DF-dRVFL: A novel deep feature based classifier for breast mass classification.

Amongst all types of cancer, breast cancer has become one of the most common cancers in the UK threatening millions of people's health. Early detection of breast cancer plays a key role in timely treatment for morbidity reduction. Compared to biopsy, which takes tissues from the lesion for further analysis, image-based methods are less time-consuming and pain-free though they are hampered by lower accuracy due to high false positivity rates. Nevertheless, mammography has become a standard screening method due to its high efficiency and low cost with promising performance. Breast mass, as the most palpable symptom of breast cancer, has received wide attention from the community. As a result, the past decades have witnessed the speeding development of computer-aided systems that are aimed at providing radiologists with useful tools for breast mass analysis based on mammograms. However, the main issues of these systems include low accuracy and require enough computational power on a large scale of datasets. To solve these issues, we developed a novel breast mass classification system called DF-dRVFL. On the public dataset DDSM with more than 3500 images, our best model based on deep random vector functional link network showed promising results through five-cross validation with an averaged AUC of 0.93 and an average accuracy of 81.71%. Compared to sole deep learning based methods, average accuracy has increased by 0.38. Compared with the state-of-the-art methods, our method showed better performance considering the number of images for evaluation and the overall accuracy.

Genome engineering for estrogen receptor mutations reveals differential responses to anti-estrogens and new prognostic gene signatures for breast cancer.

Mutations in the estrogen receptor (ESR1) gene are common in ER-positive breast cancer patients who progress on endocrine therapies. Most mutations localise to just three residues at, or near, the C-terminal helix 12 of the hormone binding domain, at leucine-536, tyrosine-537 and aspartate-538. To investigate these mutations, we have used CRISPR-Cas9 mediated genome engineering to generate a comprehensive set of isogenic mutant breast cancer cell lines. Our results confirm that L536R, Y537C, Y537N, Y537S and D538G mutations confer estrogen-independent growth in breast cancer cells. Growth assays show mutation-specific reductions in sensitivities to drugs representing three classes of clinical anti-estrogens. These differential mutation- and drug-selectivity profiles have implications for treatment choices following clinical emergence of ER mutations. Our results further suggest that mutant expression levels may be determinants of the degree of resistance to some anti-estrogens. Differential gene expression analysis demonstrates up-regulation of estrogen-responsive genes, as expected, but also reveals that enrichment for interferon-regulated gene expression is a common feature of all mutations. Finally, a new gene signature developed from the gene expression profiles in ER mutant cells predicts clinical response in breast cancer patients with ER mutations.

Shallow WGS of individual CTCs identifies actionable targets for informing treatment decisions in metastatic breast cancer.

BACKGROUND: We report copy-number profiling by low-pass WGS (LP-WGS) in individual circulating tumour cells (CTCs) for guiding treatment in patients with metastatic breast cancer (MBC), comparing CTC results with mutations detected in circulating tumour DNA (ctDNA) in the same blood samples. METHODS: Across 10 patients with MBC who were progressing at the time of blood sampling and that had >20 CTCs detected by CellSearch®, 63 single cells (50 CTCs and 13 WBCs) and 16 cell pools (8 CTC pools and 8 WBC pools) were recovered from peripheral blood by CellSearch®/DEPArray™ and sequenced with Ampli1 LowPass technology (Menarini Silicon Biosystems). Copy-number aberrations were identified using the MSBiosuite software platform, and results were compared with mutations detected in matched plasma cfDNA analysed by targeted next-generation sequencing using the Oncomine™ Breast cfDNA Assay (Thermo Fisher). RESULTS: LP-WGS data demonstrated copy-number gains/losses in individual CTCs in regions including FGFR1, JAK2 and CDK6 in five patients, ERBB2 amplification in two HER2-negative patients and BRCA loss in two patients. Seven of eight matched plasmas also had mutations in ctDNA in PIK3CA, TP53, ESR1 and KRAS genes with mutant allele frequencies (MAF) ranging from 0.05 to 33.11%. Combining results from paired CTCs and ctDNA, clinically actionable targets were identified in all ten patients. CONCLUSION: This combined analysis of CTCs and ctDNA may offer a new approach for monitoring of disease progression and to direct therapy in patients with advanced MBC, at a time when they are coming towards the end of other treatment options.

PeMNet for Pectoral Muscle Segmentation.

As an important imaging modality, mammography is considered to be the global gold standard for early detection of breast cancer. Computer-Aided (CAD) systems have played a crucial role in facilitating quicker diagnostic procedures, which otherwise could take weeks if only radiologists were involved. In some of these CAD systems, breast pectoral segmentation is required for breast region partition from breast pectoral muscle for specific analysis tasks. Therefore, accurate and efficient breast pectoral muscle segmentation frameworks are in high demand. Here, we proposed a novel deep learning framework, which we code-named PeMNet, for breast pectoral muscle segmentation in mammography images. In the proposed PeMNet, we integrated a novel attention module called the Global Channel Attention Module (GCAM), which can effectively improve the segmentation performance of Deeplabv3+ using minimal parameter overheads. In GCAM, channel attention maps (CAMs) are first extracted by concatenating feature maps after paralleled global average pooling and global maximum pooling operation. CAMs are then refined and scaled up by multi-layer perceptron (MLP) for elementwise multiplication with CAMs in next feature level. By iteratively repeating this procedure, the global CAMs (GCAMs) are then formed and multiplied elementwise with final feature maps to lead to final segmentation. By doing so, CAMs in early stages of a deep convolution network can be effectively passed on to later stages of the network and therefore leads to better information usage. The experiments on a merged dataset derived from two datasets, INbreast and OPTIMAM, showed that PeMNet greatly outperformed state-of-the-art methods by achieving an IoU of 97.46%, global pixel accuracy of 99.48%, Dice similarity coefficient of 96.30%, and Jaccard of 93.33%, respectively.

Circulating Tumor DNA Profiling From Breast Cancer Screening Through to Metastatic Disease.

PURPOSE: We investigated the utility of the Oncomine Breast cfDNA Assay for detecting circulating tumor DNA (ctDNA) in women from a breast screening population, including healthy women with no abnormality detected by mammogram, and women on follow-up through to advanced breast cancer. MATERIALS AND METHODS: Blood samples were taken from 373 women (127 healthy controls recruited through breast screening, 28 ductal carcinoma in situ, 60 primary breast cancers, 47 primary breast cancer on follow-up, and 111 metastatic breast cancers [MBC]) to recover plasma and germline DNA for analysis with the Oncomine Breast cfDNA Assay on the Ion S5 platform. RESULTS: One hundred sixteen of 373 plasma samples had one or more somatic variants detected across eight of the 10 genes and were called ctDNA-positive; MBC had the highest proportion of ctDNA-positive samples (61; 55%) and healthy controls the lowest (20; 15.7%). ESR1, TP53, and PIK3CA mutations account for 93% of all variants detected and predict poor overall survival in MBC (hazard ratio = 3.461; 95% CI, 1.866 to 6.42; P = .001). Patients with MBC had higher plasma cell-free DNA levels, higher variant allele frequencies, and more polyclonal variants, notably in ESR1 than in all other groups. Only 15 individuals had evidence of potential clonal hematopoiesis of indeterminate potential mutations. CONCLUSION: We were able detect ctDNA across the breast cancer spectrum, notably in MBC where variants in ESR1, TP53, and PIK3CA predicted poor overall survival. The assay could be used to monitor emergence of resistance mutations such as in ESR1 that herald resistance to aromatase inhibitors to tailor adjuvant therapies. However, we suggest caution is needed when interpreting results from a single plasma sample as variants were also detected in a small proportion of HCs.

Improving ductal carcinoma in situ classification by convolutional neural network with exponential linear unit and rank-based weighted pooling.

Ductal carcinoma in situ (DCIS) is a pre-cancerous lesion in the ducts of the breast, and early diagnosis is crucial for optimal therapeutic intervention. Thermography imaging is a non-invasive imaging tool that can be utilized for detection of DCIS and although it has high accuracy (~ 88%), it is sensitivity can still be improved. Hence, we aimed to develop an automated artificial intelligence-based system for improved detection of DCIS in thermographs. This study proposed a novel artificial intelligence based system based on convolutional neural network (CNN) termed CNN-BDER on a multisource dataset containing 240 DCIS images and 240 healthy breast images. Based on CNN, batch normalization, dropout, exponential linear unit and rank-based weighted pooling were integrated, along with L-way data augmentation. Ten runs of tenfold cross validation were chosen to report the unbiased performances. Our proposed method achieved a sensitivity of 94.08 ± 1.22%, a specificity of 93.58 ± 1.49 and an accuracy of 93.83 ± 0.96. The proposed method gives superior performance than eight state-of-the-art approaches and manual diagnosis. The trained model could serve as a visual question answering system and improve diagnostic accuracy.

Comparison of two targeted ultra-deep sequencing technologies for analysis of plasma circulating tumour DNA in endocrine-therapy-resistant breast cancer patients.

PURPOSE: There is growing interest in the application of circulating tumour DNA (ctDNA) as a sensitive tool for monitoring tumour evolution and guiding targeted therapy in patients with cancer. However, robust comparisons of different platform technologies are still required. Here we compared the InVisionSeq™ ctDNA Assay with the Oncomine™ Breast cfDNA Assay to assess their concordance and feasibility for the detection of mutations in plasma at low (< 0.5%) variant allele fraction (VAF). METHODS: Ninety-six plasma samples from 50 patients with estrogen receptor (ER)-positive metastatic breast cancer (mBC) were profiled using the InVision Assay. Results were compared to the Oncomine assay in 30 samples from 26 patients, where there was sufficient material and variants were covered by both assays. Longitudinal samples were analysed for 8 patients with endocrine resistance. RESULTS: We detected alterations in 59/96 samples from 34/50 patients analysed with the InVision assay, most frequently affecting ESR1, PIK3CA and TP53. Complete or partial concordance was found in 28/30 samples analysed by both assays, and VAF values were highly correlated. Excellent concordance was found for most genes, and most discordant calls occurred at VAF < 1%. In longitudinal samples from progressing patients with endocrine resistance, we detected consistent alterations in sequential samples, most commonly in ESR1 and PIK3CA. CONCLUSION: This study shows that both ultra-deep next-generation sequencing (NGS) technologies can detect genomic alternations even at low VAFs in plasma samples of mBC patients. The strong agreement of the technologies indicates sufficient reproducibility for clinical use as prognosic and predictive biomarker.

Patient acceptability of circulating tumour DNA testing in endometrial cancer follow-up.

OBJECTIVE: Circulating tumour DNA (ctDNA) is emerging as a potential option to detect disease recurrence in many cancer types, however, ensuring patient acceptability of changing clinical practice and the introduction of new technology is paramount. METHODS: Patients enrolled in a non-intervention cohort study determining the ability of ctDNA to detect recurrent endometrial cancer (EC) were invited to participate in a semi-structured interview. Analysis was performed by Template Analysis. RESULTS: Eighteen patients were interviewed. A ctDNA blood test was viewed by participants as more physically and psychologically acceptable than clinical examination to monitor for EC recurrence. In particular, participants expressed overwhelming preference for a blood test rather than pelvic examination. Although participants acknowledged that an abnormal ctDNA result could cause anxiety, they expressed a preference to be informed of their results, even if a recurrence was too small to detect radiologically. Explanations for these opinions were a desire for certainty whether their cancer would recur or not, and knowledge would help them be more aware of symptoms that should be reported to their clinician. CONCLUSIONS: ctDNA monitoring to identify EC recurrence appears to be acceptable to patients, and for many, it may be preferable to clinical examination.

ResNet-SCDA-50 for Breast Abnormality Classification.

(Aim) Breast cancer is the most common cancer in women and the second most common cancer worldwide. With the rapid advancement of deep learning, the early stages of breast cancer development can be accurately detected by radiologists with the help of artificial intelligence systems. (Method) Based on mammographic imaging, a mainstream clinical breast screening technique, we present a diagnostic system for accurate classification of breast abnormalities based on ResNet-50. To improve the proposed model, we created a new data augmentation framework called SCDA (Scaling and Contrast limited adaptive histogram equalization Data Augmentation). In its procedure, we first conduct the scaling operation to the original training set, followed by applying contrast limited adaptive histogram equalisation (CLAHE) to the scaled training set. By stacking the training set after SCDA with the original training set, we formed a new training set. The network trained by the augmented training set, was coined as ResNet-SCDA-50. Our system, which aims at a binary classification on mammographic images acquired from INbreast and MINI-MIAS, classifies masses, microcalcification as "abnormal", while normal regions are classified as "normal". (Results) We present the first attempt to use the image contrast enhancement method as the data augmentation method, resulting in an averaged 98.55 percent specificity and 92.83 percent sensitivity, which gives our best model an overall accuracy of 95.74 percent. (Conclusion) Our proposed method is effective in classifying breast abnormality.

Utility of Circulating Tumor DNA for Detection and Monitoring of Endometrial Cancer Recurrence and Progression.

Despite the increasing incidence of endometrial cancer (EC) worldwide and the poor overall survival of patients who recur, no reliable biomarker exists for detecting and monitoring EC recurrence and progression during routine follow-up. Circulating tumor DNA (ctDNA) is a sensitive method for monitoring cancer activity and stratifying patients that are likely to respond to therapy. As a pilot study, we investigated the utility of ctDNA for detecting and monitoring EC recurrence and progression in 13 patients, using targeted next-generation sequencing (tNGS) and personalized ctDNA assays. Using tNGS, at least one somatic mutation at a variant allele frequency (VAF) > 20% was detected in 69% (9/13) of patient tumors. The four patients with no detectable tumor mutations at >20% VAF were whole exome sequenced, with all four harboring mutations in genes not analyzed by tNGS. Analysis of matched and longitudinal plasma DNA revealed earlier detection of EC recurrence and progression and dynamic kinetics of ctDNA levels reflecting treatment response. We also detected acquired high microsatellite instability (MSI-H) in ctDNA from one patient whose primary tumor was MSI stable. Our study suggests that ctDNA analysis could become a useful biomarker for early detection and monitoring of EC recurrence. However, further research is needed to confirm these findings and to explore their potential implications for patient management.

Longitudinal monitoring of circulating tumour DNA improves prognostication and relapse detection in gastroesophageal adenocarcinoma.

BACKGROUND: Gastroesophageal adenocarcinoma (GOA) has poor clinical outcomes and lacks reliable blood markers. Here we present circulating tumour DNA (ctDNA) as an emerging biomarker. METHODS: Forty patients (17 palliative and 23 curative) were followed by serial plasma monitoring. Primary tumour DNA was analysed by targeted next-generation sequencing to identify somatic single-nucleotide variants (SNVs), and Nanostring nCounter® to detect copy number alterations (CNAs). Patient-specific SNVs and CNA amplifications (CNAamp) were analysed in plasma using digital droplet PCR and quantitative PCR, respectively. RESULTS: Thirty-five patients (13 palliative, 22 curative) had ≥1 SNVs and/or CNAamp detected in primary tumour DNA suitable for tracking in plasma. Eighteen of 35 patients (nine palliative, nine curative) had ≥1 ctDNA-positive plasma sample. Detection of postoperative ctDNA predicted short RFS (190 vs 934 days, HR = 3.7, p = 0.028) and subsequent relapse (PPV for relapse 0.83). High ctDNA levels (>60.5 copies/ml) at diagnosis of metastatic disease predicted poor OS (90 vs 372 days, HR = 11.7 p < 0.001). CONCLUSION: Sensitive ctDNA detection allows disease monitoring and prediction of short OS in metastatic patients. Presence of ctDNA postoperatively predicts relapse and defines a 'molecular relapse' before overt clinical disease. This lead time defines a potential therapeutic window for additional anticancer therapy.

Differences in the molecular profile of endometrial cancers from British White and British South Asian women.

OBJECTIVES: To identify differences in the mutational profile of endometrial tumours between British White (BW) and South Asian (BSA) women. METHODS: We analysed primary tumours from matched cohorts of British White (BW) and British South Asian (BSA) women resident in Leicestershire diagnosed with EC. Next Generation Sequencing was performed to investigate mutational differences in a panel of 10 genes previously identified as being commonly mutated in EC. The presence of somatic Mismatch Repair (MMR) gene deficiencies was determined by immunohistochemistry. RESULTS: In total, 57 tumours (27 BSA and 30 BW) were sequenced. There was no significant difference in the overall mutation frequency of the 10 genes analysed; however, numerous differences were observed between the groups. There was a positive association between PIK3CA and PTEN mutations in the BSA group, with 78% of PIK3CA-mutant tumours harbouring a PTEN mutation, whereas only 11% of PIK3CA wild-type (wt) tumours were PTEN mutant positive (p = 0.0012). In BW women, 90% of ARID1A mutant tumours had co-existent PI3K pathway mutations versus 50% of wild-type (wt) ARID1A patients (p = 0.0485). This trend was not significant in the BSA group (p = 0.66). The age at diagnosis was significantly higher in the BW group with a somatic MMR gene deficiency compared to those with no deficiency (72.8 years versus 59.6 years, p = 0.007), whereas this difference was not seen in the BSA group (64 years versus 60 years, p = 0.37). CONCLUSION: We have identified differences in the mutational profile of primary EC tumours from BW and BSA women. Further research is needed to confirm these findings and to explore their potential implications for early detection, treatment response and prognosis.

Plasma cell-free DNA (cfDNA) as a predictive and prognostic marker in patients with metastatic breast cancer.

BACKGROUND: Breast cancer (BC) is the most common cancer in women, and despite the introduction of new screening programmes, therapies and monitoring technologies, there is still a need to develop more useful tests for monitoring treatment response and to inform clinical decision making. The purpose of this study was to compare circulating cell-free DNA (cfDNA) and circulating tumour cells (CTCs) with conventional breast cancer blood biomarkers (CA15-3 and alkaline phosphatase (AP)) as predictors of response to treatment and prognosis in patients with metastatic breast cancer (MBC). METHODS: One hundred ninety-four female patients with radiologically confirmed MBC were recruited to the study. Total cfDNA levels were determined by qPCR and compared with CELLSEARCH® CTC counts and CA15-3 and alkaline phosphatase (AP) values. Blood biomarker data were compared with conventional tumour markers, treatment(s) and response as assessed by RECIST and survival. Non-parametric statistical hypothesis tests were used to examine differences, correlation analysis and linear regression to determine correlation and to describe its effects, logistic regression and receiver operating characteristic curve (ROC curve) to estimate the strength of the relationship between biomarkers and clinical outcomes and value normalization against standard deviation to make biomarker values comparable. Kaplan-Meier estimator and Cox regression models were used to assess survival. Univariate and multivariate models were performed where appropriate. RESULTS: Multivariate analysis showed that both the amount of total cfDNA (p value = 0.024, HR = 1.199, CI = 1.024-1.405) and the number of CTCs (p value = 0.001, HR = 1.243, CI = 1.088-1.421) are predictors of overall survival (OS), whereas total cfDNA levels is the sole predictor for progression-free survival (PFS) (p value = 0.042, HR = 1.193, CI = 1.007-1.415) and disease response when comparing response to non-response to treatment (HR = 15.917, HR = 12.481 for univariate and multivariate analysis, respectively). Lastly, combined analysis of CTCs and cfDNA is more informative than the combination of two conventional biomarkers (CA15-3 and AP) for prediction of OS. CONCLUSION: Measurement of total cfDNA levels, which is a simpler and less expensive biomarker than CTC counts, is associated with PFS, OS and response in MBC, suggesting potential clinical application of a cheap and simple blood-based test.

Personalized Detection of Circulating Tumor DNA Antedates Breast Cancer Metastatic Recurrence.

PURPOSE: Up to 30% of patients with breast cancer relapse after primary treatment. There are no sensitive and reliable tests to monitor these patients and detect distant metastases before overt recurrence. Here, we demonstrate the use of personalized circulating tumor DNA (ctDNA) profiling for detection of recurrence in breast cancer. EXPERIMENTAL DESIGN: Forty-nine primary patients with breast cancer were recruited following surgery and adjuvant therapy. Plasma samples (n = 208) were collected every 6 months for up to 4 years. Personalized assays targeting 16 variants selected from primary tumor whole-exome data were tested in serial plasma for the presence of ctDNA by ultradeep sequencing (average >100,000X). RESULTS: Plasma ctDNA was detected ahead of clinical or radiologic relapse in 16 of the 18 relapsed patients (sensitivity of 89%); metastatic relapse was predicted with a lead time of up to 2 years (median, 8.9 months; range, 0.5-24.0 months). None of the 31 nonrelapsing patients were ctDNA-positive at any time point across 156 plasma samples (specificity of 100%). Of the two relapsed patients who were not detected in the study, the first had only a local recurrence, whereas the second patient had bone recurrence and had completed chemotherapy just 13 days prior to blood sampling. CONCLUSIONS: This study demonstrates that patient-specific ctDNA analysis can be a sensitive and specific approach for disease surveillance for patients with breast cancer. More importantly, earlier detection of up to 2 years provides a possible window for therapeutic intervention.

Circulating tumor DNA in patients with colorectal adenomas: assessment of detectability and genetic heterogeneity.

Improving early detection of colorectal cancer (CRC) is a key public health priority as adenomas and stage I cancer can be treated with minimally invasive procedures. Population screening strategies based on detection of occult blood in the feces have contributed to enhance detection rates of localized disease, but new approaches based on genetic analyses able to increase specificity and sensitivity could provide additional advantages compared to current screening methodologies. Recently, circulating cell-free DNA (cfDNA) has received much attention as a cancer biomarker for its ability to monitor the progression of advanced disease, predict tumor recurrence and reflect the complex genetic heterogeneity of cancers. Here, we tested whether analysis of cfDNA is a viable tool to enhance detection of colon adenomas. To address this, we assessed a cohort of patients with adenomas and healthy controls using droplet digital PCR (ddPCR) and mutation-specific assays targeted to trunk mutations. Additionally, we performed multiregional, targeted next-generation sequencing (NGS) of adenomas and unmasked extensive heterogeneity, affecting known drivers such as APC, KRAS and mismatch repair (MMR) genes. However, tumor-related mutations were undetectable in patients' plasma. Finally, we employed a preclinical mouse model of Apc-driven intestinal adenomas and confirmed the inability to identify tumor-related alterations via cfDNA, despite the enhanced disease burden displayed by this experimental cancer model. Therefore, we conclude that benign colon lesions display extensive genetic heterogeneity, that they are not prone to release DNA into the circulation and are unlikely to be reliably detected with liquid biopsies, at least with the current technologies.

Correction to: Association of invasion-promoting tenascin-C additional domains with breast cancers in young women.

After the publication of this work [1] an error was noticed in Fig. 6 (b). In the MCF-7/Vector columns, the same image was used accidentally for the 0 h and 24 h time points. Both images were taken from the 0 h time point.

Racial differences in endometrial cancer molecular portraits in The Cancer Genome Atlas.

Endometrial cancer (EC) is now the most prevalent gynaecological malignancy in the Western world. Black or African American women (BoAA) have double the mortality of Caucasian women, and their tumours tend to be of higher grade. Despite these disparities, little is known regarding the mutational landscape of EC between races. Hence, we wished to investigate the molecular features of ECs within The Cancer Genome Atlas (TCGA) dataset by racial groupings. In total 374 Caucasian, 109 BoAA and 20 Asian patients were included in the analysis. Asian women were diagnosed at younger age, 54.2 years versus 64.5 years for Caucasian and 64.9 years for BoAA women (OR 3.432; p=0.011); BoAA women were more likely to have serous type tumors (OR 2.061; p=0.008). No difference in overall survival was evident. The most frequently mutated gene in Caucasian and Asian tumours was PTEN (63% and 85%), unlike BoAA cases where it was TP53 (49%). Mutation and somatic copy number alteration (SCNA) analysis revealed an enrichment of TP53 mutations in BoAAs; whereas POLE and RPL22 mutations were more frequent in Caucasians. Major recurrent SCNA racial differences were observed at chromosomes 3p, 8, 10, and 16, which clustered BoAA tumors into 4 distinct groups and Caucasian tumors into 5 groups. There was a significantly higher frequency of somatic mutations in DNA mismatch repair genes in Asian tumours, in particular PMS2 (p=0.0036). In conclusion, inherent racial disparities appear to be present in the molecular profile of EC, which could have potential implications on clinical management.

The genetics of gastroesophageal adenocarcinoma and the use of circulating cell free DNA for disease detection and monitoring.

INTRODUCTION: Gastroesophageal adenocarcinoma (GOA) is a frequently occurring cancer worldwide with a poor clinical outcome. Adenocarcinomas of the esophagus and gastroesophageal junction have shown a recent increase in frequency, therefore there is need to increase our understanding of GOA in order to improve our ability to detect, monitor and treat the disease. Areas covered: The authors discuss the current classification of GOA in the context of recent changes in incidence. The authors also discuss developments in the understanding of disease biology and recent discoveries from whole genome and whole exome sequencing, and studies in immunotherapy. Finally, the authors discuss the recent developments in the use of circulating tumour DNA (ctDNA). PubMed search terms were in English including 'esophageal/gastric adenocarcinoma', 'gastroesophageal junctional tumour', 'whole genome/exome sequencing', 'immunotherapy' and 'circulating tumour DNA'. Expert commentary: Shared biological and genetic changes in GOA suggest it can be investigated as a single disease entity with different molecular subtypes. A number of genes are recurrently mutated including TP53, SMAD4, PIK3CA and there are frequent somatic copy number alterations and high levels of chromosomal instability. A subset of these genetic alterations have been detected in ctDNA and may provide an important avenue of research for detecting minimal residual disease and response to chemo- and immunotherapies.