Machine learning-based tissue of origin classification for cancer of unknown primary diagnostics using genome-wide mutation features

Image-based deep learning model using DNA methylation data predicts the origin of cancer of unknown primary

Cancer of unknown primary (CUP) is a rare type of metastatic cancer in which the origin of the tumor is unknown. Since the treatment strategy for patients with metastatic tumors depends on knowing the primary site, accurate identification of the origin site is important. Here, we developed an image-based deep-learning model that utilizes a vision transformer algorithm for predicting the origin of CUP. Using DNA methylation dataset of 8,233 primary tumors from The Cancer Genome Atlas (TCGA), we categorized 29 cancer types into 18 organ classes and extracted 2,312 differentially methylated CpG sites (DMCs) from non-squamous cancer group and 420 DMCs from squamous cell cancer group. Using these DMCs, we created organ-specific DNA methylation images and used them for model training and testing. Model performance was evaluated using 394 metastatic cancer samples from TCGA (TCGA-meta) and 995 samples (693 primary and 302 metastatic cancers) obtained from 20 independent external studies. We identified that the DNA methylation image reveals a distinct pattern based on the origin of cancer. Our model achieved an overall accuracy of 96.95 % in the TCGA-meta dataset. In the external validation datasets, our classifier achieved overall accuracies of 96.39 % and 94.37 % in primary and metastatic tumors, respectively. Especially, the overall accuracies for both primary and metastatic samples of non-squamous cell cancer were exceptionally high, with 96.79 % and 96.85 %, respectively.

The evolution of molecular management of carcinoma of unknown primary

PURPOSE OF REVIEW

There is significant need to improve diagnostic and therapeutic options for patients with cancer of unknown primary (CUP). In this review, we discuss the evolving landscape of molecular profiling in CUP.

RECENT FINDINGS

Molecular profiling is becoming accepted into the diagnostic work-up of CUP patients with tumour mutation profiling now described in international CUP guidelines. Although tissue-of-origin (ToO) molecular tests utilising gene-expression and DNA methylation have existed some time, their clinical benefit remains unclear. Novel technologies utilising whole genome sequencing and machine learning algorithms are showing promise in determining ToO, however further research is required prior to clinical application. A recent international clinical trial found patients treated with molecularly-guided therapy based on comprehensive-panel DNA sequencing had improved progression-free survival compared to chemotherapy alone, confirming utility of performing genomic profiling early in the patient journey. Small phase 2 trials have demonstrated that some CUP patients are responsive to immunotherapy, but the best way to select patients for treatment is not clear.

SUMMARY

Management of CUP requires a multifaceted approach incorporating clinical, histopathological, radiological and molecular sequencing results to assist with identifying the likely ToO and clinically actionable genomic alternations. Rapidly identifying a subset of CUP patients who are likely to benefit from site specific therapy, targeted therapy and/or immunotherapy will improve patient outcomes.

Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data

Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor-type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole-genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a data set of 39,787 solid tumors sequenced using a clinically targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivaling the performance of WGS-based methods. GDD-ENS can also guide diagnoses of rare type and cancers of unknown primary and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows could provide clinically relevant tumor-type predictions to guide treatment decisions in real time.

SIGNIFICANCE

We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.

A Deep Learning Model for Cancer Type Prediction Sets a New Standard

SUMMARY

Classifying tumor types using machine learning approaches is not always trivial, particularly for challenging cases such as cancers of unknown primary. In this issue of Cancer Discovery, Darmofal and colleagues describe a new tool that uses information from a clinical sequencing panel to diagnose tumor type, and show that the model is particularly robust. See related article by Darmofal et al., p. 1064 (1).

Classification performance assessment for imbalanced multiclass data

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or Fβ -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction-an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

A cfDNA methylation-based tissue-of-origin classifier for cancers of unknown primary

Cancers of Unknown Primary (CUP) remains a diagnostic and therapeutic challenge due to biological heterogeneity and poor responses to standard chemotherapy. Predicting tissue-of-origin (TOO) molecularly could help refine this diagnosis, with tissue acquisition barriers mitigated via liquid biopsies. However, TOO liquid biopsies are unexplored in CUP cohorts. Here we describe CUPiD, a machine learning classifier for accurate TOO predictions across 29 tumour classes using circulating cell-free DNA (cfDNA) methylation patterns. We tested CUPiD on 143 cfDNA samples from patients with 13 cancer types alongside 27 non-cancer controls, with overall sensitivity of 84.6% and TOO accuracy of 96.8%. In an additional cohort of 41 patients with CUP CUPiD predictions were made in 32/41 (78.0%) cases, with 88.5% of the predictions clinically consistent with a subsequent or suspected primary tumour diagnosis, when available (23/26 patients). Combining CUPiD with cfDNA mutation data demonstrated potential diagnosis re-classification and/or treatment change in this hard-to-treat cancer group.

Optimized whole-genome sequencing workflow for tumor diagnostics in routine pathology practice

Two decades after the genomics revolution, oncology is rapidly transforming into a genome-driven discipline, yet routine cancer diagnostics is still mainly microscopy based, except for tumor type-specific predictive molecular tests. Pathology laboratories struggle to quickly validate and adopt biomarkers identified by genomics studies of new targeted therapies. Consequently, clinical implementation of newly approved biomarkers suffers substantial delays, leading to unequal patient access to these therapies. Whole-genome sequencing (WGS) can successfully address these challenges by providing a stable molecular diagnostic platform that allows detection of a multitude of genomic alterations in a single cost-efficient assay and facilitating rapid implementation, as well as by the development of new genomic biomarkers. Recently, the Whole-genome sequencing Implementation in standard Diagnostics for Every cancer patient (WIDE) study demonstrated that WGS is a feasible and clinically valid technique in routine clinical practice with a turnaround time of 11 workdays. As a result, WGS was successfully implemented at the Netherlands Cancer Institute as part of routine diagnostics in January 2021. The success of implementing WGS has relied on adhering to a comprehensive protocol including recording patient information, sample collection, shipment and storage logistics, sequencing data interpretation and reporting, integration into clinical decision-making and data usage. This protocol describes the use of fresh-frozen samples that are necessary for WGS but can be challenging to implement in pathology laboratories accustomed to using formalin-fixed paraffin-embedded samples. In addition, the protocol outlines key considerations to guide uptake of WGS in routine clinical care in hospitals worldwide.

Automatic origin prediction of liver metastases via hierarchical artificial-intelligence system trained on multiphasic CT data: a retrospective, multicentre study

Background

Currently, the diagnostic testing for the primary origin of liver metastases (LMs) can be laborious, complicating clinical decision-making. Directly classifying the primary origin of LMs at computed tomography (CT) images has proven to be challenging, despite its potential to streamline the entire diagnostic workflow.

Methods

We developed ALMSS, an artificial intelligence (AI)-based LMs screening system, to provide automated liver contrast-enhanced CT analysis for distinguishing LMs from hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC), as well as subtyping primary origin of LMs as six organ systems. We processed a CECT dataset between January 1, 2013 and June 30, 2022 (n = 3105: 840 HCC, 354 ICC, and 1911 LMs) for training and internally testing ALMSS, and two additional cohorts (n = 622) for external validation of its diagnostic performance. The performance of radiologists with and without the assistance of ALMSS in diagnosing and subtyping LMs was assessed.

Findings

ALMSS achieved average area under the curve (AUC) of 0.917 (95% confidence interval [CI]: 0.899-0.931) and 0.923 (95% [CI]: 0.905-0.937) for differentiating LMs, HCC and ICC on both the internal testing set and external testing set, outperformed that of two radiologists. Moreover, ALMSS yielded average AUC of 0.815 (95% [CI]: 0.794-0.836) and 0.818 (95% [CI]: 0.790-0.842) for predicting six primary origins on both two testing sets. Interestingly, ALMSS assigned origin diagnoses for LMs with pathological phenotypes beyond the training categories with average AUC of 0.761 (95% [CI]: 0.657-0.842), which verify the model's diagnostic expandability.

Interpretation

Our study established an AI-based diagnostic system that effectively identifies and characterizes LMs directly from multiphasic CT images.

Funding

National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Medical Image Processing.

The practical utility of AI-assisted molecular profiling in the diagnosis and management of cancer of unknown primary: an updated review

Cancer of unknown primary (CUP) presents a complex diagnostic challenge, characterized by metastatic tumors of unknown tissue origin and a dismal prognosis. This review delves into the emerging significance of artificial intelligence (AI) and machine learning (ML) in transforming the landscape of CUP diagnosis, classification, and treatment. ML approaches, trained on extensive molecular profiling data, have shown promise in accurately predicting tissue of origin. Genomic profiling, encompassing driver mutations and copy number variations, plays a pivotal role in CUP diagnosis by providing insights into tumor type-specific oncogenic alterations. Mutational signatures (MS), reflecting somatic mutation patterns, offer further insights into CUP diagnosis. Known MS with established etiology, such as ultraviolet (UV) light-induced DNA damage and tobacco exposure, have been identified in cases of dedifferentiated/transdifferentiated melanoma and carcinoma. Deep learning models that integrate gene expression data and DNA methylation patterns offer insights into tissue lineage and tumor classification. In digital pathology, machine learning algorithms analyze whole-slide images to aid in CUP classification. Finally, precision oncology, guided by molecular profiling, offers targeted therapies independent of primary tissue identification. Clinical trials assigning CUP patients to molecularly guided therapies, including targetable alterations and tumor mutation burden as an immunotherapy biomarker, have resulted in improved overall survival in a subset of patients. In conclusion, AI- and ML-driven approaches are revolutionizing CUP management by enhancing diagnostic accuracy. Precision oncology utilizing enhanced molecular profiling facilitates the identification of targeted therapies that transcend the need to identify the tissue of origin, ultimately improving patient outcomes.

Toward Explainable Artificial Intelligence for Precision Pathology

The rapid development of precision medicine in recent years has started to challenge diagnostic pathology with respect to its ability to analyze histological images and increasingly large molecular profiling data in a quantitative, integrative, and standardized way. Artificial intelligence (AI) and, more precisely, deep learning technologies have recently demonstrated the potential to facilitate complex data analysis tasks, including clinical, histological, and molecular data for disease classification; tissue biomarker quantification; and clinical outcome prediction. This review provides a general introduction to AI and describes recent developments with a focus on applications in diagnostic pathology and beyond. We explain limitations including the black-box character of conventional AI and describe solutions to make machine learning decisions more transparent with so-called explainable AI. The purpose of the review is to foster a mutual understanding of both the biomedical and the AI side. To that end, in addition to providing an overview of the relevant foundations in pathology and machine learning, we present worked-through examples for a better practical understanding of what AI can achieve and how it should be done.

Cancer as a Disease of Development Gone Awry

In the 160 years since Rudolf Virchow first postulated that neoplasia arises by the same law that regulates embryonic development, scientists have come to recognize the striking overlap between the molecular and cellular programs used by cancers and embryos. Advances in cancer biology and molecular techniques have further highlighted the similarities between carcinogenesis and embryogenesis, where cellular growth, differentiation, motility, and intercellular cross talk are mediated by common drivers and regulatory networks. This review highlights the many connections linking cancer biology and developmental biology to provide a deeper understanding of how a tissue's developmental history may both enable and constrain cancer cell evolution.

New techniques to identify the tissue of origin for cancer of unknown primary in the era of precision medicine: progress and challenges

Despite a standardized diagnostic examination, cancer of unknown primary (CUP) is a rare metastatic malignancy with an unidentified tissue of origin (TOO). Patients diagnosed with CUP are typically treated with empiric chemotherapy, although their prognosis is worse than those with metastatic cancer of a known origin. TOO identification of CUP has been employed in precision medicine, and subsequent site-specific therapy is clinically helpful. For example, molecular profiling, including genomic profiling, gene expression profiling, epigenetics and proteins, has facilitated TOO identification. Moreover, machine learning has improved identification accuracy, and non-invasive methods, such as liquid biopsy and image omics, are gaining momentum. However, the heterogeneity in prediction accuracy, sample requirements and technical fundamentals among the various techniques is noteworthy. Accordingly, we systematically reviewed the development and limitations of novel TOO identification methods, compared their pros and cons and assessed their potential clinical usefulness. Our study may help patients shift from empirical to customized care and improve their prognoses.

Significance of Distinct Liquid Biopsy Compartments in Evaluating Somatic Mutations for Targeted Therapy Selection in Cancer of Unknown Primary

PURPOSE

Cancer of unknown primary (CUP) accounts for 2-5% of all cancer diagnoses, wherein standard investigations fail to reveal the original tumor site. Basket trials allocate targeted therapeutics based on actionable somatic mutations, independent of tumor entity. These trials, however, mostly rely on variants identified in tissue biopsies. Since liquid biopsies (LB) represent the overall tumor genomic landscape, they may provide an ideal diagnostic source in CUP patients. To identify the most informative liquid biopsy compartment, we compared the utility of genomic variant analysis for therapy stratification in two LB compartments (circulating cell-free (cf) and extracellular vesicle (ev) DNA).

METHODS

CfDNA and evDNA from 23 CUP patients were analyzed using a targeted gene panel covering 151 genes. Identified genetic variants were interpreted regarding diagnostic and therapeutic relevance using the MetaKB knowledgebase.

RESULTS

LB revealed a total of 22 somatic mutations in evDNA and/or cfDNA in 11/23 patients. Out of the 22 identified somatic variants, 14 are classified as Tier I druggable somatic variants. Comparison of variants identified in evDNA and cfDNA revealed an overlap of 58% of somatic variants in both LB compartments, whereas over 40% of variants were only found in one or the other compartment.

CONCLUSION

We observed substantial overlap between somatic variants identified in evDNA and cfDNA of CUP patients. Nonetheless, interrogation of both LB compartments can potentially increase the rate of druggable alterations, stressing the significance of liquid biopsies for possible primary-independent basket and umbrella trial inclusion.

Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations

BACKGROUND

Machine learning (ML) represents a powerful tool to capture relationships between molecular alterations and cancer types and to extract biological information. Here, we developed a plain ML model aimed at distinguishing cancer types based on genetic lesions, providing an additional tool to improve cancer diagnosis, particularly for tumors of unknown origin.

METHODS

TCGA data from 9,927 samples spanning 32 different cancer types were downloaded from cBioportal. A vector space model type data transformation technique was designed to build consistently homogeneous new datasets containing, as predictive features, calls for somatic point mutations and copy number variations at chromosome arm-level, thus allowing the use of the XGBoost classifier models. Considering the imbalance in the dataset, due to large difference in the number of cases for each tumor, two preprocessing strategies were considered: i) setting a percentage cut-off threshold to remove less represented cancer types, ii) dividing cancer types into different groups based on biological criteria and training a specific XGBoost model for each of them. The performance of all trained models was mainly assessed by the out-of-sample balanced accuracy (BACC) and the AUC scores.

RESULTS

The XGBoost classifier achieved the best performance (BACC 77%; AUC 97%) on a dataset containing the 10 most represented tumor types. Moreover, dividing the 18 most represented cancers into three different groups (endocrine-related carcinomas, other carcinomas and other cancers),such analysis models achieved 78%, 71% and 86% BACC, respectively, with AUC scores greater than 96%. In addition, the model capable of linking each group to a specific cancer type reached 81% BACC and 94% AUC. Overall, the diagnostic potential of our model was comparable/higher with respect to others already described in literature and based on similar molecular data and ML approaches.

CONCLUSIONS

A boosted ML approach able to accurately discriminate different cancer types was developed. The methodology builds datasets simpler and more interpretable than the original data, while keeping enough information to accurately train standard ML models without resorting to sophisticated Deep Learning architectures. In combination with histopathological examinations, this approach could improve cancer diagnosis by using specific DNA alterations, processed by a replicable and easy-to-use automated technology. The study encourages new investigations which could further increase the classifier's performance, for example by considering more features and dividing tumors into their main molecular subtypes.

Artificial intelligence-based risk stratification, accurate diagnosis and treatment prediction in gynecologic oncology

As data-driven science, artificial intelligence (AI) has paved a promising path toward an evolving health system teeming with thrilling opportunities for precision oncology. Notwithstanding the tremendous success of oncological AI in such fields as lung carcinoma, breast tumor and brain malignancy, less attention has been devoted to investigating the influence of AI on gynecologic oncology. Hereby, this review sheds light on the ever-increasing contribution of state-of-the-art AI techniques to the refined risk stratification and whole-course management of patients with gynecologic tumors, in particular, cervical, ovarian and endometrial cancer, centering on information and features extracted from clinical data (electronic health records), cancer imaging including radiological imaging, colposcopic images, cytological and histopathological digital images, and molecular profiling (genomics, transcriptomics, metabolomics and so forth). However, there are still noteworthy challenges beyond performance validation. Thus, this work further describes the limitations and challenges faced in the real-word implementation of AI models, as well as potential solutions to address these issues.

Deep Learning Model for Tumor Type Prediction using Targeted Clinical Genomic Sequencing Data

Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a dataset of 39,787 solid tumors sequenced using a clinical targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivalling performance of WGS-based methods. GDD-ENS can also guide diagnoses on rare type and cancers of unknown primary, and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows has enabled clinically-relevant tumor type predictions to guide treatment decisions in real time.

Machine learning for genetics-based classification and treatment response prediction in cancer of unknown primary

Cancer of unknown primary (CUP) is a type of cancer that cannot be traced back to its primary site and accounts for 3-5% of all cancers. Established targeted therapies are lacking for CUP, leading to generally poor outcomes. We developed OncoNPC, a machine-learning classifier trained on targeted next-generation sequencing (NGS) data from 36,445 tumors across 22 cancer types from three institutions. Oncology NGS-based primary cancer-type classifier (OncoNPC) achieved a weighted F1 score of 0.942 for high confidence predictions ([Formula: see text]) on held-out tumor samples, which made up 65.2% of all the held-out samples. When applied to 971 CUP tumors collected at the Dana-Farber Cancer Institute, OncoNPC predicted primary cancer types with high confidence in 41.2% of the tumors. OncoNPC also identified CUP subgroups with significantly higher polygenic germline risk for the predicted cancer types and with significantly different survival outcomes. Notably, patients with CUP who received first palliative intent treatments concordant with their OncoNPC-predicted cancers had significantly better outcomes (hazard ratio (HR) = 0.348; 95% confidence interval (CI) = 0.210-0.570; P = [Formula: see text]). Furthermore, OncoNPC enabled a 2.2-fold increase in patients with CUP who could have received genomically guided therapies. OncoNPC thus provides evidence of distinct CUP subgroups and offers the potential for clinical decision support for managing patients with CUP.

Pan-cancer whole-genome comparison of primary and metastatic solid tumours

Metastatic cancer remains an almost inevitably lethal disease1-3. A better understanding of disease progression and response to therapies therefore remains of utmost importance. Here we characterize the genomic differences between early-stage untreated primary tumours and late-stage treated metastatic tumours using a harmonized pan-cancer analysis (or reanalysis) of two unpaired primary4 and metastatic5 cohorts of 7,108 whole-genome-sequenced tumours. Metastatic tumours in general have a lower intratumour heterogeneity and a conserved karyotype, displaying only a modest increase in mutations, although frequencies of structural variants are elevated overall. Furthermore, highly variable tumour-specific contributions of mutational footprints of endogenous (for example, SBS1 and APOBEC) and exogenous mutational processes (for example, platinum treatment) are present. The majority of cancer types had either moderate genomic differences (for example, lung adenocarcinoma) or highly consistent genomic portraits (for example, ovarian serous carcinoma) when comparing early-stage and late-stage disease. Breast, prostate, thyroid and kidney renal clear cell carcinomas and pancreatic neuroendocrine tumours are clear exceptions to the rule, displaying an extensive transformation of their genomic landscape in advanced stages. Exposure to treatment further scars the tumour genome and introduces an evolutionary bottleneck that selects for known therapy-resistant drivers in approximately half of treated patients. Our data showcase the potential of pan-cancer whole-genome analysis to identify distinctive features of late-stage tumours and provide a valuable resource to further investigate the biological basis of cancer and resistance to therapies.

Integrative modeling of tumor genomes and epigenomes for enhanced cancer diagnosis by cell-free DNA

Multi-cancer early detection remains a key challenge in cell-free DNA (cfDNA)-based liquid biopsy. Here, we perform cfDNA whole-genome sequencing to generate two test datasets covering 2125 patient samples of 9 cancer types and 1241 normal control samples, and also a reference dataset for background variant filtering based on 20,529 low-depth healthy samples. An external cfDNA dataset consisting of 208 cancer and 214 normal control samples is used for additional evaluation. Accuracy for cancer detection and tissue-of-origin localization is achieved using our algorithm, which incorporates cancer type-specific profiles of mutation distribution and chromatin organization in tumor tissues as model references. Our integrative model detects early-stage cancers, including those of pancreatic origin, with high sensitivity that is comparable to that of late-stage detection. Model interpretation reveals the contribution of cancer type-specific genomic and epigenomic features. Our methodologies may lay the groundwork for accurate cfDNA-based cancer diagnosis, especially at early stages.

Computational Methods Summarizing Mutational Patterns in Cancer: Promise and Limitations for Clinical Applications

Since the rise of next-generation sequencing technologies, the catalogue of mutations in cancer has been continuously expanding. To address the complexity of the cancer-genomic landscape and extract meaningful insights, numerous computational approaches have been developed over the last two decades. In this review, we survey the current leading computational methods to derive intricate mutational patterns in the context of clinical relevance. We begin with mutation signatures, explaining first how mutation signatures were developed and then examining the utility of studies using mutation signatures to correlate environmental effects on the cancer genome. Next, we examine current clinical research that employs mutation signatures and discuss the potential use cases and challenges of mutation signatures in clinical decision-making. We then examine computational studies developing tools to investigate complex patterns of mutations beyond the context of mutational signatures. We survey methods to identify cancer-driver genes, from single-driver studies to pathway and network analyses. In addition, we review methods inferring complex combinations of mutations for clinical tasks and using mutations integrated with multi-omics data to better predict cancer phenotypes. We examine the use of these tools for either discovery or prediction, including prediction of tumor origin, treatment outcomes, prognosis, and cancer typing. We further discuss the main limitations preventing widespread clinical integration of computational tools for the diagnosis and treatment of cancer. We end by proposing solutions to address these challenges using recent advances in machine learning.

A review and comparative study of cancer detection using machine learning: SBERT and SimCSE application

BACKGROUND

Using visual, biological, and electronic health records data as the sole input source, pretrained convolutional neural networks and conventional machine learning methods have been heavily employed for the identification of various malignancies. Initially, a series of preprocessing steps and image segmentation steps are performed to extract region of interest features from noisy features. Then, the extracted features are applied to several machine learning and deep learning methods for the detection of cancer.

METHODS

In this work, a review of all the methods that have been applied to develop machine learning algorithms that detect cancer is provided. With more than 100 types of cancer, this study only examines research on the four most common and prevalent cancers worldwide: lung, breast, prostate, and colorectal cancer. Next, by using state-of-the-art sentence transformers namely: SBERT (2019) and the unsupervised SimCSE (2021), this study proposes a new methodology for detecting cancer. This method requires raw DNA sequences of matched tumor/normal pair as the only input. The learnt DNA representations retrieved from SBERT and SimCSE will then be sent to machine learning algorithms (XGBoost, Random Forest, LightGBM, and CNNs) for classification. As far as we are aware, SBERT and SimCSE transformers have not been applied to represent DNA sequences in cancer detection settings.

RESULTS

The XGBoost model, which had the highest overall accuracy of 73 ± 0.13 % using SBERT embeddings and 75 ± 0.12 % using SimCSE embeddings, was the best performing classifier. In light of these findings, it can be concluded that incorporating sentence representations from SimCSE's sentence transformer only marginally improved the performance of machine learning models.

From Biology to Diagnosis and Treatment: The Ariadne’s Thread in Cancer of Unknown Primary

Cancer of unknown primary (CUP) encloses a group of heterogeneous tumours, the primary sites for which cannot be identified at the time of diagnosis, despite extensive investigations. CUP has always posed major challenges both in its diagnosis and management, leading to the hypothesis that it is rather a distinct entity with specific genetic and phenotypic aberrations, considering the regression or dormancy of the primary tumour; the development of early, uncommon systemic metastases; and the resistance to therapy. Patients with CUP account for 1–3% of all human malignancies and can be categorised into two prognostic subsets according to their clinicopathologic characteristics at presentation. The diagnosis of CUP mainly depends on the standard evaluation comprising a thorough medical history; complete physical examination; histopathologic morphology and algorithmic immunohistochemistry assessment; and CT scan of the chest, abdomen, and pelvis. However, physicians and patients do not fare well with these criteria and often perform additional time-consuming evaluations to identify the primary tumour site to guide treatment decisions. The development of molecularly guided diagnostic strategies has emerged to complement traditional procedures but has been disappointing thus far. In this review, we present the latest data on CUP regarding the biology, molecular profiling, classification, diagnostic workup, and treatment.

From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment

Machine learning (ML) is increasingly used in clinical oncology to diagnose cancers, predict patient outcomes, and inform treatment planning. Here, we review recent applications of ML across the clinical oncology workflow. We review how these techniques are applied to medical imaging and to molecular data obtained from liquid and solid tumor biopsies for cancer diagnosis, prognosis, and treatment design. We discuss key considerations in developing ML for the distinct challenges posed by imaging and molecular data. Finally, we examine ML models approved for cancer-related patient usage by regulatory agencies and discuss approaches to improve the clinical usefulness of ML.

Cancer Genomics

In the past decade, genomics has fundamentally changed our view of cancer biology, allowing comprehensive analyses of mutations, copy number alterations, structural variants, gene expression and DNA methylation profiles in large-scale studies across different cancer types. Efforts like The Cancer Genome Atlas (TCGA) and the International Cancer Genome Consortium (ICGC) have fostered international collaborations for cancer genomic analyses and have generated public databases that give scientists around the world access to thoroughly curated data, which have been extensively used as a tool for further hypothesis driven research on several aspects of cancer biology. In parallel, some of these findings are being translated into specific clinical benefits for cancer patients. In this review, we provide a brief historical description of the evolution of international public cancer genome projects and related databases, as well as we discuss about their impact on general cancer research.

Chromosomal Instability, Selection and Competition: Factors That Shape the Level of Karyotype Intra-Tumor Heterogeneity

Simple Summary

Each cancer consists of billions of cells. These cells are far from identical; hence, the population of cells that constitute a tumor is heterogeneous. A salient property that varies between cells in a tumor is their karyotype, the number and configuration of the chromosomes. The level of karyotype heterogeneity can be used to predict the survival of a patient. In this review, we describe the processes that shape the level of karyotype heterogeneity in a cancer.

Abstract

Intra-tumor heterogeneity (ITH) is a pan-cancer predictor of survival, with high ITH being correlated to a dismal prognosis. The level of ITH is, hence, a clinically relevant characteristic of a malignancy. ITH of karyotypes is driven by chromosomal instability (CIN). However, not all new karyotypes generated by CIN are viable or competitive, which limits the amount of ITH. Here, we review the cellular processes and ecological properties that determine karyotype ITH. We propose a framework to understand karyotype ITH, in which cells with new karyotypes emerge through CIN, are selected by cell intrinsic and cell extrinsic selective pressures, and propagate through a cancer in competition with other malignant cells. We further discuss how CIN modulates the cell phenotype and immune microenvironment, and the implications this has for the subsequent selection of karyotypes. Together, we aim to provide a comprehensive overview of the biological processes that shape the level of karyotype heterogeneity.