Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer

Visual histological assessment of morphological features reflects the underlying molecular profile in invasive breast cancer: a morphomolecular study

AIMS

Tumour genotype and phenotype are related and can predict outcome. In this study, we hypothesised that the visual assessment of breast cancer (BC) morphological features can provide valuable insight into underlying molecular profiles.

METHODS AND RESULTS

The Cancer Genome Atlas (TCGA) BC cohort was used (n = 743) and morphological features, including Nottingham grade and its components and nucleolar prominence, were assessed utilising whole-slide images (WSIs). Two independent scores were assigned, and discordant cases were utilised to represent cases with intermediate morphological features. Differentially expressed genes (DEGs) were identified for each feature, compared among concordant/discordant cases and tested for specific pathways. Concordant grading was observed in 467 of 743 (63%) of cases. Among concordant case groups, eight common DEGs (UGT8, DDC, RGR, RLBP1, SPRR1B, CXorf49B, PSAPL1 and SPRR2G) were associated with overall tumour grade and its components. These genes are related mainly to cellular proliferation, differentiation and metabolism. The number of DEGs in cases with discordant grading was larger than those identified in concordant cases. The largest number of DEGs was observed in discordant grade 1:3 cases (n = 1185). DEGs were identified for each discordant component. Some DEGs were uniquely associated with well-defined specific morphological features, whereas expression/co-expression of other genes was identified across multiple features and underlined intermediate morphological features.

CONCLUSION

Morphological features are probably related to distinct underlying molecular profiles that drive both morphology and behaviour. This study provides further evidence to support the use of image-based analysis of WSIs, including artificial intelligence algorithms, to predict tumour molecular profiles and outcome.

Piloting a Deep Learning Model for Predicting Nuclear BAP1 Immunohistochemical Expression of Uveal Melanoma from Hematoxylin-and-Eosin Sections

Background

Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. Monosomy 3 and BAP1 mutation are strong prognostic factors predicting metastatic risk in UM. Nuclear BAP1 (nBAP1) expression is a close immunohistochemical surrogate for both genetic alterations. Not all laboratories perform routine BAP1 immunohistochemistry or genetic testing, and rely mainly on clinical information and anatomic/morphologic analyses for UM prognostication. The purpose of our study was to pilot deep learning (DL) techniques to predict nBAP1 expression on whole slide images (WSIs) of hematoxylin and eosin (H&E) stained UM sections.

Methods

One hundred forty H&E-stained UMs were scanned at 40 × magnification, using commercially available WSI image scanners. The training cohort comprised 66 BAP1⁺ and 74 BAP1⁻ UM, with known chromosome 3 status and clinical outcomes. Nonoverlapping areas of three different dimensions (512 × 512, 1024 × 1024, and 2048 × 2048 pixels) for comparison were extracted from tumor regions in each WSI, and were resized to 256 × 256 pixels. Deep convolutional neural networks (Resnet18 pre-trained on Imagenet) and auto-encoder-decoders (U-Net) were trained to predict nBAP1 expression of these patches. Trained models were tested on the patches cropped from a test cohort of WSIs of 16 BAP1⁺ and 28 BAP1⁻ UM cases.

Results

The trained model with best performance achieved area under the curve values of 0.90 for patches and 0.93 for slides on the test set.

Conclusions

Our results show the effectiveness of DL for predicting nBAP1 expression in UM on the basis of H&E sections only.

Translational Relevance

Our pilot demonstrates a high capacity of artificial intelligence-related techniques for automated prediction on the basis of histomorphology, and may be translatable into routine histology laboratories.

Acute myeloid leukemia and artificial intelligence, algorithms and new scores

Artificial intelligence, and more narrowly machine-learning, is beginning to expand humanity's capacity to analyze increasingly large and complex datasets. Advances in computer hardware and software have led to breakthroughs in multiple sectors of our society, including a burgeoning role in medical research and clinical practice. As the volume of medical data grows at an apparently exponential rate, particularly since the human genome project laid the foundation for modern genetic inquiry, informatics tools like machine learning are becoming crucial in analyzing these data to provide meaningful tools for diagnostic, prognostic, and therapeutic purposes. Within medicine, hematologic diseases can be particularly challenging to understand and treat given the increasingly complex and intercalated genetic, epigenetic, immunologic, and regulatory pathways that must be understood to optimize patient outcomes. In acute myeloid leukemia (AML), new developments in machine learning algorithms have enabled a deeper understanding of disease biology and the development of better prognostic and predictive tools. Ongoing work in the field brings these developments incrementally closer to clinical implementation.

Artificial intelligence in gastric cancer: a systematic review

OBJECTIVE

This study aims to systematically review the application of artificial intelligence (AI) techniques in gastric cancer and to discuss the potential limitations and future directions of AI in gastric cancer.

METHODS

A systematic review was performed that follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Pubmed, EMBASE, the Web of Science, and the Cochrane Library were used to search for gastric cancer publications with an emphasis on AI that were published up to June 2020. The terms "artificial intelligence" and "gastric cancer" were used to search for the publications.

RESULTS

A total of 64 articles were included in this review. In gastric cancer, AI is mainly used for molecular bio-information analysis, endoscopic detection for Helicobacter pylori infection, chronic atrophic gastritis, early gastric cancer, invasion depth, and pathology recognition. AI may also be used to establish predictive models for evaluating lymph node metastasis, response to drug treatments, and prognosis. In addition, AI can be used for surgical training, skill assessment, and surgery guidance.

CONCLUSIONS

In the foreseeable future, AI applications can play an important role in gastric cancer management in the era of precision medicine.

Gastric cancer

Gastric cancer is the fifth most common cancer and the third most common cause of cancer death globally. Risk factors for the condition include Helicobacter pylori infection, age, high salt intake, and diets low in fruit and vegetables. Gastric cancer is diagnosed histologically after endoscopic biopsy and staged using CT, endoscopic ultrasound, PET, and laparoscopy. It is a molecularly and phenotypically highly heterogeneous disease. The main treatment for early gastric cancer is endoscopic resection. Non-early operable gastric cancer is treated with surgery, which should include D2 lymphadenectomy (including lymph node stations in the perigastric mesentery and along the celiac arterial branches). Perioperative or adjuvant chemotherapy improves survival in patients with stage 1B or higher cancers. Advanced gastric cancer is treated with sequential lines of chemotherapy, starting with a platinum and fluoropyrimidine doublet in the first line; median survival is less than 1 year. Targeted therapies licensed to treat gastric cancer include trastuzumab (HER2-positive patients first line), ramucirumab (anti-angiogenic second line), and nivolumab or pembrolizumab (anti-PD-1 third line).

Overdiagnosis of melanoma - causes, consequences and solutions

Malignant melanoma is the skin tumor that causes most deaths in Germany. At an early stage, melanoma is well treatable, so early detection is essential. However, the skin cancer screening program in Germany has been criticized because although melanomas have been diagnosed more frequently since introduction of the program, the mortality from malignant melanoma has not decreased. This indicates that the observed increase in melanoma diagnoses be due to overdiagnosis, i.e. to the detection of lesions that would never have created serious health problems for the patients. One of the reasons is the challenging distinction between some benign and malignant lesions. In addition, there may be lesions that are biologically equivocal, and other lesions that are classified as malignant according to current criteria, but that grow so slowly that they would never have posed a threat to patient's life. So far, these "indolent" melanomas cannot be identified reliably due to a lack of biomarkers. Moreover, the likelihood that an in-situ melanoma will progress to an invasive tumor still cannot be determined with any certainty. When benign lesions are diagnosed as melanoma, the consequences are unnecessary psychological and physical stress for the affected patients and incurred therapy costs. Vice versa, underdiagnoses in the sense of overlooked melanomas can adversely affect patients' prognoses and may necessitate more intense therapies. Novel diagnostic options could reduce the number of over- and underdiagnoses and contribute to more objective diagnoses in borderline cases. One strategy that has yielded promising results in pilot studies is the use of artificial intelligence-based diagnostic tools. However, these applications still await translation into clinical and pathological routine.

Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets

Recently, deep learning has unlocked unprecedented success in various domains, especially using images, text, and speech. However, deep learning is only beneficial if the data have nonlinear relationships and if they are exploitable at available sample sizes. We systematically profiled the performance of deep, kernel, and linear models as a function of sample size on UKBiobank brain images against established machine learning references. On MNIST and Zalando Fashion, prediction accuracy consistently improves when escalating from linear models to shallow-nonlinear models, and further improves with deep-nonlinear models. In contrast, using structural or functional brain scans, simple linear models perform on par with more complex, highly parameterized models in age/sex prediction across increasing sample sizes. In sum, linear models keep improving as the sample size approaches ~10,000 subjects. Yet, nonlinearities for predicting common phenotypes from typical brain scans remain largely inaccessible to the examined kernel and deep learning methods.

Predict Ki-67 Positive Cells in H&E-Stained Images Using Deep Learning Independently From IHC-Stained Images

OBJECTIVE

To obtain molecular information in slides directly from H&E staining slides, which apparently display morphological information, to show that some differences in molecular level have already encoded in morphology.

METHODS

In this paper, we selected Ki-67-expression as the representative of molecular information. We proposed a method that can predict Ki-67 positive cells directly from H&E stained slides by a deep convolutional network model. To train this model, we constructed a dataset containing Ki-67 negative or positive cell images and background images. These images were all extracted from H&E stained WSIs and the Ki-67 expression was acquired from the corresponding IHC stained WSIs. The trained model was evaluated both on classification performance and the ability to quantify Ki-67 expression in H&E stained images.

RESULTS

The model achieved an average accuracy of 0.9371 in discrimination of Ki-67 negative cell images, positive cell images and background images. As for evaluation of quantification performance, the correlation coefficient between the quantification results of H&E stained images predicted by our model and that of IHC stained images obtained by color channel filtering is 0.80.

CONCLUSION AND SIGNIFICANCE

Our study indicates that the deep learning model has a good performance both on prediction of Ki-67 positive cells and quantification of Ki-67 expression in cancer samples stained by H&E. More generally, this study shows that deep learning is a powerful tool in exploring the relationship between morphological information and molecular information.

AVAILABILITY AND IMPLEMENTATION

The main program is available at https://github.com/liuyiqing2018/predict_Ki-67_from_HE.

A deep learning model to predict RNA-Seq expression of tumours from whole slide images

Deep learning methods for digital pathology analysis are an effective way to address multiple clinical questions, from diagnosis to prediction of treatment outcomes. These methods have also been used to predict gene mutations from pathology images, but no comprehensive evaluation of their potential for extracting molecular features from histology slides has yet been performed. We show that HE2RNA, a model based on the integration of multiple data modes, can be trained to systematically predict RNA-Seq profiles from whole-slide images alone, without expert annotation. Through its interpretable design, HE2RNA provides virtual spatialization of gene expression, as validated by CD3- and CD20-staining on an independent dataset. The transcriptomic representation learned by HE2RNA can also be transferred on other datasets, even of small size, to increase prediction performance for specific molecular phenotypes. We illustrate the use of this approach in clinical diagnosis purposes such as the identification of tumors with microsatellite instability.

RNA-sequencing of tumour tissue can provide important diagnostic and prognostic information but this is costly and not routinely performed in all clinical settings. Here, the authors show that whole slide histology slides—part of routine care—can be used to predict RNA-sequencing data and thus reduce the need for additional analyses.

Deep learning links histology, molecular signatures and prognosis in cancer

Deep learning can be used to predict genomic alterations based on morphological features learned from digital histopathology. Two independent pan-cancer studies now show that automated learning from digital pathology slides and genomics can potentially decipher broader classes of molecular signatures and prognostic associations across cancer types.

Automated detection algorithm for C4d immunostaining showed comparable diagnostic performance to pathologists in renal allograft biopsy

A deep learning-based image analysis could improve diagnostic accuracy and efficiency in pathology work. Recently, we proposed a deep learning-based detection algorithm for C4d immunostaining in renal allografts. The objective of this study is to assess the diagnostic performance of the algorithm by comparing pathologists' diagnoses and analyzing the associations of the algorithm with clinical data. C4d immunostaining slides of renal allografts were obtained from two different institutions (100 slides from the Asan Medical Center and 86 slides from the Seoul National University Hospital) and scanned using two different slide scanners. Three pathologists and the algorithm independently evaluated each slide according to the Banff 2017 criteria. Subsequently, they jointly reviewed the results for consensus scoring. The result of the algorithm was compared with that of each pathologist and the consensus diagnosis. Clinicopathological associations of the results of the algorithm with allograft survival, histologic evidence of microvascular inflammation, and serologic results for donor-specific antibodies were also analyzed. As a result, the reproducibility between the pathologists was fair to moderate (kappa 0.36-0.54), which is comparable to that between the algorithm and each pathologist (kappa 0.34-0.51). The C4d scores predicted by the algorithm achieved substantial concordance with the consensus diagnosis (kappa = 0.61), and they were significantly associated with remarkable microvascular inflammation (P = 0.001), higher detection rate of donor-specific antibody (P = 0.003), and shorter graft survival (P < 0.001). In conclusion, the deep learning-based C4d detection algorithm showed a diagnostic performance similar to that of the pathologists.

Artificial Intelligence and Mechanistic Modeling for Clinical Decision Making in Oncology

The amount of "big" data generated in clinical oncology, whether from molecular, imaging, pharmacological, or biological origin, brings novel challenges. To mine efficiently this source of information, mathematical models able to produce predictive algorithms and simulations are required, with applications for diagnosis, prognosis, drug development, or prediction of the response to therapy. Such mathematical and computational constructs can be subdivided into two broad classes: biologically agnostic, statistical models using artificial intelligence techniques, and physiologically based, mechanistic models. In this review, recent advances in the applications of such methods in clinical oncology are outlined. These include machine learning applied to big data (omics, imaging, or electronic health records), pharmacometrics and quantitative systems pharmacology, as well as tumor kinetics and metastasis modeling. Focus is set on studies with high potential of clinical translation, and particular attention is given to cancer immunotherapy. Perspectives are given in terms of combinations of the two approaches: "mechanistic learning."

Deep learning in digital pathology image analysis: a survey

Deep learning (DL) has achieved state-of-the-art performance in many digital pathology analysis tasks. Traditional methods usually require hand-crafted domain-specific features, and DL methods can learn representations without manually designed features. In terms of feature extraction, DL approaches are less labor intensive compared with conventional machine learning methods. In this paper, we comprehensively summarize recent DL-based image analysis studies in histopathology, including different tasks (e.g., classification, semantic segmentation, detection, and instance segmentation) and various applications (e.g., stain normalization, cell/gland/region structure analysis). DL methods can provide consistent and accurate outcomes. DL is a promising tool to assist pathologists in clinical diagnosis.

Multiparametric MRI and Whole Slide Image-Based Pretreatment Prediction of Pathological Response to Neoadjuvant Chemoradiotherapy in Rectal Cancer: A Multicenter Radiopathomic Study

Background

The aim of this work is to combine radiological and pathological information of tumor to develop a signature for pretreatment prediction of discrepancies of pathological response at several centers and restage patients with locally advanced rectal cancer (LARC) for individualized treatment planning.

Patients and Methods

A total of 981 consecutive patients with evaluation of response according to tumor regression grade (TRG) who received nCRT were retrospectively recruited from four hospitals (primary cohort and external validation cohort 1–3); both pretreatment multiparametric MRI (mp-MRI) and whole slide image (WSI) of biopsy specimens were available for each patient. Quantitative image features were extracted from mp-MRI and WSI and used to construct a radiopathomics signature (RPS) powered by an artificial-intelligence model. Models based on mp-MRI or WSI alone were also constructed for comparison.

Results

The RPS showed overall accuracy of 79.66–87.66% in validation cohorts. The areas under the curve of RPS at specific response grades were 0.98 (TRG0), 0.93 (≤ TRG1), and 0.84 (≤ TRG2). RPS at each grade of pathological response revealed significant improvement compared with both signatures constructed without combining multiscale tumor information (P < 0.01). Moreover, RPS showed relevance to distinct probabilities of overall survival and disease-free survival in patients with LARC who underwent nCRT (P < 0.05).

Conclusions

The results of this study suggest that radiopathomics, combining both radiological information of the whole tumor and pathological information of local lesions from biopsy, could potentially predict discrepancies of pathological response prior to nCRT for better treatment planning.

Electronic supplementary material

The online version of this article (10.1245/s10434-020-08659-4) contains supplementary material, which is available to authorized users.

Pan-cancer image-based detection of clinically actionable genetic alterations

Molecular alterations in cancer can cause phenotypic changes in tumor cells and their micro-environment. Routine histopathology tissue slides - which are ubiquitously available - can reflect such morphological changes. Here, we show that deep learning can consistently infer a wide range of genetic mutations, molecular tumor subtypes, gene expression signatures and standard pathology biomarkers directly from routine histology. We developed, optimized, validated and publicly released a one-stop-shop workflow and applied it to tissue slides of more than 5000 patients across multiple solid tumors. Our findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and eosin. These predictions generalize to other populations and are spatially resolved. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach could elucidate and quantify genotype-phenotype links in cancer.

A promising approach for screening pulmonary hypertension based on frontal chest radiographs using deep learning: A retrospective study

BACKGROUND

To date, the missed diagnosis rate of pulmonary hypertension (PH) was high, and there has been limited development of a rapid, simple, and effective way to screen the disease. The purpose of this study is to develop a deep learning approach to achieve rapid detection of possible abnormalities in chest radiographs suggesting PH for screening patients suspected of PH.

METHODS

We retrospectively collected frontal chest radiographs and the pulmonary artery systolic pressure (PASP) value measured by Doppler transthoracic echocardiography from 762 patients (357 healthy controls and 405 with PH) from three institutes in China from January 2013 to May 2019. The wohle sample comprised 762 images (641 for training, 80 for internal test, and 41 for external test). We firstly performed a 8-fold cross-validation on the 641 images selected for training (561 for pre-training, 80 for validation), then decided to tune learning rate to 0.0008 according to the best score on validation data. Finally, we used all the pre-training and validation data (561+80 = 641) to train our models (Resnet50, Xception, and Inception V3), evaluated them on internal and external test dataset to classify the images as having manifestations of PH or healthy according to the area under the receiver operating characteristic curve (AUC/ROC). After that, the three deep learning models were further used for prediction of PASP using regression algorithm. Moreover, we invited an experienced chest radiologist to classify the images in the test dataset as having PH or not, and compared the prediction accuracy performed by deep learing models with that of manual classification.

RESULTS

The AUC performed by the best model (Inception V3) achieved 0.970 in the internal test, and slightly declined in the external test (0.967) when using deep learning algorithms to classify PH from normal based on chest X-rays. The mean absolute error (MAE) of the best model for prediction of PASP value was smaller in the internal test (7.45) compared to 9.95 in the external test. Manual classification of PH based on chest X-rays showed much lower AUCs compared to that performed by deep learning models both in the internal and external test.

CONCLUSIONS

The present study used deep learning algorithms to classify abnormalities suggesting PH in chest radiographs with high accuracy and good generalizability. Once tested prospectively in clinical settings, the technology could provide a non-invasive and easy-to-use method to screen patients suspected of having PH.

Automated identification of chest radiographs with referable abnormality with deep learning: need for recalibration

OBJECTIVES

To evaluate the calibration of a deep learning (DL) model in a diagnostic cohort and to improve model's calibration through recalibration procedures.

METHODS

Chest radiographs (CRs) from 1135 consecutive patients (M:F = 582:553; mean age, 52.6 years) who visited our emergency department were included. A commercialized DL model was utilized to identify abnormal CRs, with a continuous probability score for each CR. After evaluation of the model calibration, eight different methods were used to recalibrate the original model based on the probability score. The original model outputs were recalibrated using 681 randomly sampled CRs and validated using the remaining 454 CRs. The Brier score for overall performance, average and maximum calibration error, absolute Spiegelhalter's Z for calibration, and area under the receiver operating characteristic curve (AUROC) for discrimination were evaluated in 1000-times repeated, randomly split datasets.

RESULTS

The original model tended to overestimate the likelihood for the presence of abnormalities, exhibiting average and maximum calibration error of 0.069 and 0.179, respectively; an absolute Spiegelhalter's Z value of 2.349; and an AUROC of 0.949. After recalibration, significant improvements in the average (range, 0.015-0.036) and maximum (range, 0.057-0.172) calibration errors were observed in eight and five methods, respectively. Significant improvement in absolute Spiegelhalter's Z (range, 0.809-4.439) was observed in only one method (the recalibration constant). Discriminations were preserved in six methods (AUROC, 0.909-0.949).

CONCLUSION

The calibration of DL algorithm can be augmented through simple recalibration procedures. Improved calibration may enhance the interpretability and credibility of the model for users.

KEY POINTS

• A deep learning model tended to overestimate the likelihood of the presence of abnormalities in chest radiographs. • Simple recalibration of the deep learning model using output scores could improve the calibration of model while maintaining discrimination. • Improved calibration of a deep learning model may enhance the interpretability and the credibility of the model for users.

Classification of pathogens by Raman spectroscopy combined with generative adversarial networks

Rapid identification of marine pathogens is very important in marine ecology. Artificial intelligence combined with Raman spectroscopy is a promising choice for identifying marine pathogens due to its rapidity and efficiency. However, considering the cost of sample collection and the challenging nature of the experimental environment, only limited spectra are typically available to build a classification model, which hinders qualitative analysis. In this paper, we propose a novel method to classify marine pathogens by means of Raman spectroscopy combined with generative adversarial networks (GANs). Three marine strains, namely, Staphylococcus hominis, Vibrio alginolyticus, and Bacillus licheniformis, were cultured. Using Raman spectroscopy, we acquired 100 spectra of each strain, and we fitted them into GAN models for training. After 30,000 training iterations, the spectra generated by G were similar to the actual spectra, and D was used to test the accuracy of the spectra. Our results demonstrate that our method not only improves the accuracy of machine learning classification but also solves the problem of requiring a large amount of training data. Moreover, we have attempted to find potential identifying regions in the Raman spectra that can be used for reference in subsequent related work in this field. Therefore, this method has tremendous potential to be developed as a tool for pathogen identification.

Current Trends of Artificial Intelligence for Colorectal Cancer Pathology Image Analysis: A Systematic Review

Colorectal cancer (CRC) is one of the most common cancers requiring early pathologic diagnosis using colonoscopy biopsy samples. Recently, artificial intelligence (AI) has made significant progress and shown promising results in the field of medicine despite several limitations. We performed a systematic review of AI use in CRC pathology image analysis to visualize the state-of-the-art. Studies published between January 2000 and January 2020 were searched in major online databases including MEDLINE (PubMed, Cochrane Library, and EMBASE). Query terms included "colorectal neoplasm," "histology," and "artificial intelligence." Of 9000 identified studies, only 30 studies consisting of 40 models were selected for review. The algorithm features of the models were gland segmentation (n = 25, 62%), tumor classification (n = 8, 20%), tumor microenvironment characterization (n = 4, 10%), and prognosis prediction (n = 3, 8%). Only 20 gland segmentation models met the criteria for quantitative analysis, and the model proposed by Ding et al. (2019) performed the best. Studies with other features were in the elementary stage, although most showed impressive results. Overall, the state-of-the-art is promising for CRC pathological analysis. However, datasets in most studies had relatively limited scale and quality for clinical application of this technique. Future studies with larger datasets and high-quality annotations are required for routine practice-level validation.

AI in Medical Imaging Informatics: Current Challenges and Future Directions

This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.

Artificial intelligence and machine learning in nephropathology

Artificial intelligence (AI) for the purpose of this review is an umbrella term for technologies emulating a nephropathologist's ability to extract information on diagnosis, prognosis, and therapy responsiveness from native or transplant kidney biopsies. Although AI can be used to analyze a wide variety of biopsy-related data, this review focuses on whole slide images traditionally used in nephropathology. AI applications in nephropathology have recently become available through several advancing technologies, including (i) widespread introduction of glass slide scanners, (ii) data servers in pathology departments worldwide, and (iii) through greatly improved computer hardware to enable AI training. In this review, we explain how AI can enhance the reproducibility of nephropathology results for certain parameters in the context of precision medicine using advanced architectures, such as convolutional neural networks, that are currently the state of the art in machine learning software for this task. Because AI applications in nephropathology are still in their infancy, we show the power and potential of AI applications mostly in the example of oncopathology. Moreover, we discuss the technological obstacles as well as the current stakeholder and regulatory concerns about developing AI applications in nephropathology from the perspective of nephropathologists and the wider nephrology community. We expect the gradual introduction of these technologies into routine diagnostics and research for selective tasks, suggesting that this technology will enhance the performance of nephropathologists rather than making them redundant.

Artificial intelligence as the next step towards precision pathology

Pathology is the cornerstone of cancer care. The need for accuracy in histopathologic diagnosis of cancer is increasing as personalized cancer therapy requires accurate biomarker assessment. The appearance of digital image analysis holds promise to improve both the volume and precision of histomorphological evaluation. Recently, machine learning, and particularly deep learning, has enabled rapid advances in computational pathology. The integration of machine learning into routine care will be a milestone for the healthcare sector in the next decade, and histopathology is right at the centre of this revolution. Examples of potential high-value machine learning applications include both model-based assessment of routine diagnostic features in pathology, and the ability to extract and identify novel features that provide insights into a disease. Recent groundbreaking results have demonstrated that applications of machine learning methods in pathology significantly improves metastases detection in lymph nodes, Ki67 scoring in breast cancer, Gleason grading in prostate cancer and tumour-infiltrating lymphocyte (TIL) scoring in melanoma. Furthermore, deep learning models have also been demonstrated to be able to predict status of some molecular markers in lung, prostate, gastric and colorectal cancer based on standard HE slides. Moreover, prognostic (survival outcomes) deep neural network models based on digitized HE slides have been demonstrated in several diseases, including lung cancer, melanoma and glioma. In this review, we aim to present and summarize the latest developments in digital image analysis and in the application of artificial intelligence in diagnostic pathology.

DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy

Virulence factors (VFs) enable pathogens to infect their hosts. A wealth of individual, disease-focused studies has identified a wide variety of VFs, and the growing mass of bacterial genome sequence data provides an opportunity for computational methods aimed at predicting VFs. Despite their attractive advantages and performance improvements, the existing methods have some limitations and drawbacks. Firstly, as the characteristics and mechanisms of VFs are continually evolving with the emergence of antibiotic resistance, it is more and more difficult to identify novel VFs using existing tools that were previously developed based on the outdated data sets; secondly, few systematic feature engineering efforts have been made to examine the utility of different types of features for model performances, as the majority of tools only focused on extracting very few types of features. By addressing the aforementioned issues, the accuracy of VF predictors can likely be significantly improved. This, in turn, would be particularly useful in the context of genome wide predictions of VFs. In this work, we present a deep learning (DL)-based hybrid framework (termed DeepVF) that is utilizing the stacking strategy to achieve more accurate identification of VFs. Using an enlarged, up-to-date dataset, DeepVF comprehensively explores a wide range of heterogeneous features with popular machine learning algorithms. Specifically, four classical algorithms, including random forest, support vector machines, extreme gradient boosting and multilayer perceptron, and three DL algorithms, including convolutional neural networks, long short-term memory networks and deep neural networks are employed to train 62 baseline models using these features. In order to integrate their individual strengths, DeepVF effectively combines these baseline models to construct the final meta model using the stacking strategy. Extensive benchmarking experiments demonstrate the effectiveness of DeepVF: it achieves a more accurate and stable performance compared with baseline models on the benchmark dataset and clearly outperforms state-of-the-art VF predictors on the independent test. Using the proposed hybrid ensemble model, a user-friendly online predictor of DeepVF (http://deepvf.erc.monash.edu/) is implemented. Furthermore, its utility, from the user's viewpoint, is compared with that of existing toolkits. We believe that DeepVF will be exploited as a useful tool for screening and identifying potential VFs from protein-coding gene sequences in bacterial genomes.

Label-free, automated classification of microsatellite status in colorectal cancer by infrared imaging

Challenging histopathological diagnostics in cancer include microsatellite instability-high (MSI-H) colorectal cancer (CRC), which occurs in 15% of early-stage CRC and is caused by a deficiency in the mismatch repair system. The diagnosis of MSI-H cannot be reliably achieved by visual inspection of a hematoxylin and eosin stained thin section alone, but additionally requires subsequent molecular analysis. Time- and sample-intensive immunohistochemistry with subsequent fragment length analysis is used. The aim of the presented feasibility study is to test the ability of quantum cascade laser (QCL)-based infrared (IR) imaging as an alternative diagnostic tool for MSI-H in CRC. We analyzed samples from 100 patients with sporadic CRC UICC stage II and III. Forty samples were used to develop the random forest classifier and 60 samples to verify the results on an independent blinded dataset. Specifically, 100% sensitivity and 93% specificity were achieved based on the independent 30 MSI-H- and 30 microsatellite stable (MSS)-patient validation cohort. This showed that QCL-based IR imaging is able to distinguish between MSI-H and MSS for sporadic CRC - a question that goes beyond morphological features - based on the use of spatially resolved infrared spectra used as biomolecular fingerprints.

Deep Learning for the Classification of Small-Cell and Non-Small-Cell Lung Cancer

Reliable entity subtyping is paramount for therapy stratification in lung cancer. Morphological evaluation remains the basis for entity subtyping and directs the application of additional methods such as immunohistochemistry (IHC). The decision of whether to perform IHC for subtyping is subjective, and access to IHC is not available worldwide. Thus, the application of additional methods to support morphological entity subtyping is desirable. Therefore, the ability of convolutional neuronal networks (CNNs) to classify the most common lung cancer subtypes, pulmonary adenocarcinoma (ADC), pulmonary squamous cell carcinoma (SqCC), and small-cell lung cancer (SCLC), was evaluated. A cohort of 80 ADC, 80 SqCC, 80 SCLC, and 30 skeletal muscle specimens was assembled; slides were scanned; tumor areas were annotated; image patches were extracted; and cases were randomly assigned to a training, validation or test set. Multiple CNN architectures (VGG16, InceptionV3, and InceptionResNetV2) were trained and optimized to classify the four entities. A quality control (QC) metric was established. An optimized InceptionV3 CNN architecture yielded the highest classification accuracy and was used for the classification of the test set. Image patch and patient-based CNN classification results were 95% and 100% in the test set after the application of strict QC. Misclassified cases mainly included ADC and SqCC. The QC metric identified cases that needed further IHC for definite entity subtyping. The study highlights the potential and limitations of CNN image classification models for tumor differentiation.

Classification and mutation prediction based on histopathology H&E images in liver cancer using deep learning

Hepatocellular carcinoma (HCC) is the most common subtype of liver cancer, and assessing its histopathological grade requires visual inspection by an experienced pathologist. In this study, the histopathological H&E images from the Genomic Data Commons Databases were used to train a neural network (inception V3) for automatic classification. According to the evaluation of our model by the Matthews correlation coefficient, the performance level was close to the ability of a 5-year experience pathologist, with 96.0% accuracy for benign and malignant classification, and 89.6% accuracy for well, moderate, and poor tumor differentiation. Furthermore, the model was trained to predict the ten most common and prognostic mutated genes in HCC. We found that four of them, including CTNNB1, FMN2, TP53, and ZFX4, could be predicted from histopathology images, with external AUCs from 0.71 to 0.89. The findings demonstrated that convolutional neural networks could be used to assist pathologists in the classification and detection of gene mutation in liver cancer.

Development and Validation of a Deep Learning Model for Non-Small Cell Lung Cancer Survival

IMPORTANCE

There is a lack of studies exploring the performance of a deep learning survival neural network in non-small cell lung cancer (NSCLC).

OBJECTIVES

To compare the performances of DeepSurv, a deep learning survival neural network with a tumor, node, and metastasis staging system in the prediction of survival and test the reliability of individual treatment recommendations provided by the deep learning survival neural network.

DESIGN, SETTING, AND PARTICIPANTS

In this population-based cohort study, a deep learning-based algorithm was developed and validated using consecutive cases of newly diagnosed stages I to IV NSCLC between January 2010 and December 2015 in a Surveillance, Epidemiology, and End Results database. A total of 127 features, including patient characteristics, tumor stage, and treatment strategies, were assessed for analysis. The algorithm was externally validated on an independent test cohort, comprising 1182 patients with stage I to III NSCLC diagnosed between January 2009 and December 2013 in Shanghai Pulmonary Hospital. Analysis began January 2018 and ended June 2019.

MAIN OUTCOMES AND MEASURES

The deep learning survival neural network model was compared with the tumor, node, and metastasis staging system for lung cancer-specific survival. The C statistic was used to assess the performance of models. A user-friendly interface was provided to facilitate the survival predictions and treatment recommendations of the deep learning survival neural network model.

RESULTS

Of 17 322 patients with NSCLC included in the study, 13 361 (77.1%) were white and the median (interquartile range) age was 68 (61-74) years. The majority of tumors were stage I disease (10 273 [59.3%]) and adenocarcinoma (11 985 [69.2%]). The median (interquartile range) follow-up time was 24 (10-43) months. There were 3119 patients who had lung cancer-related death during the follow-up period. The deep learning survival neural network model showed more promising results in the prediction of lung cancer-specific survival than the tumor, node, and metastasis stage on the test data set (C statistic = 0.739 vs 0.706). The population who received the recommended treatments had superior survival rates than those who received treatments not recommended (hazard ratio, 2.99; 95% CI, 2.49-3.59; P < .001), which was verified by propensity score-matched groups. The deep learning survival neural network model visualization was realized by a user-friendly graphic interface.

CONCLUSIONS AND RELEVANCE

The deep learning survival neural network model shows potential benefits in prognostic evaluation and treatment recommendation with respect to lung cancer-specific survival. This novel analytical approach may provide reliable individual survival information and treatment recommendations.

Development and applications of computer image analysis algorithms for scoring of PD-L1 immunohistochemistry

Immune checkpoint inhibitors targeting programmed cell death 1 (PD-1) and programmed cell death ligand 1 (PD-L1) have rapidly become integral to standard-of-care therapy for non-small cell lung cancer and other cancers. Immunohistochemical (IHC) staining of PD-L1 is currently the accepted and approved diagnostic assay for selecting patients for PD-L1/PD-1 axis therapies in certain indications. However, the inherent biological complexity of PD-L1 and the availability of several PD-L1 assays – each with different detection systems, platforms, scoring algorithms and cut-offs – have created challenges to ensure reliable and reproducible results based on subjective visual assessment by pathologists. The increasing adoption of computer technologies into the daily workflow of pathology provides an opportunity to leverage these tools towards improving the clinical value of PD-L1 IHC assays. This review describes several image analysis software programs of computer-aided PD-L1 scoring in the hope of driving further discussion and technological advancement in digital pathology and artificial intelligence approaches, particularly as precision medicine evolves to encompass accurate simultaneous assessment of multiple features of cancer cells and their interactions with the tumor microenvironment.

Circ_0001023 Promotes Proliferation and Metastasis of Gastric Cancer Cells Through miR-409-3p/PHF10 Axis

Background

Circular RNAs (circRNAs) have been well documented to regulate the gene expression via sponging microRNA (miRNA) in diverse neoplasms including gastric cancer (GC).

Methods

In the present study, the expressions of circ_0001023, miR-409-3p, and plant homeodomain finger 10 (PHF10) in GC tissues were detected by qRT-PCR. Chi-square test was performed to analyze the associations between circ_0001023 and pathological parameters. Cell Counting Kit-8 assay, colony formation assay, flow cytometry, and transwell assay were adopted to detect the role of circ_0001023/miR-409-3p axis in the proliferation, apoptosis, and migration of GC cells, respectively. The targeting relationship between circ_0001023 and miR-409-3p was investigated by dual-luciferase gene reporter gene assay. Additionally, subcutaneous xenotransplanted tumor model in nude mice was established to detect the function of circ_0001023 on GC growth in vivo.

Results

Compared with adjacent tissues, the expression of circ_0001023 was significantly upregulated and correlated with lymph node invasion and higher T stage of GC patients. It has also been proved that circ_0001023 could target miR-409-3p. Silencing circ_0001023 can impede the proliferation of GC cells and promote apoptosis, while miR-409-3p inhibitors can partially reverse the biological behavior of GC cells mentioned above. Moreover, the expression of circ_0001023 was reversely associated with miR-409-3p expression but positively correlated with PHF10, a downstream oncogene of miR-409-3p.

Conclusion

Collectively, it is concluded that circ_0001023 promotes the progression of GC via regulating miR-409-3p/PHF10 axis.

Effects of Label Noise on Deep Learning-Based Skin Cancer Classification

Recent studies have shown that deep learning is capable of classifying dermatoscopic images at least as well as dermatologists. However, many studies in skin cancer classification utilize non-biopsy-verified training images. This imperfect ground truth introduces a systematic error, but the effects on classifier performance are currently unknown. Here, we systematically examine the effects of label noise by training and evaluating convolutional neural networks (CNN) with 804 images of melanoma and nevi labeled either by dermatologists or by biopsy. The CNNs are evaluated on a test set of 384 images by means of 4-fold cross validation comparing the outputs with either the corresponding dermatological or the biopsy-verified diagnosis. With identical ground truths of training and test labels, high accuracies with 75.03% (95% CI: 74.39–75.66%) for dermatological and 73.80% (95% CI: 73.10–74.51%) for biopsy-verified labels can be achieved. However, if the CNN is trained and tested with different ground truths, accuracy drops significantly to 64.53% (95% CI: 63.12–65.94%, p < 0.01) on a non-biopsy-verified and to 64.24% (95% CI: 62.66–65.83%, p < 0.01) on a biopsy-verified test set. In conclusion, deep learning methods for skin cancer classification are highly sensitive to label noise and future work should use biopsy-verified training images to mitigate this problem.

Deep Learning Predicts Molecular Subtype of Muscle-invasive Bladder Cancer from Conventional Histopathological Slides

BACKGROUND

Muscle-invasive bladder cancer (MIBC) is the second most common genitourinary malignancy, and is associated with high morbidity and mortality. Recently, molecular subtypes of MIBC have been identified, which have important clinical implications.

OBJECTIVE

In the current study, we tried to predict the molecular subtype of MIBC samples from conventional histomorphology alone using deep learning.

DESIGN, SETTING, AND PARTICIPANTS

Two cohorts of patients with MIBC were used: (1) The Cancer Genome Atlas Urothelial Bladder Carcinoma dataset including 407 patients and (2) our own cohort including 16 patients with treatment-naïve, primary resected MIBC. This resulted in a total of 423 digital whole slide images of tumor tissue to train, validate, and test the deep learning algorithm to predict the molecular subtype.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Various accuracy measurements including the area under the receiver operating characteristic curves were used to evaluate the deep learning model. A sliding window approach to visualize classification was used. Class activation maps were used to identify image features that are most relevant to call a specific class.

RESULTS AND LIMITATIONS

The deep learning model showed great performance in the prediction of the molecular subtype of MIBC patients from hematoxylin and eosin (HE) slides alone-similar to or better than pathology experts. Using different visualization techniques, we identified new histopathological features that were most relevant to our model.

CONCLUSIONS

Deep learning can be used to predict important molecular features in MIBC patients from HE slides alone, potentially improving the clinical management of this disease significantly.

PATIENT SUMMARY

In patients with bladder cancer, a computer program found changes in the appearance of tumor tissue under the microscope and used these to predict genetic alterations. This could potentially benefit patients.

Cell plasticity in cancer: A complex interplay of genetic, epigenetic mechanisms and tumor micro-environment

Cell plasticity, also known as lineage plasticity is defined as the ability of a cell to reprogram and change its phenotype identity. Cell plasticity is context dependent and occurs during the development of an embryo, tissue regeneration, wound healing. However when deregulated and aberrant it also contributes to cancer initiation, progression, metastases and resistance to therapies. Tumors cells exhibit varying forms of cell plasticity in each stage of the disease to evade normal regulation as would have occurred in normal cell division and homeostasis. Current evidence demonstrates complex interplay between the genes, epigenes, tumor microenvironment and the EMT in cell reprogramming and cancer cell plasticity. Herein we present experimental evidence and evolving new developments in cell plasticity in cancer cells. Additionally "Deregulated/aberrant/hijacked cell plasticity" could be considered as an additional hallmark of a cancer. In the future, combining the advances in next generation sequencing and single cell RNA techniques with evolving AI (artificial intelligence) technologies such as deep learning techniques may predict the trajectories of cancer cells and assist in navigating through the complex intricacies of the cancers. A durable, precise, personalized oncologic treatment could be a reality.

Computational analysis of pathological images enables a better diagnosis of TFE3 Xp11.2 translocation renal cell carcinoma

TFE3 Xp11.2 translocation renal cell carcinoma (TFE3-RCC) generally progresses more aggressively compared with other RCC subtypes, but it is challenging to diagnose TFE3-RCC by traditional visual inspection of pathological images. In this study, we collect hematoxylin and eosin- stained histopathology whole-slide images of 74 TFE3-RCC cases (the largest cohort to date) and 74 clear cell RCC cases (ccRCC, the most common RCC subtype) with matched gender and tumor grade. An automatic computational pipeline is implemented to extract image features. Comparative study identifies 52 image features with significant differences between TFE3-RCC and ccRCC. Machine learning models are built to distinguish TFE3-RCC from ccRCC. Tests of the classification models on an external validation set reveal high accuracy with areas under ROC curve ranging from 0.842 to 0.894. Our results suggest that automatically derived image features can capture subtle morphological differences between TFE3-RCC and ccRCC and contribute to a potential guideline for TFE3-RCC diagnosis.

Translocation renal cell carcinoma is an aggressive form of renal cancer that is often misdiagnosed to other subtypes. Here the authors demonstrated that by using machine learning and H&E stained whole-slide images, an accurate diagnose of this particular type of renal cancer can be achieved.

Les cancers colorectaux héréditaires vus par le pathologiste

The pathologist's role in the management of hereditary colorectal cancer is important. The pathologist may suspect a familial cancer when particular morphological and/or clinical criteria are present or give a response to a clinical request in the context of a possible hereditary cancer. In this setting, the pathologist's conclusions have necessarily to be integrated to a precise environment, and if needed, followed by an oncogenetic consultation and a germline mutation research. The aim of this article is to present the main aspects of hereditary colon cancers that a pathologist may see, but also to highlight the histopathological characteristics and the place of the pathologist in the management of these different entities.

Emerging role of deep learning-based artificial intelligence in tumor pathology

The development of digital pathology and progression of state-of-the-art algorithms for computer vision have led to increasing interest in the use of artificial intelligence (AI), especially deep learning (DL)-based AI, in tumor pathology. The DL-based algorithms have been developed to conduct all kinds of work involved in tumor pathology, including tumor diagnosis, subtyping, grading, staging, and prognostic prediction, as well as the identification of pathological features, biomarkers and genetic changes. The applications of AI in pathology not only contribute to improve diagnostic accuracy and objectivity but also reduce the workload of pathologists and subsequently enable them to spend additional time on high-level decision-making tasks. In addition, AI is useful for pathologists to meet the requirements of precision oncology. However, there are still some challenges relating to the implementation of AI, including the issues of algorithm validation and interpretability, computing systems, the unbelieving attitude of pathologists, clinicians and patients, as well as regulators and reimbursements. Herein, we present an overview on how AI-based approaches could be integrated into the workflow of pathologists and discuss the challenges and perspectives of the implementation of AI in tumor pathology.

Deep learning in gastric tissue diseases: a systematic review

Background

In recent years, deep learning has gained remarkable attention in medical image analysis due to its capacity to provide results comparable to specialists and, in some cases, surpass them. Despite the emergence of deep learning research on gastric tissues diseases, few intensive reviews are addressing this topic.

Method

We performed a systematic review related to applications of deep learning in gastric tissue disease analysis by digital histology, endoscopy and radiology images.

Conclusions

This review highlighted the high potential and shortcomings in deep learning research studies applied to gastric cancer, ulcer, gastritis and non-malignant diseases. Our results demonstrate the effectiveness of gastric tissue analysis by deep learning applications. Moreover, we also identified gaps of evaluation metrics, and image collection availability, therefore, impacting experimental reproducibility.

PreMSIm: An R package for predicting microsatellite instability from the expression profiling of a gene panel in cancer

Microsatellite instability (MSI) is a genomic property of the cancers with defective DNA mismatch repair and is a useful marker for cancer diagnosis and treatment in diverse cancer types. In particular, MSI has been associated with the active immune checkpoint blockade therapy response in cancer. Most of computational methods for predicting MSI are based on DNA sequencing data and a few are based on mRNA expression data. Using the RNA-Seq pan-cancer datasets for three cancer cohorts (colon, gastric, and endometrial cancers) from The Cancer Genome Atlas (TCGA) program, we developed an algorithm (PreMSIm) for predicting MSI from the expression profiling of a 15-gene panel in cancer. We demonstrated that PreMSIm had high prediction performance in predicting MSI in most cases using both RNA-Seq and microarray gene expression datasets. Moreover, PreMSIm displayed superior or comparable performance versus other DNA or mRNA-based methods. We conclude that PreMSIm has the potential to provide an alternative approach for identifying MSI in cancer.

Integrated immune gene expression signature and molecular classification in gastric cancer: New insights

Gastric cancer (GC) is characterized by extreme heterogeneity due to histopathological differences, molecular characteristics, and immune gene expression signature. Until recently, several targeted therapies failed due to this complexity. The recent immunotherapy resulted in more effective and safe approaches in several malignancies. All tumors could be considered potentially immunogenic and the new knowledge regarding the interactions among tumor cells, immune cells, and tumor microenvironment (TME) allowed to reverse possible immune resistance. The immune response is a complex multisteps process that finely regulates the balance between the recognition of non-self and the prevention of autoimmunity. Cancer cells can use these pathways to suppress tumor immunity as a major mechanism of immune resistance. The recent molecular classifications of GCs by The Cancer Genome Atlas (TCGA) and by the Asian Cancer Research (ACRG) networks, together with the identification of multiple biomarkers, open new perspectives for stratification of patients who might benefit from a long-term immune checkpoint therapy. One of the major processes that contribute to an immunosuppressive microenvironment is represented by tumor angiogenesis. The cellular mechanisms inducing both angiogenesis and immunosuppressive responses are often reached by the same cell types and soluble factors, such as vascular endothelial growth factor A (VEGFA). Recent studies point out that combinatorial strategies should be adapted as useful therapeutic approach to reverse the immunosuppressive status of microenvironment occurring in a relevant percentage of gastric tumors.

Whole slide images reflect DNA methylation patterns of human tumors

DNA methylation is an important epigenetic mechanism regulating gene expression and its role in carcinogenesis has been extensively studied. High-throughput DNA methylation assays have been used broadly in cancer research. Histopathology images are commonly obtained in cancer treatment, given that tissue sampling remains the clinical gold-standard for diagnosis. In this work, we investigate the interaction between cancer histopathology images and DNA methylation profiles to provide a better understanding of tumor pathobiology at the epigenetic level. We demonstrate that classical machine learning algorithms can associate the DNA methylation profiles of cancer samples with morphometric features extracted from whole slide images. Furthermore, grouping the genes into methylation clusters greatly improves the performance of the models. The well-predicted genes are enriched in key pathways in carcinogenesis including hypoxia in glioma and angiogenesis in renal cell carcinoma. Our results provide new insights into the link between histopathological and molecular data.

Scanning electron microscopy and machine learning reveal heterogeneity in capsular morphotypes of the human pathogen Cryptococcus spp

Phenotypic heterogeneity is an important trait for the development and survival of many microorganisms including the yeast Cryptococcus spp., a deadly pathogen spread worldwide. Here, we have applied scanning electron microscopy (SEM) to define four Cryptococcus spp. capsule morphotypes, namely Regular, Spiky, Bald, and Phantom. These morphotypes were persistently observed in varying proportions among yeast isolates. To assess the distribution of such morphotypes we implemented an automated pipeline capable of (1) identifying potentially cell-associated objects in the SEM-derived images; (2) computing object-level features; and (3) classifying these objects into their corresponding classes. The machine learning approach used a Random Forest (RF) classifier whose overall accuracy reached 85% on the test dataset, with per-class specificity above 90%, and sensitivity between 66 and 94%. Additionally, the RF model indicates that structural and texture features, e.g., object area, eccentricity, and contrast, are most relevant for classification. The RF results agree with the observed variation in these features, consistently also with visual inspection of SEM images. Finally, our work introduces morphological variants of Cryptococcus spp. capsule. These can be promptly identified and characterized using computational models so that future work may unveil morphological associations with yeast virulence.

Precision medicine for human cancers with Notch signaling dysregulation (Review)

NOTCH1, NOTCH2, NOTCH3 and NOTCH4 are transmembrane receptors that transduce juxtacrine signals of the delta‑like canonical Notch ligand (DLL)1, DLL3, DLL4, jagged canonical Notch ligand (JAG)1 and JAG2. Canonical Notch signaling activates the transcription of BMI1 proto‑oncogene polycomb ring finger, cyclin D1, CD44, cyclin dependent kinase inhibitor 1A, hes family bHLH transcription factor 1, hes related family bHLH transcription factor with YRPW motif 1, MYC, NOTCH3, RE1 silencing transcription factor and transcription factor 7 in a cellular context‑dependent manner, while non‑canonical Notch signaling activates NF‑κB and Rac family small GTPase 1. Notch signaling is aberrantly activated in breast cancer, non‑small‑cell lung cancer and hematological malignancies, such as T‑cell acute lymphoblastic leukemia and diffuse large B‑cell lymphoma. However, Notch signaling is inactivated in small‑cell lung cancer and squamous cell carcinomas. Loss‑of‑function NOTCH1 mutations are early events during esophageal tumorigenesis, whereas gain‑of‑function NOTCH1 mutations are late events during T‑cell leukemogenesis and B‑cell lymphomagenesis. Notch signaling cascades crosstalk with fibroblast growth factor and WNT signaling cascades in the tumor microenvironment to maintain cancer stem cells and remodel the tumor microenvironment. The Notch signaling network exerts oncogenic and tumor‑suppressive effects in a cancer stage‑ or (sub)type‑dependent manner. Small‑molecule γ‑secretase inhibitors (AL101, MRK‑560, nirogacestat and others) and antibody‑based biologics targeting Notch ligands or receptors [ABT‑165, AMG 119, rovalpituzumab tesirine (Rova‑T) and others] have been developed as investigational drugs. The DLL3‑targeting antibody‑drug conjugate (ADC) Rova‑T, and DLL3‑targeting chimeric antigen receptor‑modified T cells (CAR‑Ts), AMG 119, are promising anti‑cancer therapeutics, as are other ADCs or CAR‑Ts targeting tumor necrosis factor receptor superfamily member 17, CD19, CD22, CD30, CD79B, CD205, Claudin 18.2, fibroblast growth factor receptor (FGFR)2, FGFR3, receptor‑type tyrosine‑protein kinase FLT3, HER2, hepatocyte growth factor receptor, NECTIN4, inactive tyrosine‑protein kinase 7, inactive tyrosine‑protein kinase transmembrane receptor ROR1 and tumor‑associated calcium signal transducer 2. ADCs and CAR‑Ts could alter the therapeutic framework for refractory cancers, especially diffuse‑type gastric cancer, ovarian cancer and pancreatic cancer with peritoneal dissemination. Phase III clinical trials of Rova‑T for patients with small‑cell lung cancer and a phase III clinical trial of nirogacestat for patients with desmoid tumors are ongoing. Integration of human intelligence, cognitive computing and explainable artificial intelligence is necessary to construct a Notch‑related knowledge‑base and optimize Notch‑targeted therapy for patients with cancer.

Therapeutic Targeting of the Colorectal Tumor Stroma

Colorectal tumors have been classified based on histologic factors, genetic factors, and consensus molecular subtypes, all of which affect the tumor microenvironment. Elements of the tumor microenvironment serve as therapeutic targets and might be used as prognostic factors. For example, immune checkpoint inhibitors are used to treat tumors with microsatellite instability, and anti-angiogenic agents may be used in combination with other drugs to slow or inhibit tumor growth. We review the features of the colorectal tumor stroma that are associated with patient outcomes and discuss potential therapeutic agents that target these features.