Identifying primary tumor site of origin for liver metastases via a combination of handcrafted and deep learning features.

Liver is one of the most common sites for metastases, which can occur on account of primary tumors from multiple sites of origin. Identifying the primary site of origin (PSO) of a metastasis can help in guiding therapeutic options for liver metastases. In this pilot study, we hypothesized that computer extracted handcrafted (HC) histomorphometric features can be utilized to identify the PSO of liver metastases. Cellular features, including tumor nuclei morphological and graph features as well as cytoplasm texture features, were extracted by computer algorithms from 175 slides (114 patients). The study comprised three experiments: (1) comparing and (2) fusing a machine learning (ML) model trained with HC pathomic features and deep learning (DL)-based classifiers to predict site of origin; (3) identifying the section of the primary tumor from which metastases were derived. For experiment 1, we divided the cohort into training sets composed of primary and matched liver metastases [60 patients, 121 whole slide images (WSIs)], and a hold-out validation set (54 patients, 54 WSIs) composed solely of liver metastases of known site of origin. Using the extracted HC features of the training set, a combination of supervised machine classifiers and unsupervised clustering was applied to identify the PSO. A random forest classifier achieved areas under the curve (AUCs) of 0.83, 0.64, 0.82, and 0.64 in classifying the metastatic tumor from colon, esophagus, breast, and pancreas on the validation set. The top features related to nuclear and peri-nuclear shape and textural attributes. We also trained a DL network to serve as a direct comparison to our method. The DL model achieved AUCs for colon: 0.94, esophagus: 0.66, breast: 0.79, and pancreas: 0.67 in identifying PSO. A decision fusion-based strategy was deployed to fuse the trained ML and DL classifiers and achieved slightly better results than ML or DL classifier alone (colon: 0.93, esophagus: 0.68, breast: 0.81, and pancreas: 0.69). For the third experiment, WSI-level attention maps were also generated using a trained DL network to generate a composite feature similarity heat map between paired primaries and their associated metastases. Our experiments revealed that epithelium-rich and moderately differentiated tumor regions of primary tumors were quantitatively similar to paired metastatic tumors. Our findings suggest that a combination of HC and DL features could potentially help identify the PSO for liver metastases while at the same time also potentially identify the spatial sites of origin for the metastases within primary tumors.

Utility of rapid on-site evaluation in procurement of adrenal gland tissue biopsies.

BACKGROUND: While the number of adrenal biopsies has increased due to more "incidentalomas" were detected by widespread use of imaging studies, there have been very limited studies to evaluate the utility of rapid on-site evaluation (ROSE) in obtaining adequate core needle biopsy (CNB) tissue for diagnosis of adrenal lesions. METHODS: We retrospectively reviewed all percutaneous adrenal CNB cases with available ROSE for a 12-year period in our institute in order to assess the usefulness of ROSE in adrenal CNB sampling. RESULTS: A total of 83 cases were identified in our database. The majority of cases (52/83, 63%) were diagnosed as metastatic malignancies with the lung being the most common primary site. Adrenal hyperplasia/adenoma was the most common primary adrenal lesion. The concordance between the ROSE interpretations and CNB final diagnoses is 80%. The interpretation errors accounted for majority (11/17, 65%) of the discordant cases. CONCLUSION: ROSE assessment during adrenal CNB procedures is a helpful tool for obtaining adequate diagnostic tissue. Pathologists should be familiar with adrenal cytology in order to reduce interpretation errors at ROSE.

ICD-9 Code-Based Venous Thromboembolism Performance Targets Fail to Measure Up.

Venous thromboembolism (VTE) is a common complication among hospitalized patients. Suboptimal prevention practices have prompted payers to consider hospital-associated VTE as a potentially preventable condition for which financial incentives or penalties exist to drive practice improvement. The authors reviewed all cases of hospital-associated VTE at the Johns Hopkins Hospital between July 1, 2010, and June 30, 2011, that were identified by ICD-9 codes used by a state-run pay-for-performance quality improvement program. Of 157 patients identified as having developed hospital-associated, potentially preventable VTE, only 92 (58.6%) patients developed radiographically confirmed VTE that were potentially preventable. This misclassification of VTE overestimates the marginal additional treatment cost by more than $860 000 and amounts to nearly $200 000 in lost reward in one year alone. ICD-9 codes alone have extremely low positive predictive value to identify true VTE events. The authors recommend linking provision of risk-appropriate prophylaxis to VTE outcomes as a better target for performance improvement.

Comparison of viral hepatitis-associated hepatocellular carcinoma due to HBV and HCV - cohort from liver clinics in Pakistan.

BACKGROUND: Hepatocellular carcinoma (HCC) is the first cause of death in cirrhotic patients, mostly due to viral hepatitis with HCV or HBV infection. This study was performed to estimate the true prevalence of viral hepatitis-related HCC and the demographic and clinical-pathological associations with the two virus types. MATERIALS AND METHODS: This cross sectional observational study enrolled clinical data base of 188 HCC patients and variables included from baseline were age, sex, area of residence, clinical-pathological features such as underlying co-morbidity, presence or absence of liver cirrhosis, macrovascular involvement, tumor extension and metastasis, liver lobes involved, serum alpha-fetoprotein level, and hepatitis serologies. RESULTS: Overall prevalence of HCV- and HBV-related HCC was 66.0% and 34.0%, respectively. Patients with HCV were more likely to develop HCC at advanced age (52.4±11.9 vs. 40.7±12.09 years), with highly raised serum AFP levels (≥400ng/ml) 78.2% (HBV 67.1%), large tumor size (HCV-66% >5 cm, HBV-59.3%), and presence of portal vein thrombosis (8.06%, HBV 1.56%). A binominal multivariate analysis showed that HCV-HCC group were more likely to be cirrhotic (OR=0.245, 95%CI: 0.117, 0.516) and had more than two times higher rate of solitary macrovascular involvement (OR=2.533, 95%CI: 1.162, 5.521) as compared with HBV associated HCC. CONCLUSIONS: Statistically significant variations were observed from baseline to clinical-pathological characteristics in HCV vs HBV associated HCC. Our study suggests prompt and early screening for high risk patients so that the rate of progression of these chronic viral diseases to cirrhosis and cancer can be decreased.