Search PubMed⌕ Search
Home/Archive/PubMed

PubMed · 15382315

Computer-aided diagnostics.

Anthony P Reeves·Bryan M Kressler
View original source ↗Export metadata ↓

Abstract

The computer can be used in a number of ways to aid the physician to interpret CT lung images. Commercial tools are becoming available to assist the radiologist in growth rate determination, hence cancer diagnosis. Computer algorithms are in development that will permit lung health evaluation, including nodule detection. Finally, the results of such efforts will probably produce more detailed visualizations of the lung region, including depictions of the location and state of lung abnormalities. While computer methods have found a first application with the radiologist, these methods should also provide a valuable aid to surgery and pathology.

Explore related subjects

Diagnosis, Computer-AssistedFemaleHumansLung NeoplasmsMaleRadiographic Image Interpretation, Computer-AssistedSensitivity and SpecificitySolitary Pulmonary NoduleComparative StudyJournal ArticleReview

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Anthony P Reeves, Bryan M Kressler. 2004. Computer-aided diagnostics.. https://doi.org/10.1016/s1547-4127(04)00030-1

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

KEEP EXPLORING

Related citations

PubMed2005

Prediction of survival in patients with esophageal carcinoma using artificial neural networks.

BACKGROUND: Accurate estimation of outcome in patients with malignant disease is an important component of the clinical decision-making process. To create a comprehensive prognostic model for esophageal carcinoma, artificial neural networks (ANNs) were applied to the analysis of a range of patient-related and tumor-related variables. METHODS: Clinical and pathologic data were collected from 418 patients with esophageal carcinoma who underwent resection with curative intent. A data base that included 199 variables was constructed. Using ANN-based sensitivity analysis, the optimal combination of variables was determined to allow creation of a survival prediction model. The accuracy (area under the receiver operator characteristic curve [AUR]) of this ANN model subsequently was compared with the accuracy of the conventional statistical technique: linear discriminant analysis (LDA). RESULTS: The optimal ANN models for predicting outcomes at 1 year and 5 years consisted of 65 variables (AUR = 0.883) and 60 variables (AUR = 0.884), respectively. These filtered, optimal data sets were significantly more accurate (P < 0.0001) than the original data set of 199 variables. The majority of ANN models demonstrated improved accuracy compared with corresponding LDA models for 1-year and 5-year survival predictions. Furthermore, ANN models based on the optimal data set were superior predictors of survival compared with a model based solely on TNM staging criteria (P < 0.0001). CONCLUSIONS: ANNs can be used to construct a highly accurate prognostic model for patients with esophageal carcinoma. Sensitivity analysis based on ANNs is a powerful tool for seeking optimal data sets.

Diagnosis, Computer-Assisted↗
PubMed2005

Prediction of gastric cancer lymph node status by sentinel lymph node biopsy and the Maruyama computer model.

AIMS: The extent of lymph node dissection in gastric cancer remains controversial. The Maruyama computer model and the sentinel lymph node biopsy (SLNB) are compared for their value to predict the nodal status and lead to stage-adapted surgery. METHODS: Thirty four patients with stage I-IV gastric cancer underwent both staging procedures. For SLNB, 15 patients underwent endoscopic, peri-tumoural injection of (99m)Tc-colloid, and 19 patients were injected of Patent blue V. All 'hot' or blue sentinel lymph nodes (SLNs) were separately excised and histopathologically assessed. If the SLN was negative after routine staining by H&E, it was processed completely and reanalysed after immunohistochemistry. RESULTS: At least, one SLN was detected by means of SLNB in 33/34 of the patients. The sensitivity to identify a positive nodal status was 22/33 and the specificity/positive predictive value was 10/10 and 22/22. Additional micrometastases or isolated tumour cells in the SLN led to 'upstaging' of 5/15, initially classified as nodal negative by H&E-staining. Using the Maruyama computer model, a sensitivity of 22/23 for the correct prediction of the lymph node involvement was associated with a specificity of 2/10 and a positive predictive value of 22/30. CONCLUSIONS: The clinical impact of the Maruyama computer model is limited due to low specificity and a low positive predictive value, rendering the method less useful as an indicator for individualised surgery.

Diagnosis, Computer-Assisted↗