Dataset Information

Automated detection of cribriform growth patterns in prostate histology images.

ABSTRACT: Cribriform growth patterns in prostate carcinoma are associated with poor prognosis. We aimed to introduce a deep learning method to detect such patterns automatically. To do so, convolutional neural network was trained to detect cribriform growth patterns on 128 prostate needle biopsies. Ensemble learning taking into account other tumor growth patterns during training was used to cope with heterogeneous and limited tumor tissue occurrences. ROC and FROC analyses were applied to assess network performance regarding detection of biopsies harboring cribriform growth pattern. The ROC analysis yielded a mean area under the curve up to 0.81. FROC analysis demonstrated a sensitivity of 0.9 for regions larger than [Formula: see text] with on average 7.5 false positives. To benchmark method performance for intra-observer annotation variability, false positive and negative detections were re-evaluated by the pathologists. Pathologists considered 9% of the false positive regions as cribriform, and 11% as possibly cribriform; 44% of the false negative regions were not annotated as cribriform. As a final experiment, the network was also applied on a dataset of 60 biopsy regions annotated by 23 pathologists. With the cut-off reaching highest sensitivity, all images annotated as cribriform by at least 7/23 of the pathologists, were all detected as cribriform by the network and 9/60 of the images were detected as cribriform whereas no pathologist labelled them as such. In conclusion, the proposed deep learning method has high sensitivity for detecting cribriform growth patterns at the expense of a limited number of false positives. It can detect cribriform regions that are labelled as such by at least a minority of pathologists. Therefore, it could assist clinical decision making by suggesting suspicious regions.

SUBMITTER: Ambrosini P

PROVIDER: S-EPMC7483768 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated detection of cribriform growth patterns in prostate histology images.

Ambrosini Pierre P Hollemans Eva E Kweldam Charlotte F CF Leenders Geert J L H van GJLHV Stallinga Sjoerd S Vos Frans F

Scientific reports 20200910 1

Cribriform growth patterns in prostate carcinoma are associated with poor prognosis. We aimed to introduce a deep learning method to detect such patterns automatically. To do so, convolutional neural network was trained to detect cribriform growth patterns on 128 prostate needle biopsies. Ensemble learning taking into account other tumor growth patterns during training was used to cope with heterogeneous and limited tumor tissue occurrences. ROC and FROC analyses were applied to assess network p ...[more]

PMID: 32913202

Similar Datasets

Project description:BackgroundMalaria is a serious infectious disease. According to the World Health Organization, it is responsible for nearly one million deaths each year. There are various techniques to diagnose malaria of which manual microscopy is considered to be the gold standard. However due to the number of steps required in manual assessment, this diagnostic method is time consuming (leading to late diagnosis) and prone to human error (leading to erroneous diagnosis), even in experienced hands. The focus of this study is to develop a robust, unsupervised and sensitive malaria screening technique with low material cost and one that has an advantage over other techniques in that it minimizes human reliance and is, therefore, more consistent in applying diagnostic criteria.MethodA method based on digital image processing of Giemsa-stained thin smear image is developed to facilitate the diagnostic process. The diagnosis procedure is divided into two parts; enumeration and identification. The image-based method presented here is designed to automate the process of enumeration and identification; with the main advantage being its ability to carry out the diagnosis in an unsupervised manner and yet have high sensitivity and thus reducing cases of false negatives.ResultsThe image based method is tested over more than 500 images from two independent laboratories. The aim is to distinguish between positive and negative cases of malaria using thin smear blood slide images. Due to the unsupervised nature of method it requires minimal human intervention thus speeding up the whole process of diagnosis. Overall sensitivity to capture cases of malaria is 100% and specificity ranges from 50-88% for all species of malaria parasites.ConclusionImage based screening method will speed up the whole process of diagnosis and is more advantageous over laboratory procedures that are prone to errors and where pathological expertise is minimal. Further this method provides a consistent and robust way of generating the parasite clearance curves.

Project description:Invasive cribriform and intraductal carcinoma are associated with adverse clinical outcome in patients with Gleason score 7 prostate cancer. It is yet unclear whether invasive cribriform and intraductal carcinoma of the prostate both have independent prognostic value, or whether field size of invasive cribriform carcinoma has impact on disease outcome. Our objective was to determine the prognostic impact of intraductal and invasive cribriform prostate cancer histological subtypes in radical prostatectomies. We reviewed 420 prostatectomy specimens with ISUP grade 2 prostate cancer, assessed the percentages of Gleason grade 4 and tertiary 5, and performed immunohistochemistry for basal cells to discriminate intraductal from invasive cribriform growth. Small and large invasive cribriform fields were distinguished based on a diameter of at least twice the size of adjacent pre-existent normal glands. Clinicopathological parameters and biochemical recurrence-free survival were used as endpoints. Cribriform architecture was observed in 228 (54.3%) men, 103 (24.5%) of whom had intraductal, 194 (46.2%) small invasive, and 34 (8.1%) large invasive cribriform growth. Large invasive cribriform architecture was associated with older age (P < 0.001), higher percentage Gleason grade 4 (P = 0.001), extraprostatic expansion (P < 0.001), and more frequent lymph node metastases (P = 0.002), when compared with small invasive cribriform and/or intraductal carcinoma. Univariate analysis identified PSA, pT-stage, surgical margin status, and intraductal and invasive cribriform growth as significant predictors for biochemical recurrence-free survival. In multivariable Cox regression analysis, pT-stage (hazard ratio = 1.64, 95% CI: 1.02-2.63, P = 0.04), positive surgical margins (hazard ratio = 3.28, 95% CI: 2.06-5.23, P < 0.001), and large cribriform growth (hazard ratio = 4.36, 95% CI: 2.08-9.17, P < 0.001) were independent predictors for biochemical recurrence-free survival, while intraductal carcinoma, small cribriform growth, and percentage of Gleason grade 4 were not. In conclusion, large cribriform fields represent an aggressive subpattern of invasive cribriform prostate cancer and are an independent predictive factor for biochemical recurrence-free survival in ISUP grade 2 prostate cancer patients.

Dataset Information

Automated detection of cribriform growth patterns in prostate histology images.

Publications

Automated detection of cribriform growth patterns in prostate histology images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets