model was established for comparison. The predictive accuracy of our models was assessed using the C-index, Integrated Brier Score, receiver operating characteristic curve, and calibration curve.

RESULTS

Age, tumor extension, histological grade, tumor size, surgery, and distant metastasis were associated with cancer-specific survival in patients with long bone sarcoma. According to loss function values, our models converged successfully and effectively learned the survival data of the training cohort. Based on the C-index, area under the curve, calibration curve, and Integrated Brier Score, the deep learning model was more accurate and flexible in predicting survival rates than the cox proportional hazards model.

CONCLUSION

A deep learning model for predicting the survival probability of patients with long bone sarcoma was constructed and validated. It is more accurate and flexible in predicting prognosis than the classical CoxPH model.

UroPredict: Machine learning model on real-world data for prediction of kidney cancer recurrence (UroCCR-120)

Renal cell carcinoma (RCC) is most often diagnosed at a localized stage, where surgery is the standard of care. Existing prognostic scores provide moderate predictive performance, leading to challenges in establishing follow-up recommendations after surgery and in selecting patients who could benefit from adjuvant therapy. In this study, we developed a model for individual postoperative disease-free survival (DFS) prediction using machine learning (ML) on real-world prospective data. Using the French kidney cancer research network database, UroCCR, we analyzed a cohort of surgically treated RCC patients. Participating sites were randomly assigned to either the training or testing cohort, and several ML models were trained on the training dataset. The predictive performance of the best ML model was then evaluated on the test dataset and compared with the usual risk scores. In total, 3372 patients were included, with a median follow-up of 30 months. The best results in predicting DFS were achieved using Cox PH models that included 24 variables, resulting in an iAUC of 0.81 [IC95% 0.77-0.85]. The ML model surpassed the predictive performance of the most commonly used risk scores while handling incomplete data in predictors. Lastly, patients were stratified into four prognostic groups with good discrimination (iAUC = 0.79 [IC95% 0.74-0.83]). Our study suggests that applying ML to real-world prospective data from patients undergoing surgery for localized or locally advanced RCC can provide accurate individual DFS prediction, outperforming traditional prognostic scores.

The predictive value of modified-DeepSurv in overall survivals of patients with lung cancer

The traditional prognostic model may induce the possibility of incorrect assessment of mortality risk under the assumption of linearity. It is urgent to develop a non-linearity precise prognostic model for achieving personalized medicine in lung cancer. In our study, we develop and validate a prognostic model "Modified-DeepSurv" for patients with lung carcinoma based on deep learning and evaluate its value for prognosis, while Cox proportional hazard regression was used to develop another model "CPH." The C-index of the Modified-DeepSurv and CPH was 0.956 (95% confidence interval [CI]: 0.946-0.974) and 0.836 (95% CI: 0.774-0.896), respectively, in the training cohort, while the C-index of the Modified-DeepSurv and CPH was 0.932 (95%CI: 0.908-0.964) and 0.777 (95%CI: 0.633-0.919), respectively, in the test dataset. The Modified-DeepSurv model visualization was realized by a user-friendly graphic interface. Modified-DeepSurv can effectively predict the survival of lung cancer patients and is superior to the conventional CPH model.

Comparison of deep learning-based recurrence-free survival with random survival forest and Cox proportional hazard models in Stage-I NSCLC patients

BACKGROUND

The curative treatment for Stage I non-small cell lung cancer (NSCLC) is surgical resection. Even for Stage I patients, the probability of recurrence after curative treatment is around 20%.

METHODS

In this retrospective study, we included 268 operated Stage I NSCLC patients between January 2008 and June 2018 to analyze the prognostic factors (pathological stage, histological type, number of sampled mediastinal lymph node stations, type of resection, SUVmax of the lesion) that may affect relapse with three different methods, Cox proportional hazard (CoxPH), random survival forest (RSF), DeepSurv, and to compare the performance of these methods with Harrell's C-index. The dataset was randomly split into two sets, training and test sets.

RESULTS

In the training set, DeepSurv showed the best performance among the three models, the C-index of the training set was 0.832, followed by RSF (0.675) and CoxPH (0.672). In the test set, RSF showed the best performance among the three models, followed by DeepSurv with 0.677 and CoxPH methods with 0.625.

CONCLUSION

In conclusion, machine-learning techniques can be useful in predicting recurrence for lung cancer and guide clinicians both in choosing the adjuvant treatment options and best follow-up programs.

A machine learning model for colorectal liver metastasis post-hepatectomy prognostications

Background

Currently, surgical resection is the mainstay for colorectal liver metastases (CRLM) management and the only potentially curative treatment modality. Prognostication tools can support patient selection for surgical resection to maximize therapeutic benefit. This study aimed to develop a survival prediction model using machine learning based on a multicenter patient sample in Hong Kong.

Methods

Patients who underwent hepatectomy for CRLM between 1 January 2009 and 31 December 2018 in four hospitals in Hong Kong were included in the study. Survival analysis was performed using Cox proportional hazards (CPH). A stepwise selection on Cox multivariable models with Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied to a multiply-imputed dataset to build a prediction model. The model was validated in the validation set, and its performance was compared with that of Fong Clinical Risk Score (CRS) using concordance index.

Results

A total of 572 patients were included with a median follow-up of 3.6 years. The full models for overall survival (OS) and recurrence-free survival (RFS) consist of the same 8 established and novel variables, namely colorectal cancer nodal stage, CRLM neoadjuvant treatment, Charlson Comorbidity Score, pre-hepatectomy bilirubin and carcinoembryonic antigen (CEA) levels, CRLM largest tumor diameter, extrahepatic metastasis detected on positron emission-tomography (PET)-scan as well as KRAS status. Our CRLM Machine-learning Algorithm Prognostication model (CMAP) demonstrated better ability to predict OS (C-index =0.651), compared with the Fong CRS for 1-year (C-index =0.571) and 5-year OS (C-index =0.574). It also achieved a C-index of 0.651 for RFS.

Conclusions

We present a promising machine learning algorithm to individualize prognostications for patients following resection of CRLM with good discriminative ability.

Neural network-based prognostic predictive tool for gastric cardiac cancer: the worldwide retrospective study

BACKGROUNDS

The incidence of gastric cardiac cancer (GCC) has obviously increased recently with poor prognosis. It's necessary to compare GCC prognosis with other gastric sites carcinoma and set up an effective prognostic model based on a neural network to predict the survival of GCC patients.

METHODS

In the population-based cohort study, we first enrolled the clinical features from the Surveillance, Epidemiology and End Results (SEER) data (n = 31,397) as well as the public Chinese data from different hospitals (n = 1049). Then according to the diagnostic time, the SEER data were then divided into two cohorts, the train cohort (patients were diagnosed as GCC in 2010-2014, n = 4414) and the test cohort (diagnosed in 2015, n = 957). Age, sex, pathology, tumor, node, and metastasis (TNM) stage, tumor size, surgery or not, radiotherapy or not, chemotherapy or not and history of malignancy were chosen as the predictive clinical features. The train cohort was utilized to conduct the neural network-based prognostic predictive model which validated by itself and the test cohort. Area under the receiver operating characteristics curve (AUC) was used to evaluate model performance.

RESULTS

The prognosis of GCC patients in SEER database was worse than that of non GCC (NGCC) patients, while it was not worse in the Chinese data. The total of 5371 patients were used to conduct the model, following inclusion and exclusion criteria. Neural network-based prognostic predictive model had a satisfactory performance for GCC overall survival (OS) prediction, which owned 0.7431 AUC in the train cohort (95% confidence intervals, CI, 0.7423-0.7439) and 0.7419 in the test cohort (95% CI, 0.7411-0.7428).

CONCLUSIONS

GCC patients indeed have different survival time compared with non GCC patients. And the neural network-based prognostic predictive tool developed in this study is a novel and promising software for the clinical outcome analysis of GCC patients.

The Efficacy of Pretreatment 18F-FDG PET-CT-Based Deep Learning Network Structure to Predict Survival in Nasopharyngeal Carcinoma

Background

Previous studies have shown that the 5-year survival rates of patients with nasopharyngeal carcinoma (NPC) were still not ideal despite great improvement in NPC treatments. To achieve individualized treatment of NPC, we have been looking for novel models to predict the prognosis of patients with NPC. The objective of this study was to use a novel deep learning network structural model to predict the prognosis of patients with NPC and to compare it with the traditional PET-CT model combining metabolic parameters and clinical factors.

Methods

A total of 173 patients were admitted to 2 institutions between July 2014 and April 2020 for the retrospective study; each received a PET-CT scan before treatment. The least absolute shrinkage and selection operator (LASSO) was employed to select some features, including SUVpeak-P, T3, age, stage II, MTV-P, N1, stage III and pathological type, which were associated with overall survival (OS) of patients. We constructed 2 survival prediction models: an improved optimized adaptive multimodal task (a 3D Coordinate Attention Convolutional Autoencoder and an uncertainty-based jointly Optimizing Cox Model, CACA-UOCM for short) and a clinical model. The predictive power of these models was assessed using the Harrell Consistency Index (C index). Overall survival of patients with NPC was compared by Kaplan-Meier and Log-rank tests.

Results

The results showed that CACA-UOCM model could estimate OS (C index, 0.779 for training, 0.774 for validation, and 0.819 for testing) and divide patients into low and high mortality risk groups, which were significantly associated with OS (P < .001). However, the C-index of the model based only on clinical variables was only 0.42.

Conclusions

The deep learning network model based on ¹⁸F-FDG PET/CT can serve as a reliable and powerful predictive tool for NPC and provide therapeutic strategies for individual treatment.

Machine learning based prediction for oncologic outcomes of renal cell carcinoma after surgery using Korean Renal Cell Carcinoma (KORCC) database

We developed a novel prediction model for recurrence and survival in patients with localized renal cell carcinoma (RCC) after surgery and a novel statistical method of machine learning (ML) to improve accuracy in predicting outcomes using a large Asian nationwide dataset, updated KOrean Renal Cell Carcinoma (KORCC) database that covered data for a total of 10,068 patients who had received surgery for RCC. After data pre-processing, feature selection was performed with an elastic net. Nine variables for recurrence and 13 variables for survival were extracted from 206 variables. Synthetic minority oversampling technique (SMOTE) was used for the training data set to solve the imbalance problem. We applied the most of existing ML algorithms introduced so far to evaluate the performance. We also performed subgroup analysis according to the histologic type. Diagnostic performances of all prediction models achieved high accuracy (range, 0.77-0.94) and F1-score (range, 0.77-0.97) in all tested metrics. In an external validation set, high accuracy and F1-score were well maintained in both recurrence and survival. In subgroup analysis of both clear and non-clear cell type RCC group, we also found a good prediction performance.

A deep learning-based model predicts survival for patients with laryngeal squamous cell carcinoma: a large population-based study

OBJECTIVES

To assess the performance of DeepSurv, a deep learning-based model in the survival prediction of laryngeal squamous cell carcinoma (LSCC) using the Surveillance, Epidemiology, and End Results (SEER) database.

METHODS

In this large population-based study, we developed and validated a deep learning survival neural network using pathologically diagnosed patients with LSCC from the SEER database between January 2010 and December 2018. Totally 13 variables were included in this network, including patients baseline characteristics, stage, grade, site, tumor extension and treatment details. Based on the total risk score derived from this algorithm, a three-knot restricted cubic spline was plotted to exhibit the difference of survival benefits from two treatment modalities.

RESULTS

Totally 6316 patients with LSCC were included in the study, of which 4237 cases diagnosed between 2010 and 2015 were selected as the development cohort, and the rest (2079 cases diagnosed from 2016 to 2018) were the validation cohort. A state-of-the-art deep learning-based model based on 23 features (i.e., 13 variables) was generated, which showed more superior performance in the prediction of overall survival (OS) than the tumor, node, and metastasis (TNM) staging system (C-index for DeepSurv vs TNM staging = 0.71; 95% CI 0.69-0.74 vs 0.61; 95% CI 0.60-0.63). Interestingly, a significantly nonlinear association between total risk score and treatment effectiveness was observed. When the total risk score ranges 0.1-1.5, surgical treatment brought more survival benefits than nonsurgical one for LSCC patients, especially in 70.5% of patients staged III-IV.

CONCLUSIONS

The deep learning-based model shows more potential benefits in survival estimation for patients with LSCC, which may potentially serve as an auxiliary approach to provide reliable treatment recommendations.

Artificial intelligence-based prediction of overall survival in metastatic renal cell carcinoma

Background and objectives

Investigations of the prognosis are vital for better patient management and decision-making in patients with advanced metastatic renal cell carcinoma (mRCC). The purpose of this study is to evaluate the capacity of emerging Artificial Intelligence (AI) technologies to predict three- and five-year overall survival (OS) for mRCC patients starting their first-line of systemic treatment.

Patients and methods

The retrospective study included 322 Italian patients with mRCC who underwent systemic treatment between 2004 and 2019. Statistical analysis included the univariate and multivariate Cox proportional-hazard model and the Kaplan-Meier analysis for the prognostic factors' investigation. The patients were split into a training cohort to establish the predictive models and a hold-out cohort to validate the results. The models were evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. We assessed the clinical benefit of the models using decision curve analysis (DCA). Then, the proposed AI models were compared with well-known pre-existing prognostic systems.

Results

The median age of patients in the study was 56.7 years at RCC diagnosis and 78% of participants were male. The median survival time from the start of systemic treatment was 29.2 months; 95% of the patients died during the follow-up that finished by the end of 2019. The proposed predictive model, which was constructed as an ensemble of three individual predictive models, outperformed all well-known prognostic models to which it was compared. It also demonstrated better usability in supporting clinical decisions for 3- and 5-year OS. The model achieved (0.786 and 0.771) AUC and (0.675 and 0.558) specificity at sensitivity 0.90 for 3 and 5 years, respectively. We also applied explainability methods to identify the important clinical features that were found to be partially matched with the prognostic factors identified in the Kaplan-Meier and Cox analyses.

Conclusions

Our AI models provide best predictive accuracy and clinical net benefits over well-known prognostic models. As a result, they can potentially be used in clinical practice for providing better management for mRCC patients starting their first-line of systemic treatment. Larger studies would be needed to validate the developed model.

A comprehensive review on recent approaches for cancer drug discovery associated with artificial intelligence

Through the revolutionization of artificial intelligence (AI) technologies in clinical research, significant improvement is observed in diagnosis of cancer. Utilization of these AI technologies, such as machine and deep learning, is imperative for the discovery of novel anticancer drugs and improves existing/ongoing cancer therapeutics. However, building a model for complicated cancers and their types remains a challenge due to lack of effective therapeutics that hinder the establishment of effective computational tools. In this review, we exploit recent approaches and state-of-the-art in implementing AI methods for anticancer drug discovery, and discussed how advances in these applications need to be considered in the current cancer therapeutics. Considering the immense potential of AI, we explore molecular docking and their interactions to recognize metabolic activities that support drug design. Finally, we highlight corresponding strategies in applying machine and deep learning methods to various types of cancer with their pros and cons.

Application of Machine Learning Models to Predict Recurrence After Surgical Resection of Nonmetastatic Renal Cell Carcinoma

BACKGROUND

Predictive tools can be useful for adapting surveillance or including patients in adjuvant trials after surgical resection of nonmetastatic renal cell carcinoma (RCC). Current models have been built using traditional statistical modelling and prespecified variables, which limits their performance.

OBJECTIVE

To investigate the performance of machine learning (ML) framework to predict recurrence after RCC surgery and compare them with current validated models.

DESIGN, SETTING, AND PARTICIPANTS

In this observational study, we derived and tested several ML-based models (Random Survival Forests [RSF], Survival Support Vector Machines [S-SVM], and Extreme Gradient Boosting [XG boost]) to predict recurrence of patients who underwent radical or partial nephrectomy for a nonmetastatic RCC, between 2013 and 2020, at 21 French medical centres.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

The primary end point was disease-free survival. Model discrimination was assessed using the concordance index (c-index), and calibration was assessed using the Brier score. ML models were compared with four conventional prognostic models, using decision curve analysis (DCA).

RESULTS AND LIMITATIONS

A total of 4067 patients were included in this study (3253 in the development cohort and 814 in the validation cohort). Most tumours (69%) were clear cell RCC, 40% were of high grade (nuclear International Society of Urological Pathology grade 3 or 4), and 24% had necrosis. Of the patients, 4% had nodal involvement. After a median follow-up of 57 mo (interquartile range 29-76), 523 (13%) patients recurred. ML models obtained higher c-index values than conventional models. The RSF yielded the highest c-index values (0.794), followed by S-SVM (c-index 0.784) and XG boost (c-index 0.782). In addition, all models showed good calibration with low integrated Brier scores (all integrated brier scores <0.1). However, we found calibration drift over time for all models, albeit with a smaller magnitude for ML models. Finally, DCA showed an incremental net benefit from all ML models compared with conventional models currently used in practice.

CONCLUSIONS

Applying ML approaches to predict recurrence following surgical resection of RCC resulted in better prediction than that of current validated models available in clinical practice. However, there is still room for improvement, which may come from the integration of novel biological and/or imaging biomarkers.

PATIENT SUMMARY

We found that artificial intelligence algorithms could better predict the risk of recurrence after surgery for a localised kidney cancer. These algorithms may help better select patients who will benefit from medical treatment after surgery.

Deep Learning-driven classification of external DICOM studies for PACS archiving

OBJECTIVES

Over the course of their treatment, patients often switch hospitals, requiring staff at the new hospital to import external imaging studies to their local database. In this study, the authors present MOdality Mapping and Orchestration (MOMO), a Deep Learning-based approach to automate this mapping process by combining metadata analysis and a neural network ensemble.

METHODS

A set of 11,934 imaging series with existing anatomical labels was retrieved from the PACS database of the local hospital to train an ensemble of neural networks (DenseNet-161 and ResNet-152), which process radiological images and predict the type of study they belong to. We developed an algorithm that automatically extracts relevant metadata from imaging studies, regardless of their structure, and combines it with the neural network ensemble, forming a powerful classifier. A set of 843 anonymized external studies from 321 hospitals was hand-labeled to assess performance. We tested several variations of this algorithm.

RESULTS

MOMO achieves 92.71% accuracy and 2.63% minor errors (at 99.29% predictive power) on the external study classification task, outperforming both a commercial product (82.86% accuracy, 1.36% minor errors, 96.20% predictive power) and a pure neural network ensemble (72.69% accuracy, 10.3% minor errors, 99.05% predictive power) performing the same task. We find that the highest performance is achieved by an algorithm that combines all information into one vote-based classifier.

CONCLUSION

Deep Learning combined with metadata matching is a promising and flexible approach for the automated classification of external DICOM studies for PACS archiving.

KEY POINTS

• The algorithm can successfully identify 76 medical study types across seven modalities (CT, X-ray angiography, radiographs, MRI, PET (+CT/MRI), ultrasound, and mammograms). • The algorithm outperforms a commercial product performing the same task by a significant margin (> 9% accuracy gain). • The performance of the algorithm increases through the application of Deep Learning techniques.

Prediction and Risk Stratification of Cardiovascular Disease in Diabetic Kidney Disease Patients

Background

Diabetic kidney disease (DKD) patients are facing an extremely high risk of cardiovascular disease (CVD), which is a major cause of death for DKD patients. We aimed to build a deep learning model to predict CVD risk among DKD patients and perform risk stratifying, which could help them perform early intervention and improve personal health management.

Methods

A retrospective cohort study was conducted to assess the risk of the occurrence of composite cardiovascular disease, which includes coronary heart disease, cerebrovascular diseases, congestive heart failure, and peripheral artery disease, in DKD patients. A least absolute shrinkage and selection operator (LASSO) regression was used to perform the variable selection. A deep learning-based survival model called DeepSurv, based on a feed-forward neural network was developed to predict CVD risk among DKD patients. We compared the model performance with the conventional Cox proportional hazards (CPH) model and the Random survival forest (RSF) model using the concordance index (C-index), the area under the curve (AUC), and integrated Brier scores (IBS).

Results

We recruited 890 patients diagnosed with DKD in this retrospective study. During a median follow-up of 10.4 months, there are 289 patients who sustained a subsequent CVD. Seven variables, including age, high density lipoprotein (HDL), hemoglobin (Hb), systolic blood pressure (SBP), smoking status, 24 h urinary protein excretion, and total cholesterol (TC), chosen by LASSO regression were used to develop the predictive model. The DeepSurv model showed the best performance, achieved a C-index of 0.767(95% confidence intervals [CI]: 0.717–0.817), AUC of 0.780(95%CI: 0.721–0.839), and IBS of 0.067 in the validation set. Then we used the cut-off value determined by ROC (receiver operating characteristic) curve to divide the patients into different risk groups. Moreover, the DeepSurv model was also applied to develop an online calculation tool for patients to conduct risk monitoring.

Conclusion

A deep-learning-based predictive model using seven clinical variables can effectively predict CVD risk among DKD patients and perform risk stratification. An online calculator allows its easy implementation.

Precision Medicine: An Optimal Approach to Patient Care in Renal Cell Carcinoma

Renal cell cancer (RCC) is a heterogeneous tumor that shows both intra- and inter-heterogeneity. Heterogeneity is displayed not only in different patients but also among RCC cells in the same tumor, which makes treatment difficult because of varying degrees of responses generated in RCC heterogeneous tumor cells even with targeted treatment. In that context, precision medicine (PM), in terms of individualized treatment catered for a specific patient or groups of patients, can shift the paradigm of treatment in the clinical management of RCC. Recent progress in the biochemical, molecular, and histological characteristics of RCC has thrown light on many deregulated pathways involved in the pathogenesis of RCC. As PM-based therapies are rapidly evolving and few are already in current clinical practice in oncology, one can expect that PM will expand its way toward the robust treatment of patients with RCC. This article provides a comprehensive background on recent strategies and breakthroughs of PM in oncology and provides an overview of the potential applicability of PM in RCC. The article also highlights the drawbacks of PM and provides a holistic approach that goes beyond the involvement of clinicians and encompasses appropriate legislative and administrative care imparted by the healthcare system and insurance providers. It is anticipated that combined efforts from all sectors involved will make PM accessible to RCC and other patients with cancer, making a tremendous positive leap on individualized treatment strategies. This will subsequently enhance the quality of life of patients.

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

The interpretation of imaging in medicine in general and in oncology specifically remains problematic due to several limitations which include the need to incorporate detailed clinical history, patient and disease-specific history, clinical exam features, previous and ongoing treatment, and account for the dependency on reproducible human interpretation of multiple factors with incomplete data linkage. To standardize reporting, minimize bias, expedite management, and improve outcomes, the use of Artificial Intelligence (AI) has gained significant prominence in imaging analysis. In oncology, AI methods have as a result been explored in most cancer types with ongoing progress in employing AI towards imaging for oncology treatment, assessing treatment response, and understanding and communicating prognosis. Challenges remain with limited available data sets, variability in imaging changes over time augmented by a growing heterogeneity in analysis approaches. We review the imaging analysis workflow and examine how hand-crafted features also referred to as traditional Machine Learning (ML), Deep Learning (DL) approaches, and hybrid analyses, are being employed in AI-driven imaging analysis in central nervous system tumors. ML, DL, and hybrid approaches coexist, and their combination may produce superior results although data in this space is as yet novel, and conclusions and pitfalls have yet to be fully explored. We note the growing technical complexities that may become increasingly separated from the clinic and enforce the acute need for clinician engagement to guide progress and ensure that conclusions derived from AI-driven imaging analysis reflect that same level of scrutiny lent to other avenues of clinical research.

Deep neural network for the determination of transformed foci in Bhas 42 cell transformation assay

Bhas 42 cell transformation assay (CTA) has been used to estimate the carcinogenic potential of chemicals by exposing Bhas 42 cells to carcinogenic stimuli to form colonies, referred to as transformed foci, on the confluent monolayer. Transformed foci are classified and quantified by trained experts using morphological criteria. Although the assay has been certified by international validation studies and issued as a guidance document by OECD, this classification process is laborious, time consuming, and subjective. We propose using deep neural network to classify foci more rapidly and objectively. To obtain datasets, Bhas 42 CTA was conducted with a potent tumor promotor, 12-O-tetradecanoylphorbol-13-acetate, and focus images were classified by experts (1405 images in total). The labeled focus images were augmented with random image processing and used to train a convolutional neural network (CNN). The trained CNN exhibited an area under the curve score of 0.95 on a test dataset significantly outperforming conventional classifiers by beginners of focus judgment. The generalization performance of unknown chemicals was assessed by applying CNN to other tumor promotors exhibiting an area under the curve score of 0.87. The CNN-based approach could support the assay for carcinogenicity as a fundamental tool in focus scoring.

Deep learning-based histopathological segmentation for whole slide images of colorectal cancer in a compressed domain

Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score, the pixel accuracy, and the Jaccard score were 0.804 ± 0.125, 0.957 ± 0.025, and 0.690 ± 0.174, respectively. We can train the networks for the high-resolution image with the large region of interest compared to the result in the low-resolution and the small region of interest in the spatial domain. The average Dice score, pixel accuracy, and Jaccard score are significantly increased by 2.7%, 0.9%, and 2.7%, respectively. We believe that our approach has great potential for accurate diagnosis.

Predicting completion of clinical trials in pregnant women: Cox proportional hazard and neural network models

This study aimed to develop a model for predicting the completion of clinical trials involving pregnant women using the Cox proportional hazard model and neural network model (DeepSurv) and to compare the predictive performance of both methods. We collected data on 819 clinical trials performed on pregnant women and intervention studies using at least one drug as intervention from 2009 to 2018 from ClinicalTrials.gov. The Cox proportional hazard model and DeepSurv were used to develop models that predict clinical trial completion. The concordance index (C‐index) was used to evaluate the predictive performance. The Cox proportional hazard model revealed that a sample size of n ≥ 329 (hazard ratio [HR] = 0.53), very high human development index (HDI) country (HR = 0.28), abortion (HR = 3.30), labor (HR = 2.16), and iron deficiency anemia (HR = 2.29) were significantly related to the probability of clinical trial completion (all p value < 0.01). The C‐index of the model development dataset and test dataset were 0.72 and 0.73, respectively. DeepSurv model consisted of one hidden layer with 16 nodes. DeepSurv showed the C‐index comparable to the Cox proportional hazard model. The C‐index of the training dataset and test dataset were 0.76 and 0.72, respectively. Further a nomogram that calculate a probability of clinical trial completion at 1 year, 3 years, and 5 years was developed. Both the Cox proportional hazard model and DeepSurv yielded sufficient predicting performance. We hope that this study will contribute to the execution of future clinical trials in pregnant women.