Designing deep learning studies in cancer diagnostics

Artificial intelligence-based multi-omics analysis fuels cancer precision medicine

With biotechnological advancements, innovative omics technologies are constantly emerging that have enabled researchers to access multi-layer information from the genome, epigenome, transcriptome, proteome, metabolome, and more. A wealth of omics technologies, including bulk and single-cell omics approaches, have empowered to characterize different molecular layers at unprecedented scale and resolution, providing a holistic view of tumor behavior. Multi-omics analysis allows systematic interrogation of various molecular information at each biological layer while posing tricky challenges regarding how to extract valuable insights from the exponentially increasing amount of multi-omics data. Therefore, efficient algorithms are needed to reduce the dimensionality of the data while simultaneously dissecting the mysteries behind the complex biological processes of cancer. Artificial intelligence has demonstrated the ability to analyze complementary multi-modal data streams within the oncology realm. The coincident development of multi-omics technologies and artificial intelligence algorithms has fuelled the development of cancer precision medicine. Here, we present state-of-the-art omics technologies and outline a roadmap of multi-omics integration analysis using an artificial intelligence strategy. The advances made using artificial intelligence-based multi-omics approaches are described, especially concerning early cancer screening, diagnosis, response assessment, and prognosis prediction. Finally, we discuss the challenges faced in multi-omics analysis, along with tentative future trends in this field. With the increasing application of artificial intelligence in multi-omics analysis, we anticipate a shifting paradigm in precision medicine becoming driven by artificial intelligence-based multi-omics technologies.

Deep learning identifies morphological patterns of homologous recombination deficiency in luminal breast cancers from whole slide images

Homologous recombination DNA-repair deficiency (HRD) is becoming a well-recognized marker of platinum salt and polyADP-ribose polymerase inhibitor chemotherapies in ovarian and breast cancers. While large-scale screening for HRD using genomic markers is logistically and economically challenging, stained tissue slides are routinely acquired in clinical practice. With the objectives of providing a robust deep-learning method for HRD prediction from tissue slides and identifying related morphological phenotypes, we first show that digital pathology workflows are sensitive to potential biases in the training set, then we propose a method to overcome the influence of these biases, and we develop an interpretation method capable of identifying complex phenotypes. Application to our carefully curated in-house dataset allows us to predict HRD with high accuracy (area under the receiver-operator characteristics curve 0.86) and to identify morphological phenotypes related to HRD. In particular, the presence of laminated fibrosis and clear tumor cells associated with HRD open new hypotheses regarding its phenotypic impact.

Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration

Early diagnosis of lung cancer to increase the survival rate, which is currently at a low range of mid-30%, remains a critical need. Despite this, multi-omics data have rarely been applied to non-small-cell lung cancer (NSCLC) diagnosis. We developed a multi-omics data-affinitive artificial intelligence algorithm based on the graph convolutional network that integrates mRNA expression, DNA methylation, and DNA sequencing data. This NSCLC prediction model achieved a 93.7% macro F1-score, indicating that values for false positives and negatives were substantially low, which is desirable for accurate classification. Gene ontology enrichment and pathway analysis of features revealed that two major subtypes of NSCLC, lung adenocarcinoma and lung squamous cell carcinoma, have both specific and common GO biological processes. Numerous biomarkers (i.e., microRNA, long non-coding RNA, differentially methylated regions) were newly identified, whereas some biomarkers were consistent with previous findings in NSCLC (e.g., SPRR1B). Thus, using multi-omics data integration, we developed a promising cancer prediction algorithm.

Unsupervised Learning Composite Network to Reduce Training Cost of Deep Learning Model for Colorectal Cancer Diagnosis

Deep learning facilitates complex medical data analysis and is increasingly being explored in colorectal cancer diagnostics. However, the training cost of the deep learning model limits its real-world medical utility. In this study, we present a composite network that combines deep learning and unsupervised K-means clustering algorithm (RK-net) for automatic processing of medical images. RK-net was more efficient in image refinement compared with manual screening and annotation. The training of a deep learning model for colorectal cancer diagnosis was accelerated by two times with utilization of RK-net-processed images. Better performance was observed in training loss and accuracy achievement as well. RK-net could be useful to refine medical images of the ever-expanding quantity and assist in subsequent construction of the artificial intelligence model.

Application of Artificial Intelligence in Pathology: Trends and Challenges

Given the recent success of artificial intelligence (AI) in computer vision applications, many pathologists anticipate that AI will be able to assist them in a variety of digital pathology tasks. Simultaneously, tremendous advancements in deep learning have enabled a synergy with artificial intelligence (AI), allowing for image-based diagnosis on the background of digital pathology. There are efforts for developing AI-based tools to save pathologists time and eliminate errors. Here, we describe the elements in the development of computational pathology (CPATH), its applicability to AI development, and the challenges it faces, such as algorithm validation and interpretability, computing systems, reimbursement, ethics, and regulations. Furthermore, we present an overview of novel AI-based approaches that could be integrated into pathology laboratory workflows.

Deep Learning in Ischemic Stroke Imaging Analysis: A Comprehensive Review

Ischemic stroke is a cerebrovascular disease with a high morbidity and mortality rate, which poses a serious challenge to human health and life. Meanwhile, the management of ischemic stroke remains highly dependent on manual visual analysis of noncontrast computed tomography (CT) or magnetic resonance imaging (MRI). However, artifacts and noise of the equipment as well as the radiologist experience play a significant role on diagnostic accuracy. To overcome these defects, the number of computer-aided diagnostic (CAD) methods for ischemic stroke is increasing substantially during the past decade. Particularly, deep learning models with massive data learning capabilities are recognized as powerful auxiliary tools for the acute intervention and guiding prognosis of ischemic stroke. To select appropriate interventions, facilitate clinical practice, and improve the clinical outcomes of patients, this review firstly surveys the current state-of-the-art deep learning technology. Then, we summarized the major applications in acute ischemic stroke imaging, particularly in exploring the potential function of stroke diagnosis and multimodal prognostication. Finally, we sketched out the current problems and prospects.

Artificial intelligence for precision medicine in autoimmune liver disease

Autoimmune liver diseases (AiLDs) are rare autoimmune conditions of the liver and the biliary tree with unknown etiology and limited treatment options. AiLDs are inherently characterized by a high degree of complexity, which poses great challenges in understanding their etiopathogenesis, developing novel biomarkers and risk-stratification tools, and, eventually, generating new drugs. Artificial intelligence (AI) is considered one of the best candidates to support researchers and clinicians in making sense of biological complexity. In this review, we offer a primer on AI and machine learning for clinicians, and discuss recent available literature on its applications in medicine and more specifically how it can help to tackle major unmet needs in AiLDs.

Generalization of Deep Learning in Digital Pathology: Experience in Breast Cancer Metastasis Detection

Poor generalizability is a major barrier to clinical implementation of artificial intelligence in digital pathology. The aim of this study was to test the generalizability of a pretrained deep learning model to a new diagnostic setting and to a small change in surgical indication. A deep learning model for breast cancer metastases detection in sentinel lymph nodes, trained on CAMELYON multicenter data, was used as a base model, and achieved an AUC of 0.969 (95% CI 0.926-0.998) and FROC of 0.838 (95% CI 0.757-0.913) on CAMELYON16 test data. On local sentinel node data, the base model performance dropped to AUC 0.929 (95% CI 0.800-0.998) and FROC 0.744 (95% CI 0.566-0.912). On data with a change in surgical indication (axillary dissections) the base model performance indicated an even larger drop with a FROC of 0.503 (95%CI 0.201-0.911). The model was retrained with addition of local data, resulting in about a 4% increase for both AUC and FROC for sentinel nodes, and an increase of 11% in AUC and 49% in FROC for axillary nodes. Pathologist qualitative evaluation of the retrained model´s output showed no missed positive slides. False positives, false negatives and one previously undetected micro-metastasis were observed. The study highlights the generalization challenge even when using a multicenter trained model, and that a small change in indication can considerably impact the model´s performance.

A hitchhiker's guide to cancer models

Cancer is a complex and uniquely personal disease. More than 1.7 million people in the United States are diagnosed with cancer every year. As the burden of cancer grows, so does the need for new, more effective therapeutics and for predictive tools to identify optimal, personalized treatment options for every patient. Cancer models that recapitulate various aspects of the disease are fundamental to making advances along the continuum of cancer treatment from benchside discoveries to bedside delivery. In this review, we use a thought experiment as a vehicle to arrive at four broad categories of cancer models and explore the strengths, weaknesses, opportunities, and threats for each category in advancing our understanding of the disease and improving treatment strategies.

A manifesto on explainability for artificial intelligence in medicine

The rapid increase of interest in, and use of, artificial intelligence (AI) in computer applications has raised a parallel concern about its ability (or lack thereof) to provide understandable, or explainable, output to users. This concern is especially legitimate in biomedical contexts, where patient safety is of paramount importance. This position paper brings together seven researchers working in the field with different roles and perspectives, to explore in depth the concept of explainable AI, or XAI, offering a functional definition and conceptual framework or model that can be used when considering XAI. This is followed by a series of desiderata for attaining explainability in AI, each of which touches upon a key domain in biomedicine.

Deep learning in bladder cancer imaging: A review

Deep learning (DL) is a rapidly developing field in machine learning (ML). The concept of deep learning originates from research on artificial neural networks and is an upgrade of traditional neural networks. It has achieved great success in various domains and has shown potential in solving medical problems, particularly when using medical images. Bladder cancer (BCa) is the tenth most common cancer in the world. Imaging, as a safe, noninvasive, and relatively inexpensive technique, is a powerful tool to aid in the diagnosis and treatment of bladder cancer. In this review, we provide an overview of the latest progress in the application of deep learning to the imaging assessment of bladder cancer. First, we review the current deep learning approaches used for bladder segmentation. We then provide examples of how deep learning helps in the diagnosis, staging, and treatment management of bladder cancer using medical images. Finally, we summarize the current limitations of deep learning and provide suggestions for future improvements.

Can AI predict epithelial lesion categories via automated analysis of cervical biopsies: The TissueNet challenge?

The French Society of Pathology (SFP) organized its first data challenge in 2020 with the help of the Health Data Hub (HDH). The organization of this event first consisted of recruiting nearly 5000 cervical biopsy slides obtained from 20 pathology centers. After ensuring that patients did not refuse to include their slides in the project, the slides were anonymized, digitized, and annotated by expert pathologists, and finally uploaded to a data challenge platform for competitors from around the world. Competing teams had to develop algorithms that could distinguish 4 diagnostic classes in cervical epithelial lesions. Among the many submissions from competitors, the best algorithms achieved an overall score close to 95%. The final part of the competition lasted only 6 weeks, and the goal of SFP and HDH is now to allow for the collection to be published in open access for the scientific community. In this report, we have performed a "post-competition analysis" of the results. We first described the algorithmic pipelines of 3 top competitors. We then analyzed several difficult cases that even the top competitors could not predict correctly. A medical committee of several expert pathologists looked for possible explanations for these erroneous results by reviewing the images, and we present their findings here targeted for a large audience of pathologists and data scientists in the field of digital pathology.

Mapping the literature on the application of artificial intelligence in libraries (AAIL): a scientometric analysis

Purpose

Artificial Intelligence (AI) is an emerging technology and turned into a field of knowledge that has been consistently displacing technologies for a change in human life. It is applied in all spheres of life as reflected in the review of the literature section here. As applicable in the field of libraries too, this study scientifically mapped the papers on AAIL and analyze its growth, collaboration network, trending topics, or research hot spots to highlight the challenges and opportunities in adopting AI-based advancements in library systems and processes.

Design/methodology/approach

The study was developed with a bibliometric approach, considering a decade, 2012 to 2021 for data extraction from a premier database, Scopus. The steps followed are (1) identification, selection of keywords, and forming the search strategy with the approval of a panel of computer scientists and librarians and (2) design and development of a perfect algorithm to verify these selected keywords in title-abstract-keywords of Scopus (3) Performing data processing in some state-of-the-art bibliometric visualization tools, Biblioshiny R and VOSviewer (4) discussing the findings for practical implications of the study and limitations.

Findings

As evident from several papers, not much research has been conducted on AI applications in libraries in comparison to topics like AI applications in cancer, health, medicine, education, and agriculture. As per the Price law, the growth pattern is exponential. The total number of papers relevant to the subject is 1462 (single and multi-authored) contributed by 5400 authors with 0.271 documents per author and around 4 authors per document. Papers occurred mostly in open-access journals. The productive journal is the Journal of Chemical Information and Modelling (NP = 63) while the highly consistent and impactful is the Journal of Machine Learning Research (z-index=63.58 and CPP = 56.17). In the case of authors, J Chen (z-index=28.86 and CPP = 43.75) is the most consistent and impactful author. At the country level, the USA has recorded the highest number of papers positioned at the center of the co-authorship network but at the institutional level, China takes the 1st position. The trending topics of research are machine learning, large dataset, deep learning, high-level languages, etc. The present information system has a high potential to improve if integrated with AI technologies.

Practical implications

The number of scientific papers has increased over time. The evolution of themes like machine learning implicates AI as a broad field of knowledge that converges with other disciplines. The themes like large datasets imply that AI may be applied to analyze and interpret these data and support decision-making in public sector enterprises. Theme named high-level language emerged as a research hotspot which indicated that extensive research has been going on in this area to improve computer systems for facilitating the processing of data with high momentum. These implications are of high strategic worth for policymakers, library stakeholders, researchers and the government as a whole for decision-making.

Originality/value

The analysis of collaboration, prolific authors/journals using consistency factor and CPP, testing the relationship between consistency (z-index) and impact (h-index), using state-of-the-art network visualization and cluster analysis techniques make this study novel and differentiates it from the traditional bibliometric analysis. To the best of the author's knowledge, this work is the first attempt to comprehend the research streams and provide a holistic view of research on the application of AI in libraries. The insights obtained from this analysis are instrumental for both academics and practitioners.

Deep Learning-Based Prediction of Treatment Prognosis from Nasal Polyp Histology Slides

BACKGROUND

Histopathology of nasal polyps contains rich prognostic information, which is difficult to objectively extract. In the present study, we aimed to develop a prognostic indicator of patient outcomes by analyzing scanned conventional haematoxylin and eosin (H&E) -stained slides alone using deep learning.

METHODS

An interpretable supervised deep learning model was developed using 185 H&E-stained whole-slide images (WSIs) of nasal polyps, each from a patient randomly selected from the pool of 232 patients who underwent endoscopic sinus surgery at the First Affiliated Hospital of Sun Yat-sen University (internal cohort). We internally validated the model on a holdout dataset from the internal cohort (47 H&E-stained WSIs) and externally validated the model on 122 H&E-stained WSIs from the Seventh Affiliated Hospital of Sun Yat-sen University and the University of Hong Kong-Shenzhen Hospital (external cohort). A poor prognosis score (PPS) was established to evaluate patient outcomes, and then risk activation mapping was applied to visualize the histopathological features underlying PPS.

RESULTS

The model yielded a patient-level sensitivity of 79.5%, and specificity of 92.3%, with areas under the receiver operating characteristic curve of 0.943, on the multi-center external cohort. The predictive ability of PPS was superior to that of conventional tissue eosinophil number. Notably, eosinophil infiltration, goblet cell hyperplasia, glandular hyperplasia, squamous metaplasia, and fibrin deposition were identified as the main underlying features of PPS.

CONCLUSIONS

Our deep learning model is an effective method for decoding pathological images of nasal polyps, providing a valuable solution for disease prognosis prediction and precise patient treatment. This article is protected by copyright. All rights reserved.

A clinical decision support system optimising adjuvant chemotherapy for colorectal cancers by integrating deep learning and pathological staging markers: a development and validation study

BACKGROUND

The DoMore-v1-CRC marker was recently developed using deep learning and conventional haematoxylin and eosin-stained tissue sections, and was observed to outperform established molecular and morphological markers of patient outcome after primary colorectal cancer resection. The aim of the present study was to develop a clinical decision support system based on DoMore-v1-CRC and pathological staging markers to facilitate individualised selection of adjuvant treatment.

METHODS

We estimated cancer-specific survival in subgroups formed by pathological tumour stage (pT<4 or pT4), pathological nodal stage (pN0, pN1, or pN2), number of lymph nodes sampled (≤12 or >12) if not pN2, and DoMore-v1-CRC classification (good, uncertain, or poor prognosis) in 997 patients with stage II or III colorectal cancer considered to have no residual tumour (R0) from two community-based cohorts in Norway and the UK, and used these data to define three risk groups. An external cohort of 1075 patients with stage II or III R0 colorectal cancer from the QUASAR 2 trial was used for validation; these patients were treated with single-agent capecitabine. The proposed risk stratification system was evaluated using Cox regression analysis. We similarly evaluated a risk stratification system intended to reflect current guidelines and clinical practice. The primary outcome was cancer-specific survival.

FINDINGS

The new risk stratification system provided a hazard ratio of 10·71 (95% CI 6·39-17·93; p<0·0001) for high-risk versus low-risk patients and 3·06 (1·73-5·42; p=0·0001) for intermediate versus low risk in the primary analysis of the validation cohort. Estimated 3-year cancer-specific survival was 97·2% (95% CI 95·1-98·4; n=445 [41%]) for the low-risk group, 94·8% (91·7-96·7; n=339 [32%]) for the intermediate-risk group, and 77·6% (72·1-82·1; n=291 [27%]) for the high-risk group. The guideline-based risk grouping was observed to be less prognostic and informative (the low-risk group comprised only 142 [13%] of the 1075 patients).

INTERPRETATION

Integrating DoMore-v1-CRC and pathological staging markers provided a clinical decision support system that risk stratifies more accurately than its constituent elements, and identifies substantially more patients with stage II and III colorectal cancer with similarly good prognosis as the low-risk group in current guidelines. Avoiding adjuvant chemotherapy in these patients might be safe, and could reduce morbidity, mortality, and treatment costs.

FUNDING

The Research Council of Norway.

Artificial intelligence in histopathology: enhancing cancer research and clinical oncology

Artificial intelligence (AI) methods have multiplied our capabilities to extract quantitative information from digital histopathology images. AI is expected to reduce workload for human experts, improve the objectivity and consistency of pathology reports, and have a clinical impact by extracting hidden information from routinely available data. Here, we describe how AI can be used to predict cancer outcome, treatment response, genetic alterations and gene expression from digitized histopathology slides. We summarize the underlying technologies and emerging approaches, noting limitations, including the need for data sharing and standards. Finally, we discuss the broader implications of AI in cancer research and oncology.

Deep learning-based transcription factor activity for stratification of breast cancer patients

Transcription factors directly bind to DNA and regulate the expression of the gene, causing epigenetic modification of the DNA. They often mediate epigenetic parameters of transcriptional and posttranscriptional mechanisms, and their expression activities can be used to characterize genomic aberrations in cancer cell. In this study, the activity profile of transcription factors inferred by VIPER algorithm. The autoencoder model was applied for compressing the transcription factor activity profile for obtaining more useful transformed features for stratifying patients into two different breast cancer subtypes. The deep learning-based subtypes exhibited superior prognostic value and yielded better risk-stratification than the transcription factor activity-based method. Importantly, according to transformed features, a deep neural network was constructed to predict the subtypes, and achieved the accuracy of 94.98% and area under the ROC curve of 0.9663, respectively. The proposed subtypes were found to be significantly associated with immune infiltration, tumor immunogenicity and so on. Furthermore, the ceRNA network was constructed for the breast cancer subtypes. Besides, 11 master regulators were found to be associated with patients in cluster 1. Given the robustness performance of our deep learning model over multiple breast cancer cohorts, we expected this model may be useful in the area of prognosis prediction and lead some possibility for personalized medicine in breast cancer patients.

Deep learning based low-activity PET reconstruction of [11C]PiB and [18F]FE-PE2I in neurodegenerative disorders

PURPOSE

Positron Emission Tomography (PET) can support a diagnosis of neurodegenerative disorder by identifying disease-specific pathologies. Our aim was to investigate the feasibility of using activity reduction in clinical [¹⁸F]FE-PE2I and [¹¹C]PiB PET/CT scans, simulating low injected activity or scanning time reduction, in combination with AI-assisted denoising.

METHODS

A total of 162 patients with clinically uncertain Alzheimer's disease underwent amyloid [¹¹C]PiB PET/CT and 509 patients referred for clinically uncertain Parkinson's disease underwent dopamine transporter (DAT) [¹⁸F]FE-PE2I PET/CT. Simulated low-activity data were obtained by random sampling of 5% of the events from the list-mode file and a 5% time window extraction in the middle of the scan. A three-dimensional convolutional neural network (CNN) was trained to denoise the resulting PET images for each disease cohort.

RESULTS

Noise reduction of low-activity PET images was successful for both cohorts using 5% of the original activity with improvement in visual quality and all similarity metrics with respect to the ground-truth images. Clinically relevant metrics extracted from the low-activity images deviated <2% compared to ground-truth values, which were not significantly changed when extracting the metrics from the denoised images.

CONCLUSION

The presented models were based on the same network architecture and proved to be a robust tool for denoising brain PET images with two widely different tracer distributions (delocalized, ([¹¹C]PiB, and highly localized, [18F]FE-PE2I). This broad and robust application makes the presented network a good choice for improving the quality of brain images to the level of the standard-activity images without degrading clinical metric extraction. This will allow for reduced dose or scan time in PET/CT to be implemented clinically.

Security Evaluation of Financial and Insurance and Ruin Probability Analysis Integrating Deep Learning Models

To ensure safe development of the financial and insurance industry and promote the continuous growth of the social economy, the theory and its role of deep learning are firstly analyzed. Secondly, the security of financial and insurance and bankruptcy probability are discussed. Finally, an analytical model of the security bankruptcy probability of financial and insurance is designed through a deep learning model, and the model is evaluated comprehensively. The research results manifest that first, the designed security evaluation of the financial and insurance industry based on the deep learning and bankruptcy probability analysis model not only has strong learning ability but also can effectively reduce its own calculation error through short-time learning. Then, by comparing with other models, it is found that the designed model has a stronger ability to control various errors than other models, and the overall error rate of the model can be reduced to about 20%. At last, the data training indicates that the model designed by the deep learning method can accurately and effectively predict the basic situation of the financial and insurance industry, the minimum error can reach 0, and the highest is only about 3. The research provides a technical reference for the development of the financial and insurance industry and contributes to the prosperity of the social economy.

Artificial intelligence in prostate cancer: Definitions, current research, and future directions

Multiple novel modalities tasking artificial intelligence based computational pathology applications and integrating other variables, such as risk factors, tumor microenvironment, genomic testing data, laboratory findings, clinical history, and radiology findings, will improve diagnostic consistency and generate a synergistic diagnostic workflow. In this article, we present the concise and contemporary review on the utilization of artificial intelligence in prostate cancer and identify areas for possible future applications.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

Swarm learning for decentralized artificial intelligence in cancer histopathology

Artificial intelligence (AI) can predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets for which data collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL), in which partners jointly train AI models while avoiding data transfer and monopolistic data governance. Here, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images from over 5,000 patients. We show that AI models trained using SL can predict BRAF mutational status and microsatellite instability directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer. We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States, and validated the prediction performance in two independent datasets from the United Kingdom. Our data show that SL-trained AI models outperform most locally trained models, and perform on par with models that are trained on the merged datasets. In addition, we show that SL-based AI models are data efficient. In the future, SL can be used to train distributed AI models for any histopathology image analysis task, eliminating the need for data transfer.

A decentralized, privacy-preserving machine learning framework used to train a clinically relevant AI system identifies actionable molecular alterations in patients with colorectal cancer by use of routine histopathology slides collected in real-world settings.

Evaluation Analysis of the Nephrotoxicity of Tripterygium wilfordii Preparations with CONSORT Harms Statement Based on Deep Learning

In this paper, the safety of Tripterygium wilfordii polyglycoside (TW) preparation was evaluated by combining literature research and evidence-based evaluation research, so as to provide evidence-based safety information of Tripterygium wilfordii polyglycoside preparation (nephroptosis) for government decision making and clinical application. In this paper, we propose a network structure inspired by the LSTM gate mechanism. All the research methods of the included references are evaluated by internationally recognized evaluation tools or standards. Prevalence was analyzed according to the type of intervention (e.g., time of administration) and route of administration. The results of this experiment provide methods and suggestions for the evaluation of traditional Chinese medicine nephroptosis in the future.

The Essentials of Multiomics

Within the last decade, the science of molecular testing has evolved from single gene and single protein analysis to broad molecular profiling as a standard of care, quickly transitioning from research to practice. Terms such as genomics, transcriptomics, proteomics, circulating omics, and artificial intelligence are now commonplace, and this rapid evolution has left us with a significant knowledge gap within the medical community. In this paper, we attempt to bridge that gap and prepare the physician in oncology for multiomics, a group of technologies that have gone from looming on the horizon to become a clinical reality. The era of multiomics is here, and we must prepare ourselves for this exciting new age of cancer medicine.

The future of artificial intelligence in digital pathology - results of a survey across stakeholder groups

AIMS

Artificial intelligence (AI) provides a powerful tool to extract information from digitized histopathology whole slide images. In the last five years, academic and commercial actors have developed new technical solutions for a diverse set of tasks, including tissue segmentation, cell detection, mutation prediction, prognostication and prediction of treatment response. In the light of limited overall resources, it is presently unclear for researchers, practitioners and policymakers which of these topics are stable enough for clinical use in the near future and which topics are still experimental, but worth investing time and effort into.

METHODS

To identify potentially promising applications of AI in pathology, we performed an anonymous online survey of 75 computational pathology domain experts from academia and industry. Participants enrolled in 2021 were queried about their subjective opinion on promising and appealing sub-fields of computational pathology with a focus on solid tumors.

RESULTS

The results of this survey indicate that the prediction of treatment response directly from routine pathology slides is regarded as the most promising future application. This item was ranked highest in the overall analysis and in sub-groups by age and professional background. Furthermore, prediction of genetic alterations, gene expression and survival directly from routine pathology images scored consistently high across subgroups.

CONCLUSIONS

Together, these data demonstrate a possible direction for the development of computational pathology systems in clinical, academic and industrial research in the near future.

Extracellular matrix in cancer progression and therapy

The tumor ecosystem with heterogeneous cellular compositions and the tumor microenvironment has increasingly become the focus of cancer research in recent years. The extracellular matrix (ECM), the major component of the tumor microenvironment, and its interactions with the tumor cells and stromal cells have also enjoyed tremendously increased attention. Like the other components of the tumor microenvironment, the ECM in solid tumors differs significantly from that in normal organs and tissues. We review recent studies of the complex roles the tumor ECM plays in cancer progression, from tumor initiation, growth to angiogenesis and invasion. We highlight that the biomolecular, biophysical, and mechanochemical interactions between the ECM and cells not only regulate the steps of cancer progression, but also affect the efficacy of systemic cancer treatment. We further discuss the strategies to target and modify the tumor ECM to improve cancer therapy.

Cancer detection from stained biopsies using high-speed spectral imaging

The escalating demand for diagnosing pathological biopsies requires the procedures to be expedited and automated. The existing imaging systems for measuring biopsies only measure color, and even though a lot of effort is invested in deep learning analysis, there are still serious challenges regarding the performance and validity of the data for the intended medical setting. We developed a system that rapidly acquires spectral images from biopsies, followed by spectral classification algorithms. The spectral information is remarkably more informative than the color information, and leads to very high accuracy in identifying cancer cells, as tested on tens of cancer cases. This was improved even more by using artificial intelligence algorithms that required a rather small training set, indicating the high level of information that exists in the spectral images. The most important spectral differences are observed in the nucleus and they are related to aneuploidy in tumor cells. Rapid spectral imaging measurement therefore can bridge the gap in the machine-aided diagnostics of whole biopsies, thus improving patient care, and expediting the treatment procedure.

Artificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application

BACKGROUND

Microsatellite instability (MSI)/mismatch repair deficiency (dMMR) is a key genetic feature which should be tested in every patient with colorectal cancer (CRC) according to medical guidelines. Artificial intelligence (AI) methods can detect MSI/dMMR directly in routine pathology slides, but the test performance has not been systematically investigated with predefined test thresholds.

METHOD

We trained and validated AI-based MSI/dMMR detectors and evaluated predefined performance metrics using nine patient cohorts of 8343 patients across different countries and ethnicities.

RESULTS

Classifiers achieved clinical-grade performance, yielding an area under the receiver operating curve (AUROC) of up to 0.96 without using any manual annotations. Subsequently, we show that the AI system can be applied as a rule-out test: by using cohort-specific thresholds, on average 52.73% of tumors in each surgical cohort [total number of MSI/dMMR = 1020, microsatellite stable (MSS)/ proficient mismatch repair (pMMR) = 7323 patients] could be identified as MSS/pMMR with a fixed sensitivity at 95%. In an additional cohort of N = 1530 (MSI/dMMR = 211, MSS/pMMR = 1319) endoscopy biopsy samples, the system achieved an AUROC of 0.89, and the cohort-specific threshold ruled out 44.12% of tumors with a fixed sensitivity at 95%. As a more robust alternative to cohort-specific thresholds, we showed that with a fixed threshold of 0.25 for all the cohorts, we can rule-out 25.51% in surgical specimens and 6.10% in biopsies.

INTERPRETATION

When applied in a clinical setting, this means that the AI system can rule out MSI/dMMR in a quarter (with global thresholds) or half of all CRC patients (with local fine-tuning), thereby reducing cost and turnaround time for molecular profiling.

Artificial intelligence to identify genetic alterations in conventional histopathology

Precision oncology relies on the identification of targetable molecular alterations in tumor tissues. In many tumor types, a limited set of molecular tests is currently part of standard diagnostic workflows. However, universal testing for all targetable alterations, especially rare ones, is limited by the cost and availability of molecular assays. From 2017 to 2021, multiple studies have shown that artificial intelligence (AI) methods can predict the probability of specific genetic alterations directly from conventional hematoxylin and eosin (H&E) tissue slides. Although these methods are currently less accurate than gold-standard testing (e.g. immunohistochemistry, polymerase chain reaction or next-generation sequencing), they could be used as pre-screening tools to reduce the workload of genetic analyses. In this systematic literature review, we summarize the state of the art in predicting molecular alterations from H&E using AI. We found that AI methods perform reasonably well across multiple tumor types, although few algorithms have been broadly validated. In addition, we found that genetic alterations in FGFR, IDH, PIK3CA, BRAF, TP53 and DNA repair pathways are predictable from H&E in multiple tumor types, while many other genetic alterations have rarely been investigated or were only poorly predictable. Finally, we discuss the next steps for the implementation of AI-based surrogate tests in diagnostic workflows. This article is protected by copyright. All rights reserved.

Human-level COVID-19 diagnosis from low-dose CT scans using a two-stage time-distributed capsule network

Reverse transcription-polymerase chain reaction is currently the gold standard in COVID-19 diagnosis. It can, however, take days to provide the diagnosis, and false negative rate is relatively high. Imaging, in particular chest computed tomography (CT), can assist with diagnosis and assessment of this disease. Nevertheless, it is shown that standard dose CT scan gives significant radiation burden to patients, especially those in need of multiple scans. In this study, we consider low-dose and ultra-low-dose (LDCT and ULDCT) scan protocols that reduce the radiation exposure close to that of a single X-ray, while maintaining an acceptable resolution for diagnosis purposes. Since thoracic radiology expertise may not be widely available during the pandemic, we develop an Artificial Intelligence (AI)-based framework using a collected dataset of LDCT/ULDCT scans, to study the hypothesis that the AI model can provide human-level performance. The AI model uses a two stage capsule network architecture and can rapidly classify COVID-19, community acquired pneumonia (CAP), and normal cases, using LDCT/ULDCT scans. Based on a cross validation, the AI model achieves COVID-19 sensitivity of [Formula: see text], CAP sensitivity of [Formula: see text], normal cases sensitivity (specificity) of [Formula: see text], and accuracy of [Formula: see text]. By incorporating clinical data (demographic and symptoms), the performance further improves to COVID-19 sensitivity of [Formula: see text], CAP sensitivity of [Formula: see text], normal cases sensitivity (specificity) of [Formula: see text] , and accuracy of [Formula: see text]. The proposed AI model achieves human-level diagnosis based on the LDCT/ULDCT scans with reduced radiation exposure. We believe that the proposed AI model has the potential to assist the radiologists to accurately and promptly diagnose COVID-19 infection and help control the transmission chain during the pandemic.

Assessing radiomics feature stability with simulated CT acquisitions

Medical imaging quantitative features had once disputable usefulness in clinical studies. Nowadays, advancements in analysis techniques, for instance through machine learning, have enabled quantitative features to be progressively useful in diagnosis and research. Tissue characterisation is improved via the “radiomics” features, whose extraction can be automated. Despite the advances, stability of quantitative features remains an important open problem. As features can be highly sensitive to variations of acquisition details, it is not trivial to quantify stability and efficiently select stable features. In this work, we develop and validate a Computed Tomography (CT) simulator environment based on the publicly available ASTRA toolbox (www.astra-toolbox.com). We show that the variability, stability and discriminative power of the radiomics features extracted from the virtual phantom images generated by the simulator are similar to those observed in a tandem phantom study. Additionally, we show that the variability is matched between a multi-center phantom study and simulated results. Consequently, we demonstrate that the simulator can be utilised to assess radiomics features’ stability and discriminative power.

Cost-effectiveness of AI for Caries Detection: Randomized Trial

OBJECTIVES

We assessed the cost-effectiveness of AI-supported detection of proximal caries in a randomized controlled clustered cross-over superiority trial.

METHODS

Twenty-three dentists were sampled to assess 20 bitewings; 10 were randomly evaluated supported by an AI-based software (dentalXrai Pro 1.0.4, dentalXrai Ltd, Berlin, Germany) and the other 10 without AI support. The reference test had been established by four independent experts and an additional review. We evaluated the proportion of true and false positive and negative detections and the treatment decisions assigned to each detection (non-invasive, micro-invasive, invasive). Cost-effectiveness was assessed using a mixed public-private-payer perspective in German healthcare. Using the accuracy and treatment decision data from the trial, a Markov simulation model was populated and posterior permanent teeth in initially 31-years old individuals followed over their lifetime. The model allowed extrapolation from the initial detection and therapy to treatment success, re-treatments and, eventually, tooth loss and replacement, capturing long-term effectiveness (tooth retention) and costs (cumulative in Euro). Costs were estimated using the German public and private fee catalogues. Monte-Carlo microsimulations were used and incremental cost-effectiveness at different willingness-to-pay ceiling thresholds assessed.

RESULTS

In the trial, AI-supported detection was significantly more sensitive than detection without AI. However, in the AI group, lesions were more often treated invasively. As a result, AI and no AI showed identical effectiveness (tooth retention for a mean (2.5-97.5%) 49 (48-51)) and nearly identical costs (AI: 330 (250-409) Euro, no AI: 330 (248-410) Euro). 41% simulations found AI and 43% no AI to be more cost-effective. The resulting cost-effectiveness remained uncertain regardless of a payer's willingness-to-pay.

CONCLUSIONS

Higher accuracy of AI did not lead to higher cost-effectiveness, as more invasive treatment approaches generated costs and diminished possible effectiveness advantages.

CLINICAL SIGNIFICANCE

The cost-effectiveness of AI could be improved by supporting not only caries detection, but also subsequent management.

Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis

Accurate early detection of breast and cervical cancer is vital for treatment success. Here, we conduct a meta-analysis to assess the diagnostic performance of deep learning (DL) algorithms for early breast and cervical cancer identification. Four subgroups are also investigated: cancer type (breast or cervical), validation type (internal or external), imaging modalities (mammography, ultrasound, cytology, or colposcopy), and DL algorithms versus clinicians. Thirty-five studies are deemed eligible for systematic review, 20 of which are meta-analyzed, with a pooled sensitivity of 88% (95% CI 85–90%), specificity of 84% (79–87%), and AUC of 0.92 (0.90–0.94). Acceptable diagnostic performance with analogous DL algorithms was highlighted across all subgroups. Therefore, DL algorithms could be useful for detecting breast and cervical cancer using medical imaging, having equivalent performance to human clinicians. However, this tentative assertion is based on studies with relatively poor designs and reporting, which likely caused bias and overestimated algorithm performance. Evidence-based, standardized guidelines around study methods and reporting are required to improve the quality of DL research.

Artificial intelligence in liver diseases: improving diagnostics, prognostics and response prediction

Clinical routine in hepatology involves the diagnosis and treatment of a wide spectrum of metabolic, infectious, autoimmune and neoplastic diseases. Clinicians integrate qualitative and quantitative information from multiple data sources to make a diagnosis, prognosticate the disease course, and recommend a treatment. In the last 5 years, advances in artificial intelligence (AI), particularly in deep learning, have made it possible to extract clinically relevant information from complex and diverse clinical datasets. In particular, histopathology and radiology image data contain diagnostic, prognostic and predictive information which AI can extract. Ultimately, such AI systems could be implemented in clinical routine as decision support tools. However, in the context of hepatology, this requires further large-scale clinical validation and regulatory approval. Herein, we summarise the state of the art in AI in hepatology with a particular focus on histopathology and radiology data. We present a roadmap for the further development of novel biomarkers in hepatology and outline critical obstacles which need to be overcome.

Harnessing multimodal data integration to advance precision oncology

Advances in quantitative biomarker development have accelerated new forms of data-driven insights for patients with cancer. However, most approaches are limited to a single mode of data, leaving integrated approaches across modalities relatively underdeveloped. Multimodal integration of advanced molecular diagnostics, radiological and histological imaging, and codified clinical data presents opportunities to advance precision oncology beyond genomics and standard molecular techniques. However, most medical datasets are still too sparse to be useful for the training of modern machine learning techniques, and significant challenges remain before this is remedied. Combined efforts of data engineering, computational methods for analysis of heterogeneous data and instantiation of synergistic data models in biomedical research are required for success. In this Perspective, we offer our opinions on synthesizing complementary modalities of data with emerging multimodal artificial intelligence methods. Advancing along this direction will result in a reimagined class of multimodal biomarkers to propel the field of precision oncology in the coming decade.

PrACTiC: A Predictive Algorithm for Chemoradiotherapy-Induced Cytopenia in Glioblastoma Patients

Background

Chemotherapy-induced cytopenia is the most frequent side effect of chemoradiotherapy in glioblastoma patients which may lead to reduced delivery of treatment. This study aims to develop a predictive model that is able to forecast the cytopenia induced by temozolomide (TMZ) during concomitant chemoradiotherapy.

Methods

Medical records of 128 patients with newly diagnosed glioblastoma were evaluated to extract the baseline complete blood test before and during the six weeks of chemoradiotherapy to create a dataset for the development of ML models. Using the constructed dataset, different ML algorithms were trained and tested.

Results

Our proposed algorithm achieved accuracies of 85.6%, 88.7%, and 89.3% in predicting thrombocytopenia, lymphopenia, and neutropenia, respectively.

Conclusions

The algorithm designed and developed in this study, called PrACTiC, showed promising results in the accurate prediction of thrombocytopenia, neutropenia, and lymphopenia induced by TMZ in glioblastoma patients. PrACTiC can provide valuable insight for physicians and help them to make the necessary treatment modifications and prevent the toxicities.

Deep Machine Learning for Oral Cancer: From Precise Diagnosis to Precision Medicine

Oral squamous cell carcinoma (OSCC) is one of the most prevalent cancers worldwide and its incidence is on the rise in many populations. The high incidence rate, late diagnosis, and improper treatment planning still form a significant concern. Diagnosis at an early-stage is important for better prognosis, treatment, and survival. Despite the recent improvement in the understanding of the molecular mechanisms, late diagnosis and approach toward precision medicine for OSCC patients remain a challenge. To enhance precision medicine, deep machine learning technique has been touted to enhance early detection, and consequently to reduce cancer-specific mortality and morbidity. This technique has been reported to have made a significant progress in data extraction and analysis of vital information in medical imaging in recent years. Therefore, it has the potential to assist in the early-stage detection of oral squamous cell carcinoma. Furthermore, automated image analysis can assist pathologists and clinicians to make an informed decision regarding cancer patients. This article discusses the technical knowledge and algorithms of deep learning for OSCC. It examines the application of deep learning technology in cancer detection, image classification, segmentation and synthesis, and treatment planning. Finally, we discuss how this technique can assist in precision medicine and the future perspective of deep learning technology in oral squamous cell carcinoma.

The identification of gene signatures in patients with extranodal NK/T-cell lymphoma from a pair of twins

Background

There is no unified treatment standard for patients with extranodal NK/T-cell lymphoma (ENKTL). Cancer neoantigens are the result of somatic mutations and cancer-specific. Increased number of somatic mutations are associated with anti-cancer effects. Screening out ENKTL-specific neoantigens on the surface of cancer cells relies on the understanding of ENKTL mutation patterns. Hence, it is imperative to identify ENKTL-specific genes for ENKTL diagnosis, the discovery of tumor-specific neoantigens and the development of novel therapeutic strategies. We investigated the gene signatures of ENKTL patients.

Methods

We collected the peripheral blood of a pair of twins for sequencing to identify unique variant genes. One of the twins is diagnosed with ENKTL. Seventy samples were analyzed by Robust Multi-array Analysis (RMA). Two methods (elastic net and Support Vector Machine-Recursive Feature Elimination) were used to select unique genes. Next, we performed functional enrichment analysis and pathway enrichment analysis. Then, we conducted single-sample gene set enrichment analysis of immune infiltration and validated the expression of the screened markers with limma packages.

Results

We screened out 126 unique variant genes. Among them, 11 unique genes were selected by the combination of elastic net and Support Vector Machine-Recursive Feature Elimination. Subsequently, GO and KEGG analysis indicated the biological function of identified unique genes. GSEA indicated five immunity-related pathways with high signature scores. In patients with ENKTL and the group with high signature scores, a proportion of functional immune cells are all of great infiltration. We finally found that CDC27, ZNF141, FCGR2C and NES were four significantly differential genes in ENKTL patients. ZNF141, FCGR2C and NES were upregulated in patients with ENKTL, while CDC27 was significantly downregulated.

Conclusion

We identified four ENKTL markers (ZNF141, FCGR2C, NES and CDC27) in patients with extranodal NK/T-cell lymphoma.

Applications of Artificial Intelligence in Pediatric Oncology: A Systematic Review

PURPOSE

There is a need for an improved understanding of clinical and biologic risk factors in pediatric cancer to improve patient outcomes. Machine learning (ML) represents the application of computational inference from advanced statistical methods that can be applied to increasing amount of data available for study in pediatric oncology. The goal of this systematic review was to systematically characterize the state of ML in pediatric oncology and highlight advances and opportunities in the field.

METHODS

We conducted a systematic review of the Embase, Scopus, and MEDLINE databases for applications of ML in pediatric oncology. Query results from all three databases were aggregated and duplicate studies were removed.

RESULTS

A total of 42 unique articles that examined the applications of ML in pediatric oncology met inclusion criteria for review. We identified 20 studies of CNS tumors, 13 of solid tumors, and nine of leukemia. ML tasks included classification, prediction of treatment response, and dose optimization with a variety of methods being used including neural network, k-nearest neighbor, random forest, naive Bayes, and support vector machines. Strengths of the identified studies included matching or outperforming physician comparators via automated analysis and predicting therapeutic response. Common limitations included significant heterogeneity in reporting standards, clinical applicability, small sample sizes, and missing external validation cohorts.

CONCLUSION

We identified areas where ML can enhance clinical care in ways that may not otherwise be achievable. Although ML promises enormous potential in improving diagnostics, decision making, and monitoring for children with cancer, the field remains in early stages and future work will be aided by standards and guidelines to ensure rigorous methodologic design and maximizing clinical utility.

ParsVNN: parsimony visible neural networks for uncovering cancer-specific and drug-sensitive genes and pathways

Prediction of cancer-specific drug responses as well as identification of the corresponding drug-sensitive genes and pathways remains a major biological and clinical challenge. Deep learning models hold immense promise for better drug response predictions, but most of them cannot provide biological and clinical interpretability. Visible neural network (VNN) models have emerged to solve the problem by giving neurons biological meanings and directly casting biological networks into the models. However, the biological networks used in VNNs are often redundant and contain components that are irrelevant to the downstream predictions. Therefore, the VNNs using these redundant biological networks are overparameterized, which significantly limits VNNs' predictive and explanatory power. To overcome the problem, we treat the edges and nodes in biological networks used in VNNs as features and develop a sparse learning framework ParsVNN to learn parsimony VNNs with only edges and nodes that contribute the most to the prediction task. We applied ParsVNN to build cancer-specific VNN models to predict drug response for five different cancer types. We demonstrated that the parsimony VNNs built by ParsVNN are superior to other state-of-the-art methods in terms of prediction performance and identification of cancer driver genes. Furthermore, we found that the pathways selected by ParsVNN have great potential to predict clinical outcomes as well as recommend synergistic drug combinations.

Artificial intelligence for caries detection: Randomized trial

OBJECTIVES

We aimed to assess the impact of an artificial intelligence (AI)-based diagnostic-support software for proximal caries detection on bitewing radiographs.

METHODS

A cluster-randomized cross-over controlled trial was conducted. A commercially available software employing a fully convolutional neural network for caries detection (dentalXrai Pro, dentalXrai Ltd.) was randomly employed by 22 dentists, supporting their caries detection on 20 bitewings randomly chosen from a pool of 140 bitewings, with 10 bitewings randomly being supported by AI and 10 not. The reference test had been established by 4 + 1 independent experts in a pixelwise fashion. Caries was subgrouped as enamel, early dentin and advanced dentin caries, and accuracy and treatment decisions for each caries lesion assessed.

RESULTS

Dentists with AI showed a significantly higher mean (95% CI) area under the Receiver-Operating-Characteristics curve (0.89; 0.87-0.90) than those without AI (0.85; 0.83-0.86; p<0.05), mainly as their sensitivity was significantly higher (0.81; 0.74-0.87 compared with 0.72; 0.64-0.79; p<0.05) while the specificity was not significantly affected (p>0.05). This increase in sensitivity was found for enamel, but not early or advanced dentin lesions. Higher sensitivity came with an increase in non-invasive, but also invasive treatment decisions (p<0.05).

CONCLUSION

AI can increase dentists' diagnostic accuracy but may also increase invasive treatment decisions.

CLINICAL SIGNIFICANCE

AI can increase dentists' diagnostic accuracy, mainly via increasing their sensitivity for detecting enamel lesions, but may also increase invasive therapy decisions. Differences in the effects of AI for different dentists should be explored, and dentists should be guided as to which therapy to choose when detecting caries lesions using AI support.

Detection of Metastatic Tumor Cells in the Bone Marrow Aspirate Smears by Artificial Intelligence (AI)-Based Morphogo System

Introduction

Metastatic carcinomas of bone marrow (MCBM) are characterized as tumors of non-hematopoietic origin spreading to the bone marrow through blood or lymphatic circulation. The diagnosis is critical for tumor staging, treatment selection and prognostic risk stratification. However, the identification of metastatic carcinoma cells on bone marrow aspiration smears is technically challenging by conventional microscopic screening.

Objective

The aim of this study is to develop an automatic recognition system using deep learning algorithms applied to bone marrow cells image analysis. The system takes advantage of an artificial intelligence (AI)-based method in recognizing metastatic atypical cancer clusters and promoting rapid diagnosis.

Methods

We retrospectively reviewed metastatic non-hematopoietic malignancies in bone marrow aspirate smears collected from 60 cases of patients admitted to Zhongshan Hospital. High resolution digital bone marrow aspirate smear images were generated and automatically analyzed by Morphogo AI based system. Morphogo system was trained and validated using 20748 cell cluster images from randomly selected 50 MCBM patients. 5469 pre-classified cell cluster images from the remaining 10 MCBM patients were used to test the recognition performance between Morphogo and experienced pathologists.

Results

Morphogo exhibited a sensitivity of 56.6%, a specificity of 91.3%, and an accuracy of 82.2% in the recognition of metastatic cancer cells. Morphogo’s classification result was in general agreement with the conventional standard in the diagnosis of metastatic cancer clusters, with a Kappa value of 0.513. The test results between Morphogo and pathologists H1, H2 and H3 agreement demonstrated a reliability coefficient of 0.827. The area under the curve (AUC) for Morphogo to diagnose the cancer cell clusters was 0.865.

Conclusion

In patients with clinical history of cancer, the Morphogo system was validated as a useful screening tool in the identification of metastatic cancer cells in the bone marrow aspirate smears. It has potential clinical application in the diagnostic assessment of metastatic cancers for staging and in screening MCBM during morphology examination when the symptoms of the primary site are indolent.