Dataset Information

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study.

ABSTRACT: Inter-pathologist agreement for nuclear atypia scoring of breast cancer is poor. To address this problem, previous studies suggested some criteria for describing the variations appearance of tumor cells relative to normal cells. However, these criteria were still assessed subjectively by pathologists. Previous studies used quantitative computer-extracted features for scoring. However, application of these tools is limited as further improvement in their accuracy is required. This study proposes COMPASS (COMputer-assisted analysis combined with Pathologist's ASSessment) for reproducible nuclear atypia scoring. COMPASS relies on both cytological criteria assessed subjectively by pathologists as well as computer-extracted textural features. Using machine learning, COMPASS combines these two sets of features and output nuclear atypia score. COMPASS's performance was evaluated using 300 images for which expert-consensus derived reference nuclear pleomorphism scores were available, and they were scanned by two scanners from different vendors. A personalized model was built for three pathologists who gave scores to six atypia-related criteria for each image. Leave-one-out cross validation (LOOCV) was used. COMPASS was trained and tested for each pathologist separately. Percentage agreement between COMPASS and the reference nuclear scores was 93.8%, 92.9%, and 93.1% for three pathologists. COMPASS's performance in nuclear grading was almost identical for both scanners, with Cohen's kappa ranging from 0.80 to 0.86 for different pathologists and different scanners. Independently, the images were also assessed by two experienced senior pathologists. Cohen's kappa of COMPASS was comparable to the Cohen's kappa for two senior pathologists (0.79 and 0.68).

SUBMITTER: Gandomkar Z

PROVIDER: S-EPMC6737167 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study.

Gandomkar Ziba Z Brennan Patrick C PC Mello-Thoms Claudia C

Journal of digital imaging 20191001 5

Inter-pathologist agreement for nuclear atypia scoring of breast cancer is poor. To address this problem, previous studies suggested some criteria for describing the variations appearance of tumor cells relative to normal cells. However, these criteria were still assessed subjectively by pathologists. Previous studies used quantitative computer-extracted features for scoring. However, application of these tools is limited as further improvement in their accuracy is required. This study proposes ...[more]

PMID: 30719586

Similar Datasets

Project description:IntroductionThe National Health Service (NHS) Breast Screening Programme aims to detect cancer earlier when treatment is more effective but can harm women by over diagnosing and overtreating cancers which would never have become symptomatic. As well as breast cancer, a spectrum of atypical epithelial proliferations (atypia) can also be detected as part of screening. This spectrum of changes, while not cancer, may mean that a woman is more likely to develop breast cancer in the future. Follow-up of atypia is not evidence based. We currently do not know which atypia should be detected to avoid future cancer. This study will explore how atypia develops into breast cancer in terms of number of women, time of cancer development, cancer type and severity, and whether this varies for different types of atypia.Methods and analysisThe Sloane cohort study began in April 2003 with ongoing data collection including atypia diagnosed through screening at screening units in the UK. The database for England has 3645 cases (24 September 2020) of epithelial atypia, with follow-up from 1 to 15 years. The outcomes include subsequent invasive breast cancer and the nature of subsequent cancer. Descriptive statistics will be produced. The observed rates of breast cancer at 1, 3 and 6 years for types of atypia will be reported with CIs, to enable comparison to women in the general population. Time to event methods will be used to describe the time to breast cancer diagnosis for the types of atypia, including flexible parametric modelling if appropriate. Patient representatives from Independent Cancer Patients' Voice are included at every stage of the research.Ethics and disseminationThe study has received research ethics approval from the University of Warwick Biomedical and Scientific Research Ethics Committee (BSREC 10/20-21, 8 October 2020), Public Health England office for data release approvals (ODR1718_313) and approval from the English Breast Research Advisory Committee (BSPRAC_031). The findings will be disseminated to breast screening clinicians (via journal publication and conference presentation), to the NHS Breast Screening Programme to update their guidelines on how women with atypia should be followed up, and to the general public.

Project description:For French cochlear implant (CI) recipients, in-person clinical auditory rehabilitation is typically provided during the first few years post-implantation. However, this is often inconvenient, it requires substantial time resources and can be problematic when appointments are unavailable. In response, we developed a computer-based home training software ("French AngelSound™") for French CI recipients. We recently conducted a pilot study to evaluate the newly developed French AngelSound™ in 15 CI recipients (5 unilateral, 5 bilateral, 5 bimodal). Outcome measures included phoneme recognition in quiet and sentence recognition in noise. Unilateral CI users were tested with the CI alone. Bilateral CI users were tested with each CI ear alone to determine the poorer ear to be trained, as well as with both ears (binaural performance). Bimodal CI users were tested with the CI ear alone, and with the contralateral hearing aid (binaural performance). Participants trained at home over a one-month period (10 hours total). Phonemic contrast training was used; the level of difficulty ranged from phoneme discrimination in quiet to phoneme identification in multi-talker babble. Unilateral and bimodal CI users trained with the CI alone; bilateral CI users trained with the poorer ear alone. Outcomes were measured before training (pre-training), immediately after training was completed (post-training), and one month after training was stopped (follow-up). For all participants, post-training CI-only vowel and consonant recognition scores significantly improved after phoneme training with the CI ear alone. For bilateral and bimodal CI users, binaural vowel and consonant recognition scores also significantly improved after training with a single CI ear. Follow-up measures showed that training benefits were largely retained. These preliminary data suggest that the phonemic contrast training in French AngelSound™ may significantly benefit French CI recipients and may complement clinical auditory rehabilitation, especially when in-person visits are not possible.

Project description:BackgroundCollagen fibers play an important role in tumor initiation, progression, and invasion. Our previous research has already shown that large-scale tumor-associated collagen signatures (TACS) are powerful prognostic biomarkers independent of clinicopathological factors in invasive breast cancer. However, they are observed on a macroscale and are more suitable for identifying high-risk patients. It is necessary to investigate the effect of the corresponding microscopic features of TACS so as to more accurately and comprehensively predict the prognosis of breast cancer patients.MethodsIn this retrospective and multicenter study, we included 942 invasive breast cancer patients in both a training cohort (n = 355) and an internal validation cohort (n = 334) from one clinical center and in an external validation cohort (n = 253) from a different clinical center. TACS corresponding microscopic features (TCMFs) were firstly extracted from multiphoton images for each patient, and then least absolute shrinkage and selection operator (LASSO) regression was applied to select the most robust features to build a TCMF-score. Finally, the Cox proportional hazard regression analysis was used to evaluate the association of TCMF-score with disease-free survival (DFS).ResultsTCMF-score is significantly associated with DFS in univariate Cox proportional hazard regression analysis. After adjusting for clinical variables by multivariate Cox regression analysis, the TCMF-score remains an independent prognostic indicator. Remarkably, the TCMF model performs better than the clinical (CLI) model in the three cohorts and is particularly outstanding in the ER-positive and lower-risk subgroups. By contrast, the TACS model is more suitable for the ER-negative and higher-risk subgroups. When the TACS and TCMF are combined, they could complement each other and perform well in all patients. As expected, the full model (CLI+TCMF+TACS) achieves the best performance (AUC 0.905, [0.873-0.938]; 0.896, [0.860-0.931]; 0.882, [0.840-0.925] in the three cohorts).ConclusionThese results demonstrate that the TCMF-score is an independent prognostic factor for breast cancer, and the increased prognostic performance (TCMF+TACS-score) may help us develop more appropriate treatment protocols.

Project description:BackgroundIndeterminate categories of thyroid cytopathology (categories B-III and B-IV of the Bethesda system) are integrated by a heterogeneous spectrum of cytological scenarios that are generally clustered for analysis and management recommendations. It has been suggested that aspirates exhibiting nuclear atypia have a higher risk of malignancy. This study aimed to assess whether cytologically indeterminate thyroid nodules with nuclear atypia have a significantly higher cancer risk than those without nuclear atypia.MethodsOn June 30, 2016, PubMed and EMBASE were searched for articles in English or Spanish using a search strategy developed by an endocrinologist and a librarian. Case reports were excluded, and no date limits were used. The references of all included studies were also screened for relevant missing studies. Studies were included if the prevalences of malignancy of cytologically indeterminate thyroid nodules with histological confirmation with and without nuclear atypia were reported. Studies were excluded if they had: (i) nodules suspicious for malignancy; (ii) nodules with non-indeterminate (B-III or B-IV) cytology on repeated biopsy, if performed; (iii) nodules not consecutively evaluated; or (iv) cohorts overlapping with another larger series. Two investigators independently assessed the eligibility and risk of bias of the studies. PRISMA and MOOSE guidelines were followed. Summary data were extracted from published reports by one investigator and independently reviewed by another. Data were pooled using a random-effects model. Heterogeneity was explored using subgroup analysis and mixed-effect model meta-regression. The odds ratio for malignancy of cytologically indeterminate thyroid nodules with nuclear atypia over cytologically indeterminate thyroid nodules without nuclear atypia was calculated.ResultsOf 2571 retrieved studies, 20 were eligible. The meta-analysis was conducted on summary data of 3532 cytologically indeterminate thyroid nodules: 1162 with and 2370 without nuclear atypia. The odds ratio for malignancy in cytologically indeterminate thyroid nodules with nuclear atypia was 3.63 [confidence interval 3.06-4.35]. There was no evidence of publication bias, and heterogeneity was insignificant (I2 < 0.01%, p = 0.40).ConclusionsNuclear atypia is a significant indicator of malignancy in cytologically indeterminate thyroid nodules and needs to be standardized and implemented into clinical practice.

Dataset Information

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study.

Publications

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets