Deep learning for automated scoring of immunohistochemically stained tumour tissue sections - Validation across tumour types based on patient outcomes.

We aimed to develop deep learning (DL) models to detect protein expression in immunohistochemically (IHC) stained tissue-sections, and to compare their accuracy and performance with manually scored clinically relevant proteins in common cancer types. Five cancer patient cohorts (colon, two prostate, breast, and endometrial) were included. We developed separate DL models for scoring IHC-stained tissue-sections with nuclear, cytoplasmic, and membranous staining patterns. For training, we used images with annotations of cells with positive and negative staining from the colon cohort stained for Ki-67 and PMS2 (nuclear model), the prostate cohort 1 stained for PTEN (cytoplasmic model) and ß-catenin (membranous model). The nuclear DL model was validated for MSH6 in the colon, MSH6 and PMS2 in the endometrium, Ki-67 and CyclinB1 in prostate, and oestrogen and progesterone receptors in the breast cancer cohorts. The cytoplasmic DL model was validated for PTEN and Mapre2, and the membranous DL model for CD44 and Flotillin1, all in prostate cohorts. When comparing the results of manual and DL scores in the validation sets, using manual scores as the ground truth, we observed an average correct classification rate of 91.5 % (76.9-98.5 %) for the nuclear model, 85.6 % (73.3-96.6 %) for the cytoplasmic model, and 78.4 % (75.5-84.3 %) for the membranous model. In survival analyses, manual and DL scores showed similar prognostic impact, with similar hazard ratios and p-values for all DL models. Our findings demonstrate that DL models offer a promising alternative to manual IHC scoring, providing efficiency and reproducibility across various data sources and markers.

Anal and Perianal Preneoplastic Lesions.

Anal cancer, mainly squamous cell carcinoma, is rare but increasing in prevalence, as is its precursor lesion, anal squamous dysplasia. They are both strongly associated with human papillomavirus infection. The 2-tiered Lower Anogenital Squamous Terminology classification, low-grade SIL and high-grade SIL, is preferred to the 3-tiered anal intraepithelial neoplasia classification because of better interobserver agreement and clearer management implications. Immunohistochemistry with p16 is helpful to corroborate the diagnosis of squamous dysplasia. Similarly, immunohistochemistry is helpful to differentiate primary Paget disease from secondary Paget disease, which is usually due to anal squamous mucosal/epidermal involvement by primary rectal adenocarcinoma.

Macroscopic pathology and all that: a personal view.

I hope that this treatise adds to the excellent reviews by Varma and colleagues, emphasising the importance of accurate macroscopic assessment and report provision. I have especially highlighted the importance of not divorcing the clinical data and the macroscopic analysis from the microscopic assessment as all are required to provide an accurate and cogent overall composition. The review has also identified areas where the evolution of pathological practice has gone a little awry and requires to be modified and/or justified with evidence base. There is also an emphasis on block economy, as there is no doubt that considerable savings can be made if more attention is paid to more judicious block selection. It is also commended that subspecialties other than gastrointestinal pathology introduce reporting quality standards, like lymph node harvest numbers and other important prognostic and management indicators, to improve the quality of macroscopic pathology worldwide to the benefit of our service users and their patients.

Colorectal dysplasia in chronic inflammatory bowel disease: a contemporary consensus classification and interobserver study.

The clinical management of patients with dysplasia in chronic inflammatory bowel disease (IBD) is currently guided by Riddell et al.'s grading system (negative, indefinite, low grade, high grade) from 1983 which was based primarily on nuclear cytoarchitectural characteristics. Although most dysplasia in IBD resembles sporadic adenomas morphologically, other distinctive potential cancer precursors in IBD have been described over time. Recognizing the need for a updated comprehensive classification for IBD-associated dysplasia, an international working group of pathologists with extensive clinical and research experience in IBD devised a new classification system and assessed its reproducibility by having each participant assess test cases selected randomly from a repository of electronic images of potential cancer precursor lesions. The new classification system now encompasses three broad categories and nine sub-categories: 1) intestinal dysplasia (tubular/villous adenoma-like, goblet cell deficient, crypt cell, traditional serrated adenoma-like, sessile serrated lesion-like and serrated NOS), 2) gastric dysplasia (tubular/villous and serrated), and 3) mixed intestinal-gastric dysplasia. In the interobserver analysis, 67% of the diagnoses were considered definitive and achieved substantial inter-rater agreement. The key distinctions between intestinal and gastric lesions and between serrated and non-serrated lesions achieved substantial and moderate inter-rater agreement overall, respectively, however, the distinctions among certain serrated sub-categories achieved only fair agreement. Based on the Riddell grading system, definite dysplasia accounted for 86% of the collective responses (75% low grade, 11% high grade). Based on these results, this new classification of dysplasia in IBD can provide a sound foundation for future clinical and basic IBD research.

Microvesicular hyperplastic polyp and sessile serrated lesion of the large intestine: a biological continuum or separate entities?

The range of lesions with a serrated appearance within the large intestine has expanded and become more complex over the last 30 years. The majority of these were previously known as metaplastic polyps but are today called hyperplastic polyps (HPs). HPs show two main growth patterns: microvesicular and goblet cell-rich. The former type shows morphological and molecular similarities (eg, BRAF mutations) to the more recently described sessile serrated lesion (SSL). In this review, we debate whether these lesions represent a biological spectrum or separate entities. Whichever view is held, microvesicular HPs and SSLs are distinct from the goblet cell-rich HP and the traditional serrated adenoma (TSA), which may themselves share molecular changes (eg, KRAS mutations), with the goblet cell-rich HP representing a precursor to the TSA. Both SSLs and the goblet cell-rich HP-TSA pathway are routes to colorectal cancer within the serrated pathway and overlaps between them can occur, for example, a (BRAF-mutated) TSA may arise from an SSL.

Incidental findings in the bowel cancer population screening program: other polyps and malignancies - A nationwide study.

The introduction of bowel cancer population screening programs has had a profound impact on gastrointestinal pathology. While the focus is mainly on quality assurance of diagnoses relevant for the outcome of these programs (colorectal cancer and its precursors), incidental findings are increasingly diagnosed. The incidence of such findings is largely unknown. Therefore, we investigated the incidence of incidental findings within the national screening program of the Netherlands. From the Dutch nationwide pathology databank (PALGA), we retrieved all histological diagnoses of patients participating in the national bowel cancer screening program from the start in 2014 until 1/1/2021. Descriptive statistics were used. During these 7 years, in total 9407 other polyps and malignancies (262 per 10,000 colonoscopies) were diagnosed. The majority (65%) were classified as inflammatory polyps. The most common malignancies were neuroendocrine tumours (n = 198, 6 per 10,000 colonoscopies); less common were lymphomas (n = 64) and metastases (n = 33). Mesenchymal polyps, such as leiomyomas and lipomas, were relatively common (27 and 16 per 10,000 colonoscopies, respectively), in comparison with neural polyps such as perineuriomas, ganglioneuromas, and neurofibromas (respectively 3, 2, and 1 per 10,000 colonoscopies). This is the largest study into the incidence of nonconventional colorectal polyps and malignancies in a homogeneous cohort of asymptomatic patients. Several of these diagnoses may have consequences for treatment and follow-up, in particular the malignancies and detection of patients with hereditary cancer syndromes.

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.

Infrared Spectroscopic Analysis in the Differentiation of Epithelial Misplacement From Adenocarcinoma in Sigmoid Colonic Adenomatous Polyps.

Purpose: The differential diagnosis of epithelial misplacement from invasive cancer in the colon is a challenging endeavour, augmented by the introduction of bowel cancer population screening. The main aim of the work is to test, as a proof-of concept study, the ability of the infrared spectroscopic imaging approach to differentiate epithelial misplacement from adenocarcinoma in sigmoid colonic adenomatous polyps. Methods: Ten samples from each of the four diagnostic groups, normal colonic mucosa, adenomatous polyps with low grade dysplasia, epithelial misplacement in adenomatous polyps and adenocarcinoma, were analysed using IR spectroscopic imaging and data processing methods. IR spectral images were subjected to data pre-processing and cluster analysis based segmentation to identify epithelial, connective tissue and stromal regions. Statistical analysis was carried out using principal component analysis and linear discriminant analysis based cross validation, to classify spectral features according to the pathology, and the diagnostic attributes were compared. Results: The combined 4-group classification model on an average showed a sensitivity of 64%, a specificity of 88% and an accuracy of 76% for prediction based on a 'single spectrum', whilst a 'majority-vote' prediction on an average showed a sensitivity of 73%, a specificity of 90% and an accuracy of 82%. The 2-group model, for the differential diagnosis of epithelial misplacement versus adenocarcinoma, showed an average sensitivity and specificity of 82.5% for prediction based on a 'single spectrum' whilst a 'majority-vote' classification showed an average sensitivity and specificity of 90%. A 92% area under the curve (AUC) value was obtained when evaluating the classifier using the Receiver Operating Characteristics (ROC) curves. Conclusions: IR spectroscopy shows promise in its ability to differentiate epithelial misplacement from adenocarcinoma in tissue sections, considered as one of the most challenging endeavours in population-wide diagnostic histopathology. Further studies with larger series, including cases with challenging diagnostic features are required to ascertain the capability of this modern digital pathology approach. In the long-term, IR spectroscopy based pathology which is relatively low-cost and rapid, could be a promising endeavour to consider for integration into the existing histopathology pathway, in particular for population based screening programmes where large number of samples are scrutinised.

The Bowel Cancer Screening Programme Expert Board: an analysis of activity during 2017-2020.

AIMS: The inception of the National Health Service Bowel Cancer Screening Programme in England in 2006 highlighted the fact that the differential diagnosis between the presence of epithelial misplacement and adenocarcinoma occurring in colorectal adenomas is problematic. The pathology Expert Board (EB) was created to facilitate the review of difficult cases by a panel of three experienced gastrointestinal pathologists. This article describes a review of the work of the EB over a 4-year period (2017-2020). METHODS AND RESULTS: Four hundred and thirty polyps were referred to the EB from 193 pathologists and 76 hospitals during this time. The EB diagnosis was benign for 67%, malignant for 28%, and equivocal for 2% (with no consensus in the remainder). The most common diagnosis change made by the EB was from malignant to benign-made in 50% of polyps referred with an initially malignant diagnosis. The level of agreement between the individual EB members was 'good' (kappa score of 0.619) but that between the EB and the referring diagnosis was 'poor' (kappa score of 0.149). Data from one EB member indicated that the presence of lamina propria, features of torsion and cytological similarity between the superficial and deep glands were predictors of a benign diagnosis, whereas the presence of irregular neoplastic glands, a desmoplastic reaction and lymphovascular invasion were commonly observed features in polyps with a malignant diagnosis. CONCLUSION: Diagnostic agreement between EB members is better than that between the EB and referring pathologists. There was a consistent trend for the EB to change diagnoses from malignant to benign.

The use of telemedicine to assess a paediatric patient with arrhythmia presenting to a remote community coronavirus assessment centre.

In 2020, a girl aged 5 years presented to the coronavirus assessment centre on a remote Scottish island with symptoms consistent with novel coronavirus 2019 (COVID-19). Her mother was concerned as she had noted the patient to have an irregular pulse. COVID-19 has been shown to cause cardiac arrhythmia, and so after discussion with tertiary paediatric cardiology services an ECG was recommended. In order to minimise potential spread of coronavirus in the healthcare setting a portable ECG device was immediately delivered to the patient, with the ECG tracing being sent electronically to a cardiologist. A formal diagnosis was then communicated to the parents within 2 hours of the initial contact.

Current dilemmas in the pathological staging of colorectal cancer: the results of a national survey.

AIMS: Accurate and consistent pathological staging of colorectal carcinoma (CRC) in resection specimens is especially crucial to guide adjuvant therapy. The aim of this study was to assess whether certain staging scenarios yield discordant opinions in the setting of current international and UK national guidelines. METHODS AND RESULTS: Members of the UK Gastrointestinal Pathology External Quality Assurance Scheme were invited to complete an anonymous, on-line survey that presented 15 scenarios related to pT or pR staging of CRC, and three questions about the respondent. The survey invitation was e-mailed to 405 pathologists, and 184 (45%) responses were received. The respondents had discordant opinions on whether and how CRC pT or pR staging is affected by: acellular mucin lakes and duration after short-course radiotherapy; the nature of the carcinoma at a resection margin or peritoneal surface; and microscopic evidence of perforation. This discordance was rarely related to the respondent's occupation type, and was not related to duration of work as a consultant or the staging guidelines used. CONCLUSIONS: This survey confirms that there remain several clinically critical but unresolved pT and pR staging issues for CRC. These issues therefore deserve attention in future versions of international and national staging guidelines.

The indications for biopsy in routine upper gastrointestinal endoscopy.

This review describes the indications and contraindications for endoscopic biopsy, in routine practice, of the upper gastrointestinal (GI) tract. We accept that this review provides grounds for controversy, as our stance in certain situations is counter to some national guidelines. Nevertheless, we provide evidence to support our viewpoints, especially on efficiency and economic grounds. We describe the particular controversies concerning the biopsy assessment of Barrett's oesophagus, chronic gastritis and the duodenum in the investigation of coeliac disease. We accept that there are indications for more extensive upper GI biopsy protocols in children than in adults; the latter constitute our main focus in this article. We would encourage detailed discussion between pathologists and their endoscopy colleagues about the indications, or lack of them, for routine upper GI endoscopic biopsy, as studies have shown that adherence to agreed guidelines has resulted in a very considerable diminution in the biopsy workload without compromising patient management. Furthermore, where biopsy is indicated, we emphasise the importance of accompanying clinical information provided to the pathologist, in particular regarding biopsy site(s), and regular feedback to endoscopists to improve and maintain the quality of such information. Finally, local dialogue is also advised, when necessary, to indicate to endoscopists the need to appropriately segregate biopsies into separate, individually labelled specimens, to maximise the information that can be derived by pathological evaluation and thereby improve the quality of the final pathology report.

Deep learning for prediction of colorectal cancer outcome: a discovery and validation study.

BACKGROUND: Improved markers of prognosis are needed to stratify patients with early-stage colorectal cancer to refine selection of adjuvant therapy. The aim of the present study was to develop a biomarker of patient outcome after primary colorectal cancer resection by directly analysing scanned conventional haematoxylin and eosin stained sections using deep learning. METHODS: More than 12 000 000 image tiles from patients with a distinctly good or poor disease outcome from four cohorts were used to train a total of ten convolutional neural networks, purpose-built for classifying supersized heterogeneous images. A prognostic biomarker integrating the ten networks was determined using patients with a non-distinct outcome. The marker was tested on 920 patients with slides prepared in the UK, and then independently validated according to a predefined protocol in 1122 patients treated with single-agent capecitabine using slides prepared in Norway. All cohorts included only patients with resectable tumours, and a formalin-fixed, paraffin-embedded tumour tissue block available for analysis. The primary outcome was cancer-specific survival. FINDINGS: 828 patients from four cohorts had a distinct outcome and were used as a training cohort to obtain clear ground truth. 1645 patients had a non-distinct outcome and were used for tuning. The biomarker provided a hazard ratio for poor versus good prognosis of 3·84 (95% CI 2·72-5·43; p<0·0001) in the primary analysis of the validation cohort, and 3·04 (2·07-4·47; p<0·0001) after adjusting for established prognostic markers significant in univariable analyses of the same cohort, which were pN stage, pT stage, lymphatic invasion, and venous vascular invasion. INTERPRETATION: A clinically useful prognostic marker was developed using deep learning allied to digital scanning of conventional haematoxylin and eosin stained tumour tissue sections. The assay has been extensively evaluated in large, independent patient populations, correlates with and outperforms established molecular and morphological prognostic markers, and gives consistent results across tumour and nodal stage. The biomarker stratified stage II and III patients into sufficiently distinct prognostic groups that potentially could be used to guide selection of adjuvant treatment by avoiding therapy in very low risk groups and identifying patients who would benefit from more intensive treatment regimes. FUNDING: The Research Council of Norway.

The isolated caecal patch lesion: a clinical, endoscopic and histopathological study.

OBJECTIVE: To describe and investigate the potential causes of the isolated caecal patch lesion, a previously undescribed endoscopic phenomenon of a lesion fulfilling endoscopic and histopathological criteria for chronic inflammatory bowel disease but without evidence of similar inflammatory pathology elsewhere at colonoscopy. METHODS: Cases were collected prospectively by one specialist gastrointestinal pathologist over a 10-year period. Full endoscopic and histopathological analysis was undertaken and follow-up sought to understand the likely cause(s) of the lesions. RESULTS: Six cases are described. Two had very close links with ulcerative colitis, one predating the onset of classical distal disease and the other occurring after previous demonstration of classical distal ulcerative colitis. Two occurred in younger patients and we postulate that these lesions may predict the subsequent onset of chronic inflammatory bowel disease. Finally two can be reasonably attributed to the effects of non-steroidal inflammatory agent therapy. CONCLUSIONS: Caecal patch lesions can be demonstrated in isolation. Despite the strong association of caecal patch lesions with ulcerative colitis, solitary lesions may well have disparate causes but nevertheless possess a close relationship with chronic inflammatory bowel disease.

British Society of Gastroenterology guidelines on the diagnosis and management of patients at risk of gastric adenocarcinoma.

Gastric adenocarcinoma carries a poor prognosis, in part due to the late stage of diagnosis. Risk factors include Helicobacter pylori infection, family history of gastric cancer-in particular, hereditary diffuse gastric cancer and pernicious anaemia. The stages in the progression to cancer include chronic gastritis, gastric atrophy (GA), gastric intestinal metaplasia (GIM) and dysplasia. The key to early detection of cancer and improved survival is to non-invasively identify those at risk before endoscopy. However, although biomarkers may help in the detection of patients with chronic atrophic gastritis, there is insufficient evidence to support their use for population screening. High-quality endoscopy with full mucosal visualisation is an important part of improving early detection. Image-enhanced endoscopy combined with biopsy sampling for histopathology is the best approach to detect and accurately risk-stratify GA and GIM. Biopsies following the Sydney protocol from the antrum, incisura, lesser and greater curvature allow both diagnostic confirmation and risk stratification for progression to cancer. Ideally biopsies should be directed to areas of GA or GIM visualised by high-quality endoscopy. There is insufficient evidence to support screening in a low-risk population (undergoing routine diagnostic oesophagogastroduodenoscopy) such as the UK, but endoscopic surveillance every 3 years should be offered to patients with extensive GA or GIM. Endoscopic mucosal resection or endoscopic submucosal dissection of visible gastric dysplasia and early cancer has been shown to be efficacious with a high success rate and low rate of recurrence, providing that specific quality criteria are met.

Complicated appendiceal diverticulosis versus low-grade appendiceal mucinous neoplasms: a major diagnostic dilemma.

AIMS: To research and identify how often complicated diverticular disease of the appendix [appendiceal diverticular disease (ADD)] shows histological mimicry of low-grade appendiceal mucinous neoplasms (LAMNs) and to provide guidance on the useful histopathological features that allow the appropriate diagnosis to be made. METHODS AND RESULTS: Seventy-four cases of complicated appendiceal diverticular disease were identified from two specialist centres. Of the second opinion/consultation cases, 71% of the ADD cases had been diagnosed by referring pathologists as LAMNs. Salient pathological features were identified and agreed upon to reach the applicable diagnosis. For a diagnosis of complicated diverticulosis, particularly when associated with mucus cysts, the following morphological features were regarded as important: relative retention of the normal mucosal architecture with lamina propria and a maintained crypt architecture, crypts arranged in regular array, epithelial hyperplasia and a lack of nuclear abnormalities extending the length of the crypts. In a formal case-control study undertaken on 30 cases with each diagnosis, ADD and LAMN, loss of lamina propria, a filiform architecture and hypermucinosis were significantly associated with low-grade appendiceal mucinous neoplasms. Mucosal neuromas were significantly associated with diverticular disease of the appendix. CONCLUSIONS: To our knowledge, this study represents the largest series in the world literature and serves to highlight the important pathological features to distinguish complicated diverticular disease of the appendix from LAMNs, and emphasises the difficulties experienced by diagnostic pathologists in diagnosing complicated appendiceal diverticulosis. This is important, as LAMNs have a significant risk of transcoelomic spread, while complicated appendiceal diverticulosis has no such risk.

Chromatin organisation and cancer prognosis: a pan-cancer study.

BACKGROUND: Chromatin organisation affects gene expression and regional mutation frequencies and contributes to carcinogenesis. Aberrant organisation of DNA has been correlated with cancer prognosis in analyses of the chromatin component of tumour cell nuclei using image texture analysis. As yet, the methodology has not been sufficiently validated to permit its clinical application. We aimed to define and validate a novel prognostic biomarker for the automatic detection of heterogeneous chromatin organisation. METHODS: Machine learning algorithms analysed the chromatin organisation in 461 000 images of tumour cell nuclei stained for DNA from 390 patients (discovery cohort) treated for stage I or II colorectal cancer at the Aker University Hospital (Oslo, Norway). The resulting marker of chromatin heterogeneity, termed Nucleotyping, was subsequently independently validated in six patient cohorts: 442 patients with stage I or II colorectal cancer in the Gloucester Colorectal Cancer Study (UK); 391 patients with stage II colorectal cancer in the QUASAR 2 trial; 246 patients with stage I ovarian carcinoma; 354 patients with uterine sarcoma; 307 patients with prostate carcinoma; and 791 patients with endometrial carcinoma. The primary outcome was cancer-specific survival. FINDINGS: In all patient cohorts, patients with chromatin heterogeneous tumours had worse cancer-specific survival than patients with chromatin homogeneous tumours (univariable analysis hazard ratio [HR] 1·7, 95% CI 1·2-2·5, in the discovery cohort; 1·8, 1·0-3·0, in the Gloucester validation cohort; 2·2, 1·1-4·5, in the QUASAR 2 validation cohort; 3·1, 1·9-5·0, in the ovarian carcinoma cohort; 2·5, 1·8-3·4, in the uterine sarcoma cohort; 2·3, 1·2-4·6, in the prostate carcinoma cohort; and 4·3, 2·8-6·8, in the endometrial carcinoma cohort). After adjusting for established prognostic patient characteristics in multivariable analyses, Nucleotyping was prognostic in all cohorts except for the prostate carcinoma cohort (HR 1·7, 95% CI 1·1-2·5, in the discovery cohort; 1·9, 1·1-3·2, in the Gloucester validation cohort; 2·6, 1·2-5·6, in the QUASAR 2 cohort; 1·8, 1·1-3·0, for ovarian carcinoma; 1·6, 1·0-2·4, for uterine sarcoma; 1·43, 0·68-2·99, for prostate carcinoma; and 1·9, 1·1-3·1, for endometrial carcinoma). Chromatin heterogeneity was a significant predictor of cancer-specific survival in microsatellite unstable (HR 2·9, 95% CI 1·0-8·4) and microsatellite stable (1·8, 1·2-2·7) stage II colorectal cancer, but microsatellite instability was not a significant predictor of outcome in chromatin homogeneous (1·3, 0·7-2·4) or chromatin heterogeneous (0·8, 0·3-2·0) stage II colorectal cancer. INTERPRETATION: The consistent prognostic prediction of Nucleotyping in different biological and technical circumstances suggests that the marker of chromatin heterogeneity can be reliably assessed in routine clinical practice and could be used to objectively assist decision making in a range of clinical settings. An immediate application would be to identify high-risk patients with stage II colorectal cancer who might have greater absolute benefit from adjuvant chemotherapy. Clinical trials are warranted to evaluate the survival benefit and cost-effectiveness of using Nucleotyping to guide treatment decisions in multiple clinical settings. FUNDING: The Research Council of Norway, the South-Eastern Norway Regional Health Authority, the National Institute for Health Research, and the Wellcome Trust.