Belief network for grading prostate lesions.

M Bibbo; P H Bartels; T Pfeifer; D Thompson; C Minimo; H G Davidson

Home/Archive/PubMed

PubMed · 8318127

Belief network for grading prostate lesions.

M Bibbo·P H Bartels·T Pfeifer·D Thompson·C Minimo·H G Davidson

View original source ↗Export metadata ↓

Abstract

A Bayesian belief network for grading prostatic lesions into eight primary Gleason grades was developed and tested. The network employs 13 diagnostic clues, 8 based on tissue architectural features and 5 based on nuclear features. For every diagnostic clue, three to five different outcomes are specified by membership functions. The network works in a robust fashion and attained agreement with consensus visual grading in 241 of 256 microscopic fields.

Explore related subjects

Adenocarcinoma Bayes Theorem Cell Nucleus Diagnosis, Differential Humans Male Prostatic Neoplasms Journal Article Research Support, U.S. Gov't, P.H.S.

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

M Bibbo, P H Bartels, T Pfeifer, D Thompson, C Minimo, H G Davidson. 1993. Belief network for grading prostate lesions.. https://pubmed.ncbi.nlm.nih.gov/8318127/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

The case for routine use of adjuvant therapy in pancreatic cancer.

Pancreatic cancer is a devastating disease with a poor prognosis for most patients. Surgical resection remains the cornerstone of treatment, providing the only realistic hope of long-term survival. Even with optimal surgical management, 5-year survival averages 15% to 20% for resectable disease. Progress is being made, however. Currently, the benefits of postoperative therapy for resected pancreatic ductal adenocarcinoma appear clear, and recommendations for such therapy appear to us to be well justified. Additional benefit to patients awaits the development of new agents, molecular targeted drugs, and novel approaches such as immunotherapy.

Adenocarcinoma↗

PubMed2007

Proposal for a new definition of true cardia carcinoma.

BACKGROUND AND OBJECTIVES: It remains controversial whether cardia carcinoma should be categorized and treated as esophageal cancer or gastric cancer. The purpose of this study was to develop a reasonable definition of cardia carcinoma. METHODS: Patients with Siewert type II carcinomas were divided into two subgroups: 25 patients with a tumor center within 1 cm of the esophagogastric junction (EGJ) (type IIA) and 22 patients with tumor center 1-2 cm aboral of the EGJ (type IIB). Patients with subcardia carcinomas, 40 with invasion to the EGJ (type III) and 110 without (type IIIe-), were used as controls. RESULTS: The patients with type IIB carcinomas showed no different characteristics from those with type III or type IIIe- carcinomas, except for the stage of the disease. On the other hand, those with type IIA carcinomas were associated with a higher male/female ratio, higher incidences of elevated appearance, differentiated histology, and mediastinal node metastasis, and a significantly lower survival rate as compared with patients with subcardia carcinomas. Multivariate survival analysis revealed that type IIA is a significant prognostic determinant, but that type IIB is not. CONCLUSION: Type IIA carcinomas should be treated as true cardia carcinoma; type IIB as subcardia carcinoma. Our results should be confirmed by a prospective study.

Adenocarcinoma↗

PubMed2007

Favorable indications for hepatectomy in patients with liver metastasis from gastric cancer.

BACKGROUND: The prognosis of patients with liver metastasis from gastric cancer (LMGC) is dismal. The purpose of this study was to review our recent outcomes of hepatectomy for LMGC and to determine the suitable candidates for surgery. STUDY DESIGN: The outcomes of 37 patients with LMGC who underwent hepatectomy between 1990 and 2005 were assessed. No extrahepatic distant metastasis and feasibility of macroscopic curative resection were requisite indications for surgery. The prognostic values of clinicopathological factors were assessed by univariate and multivariate analyses. RESULTS: There was no in-hospital mortality. The median survival time and overall 5-year survival rate after hepatectomy of the patients with LMGC were 31 months and 11%, respectively. Intrahepatic recurrence following hepatectomy was found in 23 patients (62%). Variables independently associated with poor survival were bilobar metastasis (P = 0.002, CI = 1.9-16.3) and a maximum tumor diameter of >or= 4 cm (P = 0.006, CI = 1.4-7.7). The depth of the primary tumor and the timing of metastasis were not associated with survival. CONCLUSIONS: Surgical resection for LMGC may be indicated in patients with unilobar metastasis and/or tumors less than 4 cm in diameter. Synchronous metastasis is not a contraindication for hepatectomy.

Adenocarcinoma↗