The impact of OCR accuracy on automated cancer classification of pathology reports

Objective To evaluate the effects of Optical Character Recognition (OCR) on the automatic cancer classification of pathology reports. Method Scanned images of pathology reports were converted to electronic free-text using a commercial OCR system. A state-of-the-art cancer classification system, the Medical Text Extraction (MEDTEX) system, was used to automatically classify the OCR reports. Classifications produced by MEDTEX on the OCR versions of the reports were compared with the classification from a human amended version of the OCR reports. Results The employed OCR system was found to recognise scanned pathology reports with up to 99.12% character accuracy and up to 98.95% word accuracy. Errors in the OCR processing were found to minimally impact on the automatic classification of scanned pathology reports into notifiable groups. However, the impact of OCR errors is not negligible when considering the extraction of cancer notification items, such as primary site, histological type, etc. Conclusions The automatic cancer classification system used in this work, MEDTEX, has proven to be robust to errors produced by the acquisition of freetext pathology reports from scanned images through OCR software. However, issues emerge when considering the extraction of cancer notification items.

Classification of pathology reports for cancer registry notifications

Objective: To develop a system for the automatic classification of pathology reports for Cancer Registry notifications. Method: A two pass approach is proposed to classify whether pathology reports are cancer notifiable or not. The first pass queries pathology HL7 messages for known report types that are received by the Queensland Cancer Registry (QCR), while the second pass aims to analyse the free text reports and identify those that are cancer notifiable. Cancer Registry business rules, natural language processing and symbolic reasoning using the SNOMED CT ontology were adopted in the system. Results: The system was developed on a corpus of 500 histology and cytology reports (with 47% notifiable reports) and evaluated on an independent set of 479 reports (with 52% notifiable reports). Results show that the system can reliably classify cancer notifiable reports with a sensitivity, specificity, and positive predicted value (PPV) of 0.99, 0.95, and 0.95, respectively for the development set, and 0.98, 0.96, and 0.96 for the evaluation set. High sensitivity can be achieved at a slight expense in specificity and PPV. Conclusion: The system demonstrates how medical free-text processing enables the classification of cancer notifiable pathology reports with high reliability for potential use by Cancer Registries and pathology laboratories.

Towards a smart cancer registry

Aims Pathology notification for a Cancer Registry is regarded as the most valid information for the confirmation of a diagnosis of cancer. In view of the importance of pathology data, an automatic medical text analysis system (Medtex) is being developed to perform electronic Cancer Registry data extraction and coding of important clinical information embedded within pathology reports. Methods The system automatically scans HL7 messages received from a Queensland pathology information system and analyses the reports for terms and concepts relevant to a cancer notification. A multitude of data items for cancer notification such as primary site, histological type, stage, and other synoptic data are classified by the system. The underlying extraction and classification technology is based on SNOMED CT1 2. The Queensland Cancer Registry business rules3 and International Classification of Diseases – Oncology – Version 34 have been incorporated. Results The cancer notification services show that the classification of notifiable reports can be achieved with sensitivities of 98% and specificities of 96%5, while the coding of cancer notification items such as basis of diagnosis, histological type and grade, primary site and laterality can be extracted with an overall accuracy of 80%6. In the case of lung cancer staging, the automated stages produced were accurate enough for the purposes of population level research and indicative staging prior to multi-disciplinary team meetings2 7. Medtex also allows for detailed tumour stream synoptic reporting8. Conclusions Medtex demonstrates how medical free-text processing could enable the automation of some Cancer Registry processes. Over 70% of Cancer Registry coding resources are devoted to information acquisition. The development of a clinical decision support system to unlock information from medical free-text could significantly reduce costs arising from duplicated processes and enable improved decision support, enhancing efficiency and timeliness of cancer information for Cancer Registries.

Gelatine methacrylamide-based hydrogels : an alternative three-dimensional cancer cell culture system

Modern cancer research requires physiological, three-dimensional (3-D) cell culture platforms, wherein the physical and chemical characteristics of the extracellular matrix (ECM) can be modified. In this study, gelatine methacrylamide (GelMA)-based hydrogels were characterized and established as in vitro and in vivo spheroid-based models for ovarian cancer, reflecting the advanced disease stage of patients, with accumulation of multicellular spheroids in the tumour fluid (ascites). Polymer concentration (2.5-7% w/v) strongly influenced hydrogel stiffness (0.5±0.2kPa to 9.0±1.8kPa) but had little effect on solute diffusion. The diffusion coefficient of 70kDa fluorescein isothiocyanate (FITC)-labelled dextran in 7% GelMA-based hydrogels was only 2.3 times slower compared to water. Hydrogels of medium concentration (5% w/v GelMA) and stiffness (3.4kPa) allowed spheroid formation and high proliferation and metabolic rates. The inhibition of matrix metalloproteinases and consequently ECM degradability reduced spheroid formation and proliferation rates. The incorporation of the ECM components laminin-411 and hyaluronic acid further stimulated spheroid growth within GelMA-based hydrogels. The feasibility of pre-cultured GelMA-based hydrogels as spheroid carriers within an ovarian cancer animal model was proven and led to tumour development and metastasis. These tumours were sensitive to treatment with the anti-cancer drug paclitaxel, but not the integrin antagonist ATN-161. While paclitaxel and its combination with ATN-161 resulted in a treatment response of 33-37.8%, ATN-161 alone had no effect on tumour growth and peritoneal spread. The semi-synthetic biomaterial GelMA combines relevant natural cues with tunable properties, providing an alternative, bioengineered 3-D cancer cell culture in in vitro and in vivo model systems.

Integrin αvβ3 mediates upregulation of epidermal growth-factor receptor expression and activity in human ovarian cancer cells

Upon overexpression of integrin αvβ3 and its engagement by vitronectin, we previously showed enhanced adhesion, proliferation, and motility of human ovarian cancer cells. By studying differential expression of genes possibly related to these tumor biological events, we identified the epidermal growth-factor receptor (EGF-R) to be under control of αvβ3 expression levels. Thus in the present study we characterized αvβ3-dependent changes of EGF-R and found significant upregulation of its expression and activity which was reflected by prominent changes of EGF-R promoter activity. Upon disruption of DNA-binding motifs for the transcription factors p53, ETF, the repressor ETR, p50, and c-rel, respectively, we sought to identify DNA elements contributing to αvβ3-mediated EGF-R promoter induction. Both, the p53- and ETF-mutant, while exhibiting considerably lower EGF-R promoter activity than the wild type promoter, retained inducibility by αvβ3. Mutation of the repressor motif ETR, as expected, enhanced EGF-R promoter activity with a further moderate increase upon αvβ3 elevation. The p50-mutant displayed EGF-R promoter activity almost comparable to that of the wild type promoter with no impairment of induction by αvβ3. However, the activity of an EGF-R promoter mutant displaying a disrupted c-rel-binding motif did not only prominently decline, but, moreover, was not longer responsive to enhanced αvβ3, involving this DNA element in αvβ3-dependent EGF-R upregulation. Moreover, αvβ3 did not only increase the EGF-R but, moreover, also led to obvious co-clustering on the cancer cell surface. By studying αvβ3/EGF-R-effects on the focal adhesion kinase (FAK) and the mitogen activated protein kinases (MAPK) p44/42 (erk−1/erk−2), having important functions in synergistic crosstalk between integrins and growth-factor receptors, we found for both significant enhancement of expression and activity upon αvβ3/VN interaction and cell stimulation by EGF. Upregulation of the EGF-R by integrin αvβ3, both receptor molecules with a well-defined role as targets for cancer treatment, might represent an additional mechanism to adapt synergistic receptor signaling and crosstalk in response to an altered tumor cell microenvironment during ovarian cancer progression.

Self-management associated with fatigue in patients with advanced cancer : a prospective longitudinal study

Cancer-related fatigue is one of the most distressing symptoms experienced by patients with advanced cancer. This doctoral study identified that patients with advanced cancer commonly use a number of self-management strategies in response to fatigue, although these strategies had varying levels of effectiveness in reducing the symptom. The study identified that enhancing self-efficacy and managing depressive symptoms are important factors to consider in the design of future interventions to support fatigue self-management.

Proteomic and other analyses to determine the functional consequences of deregulated kallikrein-related peptidase (KLK) expression in prostate and ovarian cancer

Rapidly developing proteomic tools are improving detection of deregulated kallikrein-related peptidase (KLK) expression, at the protein level, in prostate and ovarian cancer, as well as facilitating the determination of functional consequences downstream. Mass spectrometry (MS)-driven proteomics uniquely allows for the detection, identification and quantification of thousands of proteins in a complex protein pool, and this has served to identify certain KLKs as biomarkers for these diseases. In this review we describe applications of this technology in KLK biomarker discovery, and elucidate MS-based techniques which have been used for unbiased, global screening of KLK substrates within complex protein pools. Although MS-based KLK degradomic studies are limited to date, they helped to discover an array of novel KLK substrates. Substrates identified by MS-based degradomics are reported with improved confidence over those determined by incubating a purified or recombinant substrate and protease of interest, in vitro. We propose that these novel proteomic approaches represent the way forward for KLK research, in order to correlate proteolysis of biological substrates with tissue-related consequences, toward clinical targeting of KLK expression and function for cancer diagnosis, prognosis and therapies.

Expression and in vitro functions of the ghrelin axis in endometrial cancer

Ghrelin is a peptide hormone produced in the stomach and a range of other tissues, where it has endocrine, paracrine and autocrine roles in both normal and disease states. Ghrelin has been shown to be an important growth factor for a number of tumours, including prostate and breast cancers. In this study, we examined the expression of the ghrelin axis (ghrelin and its receptor, the growth hormone secretagogue receptor, GHSR) in endometrial cancer. Ghrelin is expressed in a range of endometrial cancer tissues, while its cognate receptor, GHSR1a, is expressed in a small subset of normal and cancer tissues. Low to moderately invasive endometrial cancer cell lines were examined by RT-PCR and immunoblotting, demonstrating that ghrelin axis mRNA and protein expression correlate with differentiation status of Ishikawa, HEC1B and KLE endometrial cancer cell lines. Moreover, treatment with ghrelin potently stimulated cell proliferation and inhibited cell death. Taken together, these data indicate that ghrelin promotes the progression of endometrial cancer cells in vitro, and may contribute to endometrial cancer pathogenesis and represent a novel treatment target.

Educational programmes for primary prevention of skin cancer (Protocol)

This is the protocol for a review and there is no abstract. The objectives are as follows: To assess the effects of education programmes for skin cancer prevention in the general population. Description of the condition Skin cancer is a term that includes both melanoma and keratinocyte cancer. Keratinocyte cancer (also known as nonmelanoma skin cancer) generally refers to basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), although it also includes other rare cutaneous neoplasms (Madan 2010). Skin cancer is the most common cancer in populations of predominantly fair-skinned people (Donaldson 2011; Lomas 2012; Stern 2010), with incidence increasing (Garbe 2009; Leiter 2012). There are variations in annual incidence rates between these populations, with Australia reporting the highest rate of skin cancer in the world (Lomas 2012). In 2012, the estimated age-standardised incidence rate for melanoma was almost 63 per 100,000 people for Australian men, and 40 per 100,000 people for Australian women (AIHW 2012). In Europe, incidence rates range from 10 to 15 per 100,000 people (Garbe 2009; Lasithiotakis 2006), with rates highest amongst men (Stang 2006). In the United States, incidence rates are approximately 18 per 100,000 people (Garbe 2009),with the highest rates reported forwomen (Bradford 2010). Keratinocyte cancer is much more common than melanoma. In 2012, the estimated Australian age-standardised rates for BCCand SCC were 884 and 387 per 100,000 people, respectively (Staples 2006). The cumulative three-year risk of developing a subsequent keratinocyte cancer is 18% for SCC and 44% for BCC (Marcil 2000).

Classification of cancer-related death certificates using machine learning

Background Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities. Aims In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated. Method A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes. Results Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall F-measure of 0.9866 when evaluated on a set of 5,000 free-text death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers. Conclusion The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.

Antibody-based immunotherapy for ovarian cancer: where are we at?

Cytoreductive surgery and chemotherapy continue to be the mainstay of ovarian cancer treatment. However, as mortality from advanced ovarian cancer remains very high, novel therapies are required to be integrated into existing treatment regimens. Immunotherapy represents an alternative and rational therapeutic approach for ovarian cancer based on a body of evidence supporting a protective role of the immune system against these cancers, and on the clinical success of immunotherapy in other malignancies. Whether or not immunotherapy will have a role in the future management of ovarian cancer is too early to tell, but research in this field is active. This review will discuss recent clinical developments of selected immunotherapies for ovarian cancer which fulfil the following criteria: (i) they are antibody-based, (ii) target a distinct immunological pathway, and (iii) have reached the clinical trial stage. Specifically, the focus is on Catumaxomab (anti-EpCAM × anti-CD3), Abagovomab, Oregovomab (anti-CA125), Daclizumab (anti-CD25), Ipilimumab (anti-CTLA-4), and MXD-1105 (anti-PD-L1). Catumaxomab has reached phase III clinical trials and exhibits promise with reports, showing that it can cause a significant and sustained reduction in ascites. Phase I–III clinical trials continue to be conducted on the other antibodies, some of which have had encouraging reports. We will also provide our perspective on the future of immunotherapy for ovarian cancer, and how it may be best employed in treatment regimens.

Racial differences in physical activity among breast cancer survivors : implications for breast cancer care

Background: Physical activity after breast cancer diagnosis is associated with improved survival. This study examines levels of and changes in physical activity following breast cancer diagnosis, overall and by race. Methods: The Carolina Breast Cancer Study, Phase III, assessed pre- and post-diagnosis physical activity levels in a cohort of 1,735 women, aged 20-74, diagnosed with invasive breast cancer between 2008 and 2011 in 44 counties of North Carolina. Logistic regression and analysis of variance were used to examine whether demographic, behavioral and clinical characteristics were associated with activity levels. Results: Only 35% of breast cancer survivors met current physical activity guidelines post-diagnosis. A decrease in activity following diagnosis was reported by 59% of patients, with the average study participant reducing their activity by 230 minutes (95% CI: 190, 270). Following adjustment for potential confounders, when compared to white women, African-American women were less likely to meet national physical activity guidelines post-diagnosis (odds ratio: 1.38, 95% CI: 1.01, 1.88), reported less weekly post-diagnosis physical activity (182 vs. 215 minutes; p=0.13), and reported higher average reductions in pre- versus post-diagnosis weekly activity (262 vs. 230 minutes; p-value = 0.13). Conclusion: Despite compelling evidence demonstrating the benefits of physical activity post-breast cancer, it is clear that more work needs to be done to promote physical activity in breast cancer patients, especially among African-American women.

A prospective model of care for breast cancer rehabilitation : bone health and arthralgias

Musculoskeletal health can be compromised by breast cancer treatment. In particular, bone loss and arthralgias are prevalent side effects experienced by women treated with chemotherapy and/or adjuvant endocrine therapy. Bone loss leads to osteoporosis and related fractures, while arthralgias threaten quality of life and compliance to treatment. Because the processes that lead to these musculoskeletal problems are initiated when treatment begins, early identification of women who may be at higher risk of developing problems, routine monitoring of bone density and pain at certain stages of treatment, and prudent application of therapeutic interventions are key to preventing and/or minimizing musculoskeletal sequelae. Exercise may be a particularly suitable intervention strategy because of its potential to address a number of impairments; it may slow bone loss, appears to reduce joint pain in noncancer conditions, and improves other breast cancer outcomes. Research efforts continue in the areas of etiology, measurement, and treatment of bone loss and arthralgias. The purpose of this review is to provide an overview of the current knowledge on the management and treatment of bone loss and arthralgias in breast cancer survivors and to present a framework for rehabilitation care to preserve musculoskeletal health in women treated for breast cancer.